Quantifying Vegetation Biophysical Variables from Imaging Spectroscopy Data: A Review on Retrieval Methods

Predicting key water stress indicators of Eucalyptus viminalis and Callitris rhomboidea using high-resolution visible to short-wave infrared spectroscopy

Drought is one of the main factors contributing to tree mortality worldwide and drought events are set to become more frequent and intense in the face of a changing climate. Quantifying water stress of forests is crucial in predicting and understanding their vulnerability to drought-induced mortality. Here, we explore the use of high-resolution spectroscopy in predicting water stress indicators of two native Australian tree species, Callitris rhomboidea and Eucalyptus viminalis. Specific spectral features and indices derived from leaf-level spectroscopy were assessed as potential proxies to predict leaf water potential (Ψleaf), equivalent water thickness (EWT) and fuel moisture content (FMC) in a dedicated laboratory experiment. New spectral indices were identified that enabled very high confidence linear prediction of Ψleaf for both species (R2 > 0.85) with predictive capacity increasing when accounting for a breakpoint in the relationships using segmented regression (E. viminalis, R2 > 0.89; C. rhomboidea, R2 > 0.87). EWT and FMC were also linearly predicted to a high accuracy (E. viminalis, R2 > 0.90; C. rhomboidea, R2 > 0.80). This study highlights the potential of spectroscopy as a tool for predicting measures of plant water noninvasively, enabling broader applications for monitoring and managing plant water stress.

Spectroscopy-based chemometrics combined machine learning modeling predicts cashew foliar macro- and micronutrients

Precision nutrient management in orchard crops needs precise, accurate, and real-time information on the plant's nutritional status. This is limited by the fact that it requires extensive leaf sampling and chemical analysis when it is to be done over more extensive areas like field- or landscape scale. Thus, rapid, reliable, and repeatable means of nutrient estimations are needed. In this context, lab-based remote sensing or spectroscopy has been explored in the current study to predict the foliar nutritional status of the cashew crop. Novel spectral indices (normalized difference and simple ratio), chemometric modeling, and partial least square regression (PLSR) combined machine learning modeling of the visible near-infrared hyperspectral data were employed to predict macro- and micronutrients content of the cashew leaves. The full dataset was divided into calibration (70 % of the full dataset) and validation (30 % of the full dataset) datasets. An independent validation dataset was used for the validation of the algorithms tested. The approach of spectral indices yielded very poor and unreliable predictions for all eleven nutrients. Among the chemometric models tested, the performance of the PLSR was the best, but still, the predictions were not acceptable. The PLSR combined machine learning modeling approach yielded acceptable to excellent predictions for all the nutrients except sulphur and copper. The best predictions were observed when PLSR was combined with Cubist for nitrogen, phosphorus, potassium, manganese, and zinc; support vector machine regression for calcium, magnesium, iron, copper, and boron; elastic net for sulphur. The current study showed hyperspectral remote sensing-based models could be employed for non-destructive and rapid estimation of cashew leaf macro- and micro-nutrients. The developed approach is suggested to employ within the operational workflows for site-specific and precision nutrient management of the cashew orchards.

Geographical origin identification of Khao Dawk Mali 105 rice using combination of FT-NIR spectroscopy and machine learning algorithms

The mislabelled Khao Dawk Mali 105 rice coming from other geographical region outside the Thung Kula Rong Hai region is extremely profitable and difficult to detect; to prevent retail fraud (that adversely affects both the food industry and consumers), it is vital to identify geographical origin. Near infrared spectroscopy can be used to detect the specific content of organic moieties in agricultural and food products. The present study implemented the combinatorial method of FT-NIR spectroscopy with chemometrics to identify geographical origin of Khao Dawk Mali 105 rice. Rice samples were collected from 2 different region including the north and northeast of Thailand. NIR spectra data were collected in range of 12,500 - 4,000 cm-1 (800-2,500 nm). Five machine learning algorithms including linear discriminant analysis (LDA), partial least squares discriminant analysis (PLS-DA), C-support vector classification (C-SVC), backpropagation neural networks (BPNN), hybrid principal component analysis-neural network (PC-NN) and K-nearest neighbors (KNN) were employed to classify NIR data of rice samples with full wavelength and selected wavelength by Extremely Randomized Trees (Extra trees) algorithm. Based on the findings, geographical origin of rice could be specified quickly, cheaply, and reliably using combination of NIRS and machine learning. All models creating by full wavelength and selected wavelength exhibited accuracy between 65 and 100 % for identifying geographical region of rice. It was proven that NIR spectroscopy may be used for the quick and non-destructive identification of geographical origin of Khao Dawk Mali 105 rice.

Water content estimation of conifer needles using leaf-level hyperspectral data

Water is a crucial component for plant growth and survival. Accurately estimating and simulating plant water content can help us promptly monitor the physiological status and stress response of vegetation. In this study, we constructed water loss curves for three types of conifers with morphologically different needles, then evaluated the applicability of 12 commonly used water indices, and finally explored leaf water content estimation from hyperspectral data for needles with various morphology. The results showed that the rate of water loss of Olgan larch is approximately 8 times higher than that of Chinese fir pine and 21 times that of Korean pine. The reflectance changes were most significant in the near infrared region (NIR, 780-1300 nm) and the short-wave infrared region (SWIR, 1300-2500 nm). The water sensitive bands for conifer needles were mainly concentrated in the SWIR region. The water indices were suitable for estimating the water content of a single type of conifer needles. The partial least squares regression (PLSR) model is effective for the water content estimation of all three morphologies of conifer needles, demonstrating that the hyperspectral PLSR model is a promising tool for estimating needles water content.

Unveiling the transferability of PLSR models for leaf trait estimation: lessons from a comprehensive analysis with a novel global dataset

Leaf traits are essential for understanding many physiological and ecological processes. Partial least squares regression (PLSR) models with leaf spectroscopy are widely applied for trait estimation, but their transferability across space, time, and plant functional types (PFTs) remains unclear. We compiled a novel dataset of paired leaf traits and spectra, with 47 393 records for > 700 species and eight PFTs at 101 globally distributed locations across multiple seasons. Using this dataset, we conducted an unprecedented comprehensive analysis to assess the transferability of PLSR models in estimating leaf traits. While PLSR models demonstrate commendable performance in predicting chlorophyll content, carotenoid, leaf water, and leaf mass per area prediction within their training data space, their efficacy diminishes when extrapolating to new contexts. Specifically, extrapolating to locations, seasons, and PFTs beyond the training data leads to reduced R2 (0.12-0.49, 0.15-0.42, and 0.25-0.56) and increased NRMSE (3.58-18.24%, 6.27-11.55%, and 7.0-33.12%) compared with nonspatial random cross-validation. The results underscore the importance of incorporating greater spectral diversity in model training to boost its transferability. These findings highlight potential errors in estimating leaf traits across large spatial domains, diverse PFTs, and time due to biased validation schemes, and provide guidance for future field sampling strategies and remote sensing applications.

Improvement of pasture biomass modelling using high-resolution satellite imagery and machine learning

Robust quantification of vegetative biomass using satellite imagery using one or more forms of machine learning (ML) has hitherto been hindered by the extent and quality of training data. Here, we showcase how ML predictive demonstrably improves when additional training data is used. We collated field datasets of pasture biomass obtained via destructive sampling, 'C-Dax' reflective measurements and rising plate meters (RPM) from ten livestock farms across four States in Australia. Remotely sensed data from the Sentinel-2 constellation was used to retrieve aboveground biomass using a novel machine learning paradigm hereafter termed "SPECTRA-FOR" (Spectral Pasture Estimation using Combined Techniques of Random-forest Algorithm for Features Optimisation and Retrieval). Using this framework, we show that the low temporal resolution of Sentinel-2 in high latitude regions with persistent cloud cover leads to extensive gaps between cloud-free images, hindering model performance and, thus, contemporaneous ability to forecast real-time pasture biomass. By leveraging the spectral consistency between Sentinel-2 and Planet Lab SuperDove to overcome this limitation, we used ten spectral bands of Sentinel-2, four bands of Sentinel-2 as a proxy for pre-2022 SuperDove (referred to as synthetic SuperDove or SSD), and the actual SuperDove (ASD), given that SuperDove imagery has a higher resolution and more frequent passage compared with Sentinel-2. Using their respective bands as input features to SPECRA-FOR, model performance for the ten bands of Sentinel-2 were R2 = 0.87, root mean squared error (RMSE) of 439 kg DM/ha and mean absolute error (MAE) of 255 kg DM/ha, while that for SSD increased to an R2 of 0.92, RMSE of 346 kg DM/ha and MAE = 208 kg DM/ha. The study revealed the importance of robust data mining, imagery harmonisation and model validation for accurate real-time modelling of pasture biomass with ML.

Image-based vegetation analysis of desertified area by using a combination of ImageJ and Photoshop software

Fractional vegetation cover (FVC) is a crucial indicator to estimate degradation and desertification for grasslands. However, traditional small-scale FVC analysis methods, such as visual estimation and point-sampling, are cumbersome and imprecise. Innovative methods like image-based FVC analysis methods, while accurate, face challenges such as complex analytical procedures and the necessary training for operations. Therefore, in this study, a combined application of ImageJ and Photoshop was employed to achieve a more effective analysis of FVC values in desertification areas. Our results showed that the FVC results obtained by combination of Photoshop and ImageJ were dependable and precise (R2 > 0.98), demonstrating equivalency to results obtained through either visual estimation or Photoshop-based methods. Furthermore, even in the face of background interference and varied shooting angles, the combination of ImageJ and Photoshop software was still able to maintain a low error rate when analyzing FVC values (average error rate =  - 2.6%). In conclusion, the imaged-based combined FVC analysis method employed in our research was an effective, precise, and efficient technique for analyzing small-scale FVC, promising substantial improvement over conventional methods.

