Hyperspectral Leaf Reflectance as Proxy for Photosynthetic Capacities: An Ensemble Approach Based on Multiple Machine Learning Algorithms

Determination of antioxidant capacity and phenolic content of haskap berries (Lonicera caerulea L.) by attenuated total reflectance-Fourier transformed-infrared spectroscopy

The total phenolic content (TPC) and antioxidant capacity (TAC) of haskap berries cultivated in various locations across Alberta were analyzed using attenuated total reflectance-Fourier transform infrared (ATR-FTIR) spectroscopy. The Folin-Ciocalteu assay was used to determine TPC, while TAC was quantified by 2,2-diphenyl-1-picrylhydrazl radicals (DPPH) assay and oxygen radical absorbance capacity (ORAC) assay. Three tenfold cross-validated partial least-squares regression (PLSR) models and three fivefold cross-validated deep learning models were developed separately based on FT-IR spectra collected from 22 haskap berry samples and their corresponding reference values determined through Folin-Ciocalteu, DPPH, and ORAC assays. The deep learning models (R2 = 0.95, 0.93, and 0.90 for Folin-Ciocalteu, DPPH, and ORAC assays, respectively) demonstrated better prediction capability compared to the PLSR models (R2 = 0.74, 0.72, and 0.66 for Folin-Ciocalteu, DPPH, and ORAC assays, respectively). In addition, PLS loading plots indicated that phenolic contents and polysaccharides in haskap berries could contribute to their antioxidant capacity. Using ATR-FTIR to estimate the TPC and TAC of fruits offers a rapid alternative to the conventional chemical assays.

Using VIS-NIR hyperspectral imaging and deep learning for non-destructive high-throughput quantification and visualization of nutrients in wheat grains

High-throughput and low-cost quantification of the nutrient content in crop grains is crucial for food processing and nutritional research. However, traditional methods are time-consuming and destructive. A high-throughput and low-cost method of quantification of wheat nutrients with VIS-NIR (400-1700 nm) hyperspectral imaging is proposed in this study. Stepwise linear regression (SLR) was used to predict hundreds of nutrients accurately (R2 > 0.6); results improved when the hyperspectral data was processed with the first derivative. Knockout materials were also used to verify their practical application value. Various nutrients' characteristic wavelengths were mainly concentrated in the visible regions of 400-500 nm and 900-1000 nm. Finally, we proposed an improved pix2pix conditional generative network model to visualize the nutrients distribution and showed better results compared with the original. This research highlights the potential of hyperspectral technology in high-throughput and non-destructive determination and visualization of grain nutrients with deep learning.

Prediction of wheat SPAD using integrated multispectral and support vector machines

Rapidly obtaining the chlorophyll content of crop leaves is of great significance for timely diagnosis of crop health and effective field management. Multispectral imagery obtained from unmanned aerial vehicles (UAV) is being used to remotely sense the SPAD (Soil and Plant Analyzer Development) values of wheat crops. However, existing research has not yet fully considered the impact of different growth stages and crop populations on the accuracy of SPAD estimation. In this study, 300 materials from winter wheat natural populations in Xinjiang, collected between 2020 to 2022, were analyzed. UAV multispectral images were obtained in the experimental area, and vegetation indices were extracted to analyze the correlation between the selected vegetation indices and SPAD values. The input variables for the model were screened, and a support vector machine (SVM) model was constructed to estimate SPAD values during the heading, flowering, and filling stages under different water stresses. The aim was to provide a method for the rapid acquisition of winter wheat SPAD values. The results showed that the SPAD values under normal irrigation were higher than those under water restriction. Multiple vegetation indices were significantly correlated with SPAD values. In the prediction model construction of SPAD, the different models had high estimation accuracy under both normal irrigation and water limitation treatments, with correlation coefficients of predicted and measured values under normal irrigation in different environments the value of r from 0.59 to 0.81 and RMSE from 2.15 to 11.64, compared to RE from 0.10% to 1.00%; and under drought stress in different environments, correlation coefficients of predicted and measured values of r was 0.69-0.79, RMSE was 2.30-12.94, and RE was 0.10%-1.30%. This study demonstrated that the optimal combination of feature selection methods and machine learning algorithms can lead to a more accurate estimation of winter wheat SPAD values. In summary, the SVM model based on UAV multispectral images can rapidly and accurately estimate winter wheat SPAD value.

Hyperspectral and Chlorophyll Fluorescence Analyses of Comparative Leaf Surfaces Reveal Cellular Influences on Leaf Optical Properties in Tradescantia Plants

The differential effects of cellular and ultrastructural characteristics on the optical properties of adaxial and abaxial leaf surfaces in the genus Tradescantia highlight the intricate relationships between cellular arrangement and pigment distribution in the plant cells. We examined hyperspectral and chlorophyll a fluorescence (ChlF) kinetics using spectroradiometers and optical and electron microscopy techniques. The leaves were analysed for their spectral properties and cellular makeup. The biochemical compounds were measured and correlated with the biophysical and ultrastructural features. The main findings showed that the top and bottom leaf surfaces had different amounts and patterns of pigments, especially anthocyanins, flavonoids, total phenolics, chlorophyll-carotenoids, and cell and organelle structures, as revealed by the hyperspectral vegetation index (HVI). These differences were further elucidated by the correlation coefficients, which influence the optical signatures of the leaves. Additionally, ChlF kinetics varied between leaf surfaces, correlating with VIS-NIR-SWIR bands through distinct cellular structures and pigment concentrations in the hypodermis cells. We confirmed that the unique optical properties of each leaf surface arise not only from pigmentation but also from complex cellular arrangements and structural adaptations. Some of the factors that affect how leaves reflect light are the arrangement of chloroplasts, thylakoid membranes, vacuoles, and the relative size of the cells themselves. These findings improve our knowledge of the biophysical and biochemical reasons for leaf optical diversity, and indicate possible implications for photosynthetic efficiency and stress adaptation under different environmental conditions in the mesophyll cells of Tradescantia plants.