Assessment of maize nitrogen uptake from PRISMA hyperspectral data through hybrid modelling

The spaceborne imaging spectroscopy mission PRecursore IperSpettrale della Missione Applicativa (PRISMA), launched on 22 March 2019 by the Italian Space Agency, opens new opportunities in many scientific domains, including precision farming and sustainable agriculture. This new Earth Observation (EO) data stream requires new-generation approaches for the estimation of important biophysical crop variables (BVs). In this framework, this study evaluated a hybrid approach, combining the radiative transfer model PROSAIL-PRO and several machine learning (ML) regression algorithms, for the retrieval of canopy chlorophyll content (CCC) and canopy nitrogen content (CNC) from synthetic PRISMA data. PRISMA-like data were simulated from two images acquired by the airborne sensor HyPlant, during a campaign performed in Grosseto (Italy) in 2018. CCC and CNC estimations, assessed from the best performing ML algorithms, were used to define two relations with plant nitrogen uptake (PNU). CNC proved to be slightly more correlated to PNU than CCC (R2 = 0.82 and R2 = 0.80, respectively). The CNC-PNU model was then applied to actual PRISMA images acquired in 2020. The results showed that the estimated PNU values are within the expected ranges, and the temporal trends are compatible with plant phenology stages.

Estimation of Biochemical Pigment Content in Poplar Leaves Using Proximal Multispectral Imaging and Regression Modeling Combined with Feature Selection

Monitoring the biochemical pigment contents in individual plants is crucial for assessing their health statuses and physiological states. Fast, low-cost measurements of plants' biochemical traits have become feasible due to advances in multispectral imaging sensors in recent years. This study evaluated the field application of proximal multispectral imaging combined with feature selection and regressive analysis to estimate the biochemical pigment contents of poplar leaves. The combination of 6 spectral bands and 26 vegetation indices (VIs) derived from the multispectral bands was taken as the group of initial variables for regression modeling. Three variable selection algorithms, including the forward selection algorithm with correlation analysis (CORR), recursive feature elimination algorithm (RFE), and sequential forward selection algorithm (SFS), were explored as candidate methods for screening combinations of input variables from the 32 spectral-derived initial variables. Partial least square regression (PLSR) and nonlinear support vector machine regression (SVR) were both applied to estimate total chlorophyll content (Chla+b) and carotenoid content (Car) at the leaf scale. The results show that the nonlinear SVR prediction model based on optimal variable combinations, selected by SFS using multiple scatter correction (MSC) preprocessing data, achieved the best estimation accuracy and stable prediction performance for the leaf pigment content. The Chla+b and Car models developed using the optimal model had R2 and RMSE predictive statistics of 0.849 and 0.825 and 5.116 and 0.869, respectively. This study demonstrates the advantages of using a nonlinear SVR model combined with SFS variable selection to obtain a more reliable estimation model for leaf biochemical pigment content.

Comparing CNNs and PLSr for estimating wheat organs biophysical variables using proximal sensing

Estimation of biophysical vegetation variables is of interest for diverse applications, such as monitoring of crop growth and health or yield prediction. However, remote estimation of these variables remains challenging due to the inherent complexity of plant architecture, biology and surrounding environment, and the need for features engineering. Recent advancements in deep learning, particularly convolutional neural networks (CNN), offer promising solutions to address this challenge. Unfortunately, the limited availability of labeled data has hindered the exploration of CNNs for regression tasks, especially in the frame of crop phenotyping. In this study, the effectiveness of various CNN models in predicting wheat dry matter, nitrogen uptake, and nitrogen concentration from RGB and multispectral images taken from tillering to maturity was examined. To overcome the scarcity of labeled data, a training pipeline was devised. This pipeline involves transfer learning, pseudo-labeling of unlabeled data and temporal relationship correction. The results demonstrated that CNN models significantly benefit from the pseudolabeling method, while the machine learning approach employing a PLSr did not show comparable performance. Among the models evaluated, EfficientNetB4 achieved the highest accuracy for predicting above-ground biomass, with an R² value of 0.92. In contrast, Resnet50 demonstrated superior performance in predicting LAI, nitrogen uptake, and nitrogen concentration, with R² values of 0.82, 0.73, and 0.80, respectively. Moreover, the study explored multi-output models to predict the distribution of dry matter and nitrogen uptake between stem, inferior leaves, flag leaf, and ear. The findings indicate that CNNs hold promise as accessible and promising tools for phenotyping quantitative biophysical variables of crops. However, further research is required to harness their full potential.

Making the Genotypic Variation Visible: Hyperspectral Phenotyping in Scots Pine Seedlings

Hyperspectral reflectance contains valuable information about leaf functional traits, which can indicate a plant's physiological status. Therefore, using hyperspectral reflectance for high-throughput phenotyping of foliar traits could be a powerful tool for tree breeders and nursery practitioners to distinguish and select seedlings with desired adaptation potential to local environments. We evaluated the use of 2 nondestructive methods (i.e., leaf and proximal/canopy) measuring hyperspectral reflectance in the 350- to 2,500-nm range for phenotyping on 1,788 individual Scots pine seedlings belonging to lowland and upland ecotypes of 3 different local populations from the Czech Republic. Leaf-level measurements were collected using a spectroradiometer and a contact probe with an internal light source to measure the biconical reflectance factor of a sample of needles placed on a black background in the contact probe field of view. The proximal canopy measurements were collected under natural solar light, using the same spectroradiometer with fiber optical cable to collect data on individual seedlings' hemispherical conical reflectance factor. The latter method was highly susceptible to changes in incoming radiation. Both spectral datasets showed statistically significant differences among Scots pine populations in the whole spectral range. Moreover, using random forest and support vector machine learning algorithms, the proximal data obtained from the top of the seedlings offered up to 83% accuracy in predicting 3 different Scots pine populations. We conclude that both approaches are viable for hyperspectral phenotyping to disentangle the phenotypic and the underlying genetic variation within Scots pine seedlings.

LAI estimation based on physical model combining airborne LiDAR waveform and Sentinel-2 imagery

Leaf area index (LAI) is an important biophysical parameter of vegetation and serves as a significant indicator for assessing forest ecosystems. Multi-source remote sensing data enables large-scale and dynamic surface observations, providing effective data for quantifying various indices in forest and evaluating ecosystem changes. However, employing single-source remote sensing spectral or LiDAR waveform data poses limitations for LAI inversion, making the integration of multi-source remote sensing data a trend. Currently, the fusion of active and passive remote sensing data for LAI inversion primarily relies on empirical models, which are mainly constructed based on field measurements and do not provide a good explanation of the fusion mechanism. In this study, we aimed to estimate LAI based on physical model using both spectral imagery and LiDAR waveform, exploring whether data fusion improved the accuracy of LAI inversion. Specifically, based on the physical model geometric-optical and radiative transfer (GORT), a fusion strategy was designed for LAI inversion. To ensure inversion accuracy, we enhanced the data processing by introducing a constraint-based EM waveform decomposition method. Considering the spatial heterogeneity of canopy/ground reflectivity ratio in regional forests, calculation strategy was proposed to improve this parameter in inversion model. The results showed that the constraint-based EM waveform decomposition method improved the decomposition accuracy with an average 12% reduction in RMSE, yielding more accurate waveform energy parameters. The proposed calculation strategy for the canopy/ground reflectivity ratio, considering dynamic variation of parameter, effectively enhanced previous research that relied on a fixed value, thereby improving the inversion accuracy that increasing on the correlation by 5% to 10% and on R2 by 62.5% to 132.1%. Based on the inversion strategy we proposed, data fusion could effectively be used for LAI inversion. The inversion accuracy achieved using both spectral and LiDAR data (correlation=0.81, R2 = 0.65, RMSE=1.01) surpassed that of using spectral data or LiDAR alone. This study provides a new inversion strategy for large-scale and high-precision LAI inversion, supporting the field of LAI research.

The role of remote sensing in tropical grassland nutrient estimation: a review

The carbon (C) and nitrogen (N) ratio is a key indicator of nutrient utilization and limitations in rangelands. To understand the distribution of herbivores and grazing patterns, information on grass quality and quantity is important. In heterogeneous environments, remote sensing offers a timely, economical, and effective method for assessing foliar biochemical ratios at varying spatial and temporal scales. Hence, this study provides a synopsis of the advancement in remote sensing technology, limitations, and emerging opportunities in mapping the C:N ratio in rangelands. Specifically, the paper focuses on multispectral and hyperspectral sensors and investigates their properties, absorption features, empirical and physical methods, and algorithms in predicting the C:N ratio in grasslands. Literature shows that the determination of the C:N ratio in grasslands is not in line with developments in remote sensing technologies. Thus, the use of advanced and freely available sensors with improved spectral and spatial properties such as Sentinel 2 and Landsat 8/9 with sophisticated algorithms may provide new opportunities to estimate C:N ratio in grasslands at regional scales, especially in developing countries. Spectral bands in the near-infrared, shortwave infrared, red, and red edge were identified to predict the C:N ratio in plants. New indices developed from recent multispectral satellite imagery, for example, Sentinel 2 aided by cutting-edge algorithms, can improve the estimation of foliar biochemical ratios. Therefore, this study recommends that future research should adopt new satellite technologies with recent development in machine learning algorithms for improved mapping of the C:N ratio in grasslands.

Impact of potentially toxic elements on pines in a former ore processing mine: Exploitation of hyperspectral response from needle and canopy scales

Anthropic potentially toxic element (PTE) releases can lead to persistent pollution in soil. Monitoring PTEs by their detection and quantification on large scale is of great interest. The vegetation exposed to PTEs can exhibit a reduction of physiological activities, structural damage … Such vegetation trait changes impact the spectral signature in the reflective domain 0.4-2.5 μm. The objective of this study is to characterize the impact of PTEs on the spectral signature of two pine species (Aleppo and Stone pines) in the reflective domain and ensure their assessment. The study focuses on nine PTEs: As, Cr, Cu, Fe, Mn, Mo, Ni, Pb, Zn. The spectra are measured by an in-field spectrometer and an aerial hyperspectral instrument on a former ore processing site. They are completed by measurements related to vegetation traits at needle and tree scales (photosynthetic pigments, dry matter, morphometry …) to define the most sensitive vegetation parameter to each PTE in soil. A result of this study is that chlorophylls and carotenoids are the most correlated to PTE contents. Context-specific spectral indices are specified and used to assess metal contents in soil by regression. These new vegetation indices are compared at needle and canopy scales to literature indices. Most of the PTE contents are predicted at both scales with Pearson correlation scores between 0.6 and 0.9, depending on species and scale.