A novel hybrid modelling framework for GPP estimation: Integrating a multispectral surface reflectance based Vcmax25 simulator into the process-based model

Terrestrial gross primary productivity (GPP) is the key element in the carbon cycle process. Accurate GPP estimation hinges on the maximum carboxylation rate (Vcmax,025). The high uncertainty in deriving ecosystem-level Vcmax,025 has long hampered efforts toward the performance of the GPP model. Recently studies suggest the strong relationship between spectral reflectance and Vcmax,025. We proposed the multispectral surface reflectance-driven Vcmax,025 simulator using the fully connected deep neural network and built the hybrid modelling framework for GPP estimation by integrating the data-driven Vcmax,025 simulator in the process-based model. The performance of hybrid GPP model was evaluated at 95 flux sites. The result shows that the multispectral surface reflectance-driven Vcmax,025 simulator acquires the satisfactory estimation, with correlation coefficient (R), root mean square error (RMSE) and median absolute percentage error (MdAPE) ranging from 0.34 to 0.80, 14 to 43 μmol m-2 s-1 and 21 % to 66 % across different land cover types, respectively. The hybrid framework generates good GPP estimates with R, RMSE and MdAPE varying from 0.76 to 0.89, 1.79 to 6.16 μmol m-2 s-1 and 27 % to 90 %, respectively. Compared with EVI-driven method, the multispectral surface reflectance significantly improves the Vcmax,025 and GPP estimates, with MdAPE declining by 0.6 %-18 % and 1 % to 21 %, respectively. The Shapley value analysis reveals that red (620-670 nm), near-infrared (841-876 nm) and shortwave infrared (1628-1652 nm and 2105-2155 nm) are the key bands for Vcmax,025 estimation. This study highlights the potential of multispectral surface reflectance for quantifying ecosystem-level Vcmax,025. The new hybrid framework fully extracts the information of all available spectral bands using deep learning to reduce parameter uncertainty while maintains the description of photosynthetic process to ensure its physical reasonability. It can serve as a powerful tool for accurate global GPP estimation.

Hyperspectral Proximal Sensing for Estimating Photosynthetic Capacities at Leaf and Canopy Scales

Agronomists, plant breeders, and plant biologists have been promoting the need to develop high-throughput methods to measure plant traits of interest for decades. Measuring these plant traits or phenotypes is often a bottleneck since skilled personnel, resources, and ample time are required. Additionally, plant phenotypic traits from only a select number of breeding lines or varieties can be quantified because the "gold standard" measurement of a desired trait cannot be completed in a timely manner. As such, numerous approaches have been developed and implemented to better understand the biology and production of crops and ecosystems. In this chapter, we explain one of the recent approaches leveraging hyperspectral measurements to estimate different aspects of photosynthesis. Notably, we outline the use of hyperspectral radiometer and imaging to rapidly estimate two of the rate-limiting steps of photosynthesis: the maximum rate of the carboxylation of Rubisco (Vcmax) and the maximum rate of electron transfer or regeneration of RuBP (Jmax).

Machine learning in photosynthesis: Prospects on sustainable crop development

Improving photosynthesis is a promising avenue to increase food security. Studying photosynthetic traits with the aim to improve efficiency has been one of many strategies to increase crop yield but analyzing large data sets presents an ongoing challenge. Machine learning (ML) represents a ubiquitous tool that can provide a more elaborate data analysis. Here we review the application of ML in various domains of photosynthetic research, as well as in photosynthetic pigment studies. We highlight how correlating hyperspectral data with photosynthetic parameters to improve crop yield could be achieved through various ML algorithms. We also propose strategies to employ ML in promoting photosynthetic pigment research for furthering crop yield.

Non-Invasive Assessment, Classification, and Prediction of Biophysical Parameters Using Reflectance Hyperspectroscopy

Hyperspectral technology offers significant potential for non-invasive monitoring and prediction of morphological parameters in plants. In this study, UV-VIS-NIR-SWIR reflectance hyperspectral data were collected from Nicotiana tabacum L. plants using a spectroradiometer. These plants were grown under different light and gibberellic acid (GA₃) concentrations. Through spectroscopy and multivariate analyses, key growth parameters, such as height, leaf area, energy yield, and biomass, were effectively evaluated based on the interaction of light with leaf structures. The shortwave infrared (SWIR) bands, specifically SWIR1 and SWIR2, showed the strongest correlations with these growth parameters. When classifying tobacco plants grown under different GA₃ concentrations in greenhouses, artificial intelligence (AI) and machine learning (ML) algorithms were employed, achieving an average accuracy of over 99.1% using neural network (NN) and gradient boosting (GB) algorithms. Among the 34 tested vegetation indices, the photochemical reflectance index (PRI) demonstrated the strongest correlations with all evaluated plant phenotypes. Partial least squares regression (PLSR) models effectively predicted morphological attributes, with R²_CV values ranging from 0.81 to 0.87 and RPD_P values exceeding 2.09 for all parameters. Based on Pearson's coefficient XYZ interpolations and HVI algorithms, the NIR-SWIR band combination proved the most effective for predicting height and leaf area, while VIS-NIR was optimal for optimal energy yield, and VIS-VIS was best for predicting biomass. To further corroborate these findings, the SWIR bands for certain morphological characteristic wavelengths selected with s-PLS were most significant for SWIR1 and SWIR2, while i-PLS showed a more uniform distribution in VIS-NIR-SWIR bands. Therefore, SWIR hyperspectral bands provide valuable insights into developing alternative bands for remote sensing measurements to estimate plant morphological parameters. These findings underscore the potential of remote sensing technology for rapid, accurate, and non-invasive monitoring within stationary high-throughput phenotyping systems in greenhouses. These insights align with advancements in digital and precision technology, indicating a promising future for research and innovation in this field.

D, Olivo M, Urano D. Classification of Plant Endogenous States Using Machine Learning-Derived Agricultural Indices

Leaf color patterns vary depending on leaf age, pathogen infection, and environmental and nutritional stresses; thus, they are widely used to diagnose plant health statuses in agricultural fields. The visible-near infrared-shortwave infrared (VIS-NIR-SWIR) sensor measures the leaf color pattern from a wide spectral range with high spectral resolution. However, spectral information has only been employed to understand general plant health statuses (e.g., vegetation index) or phytopigment contents, rather than pinpointing defects of specific metabolic or signaling pathways in plants. Here, we report feature engineering and machine learning methods that utilize VIS-NIR-SWIR leaf reflectance for robust plant health diagnostics, pinpointing physiological alterations associated with the stress hormone, abscisic acid (ABA). Leaf reflectance spectra of wild-type, ABA2-overexpression, and deficient plants were collected under watered and drought conditions. Drought- and ABA-associated normalized reflectance indices (NRIs) were screened from all possible pairs of wavelength bands. Drought associated NRIs showed only a partial overlap with those related to ABA deficiency, but more NRIs were associated with drought due to additional spectral changes within the NIR wavelength range. Interpretable support vector machine classifiers built with 20 NRIs predicted treatment or genotype groups with an accuracy greater than those with conventional vegetation indices. Major selected NRIs were independent from leaf water content and chlorophyll content, 2 well-characterized physiological changes under drought. The screening of NRIs, streamlined with the development of simple classifiers, serves as the most efficient means of detecting reflectance bands that are highly relevant to characteristics of interest.

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.