Based on machine learning algorithms for estimating leaf phosphorus concentration of rice using optimized spectral indices and continuous wavelet transform

Remotely estimating leaf phosphorus concentration (LPC) is crucial for fertilization management, crop growth monitoring, and the development of precision agricultural strategy. This study aimed to explore the best prediction model for the LPC of rice (Oryza sativa L.) using machine learning algorithms fed with full-band (OR), spectral indices (SIs), and wavelet features. To obtain the LPC and leaf spectra reflectance, the pot experiments with four phosphorus (P) treatments and two rice cultivars were carried out in a greenhouse in 2020-2021. The results indicated that P deficiency increased leaf reflectance in the visible region (350-750 nm) and decreased the reflectance in the near-infrared (NIR, 750-1350 nm) regions compared to the P-sufficient treatment. Difference spectral index (DSI) composed of 1080 nm and 1070 nm showed the best performance for LPC estimation in calibration (R² = 0.54) and validation (R² = 0.55). To filter and denoise spectral data effectively, continuous wavelet transform (CWT) of the original spectrum was used to improve the accuracy of prediction. The model based on Mexican Hat (Mexh) wavelet function (1680 nm, Scale 6) demonstrated the best performance with the calibration R² of 0.58, validation R² of 0.56 and RMSE of 0.61 mg g^-1. In machine learning, random forest (RF) had the best model accuracy in OR, SIs, CWT, and SIs + CWT compared with other four algorithms. The SIs and CWT coupling with the RF algorithm had the best results of model validation, the R² was 0.73 and the RMSE was 0.50 mg g^-1, followed by CWT (R² = 0.71, RMSE = 0.51 mg g^-1), OR (R² = 0.66, RMSE = 0.60 mg g^-1), and SIs (R² = 0.57, RMSE = 0.64 mg g^-1). Compared with the best performing SIs based on the linear regression models, the RF algorithm combining SIs and CWT improved the prediction of LPC with R² increased by 32%. Our results provide a valuable reference for spectral monitoring of rice LPC under different soil P-supplying levels in a large scale.

Remotely Sensed Phenotypic Traits for Heritability Estimates and Grain Yield Prediction of Barley Using Multispectral Imaging from UAVs

This study tested the potential of parametric and nonparametric regression modeling utilizing multispectral data from two different unoccupied aerial vehicles (UAVs) as a tool for the prediction of and indirect selection of grain yield (GY) in barley breeding experiments. The coefficient of determination (R²) of the nonparametric models for GY prediction ranged between 0.33 and 0.61 depending on the UAV and flight date, where the highest value was achieved with the DJI Phantom 4 Multispectral (P4M) image from 26 May (milk ripening). The parametric models performed worse than the nonparametric ones for GY prediction. Independent of the retrieval method and UAV, GY retrieval was more accurate in milk ripening than dough ripening. The leaf area index (LAI), fraction of absorbed photosynthetically active radiation (fAPAR), fraction vegetation cover (fCover), and leaf chlorophyll content (LCC) were modeled at milk ripening using nonparametric models with the P4M images. A significant effect of the genotype was found for the estimated biophysical variables, which was referred to as remotely sensed phenotypic traits (RSPTs). Measured GY heritability was lower, with a few exceptions, compared to the RSPTs, indicating that GY was more environmentally influenced than the RSPTs. The moderate to strong genetic correlation of the RSPTs to GY in the present study indicated their potential utility as an indirect selection approach to identify high-yield genotypes of winter barley.

An Assessment of Relations between Vegetation Green FPAR and Vegetation Indices through a Radiative Transfer Model

The fraction of absorbed photosynthetically active radiation (FPAR) is widely used in remote sensing-based production models to estimate gross or net primary production. The forest canopy is composed primarily of photosynthetically active vegetation (PAV, green leaves) and non-photosynthetic vegetation (NPV e.g., branches), which absorb PAR but only the PAR absorbed by PAV is used for photosynthesis. Green FPAR (the fraction of PAR absorbed by PAV) is essential for the accurate estimation of GPP. In this study, the scattering by arbitrary inclined leaves (SAIL) model was reconfigured to partition the PAR absorbed by forest canopies. The characteristics of green FPAR and its relationships with spectral vegetation indices (NDVI, EVI, EVI2, and SAVI) were analyzed. The results showed that green FPAR varied with the canopy structure. In the forests with high coverage, the green FPAR was close to the total FPAR, while in the open forests, the green FPAR was far smaller than the total FPAR. Plant area index had more important impacts on the green FPAR than the proportion of PAV and optical properties of PAV. The significant relationships were found between spectral vegetation indices and the green FPAR, but EVI was more suitable to describe the variation of canopy green FPAR.

Hyperspectral remote sensing for tobacco quality estimation, yield prediction, and stress detection: A review of applications and methods

Tobacco is an important economic crop and the main raw material of cigarette products. Nowadays, with the increasing consumer demand for high-quality cigarettes, the requirements for their main raw materials are also varying. In general, tobacco quality is primarily determined by the exterior quality, inherent quality, chemical compositions, and physical properties. All these aspects are formed during the growing season and are vulnerable to many environmental factors, such as climate, geography, irrigation, fertilization, diseases and pests, etc. Therefore, there is a great demand for tobacco growth monitoring and near real-time quality evaluation. Herein, hyperspectral remote sensing (HRS) is increasingly being considered as a cost-effective alternative to traditional destructive field sampling methods and laboratory trials to determine various agronomic parameters of tobacco with the assistance of diverse hyperspectral vegetation indices and machine learning algorithms. In light of this, we conduct a comprehensive review of the HRS applications in tobacco production management. In this review, we briefly sketch the principles of HRS and commonly used data acquisition system platforms. We detail the specific applications and methodologies for tobacco quality estimation, yield prediction, and stress detection. Finally, we discuss the major challenges and future opportunities for potential application prospects. We hope that this review could provide interested researchers, practitioners, or readers with a basic understanding of current HRS applications in tobacco production management, and give some guidelines for practical works.

LAI estimation through remotely sensed NDVI following hail defoliation in maize (Zea mays L.) using Sentinel-2 and UAV imagery

Extreme events such as hailstorms are a cause for concern in agriculture, leading to both economic and food supply losses. Traditional damage estimation techniques have recently been called into question since damages have rarely been quantified at the large-field scale. Damage-estimation methods used by field inspectors are complex and sometimes subjective and hardly account for damage spatial variability. In this work, a normalized difference vegetation index (NDVI)-based parametric method was applied using both unmanned aerial vehicles (UAV) and Sentinel-2 sensors to estimate the leaf area index (LAI) of maize (Zea mays L.) resulting from simulated hail damage. These methods were then compared to the LAI values generated from the Sentinel-2 Biophysical Processor. A two-year experiment (2020-2021) was conducted during the maize cropping season, with hail events simulated during a range of maize developmental stages (the 8th-leaf, flowering, milky and dough stages) using a 0-40% defoliation gradient of damage intensities performed with the aid of specifically designed prototype machines. The results showed that both sensors were able to accurately estimate LAI in a nonstandard damaged canopy while requiring only the calibration of the extinction coefficient k ( ϑ ) in the case of parametric estimations. In this case, the calibration was performed using 2020 data, providing k ( ϑ ) values of 0.59 for Sentinel-2 and 0.37 for the UAV sensor. The validation was performed on 2021 data, and showed that the UAV sensor had the best accuracy (R2 of 0.86, root-mean-square error (RMSE) of 0.71). The k ( ϑ ) value proved to be sensor-specific, accounting for the NDVI retrieval differences likely caused by the different spatial operational scales of the two sensors. NDVI proved effective in parametrically estimating maize LAI under damaged canopy conditions at different defoliation degrees. The parametric method matched the Sentinel-2 biophysical process-generated LAI well, leading to less underestimations and more accurate LAI retrieval.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11119-023-09993-9.

Simultaneous retrieval of sugarcane variables from Sentinel-2 data using Bayesian regularized neural network

Quantifying biophysical and biochemical vegetation variables is of great importance in precision agriculture. Here, the ability of artificial neural networks (ANNs) to generate multiple outputs is exploited to simultaneously retrieve Leaf area index (LAI), leaf sheath moisture (LSM), leaf chlorophyll content (LCC), and leaf nitrogen concentration (LNC) of sugarcane from Sentinel-2 spectra. We apply a type of ANNs, Bayesian Regularized ANN (BRANN), which incorporates the Bayes' theorem into a regularization scheme to tackle the overfitting problem of ANN and improve its generalizability. Quantitatively assessing the result accuracy indicated RMSE values of 0.48 (m²/m²) for LAI, 2.36 (% wb) for LSM, 5.85 (μg/cm²) for LCC, and 0.23 (%) for LNC, applying simultaneous retrieval. It was demonstrated that simultaneous retrievals of the variables outperformed the individual retrievals. The superiority of the proposed BRANN over a conventional ANN trained with the Levenberg-Marquardt algorithm was confirmed through statistical comparison of their results. The model was applied over the entire Sentinel-2 images to map the considered variables. The maps were probed to qualitatively evaluate the model performance. The results indicated that the retrievals reasonably represent spatial and temporal variations of the variables. Generally, this study demonstrated that the BRANN simultaneous retrieval model can provide faster and more accurate retrievals than those obtained from conventional ANNs and individual retrievals.

Quantifying Irrigated Winter Wheat LAI in Argentina Using Multiple Sentinel-1 Incidence Angles

Synthetic aperture radar (SAR) data provides an appealing opportunity for all-weather day or night Earth surface monitoring. The European constellation Sentinel-1 (S1) consisting of S1-A and S1-B satellites offers a suitable revisit time and spatial resolution for the observation of croplands from space. The C-band radar backscatter is sensitive to vegetation structure changes and phenology as well as soil moisture and roughness. It also varies depending on the local incidence angle (LIA) of the SAR acquisition's geometry. The LIA backscatter dependency could therefore be exploited to improve the retrieval of the crop biophysical variables. The availability of S1 radar time-series data at distinct observation angles holds the feasibility to retrieve leaf area index (LAI) evolution considering spatiotemporal coverage of intensively cultivated areas. Accordingly, this research presents a workflow merging multi-date S1 smoothed data acquired at distinct LIA with a Gaussian processes regression (GPR) and a cross-validation (CV) strategy to estimate cropland LAI of irrigated winter wheat. The GPR-S1-LAI model was tested against in situ data of the 2020 winter wheat campaign in the irrigated valley of Colorador river, South of Buenos Aires Province, Argentina. We achieved adequate validation results for LAI with R C V 2 = 0.67 and RMSE _CV = 0.88 m² m^-2. The trained model was further applied to a series of S1 stacked images, generating temporal LAI maps that well reflect the crop growth cycle. The robustness of the retrieval workflow is supported by the associated uncertainties along with the obtained maps. We found that processing S1 smoothed imagery with distinct acquisition geometries permits accurate radar-based LAI modeling throughout large irrigated areas and in consequence can support agricultural management practices in cloudprone agri-environments.

Retrieval of carbon content and biomass from hyperspectral imagery over cultivated areas

Spaceborne imaging spectroscopy is a highly promising data source for all agricultural management and research disciplines that require spatio-temporal information on crop properties. Recently launched science-driven missions, such as the Environmental Mapping and Analysis Program (EnMAP), deliver unprecedented data from the Earth's surface. This new kind of data should be explored to develop robust retrieval schemes for deriving crucial variables from future routine missions. Therefore, we present a workflow for inferring crop carbon content (Carea ), and aboveground dry and wet biomass (AGBdry , AGBfresh ) from EnMAP data. To achieve this, a hybrid workflow was generated, combining radiative transfer modeling (RTM) with machine learning regression algorithms. The key concept involves: (1) coupling the RTMs PROSPECT-PRO and 4SAIL for simulation of a wide range of vegetation states, (2) using dimensionality reduction to deal with collinearity, (3) applying a semi-supervised active learning technique against a 4-years campaign dataset, followed by (4) training of a Gaussian process regression (GPR) machine learning algorithm and (5) validation with an independent in situ dataset acquired during the ESA Hypersense experiment campaign at a German test site. Internal validation of the GPR-Carea and GPR-AGB models achieved coefficients of determination (R 2) of 0.80 for Carea and 0.80, 0.71 for AGBdry and AGBfresh , respectively. The mapping capability of these models was successfully demonstrated using airborne AVIRIS-NG hyperspectral imagery, which was spectrally resampled to EnMAP spectral properties. Plausible estimates were achieved over both bare and green fields after adding bare soil spectra to the training data. Validation over green winter wheat fields generated reliable estimates as suggested by low associated model uncertainties (< 40%). These results suggest a high degree of model reliability for cultivated areas during active growth phases at canopy closure. Overall, our proposed carbon and biomass models based on EnMAP spectral sampling demonstrate a promising path toward the inference of these crucial variables over cultivated areas from future spaceborne operational hyperspectral missions.

Multi-sensor spectral synergies for crop stress detection and monitoring in the optical domain: A review

Remote detection and monitoring of the vegetation responses to stress became relevant for sustainable agriculture. Ongoing developments in optical remote sensing technologies have provided tools to increase our understanding of stress-related physiological processes. Therefore, this study aimed to provide an overview of the main spectral technologies and retrieval approaches for detecting crop stress in agriculture. Firstly, we present integrated views on: i) biotic and abiotic stress factors, the phases of stress, and respective plant responses, and ii) the affected traits, appropriate spectral domains and corresponding methods for measuring traits remotely. Secondly, representative results of a systematic literature analysis are highlighted, identifying the current status and possible future trends in stress detection and monitoring. Distinct plant responses occurring under shortterm, medium-term or severe chronic stress exposure can be captured with remote sensing due to specific light interaction processes, such as absorption and scattering manifested in the reflected radiance, i.e. visible (VIS), near infrared (NIR), shortwave infrared, and emitted radiance, i.e. solar-induced fluorescence and thermal infrared (TIR). From the analysis of 96 research papers, the following trends can be observed: increasing usage of satellite and unmanned aerial vehicle data in parallel with a shift in methods from simpler parametric approaches towards more advanced physically-based and hybrid models. Most study designs were largely driven by sensor availability and practical economic reasons, leading to the common usage of VIS-NIR-TIR sensor combinations. The majority of reviewed studies compared stress proxies calculated from single-source sensor domains rather than using data in a synergistic way. We identified new ways forward as guidance for improved synergistic usage of spectral domains for stress detection: (1) combined acquisition of data from multiple sensors for analysing multiple stress responses simultaneously (holistic view); (2) simultaneous retrieval of plant traits combining multi-domain radiative transfer models and machine learning methods; (3) assimilation of estimated plant traits from distinct spectral domains into integrated crop growth models. As a future outlook, we recommend combining multiple remote sensing data streams into crop model assimilation schemes to build up Digital Twins of agroecosystems, which may provide the most efficient way to detect the diversity of environmental and biotic stresses and thus enable respective management decisions.

Seasonal Mapping of Irrigated Winter Wheat Traits in Argentina with a Hybrid Retrieval Workflow Using Sentinel-2 Imagery

Earth observation offers an unprecedented opportunity to monitor intensively cultivated areas providing key support to assess fertilizer needs and crop water uptake. Routinely, vegetation traits mapping can help farmers to monitor plant development along the crop's phenological cycle, which is particularly relevant for irrigated agricultural areas. The high spatial and temporal resolution of the Sentinel-2 (S2) multispectral instrument leverages the possibility to estimate leaf area index (LAI), canopy chlorophyll content (CCC), and vegetation water content (VWC) from space. Therefore, our study presents a hybrid retrieval workflow combining a physically-based strategy with a machine learning regression algorithm, i.e., Gaussian processes regression, and an active learning technique to estimate LAI, CCC and VWC of irrigated winter wheat. The established hybrid models of the three traits were validated against in-situ data of a wheat campaign in the Bonaerense valley, South of the Buenos Aires Province, Argentina, in the year 2020. We obtained good to highly accurate validation results with LAI: R2 = 0.92, RMSE = 0.43 m2 m-2, CCC: R2 = 0.80, RMSE = 0.27 g m-2 and VWC: R2 = 0.75, RMSE = 416 g m-2. The retrieval models were also applied to a series of S2 images, producing time series along the seasonal cycle, which reflected the effects of fertilizer and irrigation on crop growth. The associated uncertainties along with the obtained maps underlined the robustness of the hybrid retrieval workflow. We conclude that processing S2 imagery with optimised hybrid models allows accurate space-based crop traits mapping over large irrigated areas and thus can support agricultural management decisions.

Introducing ARTMO's Machine-Learning Classification Algorithms Toolbox: Application to Plant-Type Detection in a Semi-Steppe Iranian Landscape

Accurate plant-type (PT) detection forms an important basis for sustainable land management maintaining biodiversity and ecosystem services. In this sense, Sentinel-2 satellite images of the Copernicus program offer spatial, spectral, temporal, and radiometric characteristics with great potential for mapping and monitoring PTs. In addition, the selection of a best-performing algorithm needs to be considered for obtaining PT classification as accurate as possible. To date, no freely downloadable toolbox exists that brings the diversity of the latest supervised machine-learning classification algorithms (MLCAs) together into a single intuitive user-friendly graphical user interface (GUI). To fill this gap and to facilitate and automate the usage of MLCAs, here we present a novel GUI software package that allows systematically training, validating, and applying pixel-based MLCA models to remote sensing imagery. The so-called MLCA toolbox has been integrated within ARTMO's software framework developed in Matlab which implements most of the state-of-the-art methods in the machine learning community. To demonstrate its utility, we chose a heterogeneous case study scene, a landscape in Southwest Iran to map PTs. In this area, four main PTs were identified, consisting of shrub land, grass land, semi-shrub land, and shrub land-grass land vegetation. Having developed 21 MLCAs using the same training and validation, datasets led to varying accuracy results. Gaussian process classifier (GPC) was validated as the top-performing classifier, with an overall accuracy (OA) of 90%. GPC follows a Laplace approximation to the Gaussian likelihood under the supervised classification framework, emerging as a very competitive alternative to common MLCAs. Random forests resulted in the second-best performance with an OA of 86%. Two other types of ensemble-learning algorithms, i.e., tree-ensemble learning (bagging) and decision tree (with error-correcting output codes), yielded an OA of 83% and 82%, respectively. Following, thirteen classifiers reported OA between 70% and 80%, and the remaining four classifiers reported an OA below 70%. We conclude that GPC substantially outperformed all classifiers, and thus, provides enormous potential for the classification of a diversity of land-cover types. In addition, its probabilistic formulation provides valuable band ranking information, as well as associated predictive variance at a pixel level. Nevertheless, as these are supervised (data-driven) classifiers, performances depend on the entered training data, meaning that an assessment of all MLCAs is crucial for any application. Our analysis demonstrated the efficacy of ARTMO's MLCA toolbox for an automated evaluation of the classifiers and subsequent thematic mapping.

Quantifying mangrove leaf area index from Sentinel-2 imagery using hybrid models and active learning

Mangrove forests provide vital ecosystem services. The increasing threats to mangrove forest extent and fragmentation can be monitored from space. Accurate spatially explicit quantification of key vegetation characteristics of mangroves, such as leaf area index (LAI), would further advance our monitoring efforts to assess ecosystem health and functioning. Here, we investigated the potential of radiative transfer models (RTM), combined with active learning (AL), to estimate LAI from Sentinel-2 spectral reflectance in the mangrove-dominated region of Ngoc Hien, Vietnam. We validated the retrieval of LAI estimates against in-situ measurements based on hemispherical photography and compared against red-edge NDVI and the Sentinel Application Platform (SNAP) biophysical processor. Our results highlight the performance of physics-based machine learning using Gaussian processes regression (GPR) in combination with AL for the estimation of mangrove LAI. Our AL-driven hybrid GPR model substantially outperformed SNAP (R2 = 0.77 and 0.44 respectively) as well as the red-edge NDVI approach. Comparing two canopy RTMs, the highest accuracy was achieved by PROSAIL (RMSE = 0.13 m2.m-2, NRMSE = 9.57%, MAE = 0.1 m2.m-2). The successful retrieval of mangrove LAI from Sentinel-2 can overcome extensive reliance on scarce in-situ measurements for training seen in other approaches and present a more scalable applicability by relying on the universal principles of physics in combination with uncertainty estimates. AL-based GPR models using RTM simulations allow us to adapt the genericity of RTMs to the peculiarities of distinct ecosystems such as mangrove forests with limited ancillary data. These findings bode potential for retrieving a wider range of vegetation variables to quantify large-scale mangrove ecosystem dynamics in space and time.