Retrieving rice (Oryza sativa L.) net photosynthetic rate from UAV multispectral images based on machine learning methods

Photosynthesis is the key physiological activity in the process of crop growth and plays an irreplaceable role in carbon assimilation and yield formation. This study extracted rice (Oryza sativa L.) canopy reflectance based on the UAV multispectral images and analyzed the correlation between 25 vegetation indices (VIs), three textural indices (TIs), and net photosynthetic rate (Pn) at different growth stages. Linear regression (LR), support vector regression (SVR), gradient boosting decision tree (GBDT), random forest (RF), and multilayer perceptron neural network (MLP) models were employed for Pn estimation, and the modeling accuracy was compared under the input condition of VIs, VIs combined with TIs, and fusion of VIs and TIs with plant height (PH) and SPAD. The results showed that VIs and TIs generally had the relatively best correlation with Pn at the jointing-booting stage and the number of VIs with significant correlation (p< 0.05) was the largest. Therefore, the employed models could achieve the highest overall accuracy [coefficient of determination (R ²) of 0.383-0.938]. However, as the growth stage progressed, the correlation gradually weakened and resulted in accuracy decrease (R ² of 0.258-0.928 and 0.125-0.863 at the heading-flowering and ripening stages, respectively). Among the tested models, GBDT and RF models could attain the best performance based on only VIs input (with R ² ranging from 0.863 to 0.938 and from 0.815 to 0.872, respectively). Furthermore, the fusion input of VIs, TIs with PH, and SPAD could more effectively improve the model accuracy (R ² increased by 0.049-0.249, 0.063-0.470, and 0.113-0.471, respectively, for three growth stages) compared with the input combination of VIs and TIs (R ² increased by 0.015-0.090, 0.001-0.139, and 0.023-0.114). Therefore, the GBDT and RF model with fused input could be highly recommended for rice Pn estimation and the methods could also provide reference for Pn monitoring and further yield prediction at field scale.

Dissection of Hyperspectral Reflectance to Estimate Photosynthetic Characteristics in Upland Cotton (Gossypium hirsutum L.) under Different Nitrogen Fertilizer Application Based on Machine Learning Algorithms

Hyperspectral technology has enabled rapid and efficient nitrogen monitoring in crops. However, most approaches involve direct monitoring of nitrogen content or physiological and biochemical indicators directly related to nitrogen, which cannot reflect the overall plant nutritional status. Two important photosynthetic traits, the fraction of absorbed photosynthetically active radiation (FAPAR) and the net photosynthetic rate (Pn), were previously shown to respond positively to nitrogen changes. Here, Pn and FAPAR were used for correlation analysis with hyperspectral data to establish a relationship between nitrogen status and hyperspectral characteristics through photosynthetic traits. Using principal component and band autocorrelation analyses of the original spectral reflectance, two band positions (350-450 and 600-750 nm) sensitive to nitrogen changes were obtained. The performances of four machine learning algorithm models based on six forms of hyperspectral transformations showed that the light gradient boosting machine (LightGBM) model based on the hyperspectral first derivative could better invert the Pn of function-leaves in cotton, and the random forest (RF) model based on hyperspectral first derivative could better invert the FAPAR of the cotton canopy. These results provide advanced metrics for non-destructive tracking of cotton nitrogen status, which can be used to diagnose nitrogen nutrition and cotton growth status in large farms.

Sustaining yield and nutritional quality of peanuts in harsh environments: Physiological and molecular basis of drought and heat stress tolerance

Climate change is significantly impacting agricultural production worldwide. Peanuts provide food and nutritional security to millions of people across the globe because of its high nutritive values. Drought and heat stress alone or in combination cause substantial yield losses to peanut production. The stress, in addition, adversely impact nutritional quality. Peanuts exposed to drought stress at reproductive stage are prone to aflatoxin contamination, which imposes a restriction on use of peanuts as health food and also adversely impact peanut trade. A comprehensive understanding of the impact of drought and heat stress at physiological and molecular levels may accelerate the development of stress tolerant productive peanut cultivars adapted to a given production system. Significant progress has been achieved towards the characterization of germplasm for drought and heat stress tolerance, unlocking the physiological and molecular basis of stress tolerance, identifying significant marker-trait associations as well major QTLs and candidate genes associated with drought tolerance, which after validation may be deployed to initiate marker-assisted breeding for abiotic stress adaptation in peanut. The proof of concept about the use of transgenic technology to add value to peanuts has been demonstrated. Advances in phenomics and artificial intelligence to accelerate the timely and cost-effective collection of phenotyping data in large germplasm/breeding populations have also been discussed. Greater focus is needed to accelerate research on heat stress tolerance in peanut. A suits of technological innovations are now available in the breeders toolbox to enhance productivity and nutritional quality of peanuts in harsh environments. A holistic breeding approach that considers drought and heat-tolerant traits to simultaneously address both stresses could be a successful strategy to produce climate-resilient peanut genotypes with improved nutritional quality.

Proximal and remote sensing in plant phenomics: 20 years of progress, challenges, and perspectives

Plant phenomics (PP) has been recognized as a bottleneck in studying the interactions of genomics and environment on plants, limiting the progress of smart breeding and precise cultivation. High-throughput plant phenotyping is challenging owing to the spatio-temporal dynamics of traits. Proximal and remote sensing (PRS) techniques are increasingly used for plant phenotyping because of their advantages in multi-dimensional data acquisition and analysis. Substantial progress of PRS applications in PP has been observed over the last two decades and is analyzed here from an interdisciplinary perspective based on 2972 publications. This progress covers most aspects of PRS application in PP, including patterns of global spatial distribution and temporal dynamics, specific PRS technologies, phenotypic research fields, working environments, species, and traits. Subsequently, we demonstrate how to link PRS to multi-omics studies, including how to achieve multi-dimensional PRS data acquisition and processing, how to systematically integrate all kinds of phenotypic information and derive phenotypic knowledge with biological significance, and how to link PP to multi-omics association analysis. Finally, we identify three future perspectives for PRS-based PP: (1) strengthening the spatial and temporal consistency of PRS data, (2) exploring novel phenotypic traits, and (3) facilitating multi-omics communication.

A stacked regression ensemble approach for the quantitative determination of biomass feedstock compositions using near infrared spectroscopy

Rapid, robust, and accurate biomass compositional analyses are required in the bioenergy industry to accurately determine the chemical composition of biomass feedstocks. A stacked regression ensemble approach using near infrared spectroscopic method was developed for the quantitative determination of glucan, xylan, lignin, ash, and extract in biomass feedstocks. A comprehensive comparison of the performance of various machine learning techniques including support vector regression (linear and radial), least absolute shrinkage and selection operator (LASSO), ridge regression, elastic net, partial least squares, random forests, recursive partitioning and regression trees, gradient boosting, and gaussian process regression was assessed in the training set data (n = 188). The predictive performance of the aforementioned machine learning approaches was then compared with stacked regression, an ensemble learning algorithm which collates the performance of the abovementioned machine learning regression techniques. Results show that the stacked regression primarily outperformed other machine learning techniques (Root mean square error of prediction (RMSEP)_average=1.660%wt,R²=0.907) across all five constituents in the validation set data (n = 81). Further results also show that the RMSEP of the stacked ensemble technique is significantly different than that of the partial least squares (PLS) approach in predicting glucan, ash, lignin, and extract components in biomass samples. The stacked ensemble learning approach offers an alternative method for a more accurate prediction of biomass compositions than the traditional PLS technique.