Monitoring Key Wheat Growth Variables by Integrating Phenology and UAV Multispectral Imagery Data into Random Forest Model

Rapidly developing remote sensing techniques are shedding new light on large-scale crop growth status monitoring, especially in recent applications of unmanned aerial vehicles (UAVs). Many inversion models have been built to estimate crop growth variables. However, the present methods focused on building models for each single crop stage, and the features generally used in the models are vegetation indices (VI) or joint VI with data derived from UAV-based sensors (e.g., texture, RGB color information, or canopy height). It is obvious these models are either limited to a single stage or have an unstable performance across stages. To address these issues, this study selected four key wheat growth parameters for inversion: above-ground biomass (AGB), plant nitrogen accumulation (PNA) and concentration (PNC), and the nitrogen nutrition index (NNI). Crop data and multispectral data were acquired in five wheat growth stages. Then, the band reflectance and VI were obtained from multispectral data, along with the five stages that were recorded as phenology indicators (PIs) according to the stage of Zadok’s scale. These three types of data formed six combinations (C1–C6): C1 used all of the band reflectances, C2 used all VIs, C3 used bands and VIs, C4 used bands and PIs, C5 used VIs and PIs, and C6 used bands, Vis, and PIs. Some of the combinations were integrated with PIs to verify if PIs can improve the model accuracy. Random forest (RF) was used to build models with combinations of different parameters and evaluate the feature importance. The results showed that all models of different combinations have good performance in the modeling of crop parameters, such as R2 from 0.6 to 0.79 and NRMSE from 10.51 to 15.83%. Then, the model was optimized to understand the importance of PIs. The results showed that the combinations that integrated PIs showed better estimations and the potential of using PIs to minimize features while still achieving good predictions. Finally, the varied model results were evaluated to analyze their performances in different stages or fertilizer treatments. The results showed the models have good performances at different stages or treatments (R2 > 0.6). This paper provides a reference for monitoring and estimating wheat growth parameters based on UAV multispectral imagery and phenology information.

A Review of Hybrid Approaches for Quantitative Assessment of Crop Traits Using Optical Remote Sensing: Research Trends and Future Directions

Remote sensing technology allows to provide information about biochemical and biophysical crop traits and monitor their spatiotemporal dynamics of agriculture ecosystems. Among multiple retrieval techniques, hybrid approaches have been found to provide outstanding accuracy, for instance, for the inference of leaf area index (LAI), fractional vegetation cover (fCover), and leaf and canopy chlorophyll content (LCC and CCC). The combination of radiative transfer models (RTMs) and data-driven models creates an advantage in the use of hybrid methods. Through this review paper, we aim to provide state-of-the-art hybrid retrieval schemes and theoretical frameworks. To achieve this, we reviewed and systematically analyzed publications over the past 22 years. We identified two hybrid-based parametric and hybrid-based nonparametric regression models and evaluated their performance for each variable of interest. From the results of our extensive literature survey, most research directions are now moving towards combining RTM and machine learning (ML) methods in a symbiotic manner. In particular, the development of ML will open up new ways to integrate innovative approaches such as integrating shallow or deep neural networks with RTM using remote sensing data to reduce errors in crop trait estimations and improve control of crop growth conditions in very large areas serving precision agriculture applications.

UAV Remote Sensing for High-Throughput Phenotyping and for Yield Prediction of Miscanthus by Machine Learning Techniques

Miscanthus holds a great potential in the frame of the bioeconomy, and yield prediction can help improve Miscanthus’ logistic supply chain. Breeding programs in several countries are attempting to produce high-yielding Miscanthus hybrids better adapted to different climates and end-uses. Multispectral images acquired from unmanned aerial vehicles (UAVs) in Italy and in the UK in 2021 and 2022 were used to investigate the feasibility of high-throughput phenotyping (HTP) of novel Miscanthus hybrids for yield prediction and crop traits estimation. An intercalibration procedure was performed using simulated data from the PROSAIL model to link vegetation indices (VIs) derived from two different multispectral sensors. The random forest algorithm estimated with good accuracy yield traits (light interception, plant height, green leaf biomass, and standing biomass) using 15 VIs time series, and predicted yield using peak descriptors derived from these VIs time series with root mean square error of 2.3 Mg DM ha−1. The study demonstrates the potential of UAVs’ multispectral images in HTP applications and in yield prediction, providing important information needed to increase sustainable biomass production.

Improving the remote estimation of soil organic carbon in complex ecosystems with Sentinel-2 and GIS using Gaussian processes regression

BACKGROUND AND AIMS

The quantitative retrieval of soil organic carbon (SOC) storage, particularly for soils with a large potential for carbon sequestration, is of global interest due to its link with the carbon cycle and the mitigation of climate change. However, complex ecosystems with good soil qualities for SOC storage are poorly studied.

METHODS

The interrelation between SOC and various vegetation remote sensing drivers is understood to demonstrate the link between the carbon stored in the vegetation layer and SOC of the top soil layers. Based on the mapping of SOC in two horizons (0-30 cm and 30-60 cm) we predict SOC with high accuracy in the complex and mountainous heterogeneous páramo system in Ecuador. A large SOC database (in weight % and in Mg/ha) of 493 and 494 SOC sampling data points from 0-30 cm and 30-60 cm soil profiles, respectively, were used to calibrate GPR models using Sentinel-2 and GIS predictors (i.e., Temperature, Elevation, Soil Taxonomy, Geological Unit, Slope Length and Steepness (LS Factor), Orientation and Precipitation).

RESULTS

In the 0-30 cm soil profile, the models achieved a R² of 0.85 (SOC%) and a R² of 0.79 (SOC Mg/ha). In the 30-60 cm soil profile, models achieved a R² of 0.86 (SOC%), and a R² of 0.79 (SOC Mg/ha).

CONCLUSIONS

The used Sentinel-2 variables (FVC, CWC, LCC/C_ab, band 5 (705 nm) and SeLI index) were able to improve the estimation accuracy between 3-21% compared to previous results of the same study area. CWC emerged as the most relevant biophysical variable for SOC prediction.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s11104-022-05506-1.

Estimating soil moisture content under grassland with hyperspectral data using radiative transfer modelling and machine learning

The monitoring of soil moisture content (SMC) at very high spatial resolution (<10m) using unmanned aerial systems (UAS) is of high interest for precision agriculture and the validation of large scale SMC products. Data-driven approaches are the most common method to retrieve SMC with UAS-borne data at water limited sites over non-disturbed agricultural crops. A major disadvantage of data-driven algorithms is the limited transferability in space and time and the need of a high number of ground reference samples. Physically-based approaches are less dependent on the amount of samples and are transferable in space and time. This study explores the potential of (1) a hybrid method targeting the soil brightness factor of the PROSAIL model using a variational heteroscedastic Gaussian Processes regression (VHGPR) algorithm, and (2) a data-driven method employing VHGPR for the retrieval of SMC over three grassland sites based on UAS-borne VIS-NIR (399-1001 nm) hyperspectral data. The sites were managed by mowing (Fendt), grazing (Grosses Bruch) and irrigation (Marquardt). With these distinct local pre-conditions we aimed to identify factors that favor and limit the retrieval of SMC. The hybrid approach presented encouraging results in Marquardt (RMSE = 1.5 Vol_%, R2 = 0.2). At the permanent grassland sites (Fendt, Grosses Bruch) the thatch layer jeopardized the application of the hybrid model. We identified the complex canopy structure of grassland as the main factor impacting the hybrid SMC retrieval. The data-driven approach showed high accuracy for Fendt (R2 = 0.84, RMSE = 8.66) and Marquardt (R2 = 0.4, RMSE = 10.52). All data-driven models build on the LAI-SMC relationship. However, this relationship was hampered by mowing (Fendt), leading to a lack of transferability in time. The alteration of plant traits by grazing prevents finding a relationship with SMC in Grosses Bruch. In Marquardt, we identified the timelag between changes in SMC and plant response as the main reason of decrease in model accuracy. Yet, the model performance is accurate in undisturbed and water-limited areas (Marquardt). The analysis points to challenges that need to be tackled in future research and opens the discussion for the development of robust models to retrieve high resolution SMC from UAS-borne remote sensing observations.

Revealing the Complex Relationship Among Hyperspectral Reflectance, Photosynthetic Pigments, and Growth in Norway Spruce Ecotypes

Norway spruce has a wide natural distribution range, harboring substantial physiological and genetic variation. There are three altitudinal ecotypes described in this species. Each ecotype has been shaped by natural selection and retains morphological and physiological characteristics. Foliar spectral reflectance is readily used in evaluating the physiological status of crops and forest ecosystems. However, underlying genetics of foliar spectral reflectance and pigment content in forest trees has rarely been investigated. We assessed the reflectance in a clonal bank comprising three ecotypes in two dates covering different vegetation season conditions. Significant seasonal differences in spectral reflectance among Norway spruce ecotypes were manifested in a wide-ranging reflectance spectrum. We estimated significant heritable variation and uncovered phenotypic and genetic correlations among growth and physiological traits through bivariate linear models utilizing spatial corrections. We confirmed the relative importance of the red edge within the context of the study site's ecotypic variation. When interpreting these findings, growth traits such as height, diameter, crown length, and crown height allowed us to estimate variable correlations across the reflectance spectrum, peaking in most cases in wavelengths connected to water content in plant tissues. Finally, significant differences among ecotypes in reflectance and other correlated traits were detected.

Prototyping Crop Traits Retrieval Models for CHIME: Dimensionality Reduction Strategies Applied to PRISMA Data

In preparation for new-generation imaging spectrometer missions and the accompanying unprecedented inflow of hyperspectral data, optimized models are needed to generate vegetation traits routinely. Hybrid models, combining radiative transfer models with machine learning algorithms, are preferred, however, dealing with spectral collinearity imposes an additional challenge. In this study, we analyzed two spectral dimensionality reduction methods: principal component analysis (PCA) and band ranking (BR), embedded in a hybrid workflow for the retrieval of specific leaf area (SLA), leaf area index (LAI), canopy water content (CWC), canopy chlorophyll content (CCC), the fraction of absorbed photosynthetic active radiation (FAPAR), and fractional vegetation cover (FVC). The SCOPE model was used to simulate training data sets, which were optimized with active learning. Gaussian process regression (GPR) algorithms were trained over the simulations to obtain trait-specific models. The inclusion of PCA and BR with 20 features led to the so-called GPR-20PCA and GPR-20BR models. The 20PCA models encompassed over 99.95% cumulative variance of the full spectral data, while the GPR-20BR models were based on the 20 most sensitive bands. Validation against in situ data obtained moderate to optimal results with normalized root mean squared error (NRMSE) from 13.9% (CWC) to 22.3% (CCC) for GPR-20PCA models, and NRMSE from 19.6% (CWC) to 29.1% (SLA) for GPR-20BR models. Overall, the GPR-20PCA slightly outperformed the GPR-20BR models for all six variables. To demonstrate mapping capabilities, both models were tested on a PRecursore IperSpettrale della Missione Applicativa (PRISMA) scene, spectrally resampled to Copernicus Hyperspectral Imaging Mission for the Environment (CHIME), over an agricultural test site (Jolanda di Savoia, Italy). The two strategies obtained plausible spatial patterns, and consistency between the two models was highest for FVC and LAI (R 2 = 0.91, R 2 = 0.86) and lowest for SLA mapping (R 2 = 0.53). From these findings, we recommend implementing GPR-20PCA models as the most efficient strategy for the retrieval of multiple crop traits from hyperspectral data streams. Hence, this workflow will support and facilitate the preparations of traits retrieval models from the next-generation operational CHIME.

Multi-Temporal Landsat-8 Images for Retrieval and Broad Scale Mapping of Soil Copper Concentration Using Empirical Models

Mapping soil heavy metal concentration using machine learning models based on readily available satellite remote sensing images is highly desirable. Accurate mapping relies on appropriate data, feature extraction, and model selection. To this end, a data processing pipeline for soil copper (Cu) concentration estimation has been designed. First, instead of using single Landsat scenes, the utilization of multiple Landsat scenes of the same location over time is considered. Second, to generate a preferred feature set as input to a regression model, a number of feature extraction methods are motivated and compared. Third, to find a preferred regression model, a variety of approaches are implemented and compared for accuracy. In this research, 11 Landsat-8 images from 2013 to 2017 of Gulin County, Sichuan China, and 138 soil samples with lab-measured Cu concentrations collected from the area in 2015 are used. A variety a metrics under cross-validation are used for comparison. The results indicate that multi-temporal images increase accuracy compared to single Landsat images. The preferred feature extraction varies based on the regression model used; however, the best results are obtained using support vector regression and the original data. The final soil Cu map generated using the recommended data processing pipeline shows a consistent spatial pattern with a ground-truth land cover classification map. These results indicate that machine learning has the ability to perform large-scale soil heavy metal mapping from widely available satellite remote sensing images.

Gaussian processes retrieval of crop traits in Google Earth Engine based on Sentinel-2 top-of-atmosphere data

The unprecedented availability of optical satellite data in cloud-based computing platforms, such as Google Earth Engine (GEE), opens new possibilities to develop crop trait retrieval models from the local to the planetary scale. Hybrid retrieval models are of interest to run in these platforms as they combine the advantages of physically- based radiative transfer models (RTM) with the flexibility of machine learning regression algorithms. Previous research with GEE primarily relied on processing bottom-of-atmosphere (BOA) reflectance data, which requires atmospheric correction. In the present study, we implemented hybrid models directly into GEE for processing Sentinel-2 (S2) Level-1C (L1C) top-of-atmosphere (TOA) reflectance data into crop traits. To achieve this, a training dataset was generated using the leaf-canopy RTM PROSAIL in combination with the atmospheric model 6SV. Gaussian process regression (GPR) retrieval models were then established for eight essential crop traits namely leaf chlorophyll content, leaf water content, leaf dry matter content, fractional vegetation cover, leaf area index (LAI), and upscaled leaf variables (i.e., canopy chlorophyll content, canopy water content and canopy dry matter content). An important pre-requisite for implementation into GEE is that the models are sufficiently light in order to facilitate efficient and fast processing. Successful reduction of the training dataset by 78% was achieved using the active learning technique Euclidean distance-based diversity (EBD). With the EBD-GPR models, highly accurate validation results of LAI and upscaled leaf variables were obtained against in situ field data from the validation study site Munich-North-Isar (MNI), with normalized root mean square errors (NRMSE) from 6% to 13%. Using an independent validation dataset of similar crop types (Italian Grosseto test site), the retrieval models showed moderate to good performances for canopy-level variables, with NRMSE ranging from 14% to 50%, but failed for the leaf-level estimates. Obtained maps over the MNI site were further compared against Sentinel-2 Level 2 Prototype Processor (SL2P) vegetation estimates generated from the ESA Sentinels' Application Platform (SNAP) Biophysical Processor, proving high consistency of both retrievals (R 2 from 0.80 to 0.94). Finally, thanks to the seamless GEE processing capability, the TOA-based mapping was applied over the entirety of Germany at 20 m spatial resolution including information about prediction uncertainty. The obtained maps provided confidence of the developed EBD-GPR retrieval models for integration in the GEE framework and national scale mapping from S2-L1C imagery. In summary, the proposed retrieval workflow demonstrates the possibility of routine processing of S2 TOA data into crop traits maps at any place on Earth as required for operational agricultural applications.

Linking Land Use and Plant Functional Diversity Patterns in Sabah, Borneo, through Large-Scale Spatially Continuous Sentinel-2 Inference

Global biodiversity losses erode the functioning of our vital ecosystems. Functional diversity is increasingly recognized as a critical link between biodiversity and ecosystem functioning. Satellite earth observation was proposed to address the current absence of information on large-scale continuous patterns of plant functional diversity. This study demonstrates the inference and spatial mapping of functional diversity metrics through satellite remote sensing over a large key biodiversity region (Sabah, Malaysian Borneo, ~53,000 km2) and compares the derived estimates across a land-use gradient as an initial qualitative assessment to test the potential merits of the approach. Functional traits (leaf water content, chlorophyll-a and -b, and leaf area index) were estimated from Sentinel-2 spectral reflectance using a pre-trained neural network on radiative transfer modeling simulations. Multivariate functional diversity metrics were calculated, including functional richness, divergence, and evenness. Spatial patterns of functional diversity were related to land-use data distinguishing intact forest, logged forest, and oil palm plantations. Spatial patterns of satellite remotely sensed functional diversity are significantly related to differences in land use. Intact forests, as well as logged forests, featured consistently higher functional diversity compared to oil palm plantations. Differences were profound for functional divergence, whereas functional richness exhibited relatively large variances within land-use classes. By linking large-scale patterns of functional diversity as derived from satellite remote sensing to land-use information, this study indicated initial responsiveness to broad human disturbance gradients over large geographical and spatially contiguous extents. Despite uncertainties about the accuracy of the spatial patterns, this study provides a coherent early application of satellite-derived functional diversity toward further validation of its responsiveness across ecological gradients.

Multi-Season Phenology Mapping of Nile Delta Croplands Using Time Series of Sentinel-2 and Landsat 8 Green LAI

Space-based cropland phenology monitoring substantially assists agricultural managing practices and plays an important role in crop yield predictions. Multitemporal satellite observations allow analyzing vegetation seasonal dynamics over large areas by using vegetation indices or by deriving biophysical variables. The Nile Delta represents about half of all agricultural lands of Egypt. In this region, intensifying farming systems are predominant and multi-cropping rotations schemes are increasing, requiring a high temporal and spatial resolution monitoring for capturing successive crop growth cycles. This study presents a workflow for cropland phenology characterization and mapping based on time series of green Leaf Area Index (LAI) generated from NASA's Harmonized Landsat 8 (L8) and Sentinel-2 (S2) surface reflectance dataset from 2016 to 2019. LAI time series were processed for each satellite dataset, which were used separately and combined to identify seasonal dynamics for a selection of crop types (wheat, clover, maize and rice). For the combination of L8 with S2 LAI products, we proposed two time series smoothing and fitting methods: (1) the Savitzky-Golay (SG) filter and (2) the Gaussian Processes Regression (GPR) fitting function. Single-sensor and L8-S2 combined LAI time series were used for the calculation of key crop Land Surface Phenology (LSP) metrics (start of season, end of season, length of season), whereby the detection of cropland growing seasons was based on two established threshold methods, i.e., a seasonal or a relative amplitude value. Overall, the developed phenology extraction scheme enabled identifying up to two successive crop cycles within a year, with a superior performance observed for the seasonal than for the relative threshold method, in terms of consistency and cropland season detection capability. Differences between the time series collections were analyzed by comparing the phenology metrics per crop type and year. Results suggest that L8-S2 combined LAI data streams with GPR led to a more precise detection of the start and end of growing seasons for most crop types, reaching an overall detection of 74% over the total planted crops versus 69% with S2 and 63% with L8 alone. Finally, the phenology mapping allowed us to evaluate the spatial and temporal evolution of the croplands over the agroecosystem in the Nile Delta.