Estimation of amino acid contents in maize leaves based on hyperspectral imaging

Estimation of the amino acid content in maize leaves is helpful for improving maize yield estimation and nitrogen use efficiency. Hyperspectral imaging can be used to obtain the physiological and biochemical parameters of maize leaves with the advantages of being rapid, non-destructive, and high throughput. This study aims to estimate the multiple amino acid contents in maize leaves using hyperspectral imaging data. Two nitrogen (N) fertilizer experiments were carried out to obtain the hyperspectral images of fresh maize leaves. The partial least squares regression (PLSR) method was used to build the estimation models of various amino acid contents by using the reflectance of all bands, sensitive band range, and sensitive bands. The models were then validated with the independent dataset. The results showed that (1) the spectral reflectance of most amino acids was more sensitive in the range of 400-717.08 nm than other bands. The estimation accuracy was better by using the reflectance of the sensitive band range than that of all bands; (2) the sensitive bands of most amino acids were in the ranges of 505.39-605 nm and 651-714 nm; and (3) among the 24 amino acids, the estimation models of the β-aminobutyric acid, ornithine, citrulline, methionine, and histidine achieved higher accuracy than those of other amino acids, with the R ², relative root mean square error (RE), and relative percent deviation (RPD) of the measured and estimated value of testing samples in the range of 0.84-0.96, 8.79%-19.77%, and 2.58-5.18, respectively. This study can provide a non-destructive and rapid diagnostic method for genetic sensitive analysis and variety improvement of maize.

UAV-based multi-sensor data fusion and machine learning algorithm for yield prediction in wheat

Early prediction of grain yield helps scientists to make better breeding decisions for wheat. Use of machine learning (ML) methods for fusion of unmanned aerial vehicle (UAV)-based multi-sensor data can improve the prediction accuracy of crop yield. For this, five ML algorithms including Cubist, support vector machine (SVM), deep neural network (DNN), ridge regression (RR) and random forest (RF) were used for multi-sensor data fusion and ensemble learning for grain yield prediction in wheat. A set of thirty wheat cultivars and breeding lines were grown under three irrigation treatments i.e., light, moderate and high irrigation treatments to evaluate the yield prediction capabilities of a low-cost multi-sensor (RGB, multi-spectral and thermal infrared) UAV platform. Multi-sensor data fusion-based yield prediction showed higher accuracy compared to individual-sensor data in each ML model. The coefficient of determination (R ²) values for Cubist, SVM, DNN and RR models regarding grain yield prediction were observed from 0.527 to 0.670. Moreover, the results of ensemble learning through integrating the above models illustrated further increase in accuracy. The predictions of ensemble learning showed high R ² values up to 0.692, which was higher as compared to individual ML models across the multi-sensor data. Root mean square error (RMSE), residual prediction deviation (RPD) and ratio of prediction performance to inter-quartile range (RPIQ) were calculated to be 0.916 t ha^-1, 1.771 and 2.602, respectively. The results proved that low altitude UAV-based multi-sensor data can be used for early grain yield prediction using data fusion and an ensemble learning framework with high accuracy. This high-throughput phenotyping approach is valuable for improving the efficiency of selection in large breeding activities.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s11119-022-09938-8.

Machine learning methods for assessing photosynthetic activity: environmental monitoring applications

Monitoring of the photosynthetic activity of natural and artificial biocenoses is of crucial importance. Photosynthesis is the basis for the existence of life on Earth, and a decrease in primary photosynthetic production due to anthropogenic influences can have catastrophic consequences. Currently, great efforts are being made to create technologies that allow continuous monitoring of the state of the photosynthetic apparatus of terrestrial plants and microalgae. There are several sources of information suitable for assessing photosynthetic activity, including gas exchange and optical (reflectance and fluorescence) measurements. The advent of inexpensive optical sensors makes it possible to collect data locally (manually or using autonomous sea and land stations) and globally (using aircraft and satellite imaging). In this review, we consider machine learning methods proposed for determining the functional parameters of photosynthesis based on local and remote optical measurements (hyperspectral imaging, solar-induced chlorophyll fluorescence, local chlorophyll fluorescence imaging, and various techniques of fast and delayed chlorophyll fluorescence induction). These include classical and novel (such as Partial Least Squares) regression methods, unsupervised cluster analysis techniques, various classification methods (support vector machine, random forest, etc.) and artificial neural networks (multilayer perceptron, long short-term memory, etc.). Special aspects of time-series analysis are considered. Applicability of particular information sources and mathematical methods for assessment of water quality and prediction of algal blooms, for estimation of primary productivity of biocenoses, stress tolerance of agricultural plants, etc. is discussed.

Prediction of Chlorophyll Content in Multi-Temporal Winter Wheat Based on Multispectral and Machine Learning

To obtain the canopy chlorophyll content of winter wheat in a rapid and non-destructive high-throughput manner, the study was conducted on winter wheat in Xinjiang Manas Experimental Base in 2021, and the multispectral images of two water treatments' normal irrigation (NI) and drought stress (DS) in three key fertility stages (heading, flowering, and filling) of winter wheat were obtained by DJI P4M unmanned aerial vehicle (UAV). The flag leaf chlorophyll content (CC) data of different genotypes in the field were obtained by SPAD-502 Plus chlorophyll meter. Firstly, the CC distribution of different genotypes was studied, then, 13 vegetation indices, combined with the Random Forest algorithm and correlation evaluation of CC, and 14 vegetation indices were used for vegetation index preference. Finally, preferential vegetation indices and nine machine learning algorithms, Ridge regression with cross-validation (RidgeCV), Ridge, Adaboost Regression, Bagging_Regressor, K_Neighbor, Gradient_Boosting_Regressor, Random Forest, Support Vector Machine (SVM), and Least absolute shrinkage and selection operator (Lasso), were preferentially selected to construct the CC estimation models under two water treatments at three different fertility stages, which were evaluated by correlation coefficient (r), root means square error (RMSE) and the normalized root mean square error (NRMSE) to select the optimal estimation model. The results showed that the CC values under normal irrigation were higher than those underwater limitation treatment at different fertility stages; several vegetation indices and CC values showed a highly significant correlation, with the highest correlation reaching.51; in the prediction model construction of CC values, different models under normal irrigation and water limitation treatment had high estimation accuracy, among which the model with the highest prediction accuracy under normal irrigation was at the heading stage. The highest precision of the model prediction under normal irrigation was in the RidgeCV model (r = 0.63, RMSE = 3.28, NRMSE = 16.2%) and the highest precision of the model prediction under water limitation treatment was in the SVM model (r = 0.63, RMSE = 3.47, NRMSE = 19.2%).