Evaluation of Hybrid Models to Estimate Chlorophyll and Nitrogen Content of Maize Crops in the Framework of the Future CHIME Mission

In the next few years, the new Copernicus Hyperspectral Imaging Mission (CHIME) is foreseen to be launched by the European Space Agency (ESA). This missions will provide an unprecedented amount of hyperspectral data, enabling new research possibilities within several fields of natural resources, including the "agriculture and food security" domain. In order to efficiently exploit this upcoming hyperspectral data stream, new processing methods and techniques need to be studied and implemented. In this work, the hybrid approach (HYB) and its variant, featuring sampling dimensionality reduction through active learning heuristics (HAL), were applied to CHIME-like data to evaluate the retrieval of crop traits, such as chlorophyll and nitrogen content at both leaf (LCC and LNC) and canopy level (CCC and CNC). The results showed that HYB was able to provide reliable estimations at canopy level (R2 = 0.79, RMSE = 0.38 g m-2 for CCC and R2 = 0.84, RMSE = 1.10 g m-2 for CNC) but failed at leaf level. The HAL approach improved retrieval accuracy at canopy level (best metric: R2 = 0.88 and RMSE = 0.21 g m-2 for CCC; R2 = 0.93 and RMSE = 0.71 g m-2 for CNC), providing good results also at leaf level (best metrics: R2 = 0.72 and RMSE = 3.31 μg cm-2 for LCC; R2 = 0.56 and RMSE = 0.02 mg cm-2 for LNC). The promising results obtained through the hybrid approach support the feasibility of an operational retrieval of chlorophyll and nitrogen content, e.g., in the framework of the future CHIME mission. However, further efforts are required to investigate the approach across different years, sites and crop types in order to improve its transferability to other contexts.

Machine Learning Strategies for the Retrieval of Leaf-Chlorophyll Dynamics: Model Choice, Sequential Versus Retraining Learning, and Hyperspectral Predictors

Monitoring leaf Chlorophyll (Chl) in-situ is labor-intensive, limiting representative sampling for detailed mapping of Chl variability at field scales across time. Unmanned aeria-l vehicles (UAV) and hyperspectral cameras provide flexible platforms for observing agricultural systems, overcoming this spatio-temporal sampling constraint. Here, we evaluate a customized machine learning (ML) workflow to retrieve multi-temporal leaf-Chl levels, combining sub-centimeter resolution UAV-hyperspectral imagery (400-1,000 nm) with leaf-level reflectance spectra and SPAD measurements, capturing temporal correlations, selecting relevant predictors, and retrieving accurate results under different conditions. The study is performed within a phenotyping experiment to monitor wild tomato plants' development. Several analyses were conducted to evaluate multiple ML strategies, including: (1) exploring sequential versus retraining learning; (2) comparing insights gained from using 272 spectral bands versus 60 pigment-based vegetation indices (VIs); and (3) assessing six regression methods (linear, partial-least-square regression; PLSR, decision trees, support vector, ensemble trees, and Gaussian process; GPR). Goodness-of-fit (R 2) and accuracy metrics (MAE, RMSE) were determined using training/testing and validation data subsets to assess the models' performance. Overall, while equally good performance was obtained using either PLSR, GPR, or random forest, results show: (1) the retraining strategy improved the ability of most of the approaches to model SPAD-based Chl dynamics; (2) comparative analysis between retrievals and validation data distributions informed the models' ability to capture Chl dynamics through SPAD levels; (3) VI predictors slightly improved R 2 (e.g., from 0.59 to 0.74 units for GPR) and accuracy (e.g., MAE and RMSE differences of up to 2 SPAD units) in specific algorithms; (4) feature importance examined through these methods, revealed strong overlaps between relevant bands and VI predictors, highlighting a few decisive spectral ranges and indices useful for retrieving leaf-Chl levels. The proposed ML framework allows the retrieval of high-quality spatially distributed and multi-temporal SPAD-based chlorophyll maps at an ultra-high pixel resolution (e.g., 7 mm).

Quantifying Fundamental Vegetation Traits over Europe Using the Sentinel-3 OLCI Catalogue in Google Earth Engine

Thanks to the emergence of cloud-computing platforms and the ability of machine learning methods to solve prediction problems efficiently, this work presents a workflow to automate spatiotemporal mapping of essential vegetation traits from Sentinel-3 (S3) imagery. The traits included leaf chlorophyll content (LCC), leaf area index (LAI), fraction of absorbed photosynthetically active radiation (FAPAR), and fractional vegetation cover (FVC), being fundamental for assessing photosynthetic activity on Earth. The workflow involved Gaussian process regression (GPR) algorithms trained on top-of-atmosphere (TOA) radiance simulations generated by the coupled canopy radiative transfer model (RTM) SCOPE and the atmospheric RTM 6SV. The retrieval models, named to S3-TOA-GPR-1.0, were directly implemented in Google Earth Engine (GEE) to enable the quantification of the traits from TOA data as acquired from the S3 Ocean and Land Colour Instrument (OLCI) sensor.Following good to high theoretical validation results with normalized root mean square error (NRMSE) ranging from 5% (FAPAR) to 19% (LAI), a three fold evaluation approach over diverse sites and land cover types was pursued: (1) temporal comparison against LAI and FAPAR products obtained from Moderate Resolution Imaging Spectroradiometer (MODIS) for the time window 2016-2020, (2) spatial difference mapping with Copernicus Global Land Service (CGLS) estimates, and (3) direct validation using interpolated in situ data from the VALERI network. For all three approaches, promising results were achieved. Selected sites demonstrated coherent seasonal patterns compared to LAI and FAPAR MODIS products, with differences between spatially averaged temporal patterns of only 6.59%. In respect of the spatial mapping comparison, estimates provided by the S3-TOA-GPR-1.0 models indicated highest consistency with FVC and FAPAR CGLS products. Moreover, the direct validation of our S3-TOA-GPR-1.0 models against VALERI estimates indicated with regard to jurisdictional claims in good retrieval performance for LAI, FAPAR and FVC. We conclude that our retrieval workflow of spatiotemporal S3 TOA data processing into GEE opens the path towards global monitoring of fundamental vegetation traits, accessible to the whole research community.

Retrieval of Crop Variables from Proximal Multispectral UAV Image Data Using PROSAIL in Maize Canopy

Mapping crop variables at different growth stages is crucial to inform farmers and plant breeders about the crop status. For mapping purposes, inversion of canopy radiative transfer models (RTMs) is a viable alternative to parametric and non-parametric regression models, which often lack transferability in time and space. Due to the physical nature of RTMs, inversion outputs can be delivered in sound physical units that reflect the underlying processes in the canopy. In this study, we explored the capabilities of the coupled leaf-canopy RTM PROSAIL applied to high-spatial-resolution (0.015 m) multispectral unmanned aerial vehicle (UAV) data to retrieve the leaf chlorophyll content (LCC), leaf area index (LAI) and canopy chlorophyll content (CCC) of sweet and silage maize throughout one growing season. Two different retrieval methods were tested: (i) applying the RTM inversion scheme to mean reflectance data derived from single breeding plots (mean reflectance approach) and (ii) applying the same inversion scheme to an orthomosaic to separately retrieve the target variables for each pixel of the breeding plots (pixel-based approach). For LCC retrieval, soil and shaded pixels were removed by applying simple vegetation index thresholding. Retrieval of LCC from UAV data yielded promising results compared to ground measurements (sweet maize RMSE = 4.92 μg/cm2, silage maize RMSE = 3.74 μg/cm2) when using the mean reflectance approach. LAI retrieval was more challenging due to the blending of sunlit and shaded pixels present in the UAV data, but worked well at the early developmental stages (sweet maize RMSE = 0.70m2/m2, silage RMSE = 0.61m2/m2 across all dates). CCC retrieval significantly benefited from the pixel-based approach compared to the mean reflectance approach (RMSEs decreased from 45.6 to 33.1 μg/m2). We argue that high-resolution UAV imagery is well suited for LCC retrieval, as shadows and background soil can be precisely removed, leaving only green plant pixels for the analysis. As for retrieving LAI, it proved to be challenging for two distinct varieties of maize that were characterized by contrasting canopy geometry.

Phenotypic Traits Estimation and Preliminary Yield Assessment in Different Phenophases of Wheat Breeding Experiment Based on UAV Multispectral Images

The utility of unmanned aerial vehicles (UAV) imagery in retrieving phenotypic data to support plant breeding research has been a topic of increasing interest in recent years. The advantages of image-based phenotyping are related to the high spatial and temporal resolution of the retrieved data and the non-destructive and rapid method of data acquisition. This study trains parametric and nonparametric regression models to retrieve leaf area index (LAI), fraction of absorbed photosynthetically active radiation (fAPAR), fractional vegetation cover (fCover), leaf chlorophyll content (LCC), canopy chlorophyll content (CCC), and grain yield (GY) of winter durum wheat breeding experiment from four-bands UAV images. A ground dataset, collected during two field campaigns and complemented with data from a previous study, is used for model development. The dataset is split at random into two parts, one for training and one for testing the models. The tested parametric models use the vegetation index formula and parametric functions. The tested nonparametric models are partial least square regression (PLSR), random forest regression (RFR), support vector regression (SVR), kernel ridge regression (KRR), and Gaussian processes regression (GPR). The retrieved biophysical variables along with traditional phenotypic traits (plant height, yield, and tillering) are analysed for detection of genetic diversity, proximity, and similarity in the studied genotypes. Analysis of variance (ANOVA), Duncan’s multiple range test, correlation analysis, and principal component analysis (PCA) are performed with the phenotypic traits. The parametric and nonparametric models show close results for GY retrieval, with parametric models indicating slightly higher accuracy (R2 = 0.49; MRSE = 0.58 kg/plot; rRMSE = 6.1%). However, the nonparametric model, GPR, computes per pixel uncertainty estimation, making it more appealing for operational use. Furthermore, our results demonstrate that grain filling was better than flowering phenological stage to predict GY. The nonparametric models show better results for biophysical variables retrieval, with GPR presenting the highest prediction performance. Nonetheless, robust models are found only for LAI (R2 = 0.48; MRSE = 0.64; rRMSE = 13.5%) and LCC (R2 = 0.49; MRSE = 31.57 mg m−2; rRMSE = 6.4%) and therefore these are the only remotely sensed phenotypic traits included in the statistical analysis for preliminary assessment of wheat productivity. The results from ANOVA and PCA illustrate that the retrieved remotely sensed phenotypic traits are a valuable addition to the traditional phenotypic traits for plant breeding studies. We believe that these preliminary results could speed up crop improvement programs; however, stronger interdisciplinary research is still needed, as well as uncertainty estimation of the remotely sensed phenotypic traits.