Advances in field-based high-throughput photosynthetic phenotyping

Gas exchange techniques revolutionized plant research and advanced understanding, including associated fluxes and efficiencies, of photosynthesis, photorespiration, and respiration of plants from cellular to ecosystem scales. These techniques remain the gold standard for inferring photosynthetic rates and underlying physiology/biochemistry, although their utility for high-throughput phenotyping (HTP) of photosynthesis is limited both by the number of gas exchange systems available and the number of personnel available to operate the equipment. Remote sensing techniques have long been used to assess ecosystem productivity at coarse spatial and temporal resolutions, and advances in sensor technology coupled with advanced statistical techniques are expanding remote sensing tools to finer spatial scales and increasing the number and complexity of phenotypes that can be extracted. In this review, we outline the photosynthetic phenotypes of interest to the plant science community and describe the advances in high-throughput techniques to characterize photosynthesis at spatial scales useful to infer treatment or genotypic variation in field-based experiments or breeding trials. We will accomplish this objective by presenting six lessons learned thus far through the development and application of proximal/remote sensing-based measurements and the accompanying statistical analyses. We will conclude by outlining what we perceive as the current limitations, bottlenecks, and opportunities facing HTP of photosynthesis.

Mining for allelic gold: finding genetic variation in photosynthetic traits in crops and wild relatives

Improvement of photosynthetic traits in crops to increase yield potential and crop resilience has recently become a major breeding target. Synthetic biology and genetic technologies offer unparalleled opportunities to create new genetics for photosynthetic traits driven by existing fundamental knowledge. However, large 'gene bank' collections of germplasm comprising historical collections of crop species and their relatives offer a wealth of opportunities to find novel allelic variation in the key steps of photosynthesis, to identify new mechanisms and to accelerate genetic progress in crop breeding programmes. Here we explore the available genetic resources in food and fibre crops, strategies to selectively target allelic variation in genes underpinning key photosynthetic processes, and deployment of this variation via gene editing in modern elite material.

Phenotypic variation in photosynthetic traits in wheat grown under field versus glasshouse conditions

Recognition of the untapped potential of photosynthesis to improve crop yields has spurred research to identify targets for breeding. The CO2-fixing enzyme Rubisco is characterized by a number of inefficiencies, and frequently limits carbon assimilation at the top of the canopy, representing a clear target for wheat improvement. Two bread wheat lines with similar genetic backgrounds and contrasting in vivo maximum carboxylation activity of Rubisco per unit leaf nitrogen (Vc,max,25/Narea) determined using high-throughput phenotyping methods were selected for detailed study from a panel of 80 spring wheat lines. Detailed phenotyping of photosynthetic traits in the two lines using glasshouse-grown plants showed no difference in Vc,max,25/Narea determined directly via in vivo and in vitro methods. Detailed phenotyping of glasshouse-grown plants of the 80 wheat lines also showed no correlation between photosynthetic traits measured via high-throughput phenotyping of field-grown plants. Our findings suggest that the complex interplay between traits determining crop productivity and the dynamic environments experienced by field-grown plants needs to be considered in designing strategies for effective wheat crop yield improvement when breeding for particular environments.

Wheat photosystem II heat tolerance responds dynamically to short- and long-term warming

Wheat photosynthetic heat tolerance can be characterized using minimal chlorophyll fluorescence to quantify the critical temperature (Tcrit) above which incipient damage to the photosynthetic machinery occurs. We investigated intraspecies variation and plasticity of wheat Tcrit under elevated temperature in field and controlled-environment experiments, and assessed whether intraspecies variation mirrored interspecific patterns of global heat tolerance. In the field, wheat Tcrit varied diurnally-declining from noon through to sunrise-and increased with phenological development. Under controlled conditions, heat stress (36 °C) drove a rapid (within 2 h) rise in Tcrit that peaked after 3-4 d. The peak in Tcrit indicated an upper limit to PSII heat tolerance. A global dataset [comprising 183 Triticum and wild wheat (Aegilops) species] generated from the current study and a systematic literature review showed that wheat leaf Tcrit varied by up to 20 °C (roughly two-thirds of reported global plant interspecies variation). However, unlike global patterns of interspecies Tcrit variation that have been linked to latitude of genotype origin, intraspecific variation in wheat Tcrit was unrelated to that. Overall, the observed genotypic variation and plasticity of wheat Tcrit suggest that this trait could be useful in high-throughput phenotyping of wheat photosynthetic heat tolerance.

Prediction of Photosynthetic, Biophysical, and Biochemical Traits in Wheat Canopies to Reduce the Phenotyping Bottleneck

To achieve food security, it is necessary to increase crop radiation use efficiency (RUE) and yield through the enhancement of canopy photosynthesis to increase the availability of assimilates for the grain, but its study in the field is constrained by low throughput and the lack of integrative measurements at canopy level. In this study, partial least squares regression (PLSR) was used with high-throughput phenotyping (HTP) data in spring wheat to build predictive models of photosynthetic, biophysical, and biochemical traits for the top, middle, and bottom layers of wheat canopies. The combined layer model predictions performed better than individual layer predictions with a significance as follows for photosynthesis R ² = 0.48, RMSE = 5.24 μmol m^-2 s^-1 and stomatal conductance: R ² = 0.36, RMSE = 0.14 mol m^-2 s^-1. The predictions of these traits from PLSR models upscaled to canopy level compared to field observations were statistically significant at initiation of booting (R ² = 0.3, p < 0.05; R ² = 0.29, p < 0.05) and at 7 days after anthesis (R ² = 0.15, p < 0.05; R ² = 0.65, p < 0.001). Using HTP allowed us to increase phenotyping capacity 30-fold compared to conventional phenotyping methods. This approach can be adapted to screen breeding progeny and genetic resources for RUE and to improve our understanding of wheat physiology by adding different layers of the canopy to physiological modeling.

Inference of photosynthetic capacity parameters from chlorophyll a fluorescence is affected by redox state of PSII reaction centers

Solar-induced chlorophyll fluorescence (SIF) has been used to infer photosynthetic capacity parameters (e.g., the maximum carboxylation rate V_cmax , and the maximum electron transport rate J_max ). However, the precise mechanism and practical utility of such approach under dynamic environments remain unclear. We used the balance between the light and carbon reactions to derive theoretical equations relating chlorophyll a fluorescence (ChlF) emission and photosynthetic capacity parameters, and formulated testable hypotheses regarding the dynamic relationships between the true total ChlF emitted from PSII (SIF_PSII ) and V_cmax and J_max . We employed concurrent measurements of gas exchanges and ChlF parameters for 15 species from six biomes to test the formulated hypotheses across species, temperatures, and limitation state of carboxylation. Our results revealed that SIF_PSII alone is incapable of informing the variations in V_cmax and J_max across species, even when SIF_PSII is determined under the same environmental conditions. In contrast, the product of SIF_PSII and the fraction of open PSII reactions q_L , which indicates the redox state of PSII, is a strong predictor of both V_cmax and J_max , although their precise relationships vary somewhat with environmental conditions. Our findings suggest the redox state of PSII strongly influences the relationship between SIF_PSII and V_cmax and J_max .

High-throughput field crop phenotyping: current status and challenges

In contrast to the rapid advances made in plant genotyping, plant phenotyping is considered a bottleneck in plant science. This has promoted high-throughput plant phenotyping (HTP) studies, resulting in an exponential increase in phenotyping-related publications. The development of HTP was originally intended for use as indoor HTP technologies for model plant species under controlled environments. However, this subsequently shifted to HTP for use in crops in fields. Although HTP in fields is much more difficult to conduct due to unstable environmental conditions compared to HTP in controlled environments, recent advances in HTP technology have allowed these difficulties to be overcome, allowing for rapid, efficient, non-destructive, non-invasive, quantitative, repeatable, and objective phenotyping. Recent HTP developments have been accelerated by the advances in data analysis, sensors, and robot technologies, including machine learning, image analysis, three dimensional (3D) reconstruction, image sensors, laser sensors, environmental sensors, and drones, along with high-speed computational resources. This article provides an overview of recent HTP technologies, focusing mainly on canopy-based phenotypes of major crops, such as canopy height, canopy coverage, canopy biomass, and canopy stressed appearance, in addition to crop organ detection and counting in the fields. Current topics in field HTP are also presented, followed by a discussion on the low rates of adoption of HTP in practical breeding programs.

Prediction of South American Leaf Blight and Disease-Induced Photosynthetic Changes in Rubber Tree, Using Machine Learning Techniques on Leaf Hyperspectral Reflectance

The efficiency of visible and near-infrared (VIS/NIR) sensors and predictive modeling for detecting and classifying South American Leaf Blight (SALB) (Pseudocercospora ulei) in rubber trees (Hevea brasiliensis) has been poorly explored. Furthermore, the performance of VIS/NIR analysis combined with machine learning (ML) algorithms for predicting photosynthetic alterations caused by SALB is unknown. Therefore, this study aimed to detect and classify the SALB levels, as well as to predict, for the first time, disease-induced photosynthetic changes in rubber trees. Leaf hyperspectral reflectance combined with five ML techniques (random forest (RF), boosted regression tree (BRT), bagged classification and regression trees (BCART), artificial neural network (ANN), and support vector machine (SVM)) were used. The RF, ANN, and BCART models achieved the best performance for classifying the SALB levels on the training dataset (accuracies of 98.0 to 99.8%), with 10-fold cross-validation repeated five times, and test dataset (accuracies of 97.1 to 100%). The ANN and RF models were better at predicting leaf gas exchange-related traits such as net CO₂ assimilation rate (A) and extrinsic water use efficiency (WUEe) in the training (R² ranged from 0.97 to 0.99) and testing (R² ranged from 0.96 to 0.99) phases. In comparison, lower performances (R² ranged from 0.24 to 0.52) were evidenced for the photochemical traits. This research provides a basis for future designs of a remote monitoring system based on early detection and accurate diagnosis of biotic stress caused by SALB, which is fundamental for more effective rubber crop protection.

Selecting informative bands for partial least squares regressions improves their goodness-of-fits to estimate leaf photosynthetic parameters from hyperspectral data

The plant photosynthetic capacity determines the photosynthetic rates of the terrestrial biosphere. Timely approaches to obtain the spatiotemporal variations of the photosynthetic parameters are urgently needed to grasp the gas exchange rhythms of the terrestrial biosphere. While partial least squares regression (PLSR) is a promising way to predict the photosynthetic parameters maximum carboxylation rate (V_cmax) and maximum electron transport rate (J_max) rapidly and non-destructively from hyperspectral data, the approach, however, faces a high risk of overfitting and remains a high hurdle for applications. In this study, we propose to incorporate proper band selection techniques for PLSR analysis to refine the goodness-of-fit (GoF) in estimating V_cmax and J_max. Different band selection procedures coupled with different hyperspectral forms (reflectance, apparent absorption, as well as derivatives) were examined. Our results demonstrate that the GoFs of PLSR models could be greatly improved by combining proper band selection methods (especially the iterative stepwise elimination approach) rather than using full bands as commonly done with PLSR. The results also show that the 1st order derivative spectra had a balance between accuracy (R² = 0.80 for V_cmax, and 0.94 for J_max) and denoising (when a Gaussian noise was added to each leaf reflectance spectrum at each wavelength with a standard deviation of 1%) on retrieving photosynthetic parameters from hyperspectral data. Our results clearly illustrate the advantage of using the band selection approach for PLSR dimensionality reduction and model optimization, highlighting the superiority of using derivative spectra for V_cmax and J_max estimations, which should provide valuable insights for retrieving photosynthetic parameters from hyperspectral remotely sensed data.

Predicting biochemical acclimation of leaf photosynthesis in soybean under in-field canopy warming using hyperspectral reflectance

Traditional gas exchange measurements are cumbersome, which makes it difficult to capture variation in biochemical parameters, namely the maximum rate of carboxylation measured at a reference temperature (Vcmax25 ) and the maximum electron transport at a reference temperature (Jmax25 ), in response to growth temperature over time from days to weeks. Hyperspectral reflectance provides reliable measures of Vcmax25 and Jmax25 ; however, the capability of this method to capture biochemical acclimations of the two parameters to high growth temperature over time has not been demonstrated. In this study, Vcmax25 and Jmax25 were measured over multiple growth stages during two growing seasons for field-grown soybeans using both gas exchange techniques and leaf spectral reflectance under ambient and four elevated canopy temperature treatments (ambient+1.5, +3, +4.5, and +6°C). Spectral vegetation indices and machine learning methods were used to build predictive models for Vcmax25 and Jmax25 , based on the leaf reflectance. Results showed that these models yielded an R2 of 0.57-0.65 and 0.48-0.58 for Vcmax25 and Jmax25 , respectively. Hyperspectral reflectance captured biochemical acclimation of leaf photosynthesis to high temperature in the field, improving spatial and temporal resolution in the ability to assess the impact of future warming on crop productivity.