Spectral Retrieval of Eucalypt Leaf Biochemical Traits by Inversion of the Fluspect-Cx Model

Leaf biochemical traits indicating early symptoms of plant stress can be assessed using imaging spectroscopy combined with radiative transfer modelling (RTM). In this study, we assessed the potential applicability of the leaf radiative transfer model Fluspect-Cx to simulate optical properties and estimate leaf biochemical traits through inversion of two native Australian eucalypt species: Eucalyptus dalrympleana and E. delegetensis. The comparison of measured and simulated optical properties revealed the necessity to recalibrate the refractive index and specific absorption coefficients of the eucalypt leaves’ biochemical constituents. Subsequent validation of the modified Fluspect-Cx showed a closer agreement with the spectral measurements. The average root mean square error (RMSE) of reflectance, transmittance and absorptance values within the wavelength interval of 450–1600 nm was smaller than 1%. We compared the performance of both the original and recalibrated Fluspect-Cx versions through inversions aiming to simultaneously retrieve all model inputs from leaf optical properties with and without prior information. The inversion of recalibrated Fluspect-Cx constrained by laboratory-based measurements produced a superior accuracy in estimations of leaf water content (RMSE = 0.0013 cm, NRMSE = 6.55%) and dry matter content (RMSE = 0.0036 g·cm−2, NRMSE = 21.28%). The estimation accuracies of chlorophyll content (RMSE = 8.46 µg·cm−2, NRMSE = 24.73%), carotenoid content (RMSE = 3.83 µg·cm−2, NRMSE = 30.82%) and anthocyanin content (RMSE = 1.69 µg·cm−2, NRMSE = 37.12%) were only marginally better than for the inversion without any constraints. Additionally, we investigated the possibility to substitute the prior information derived in the laboratory by non-destructive reflectance-based spectral indices sensitive to the retrieved biochemical traits, resulting in the most accurate estimation of carotenoid content (RMSE = 3.65 µg·cm−2, NRMSE = 29%). Future coupling of the recalibrated Fluspect with a forest canopy RTM is expected to facilitate retrieval of biophysical traits from spectral air/space-borne image data, allowing for assessing the actual physiological status and health of eucalypt forest canopies.

Winter Wheat Nitrogen Estimation Based on Ground-Level and UAV-Mounted Sensors

A better understanding of wheat nitrogen status is important for improving N fertilizer management in precision farming. In this study, four different sensors were evaluated for their ability to estimate winter wheat nitrogen. A Gaussian process regression (GPR) method with the sequential backward feature removal (SBBR) routine was used to identify the best combinations of vegetation indices (VIs) sensitive to wheat N indicators for different sensors. Wheat leaf N concentration (LNC), plant N concentration (PNC), and the nutrition index (NNI) were estimated by the VIs through parametric regression (PR), multivariable linear regression (MLR), and Gaussian process regression (GPR). The study results reveal that the optical fluorescence sensor provides more accurate estimates of winter wheat N status at a low-canopy coverage condition. The Dualex Nitrogen Balance Index (NBI) is the best leaf-level indicator for wheat LNC, PNC and NNI at the early wheat growth stage. At the early growth stage, Multiplex indices are the best canopy-level indicators for LNC, PNC, and NNI. At the late growth stage, ASD VIs provide accurate estimates for wheat N indicators. This study also reveals that the GPR with SBBR analysis method provides more accurate estimates of winter wheat LNC, PNC, and NNI, with the best VI combinations for these sensors across the different winter wheat growth stages, compared with the MLR and PR methods.

Monitoring Cropland Phenology on Google Earth Engine Using Gaussian Process Regression

Monitoring cropland phenology from optical satellite data remains a challenging task due to the influence of clouds and atmospheric artifacts. Therefore, measures need to be taken to overcome these challenges and gain better knowledge of crop dynamics. The arrival of cloud computing platforms such as Google Earth Engine (GEE) has enabled us to propose a Sentinel-2 (S2) phenology end-to-end processing chain. To achieve this, the following pipeline was implemented: (1) the building of hybrid Gaussian Process Regression (GPR) retrieval models of crop traits optimized with active learning, (2) implementation of these models on GEE (3) generation of spatiotemporally continuous maps and time series of these crop traits with the use of gap-filling through GPR fitting, and finally, (4) calculation of land surface phenology (LSP) metrics such as the start of season (SOS) or end of season (EOS). Overall, from good to high performance was achieved, in particular for the estimation of canopy-level traits such as leaf area index (LAI) and canopy chlorophyll content, with normalized root mean square errors (NRMSE) of 9% and 10%, respectively. By means of the GPR gap-filling time series of S2, entire tiles were reconstructed, and resulting maps were demonstrated over an agricultural area in Castile and Leon, Spain, where crop calendar data were available to assess the validity of LSP metrics derived from crop traits. In addition, phenology derived from the normalized difference vegetation index (NDVI) was used as reference. NDVI not only proved to be a robust indicator for the calculation of LSP metrics, but also served to demonstrate the good phenology quality of the quantitative trait products. Thanks to the GEE framework, the proposed workflow can be realized anywhere in the world and for any time window, thus representing a shift in the satellite data processing paradigm. We anticipate that the produced LSP metrics can provide meaningful insights into crop seasonal patterns in a changing environment that demands adaptive agricultural production.

Intelligent Sampling for Vegetation Nitrogen Mapping Based on Hybrid Machine Learning Algorithms

Upcoming satellite imaging spectroscopy missions will deliver spatiotemporal explicit data streams to be exploited for mapping vegetation properties, such as nitrogen (N) content. Within retrieval workflows for real-time mapping over agricultural regions, such crop-specific information products need to be derived precisely and rapidly. To allow fast processing, intelligent sampling schemes for training databases should be incorporated to establish efficient machine learning (ML) models. In this study, we implemented active learning (AL) heuristics using kernel ridge regression (KRR) to minimize and optimize a training database for variational heteroscedastic Gaussian processes regression (VHGPR) to estimate aboveground N content. Several uncertainty and diversity criteria were applied on a lookup table (LUT) composed of aboveground N content and corresponding hyperspectral reflectance simulated by the PROSAIL-PRO model. The best-performing AL criteria were Euclidian distance-based diversity (EBD) resulting in a reduction of the LUT training data set by 81% (50 initial samples plus 141 samples selected from a pool of 1000 samples). This reduced LUT was used for training VHGPR, which is not only a competitive algorithm but also provides uncertainty estimates. Validation against in situ N reference data provided excellent results with a root-mean-square error (RMSE) of 1.84 g/m2 and a coefficient of determination (R2 ) of 0.92. Mapping aboveground N content over an agricultural region yielded reliable estimates and meaningful associated uncertainties. These promising results encourage the transfer of such hybrid workflows into space and time within the frame of future operational N monitoring from satellite imaging spectroscopy data.

Assessing Non-Photosynthetic Cropland Biomass from Spaceborne Hyperspectral Imagery

Non-photosynthetic vegetation (NPV) biomass has been identified as a priority variable for upcoming spaceborne imaging spectroscopy missions, calling for a quantitative estimation of lignocellulosic plant material as opposed to the sole indication of surface coverage. Therefore, we propose a hybrid model for the retrieval of non-photosynthetic cropland biomass. The workflow included coupling the leaf optical model PROSPECT-PRO with the canopy reflectance model 4SAIL, which allowed us to simulate NPV biomass from carbon-based constituents (CBC) and leaf area index (LAI). PROSAIL-PRO provided a training database for a Gaussian process regression (GPR) algorithm, simulating a wide range of non-photosynthetic vegetation states. Active learning was employed to reduce and optimize the training data set. In addition, we applied spectral dimensionality reduction to condense essential information of non-photosynthetic signals. The resulting NPV-GPR model was successfully validated against soybean field data with normalized root mean square error (nRMSE) of 13.4% and a coefficient of determination (R2) of 0.85. To demonstrate mapping capability, the NPV-GPR model was tested on a PRISMA hyperspectral image acquired over agricultural areas in the North of Munich, Germany. Reliable estimates were mainly achieved over senescent vegetation areas as suggested by model uncertainties. The proposed workflow is the first step towards the quantification of non-photosynthetic cropland biomass as a next-generation product from near-term operational missions, such as CHIME.

Emulation of Sun-Induced Fluorescence from Radiance Data Recorded by the HyPlant Airborne Imaging Spectrometer

The retrieval of sun-induced fluorescence (SIF) from hyperspectral radiance data grew to maturity with research activities around the FLuorescence EXplorer satellite mission FLEX, yet full-spectrum estimation methods such as the spectral fitting method (SFM) are computationally expensive. To bypass this computational load, this work aims to approximate the SFM-based SIF retrieval by means of statistical learning, i.e., emulation. While emulators emerged as fast surrogate models of simulators, the accuracy-speedup trade-offs are still to be analyzed when the emulation concept is applied to experimental data. We evaluated the possibility of approximating the SFM-like SIF output directly based on radiance data while minimizing the loss in precision as opposed to SFM-based SIF. To do so, we implemented a double principal component analysis (PCA) dimensionality reduction, i.e., in both input and output, to achieve emulation of multispectral SIF output based on hyperspectral radiance data. We then evaluated systematically: (1) multiple machine learning regression algorithms, (2) number of principal components, (3) number of training samples, and (4) quality of training samples. The best performing SIF emulator was then applied to a HyPlant flight line containing at sensor radiance information, and the results were compared to the SFM SIF map of the same flight line. The emulated SIF map was quasi-instantaneously generated, and a good agreement against the reference SFM map was obtained with a R 2 of 0.88 and NRMSE of 3.77%. The SIF emulator was subsequently applied to 7 HyPlant flight lines to evaluate its robustness and portability, leading to a R 2 between 0.68 and 0.95, and a NRMSE between 6.42% and 4.13%. Emulated SIF maps proved to be consistent while processing time was in the order of 3 min. In comparison, the original SFM needed approximately 78 min to complete the SIF processing. Our results suggest that emulation can be used to efficiently reduce computational loads of SIF retrieval methods.