UAV- and Machine Learning-Based Retrieval of Wheat SPAD Values at the Overwintering Stage for Variety Screening

In recent years, the delay in sowing has become a major obstacle to high wheat yield in Jiangsu Province, one of the major wheat producing areas in China; hence, it is necessary to screen wheat varieties are resilient for late sowing. This study aimed to provide an effective, fast, and non-destructive monitoring method of soil plant analysis development (SPAD) values, which can represent leaf chlorophyll contents, for late-sown winter wheat variety screening. This study acquired multispectral images using an unmanned aerial vehicle (UAV) at the overwintering stage of winter wheat growth, and further processed these images to extract reflectance of five single spectral bands and calculated 26 spectral vegetation indices. Based on these 31 variables, this study combined three variable selection methods (i.e., recursive feature elimination (RFE), random forest (RF), and Pearson correlation coefficient (r)) with four machine learning algorithms (i.e., random forest regression (RFR), linear kernel-based support vector regression (SVR), radial basis function (RBF) kernel-based SVR, and sigmoid kernel-based SVR), resulted in seven SVR models (i.e., RFE-SVR_linear, RF-SVR_linear, RF-SVR_RBF, RF-SVR_sigmoid, r-SVR_linear, r-SVR_RBF, and r-SVR_sigmoid) and three RFR models (i.e., RFE-RFR, RF-RFR, and r-RFR). The performances of the 10 machine learning models were evaluated and compared with each other according to the achieved coefficient of determination (R2), residual prediction deviation (RPD), root mean square error (RMSE), and relative RMSE (RRMSE) in SPAD estimation. Of the 10 models, the best one was the RF-SVR_sigmoid model, which was the combination of the RF variable selection method and the sigmoid kernel-based SVR algorithm. It achieved high accuracy in estimating SPAD values of the wheat canopy (R2 = 0.754, RPD = 2.017, RMSE = 1.716 and RRMSE = 4.504%). The newly developed UAV- and machine learning-based model provided a promising and real time method to monitor chlorophyll contents at the overwintering stage, which can benefit late-sown winter wheat variety screening.

Logistic Models Derived via LASSO Methods for Quantifying the Risk of Natural Contamination of Maize Grain with Deoxynivalenol

Models were developed to quantify the risk of deoxynivalenol (DON) contamination of maize grain based on weather, cultural practices, hybrid resistance, and Gibberella ear rot (GER) intensity. Data on natural DON contamination of 15 to 16 hybrids and weather were collected from 10 Ohio locations over 4 years. Logistic regression with 10-fold cross-validation was used to develop models to predict the risk of DON ≥1 ppm. The presence and severity of GER predicted DON risk with an accuracy of 0.81 and 0.87, respectively. Temperature, relative humidity, surface wetness, and rainfall were used to generate 37 weather-based predictor variables summarized over each of six 15-day windows relative to maize silking (R1). With these variables, least absolute shrinkage and selection operator (LASSO) followed by all-subsets variable selection and logistic regression with 10-fold cross-validation were used to build single-window weather-based models, from which 11 with one or two predictors were selected based on performance metrics and simplicity. LASSO logistic regression was also used to build more complex multiwindow models with up to 22 predictors. The performance of the best single-window models was comparable to that of the best multiwindow models, with accuracy ranging from 0.81 to 0.83 for the former and 0.83 to 0.87 for the latter group of models. These results indicated that the risk of DON ≥1 ppm can be accurately predicted with simple models built using temperature- and moisture-based predictors from a single window. These models will be the foundation for developing tools to predict the risk of DON contamination of maize grain.

Prediction of the importance of auxiliary traits using computational intelligence and machine learning: A simulation study

The present study evaluated the importance of auxiliary traits of a principal trait based on phenotypic information and previously known genetic structure using computational intelligence and machine learning to develop predictive tools for plant breeding. Data of an F₂ population represented by 500 individuals, obtained from a cross between contrasting homozygous parents, were simulated. Phenotypic traits were simulated based on previously established means and heritability estimates (30%, 50%, and 80%); traits were distributed in a genome with 10 linkage groups, considering two alleles per marker. Four different scenarios were considered. For the principal trait, heritability was 50%, and 40 control loci were distributed in five linkage groups. Another phenotypic control trait with the same complexity as the principal trait but without any genetic relationship with it and without pleiotropy or a factorial link between the control loci for both traits was simulated. These traits shared a large number of control loci with the principal trait, but could be distinguished by the differential action of the environment on them, as reflected in heritability estimates (30%, 50%, and 80%). The coefficient of determination were considered to evaluate the proposed methodologies. Multiple regression, computational intelligence, and machine learning were used to predict the importance of the tested traits. Computational intelligence and machine learning were superior in extracting nonlinear information from model inputs and quantifying the relative contributions of phenotypic traits. The R² values ranged from 44.0% - 83.0% and 79.0% - 94.0%, for computational intelligence and machine learning, respectively. In conclusion, the relative contributions of auxiliary traits in different scenarios in plant breeding programs can be efficiently predicted using computational intelligence and machine learning.

Gas exchange measurements in the unsteady state

Leaf level gas exchange is a widely used technique that provides real-time measurement of leaf physiological properties, including CO₂ assimilation (A), stomatal conductance to water vapour (g_sw ) and intercellular CO₂ (C_i ). Modern open-path gas exchange systems offer greater portability than the laboratory-built systems of the past and take advantage of high-precision infrared gas analyzers and optimized system design. However, the basic measurement paradigm has long required steady-state conditions for accurate measurement. For CO₂ response curves, this requirement has meant that each point on the curve needs 1-3 min and a full response curve generally requires 20-35 min to obtain a sufficient number of points to estimate parameters such as the maximum velocity of carboxylation (V_c,max ) and the maximum rate of electron transport (J_max ). For survey measurements, the steady-state requirement has meant that accurate measurement of assimilation has required about 1-2 min. However, steady-state conditions are not a strict prerequisite for accurate gas exchange measurements. Here, we present a new method, termed dynamic assimilation, that is based on first principles and allows for more rapid gas exchange measurements, helping to make the technique more useful for high throughput applications.

Wheat physiology predictor: predicting physiological traits in wheat from hyperspectral reflectance measurements using deep learning

BACKGROUND

The need for rapid in-field measurement of key traits contributing to yield over many thousands of genotypes is a major roadblock in crop breeding. Recently, leaf hyperspectral reflectance data has been used to train machine learning models using partial least squares regression (PLSR) to rapidly predict genetic variation in photosynthetic and leaf traits across wheat populations, among other species. However, the application of published PLSR spectral models is limited by a fixed spectral wavelength range as input and the requirement of separate custom-built models for each trait and wavelength range. In addition, the use of reflectance spectra from the short-wave infrared region requires expensive multiple detector spectrometers. The ability to train a model that can accommodate input from different spectral ranges would potentially make such models extensible to more affordable sensors. Here we compare the accuracy of prediction of PLSR with various deep learning approaches and an ensemble model, each trained and tested using previously published data sets.

RESULTS

We demonstrate that the accuracy of PLSR to predict photosynthetic and related leaf traits in wheat can be improved with deep learning-based and ensemble models without overfitting. Additionally, these models can be flexibly applied across spectral ranges without significantly compromising accuracy.

CONCLUSION

The method reported provides an improved prediction of wheat leaf and photosynthetic traits from leaf hyperspectral reflectance and do not require a full range, high cost leaf spectrometer. We provide a web service for deploying these algorithms to predict physiological traits in wheat from a variety of spectral data sets, with important implications for wheat yield prediction and crop breeding.

High-Throughput Phenotyping and Random Regression Models Reveal Temporal Genetic Control of Soybean Biomass Production

Understanding temporal accumulation of soybean above-ground biomass (AGB) has the potential to contribute to yield gains and the development of stress-resilient cultivars. Our main objectives were to develop a high-throughput phenotyping method to predict soybean AGB over time and to reveal its temporal quantitative genomic properties. A subset of the SoyNAM population (n = 383) was grown in multi-environment trials and destructive AGB measurements were collected along with multispectral and RGB imaging from 27 to 83 days after planting (DAP). We used machine-learning methods for phenotypic prediction of AGB, genomic prediction of breeding values, and genome-wide association studies (GWAS) based on random regression models (RRM). RRM enable the study of changes in genetic variability over time and further allow selection of individuals when aiming to alter the general response shapes over time. AGB phenotypic predictions were high (R 2 = 0.92-0.94). Narrow-sense heritabilities estimated over time ranged from low to moderate (from 0.02 at 44 DAP to 0.28 at 33 DAP). AGB from adjacent DAP had highest genetic correlations compared to those DAP further apart. We observed high accuracies and low biases of prediction indicating that genomic breeding values for AGB can be predicted over specific time intervals. Genomic regions associated with AGB varied with time, and no genetic markers were significant in all time points evaluated. Thus, RRM seem a powerful tool for modeling the temporal genetic architecture of soybean AGB and can provide useful information for crop improvement. This study provides a basis for future studies to combine phenotyping and genomic analyses to understand the genetic architecture of complex longitudinal traits in plants.

Hyperspectral reflectance-based phenotyping for quantitative genetics in crops: Progress and challenges

Many biochemical and physiological properties of plants that are of interest to breeders and geneticists have extremely low throughput and/or can only be measured destructively. This has limited the use of information on natural variation in nutrient and metabolite abundance, as well as photosynthetic capacity in quantitative genetic contexts where it is necessary to collect data from hundreds or thousands of plants. A number of recent studies have demonstrated the potential to estimate many of these traits from hyperspectral reflectance data, primarily in ecophysiological contexts. Here, we summarize recent advances in the use of hyperspectral reflectance data for plant phenotyping, and discuss both the potential benefits and remaining challenges to its application in plant genetics contexts. The performances of previously published models in estimating six traits from hyperspectral reflectance data in maize were evaluated on new sample datasets, and the resulting predicted trait values shown to be heritable (e.g., explained by genetic factors) were estimated. The adoption of hyperspectral reflectance-based phenotyping beyond its current uses may accelerate the study of genes controlling natural variation in biochemical and physiological traits.

Assessment of Ensemble Learning to Predict Wheat Grain Yield Based on UAV-Multispectral Reflectance

Grain yield is increasingly affected by climate factors such as drought and heat. To develop resilient and high-yielding cultivars, high-throughput phenotyping (HTP) techniques are essential for precise decisions in wheat breeding. The ability of unmanned aerial vehicle (UAV)-based multispectral imaging and ensemble learning methods to increase the accuracy of grain yield prediction in practical breeding work is evaluated in this study. For this, 211 winter wheat genotypes were planted under full and limited irrigation treatments, and multispectral data were collected at heading, flowering, early grain filling (EGF), and mid-grain filling (MGF) stages. Twenty multispectral vegetation indices (VIs) were estimated, and VIs with heritability greater than 0.5 were selected to evaluate the models across the growth stages under both irrigation treatments. A framework for ensemble learning was developed by combining multiple base models such as random forest (RF), support vector machine (SVM), Gaussian process (GP), and ridge regression (RR). The R2 values between VIs and grain yield for individual base models were ranged from 0.468 to 0.580 and 0.537 to 0.598 for grain yield prediction in full and limited irrigation treatments across growth stages, respectively. The prediction results of ensemble models were ranged from 0.491 to 0.616 and 0.560 to 0.616 under full and limited irrigation treatments respectively, and were higher than that of the corresponding base learners. Moreover, the grain yield prediction results were observed high at mid grain filling stage under both full (R2 = 0.625) and limited (R2 = 0.628) irrigation treatments through ensemble learning based stacking of four base learners. Further improvements in ensemble learning models can accelerate the use of UAV-based multispectral data for accurate predictions of complex traits like grain yield in wheat.

Evaluating the Performance of Hyperspectral Leaf Reflectance to Detect Water Stress and Estimation of Photosynthetic Capacities

Advanced techniques capable of early, rapid, and nondestructive detection of the impacts of drought on fruit tree and the measurement of the underlying photosynthetic traits on a large scale are necessary to meet the challenges of precision farming and full prediction of yield increases. We tested the application of hyperspectral reflectance as a high-throughput phenotyping approach for early identification of water stress and rapid assessment of leaf photosynthetic traits in citrus trees by conducting a greenhouse experiment. To this end, photosynthetic CO2 assimilation rate (Pn), stomatal conductance (Cond) and transpiration rate (Trmmol) were measured with gas-exchange approaches alongside measurements of leaf hyperspectral reflectance from citrus grown across a gradient of soil drought levels six times, during 20 days of stress induction and 13 days of rewatering. Water stress caused Pn, Cond, and Trmmol rapid and continuous decline throughout the entire drought period. The upper layer was more sensitive to drought than middle and lower layers. Water stress could also bring continuous and dynamic changes of the mean spectral reflectance and absorptance over time. After trees were rewatered, these differences were not obvious. The original reflectance spectra of the four water stresses were surprisingly of low diversity and could not track drought responses, whereas specific hyperspectral spectral vegetation indices (SVIs) and absorption features or wavelength position variables presented great potential. The following machine-learning algorithms: random forest (RF), support vector machine (SVM), gradient boost (GDboost), and adaptive boosting (Adaboost) were used to develop a measure of photosynthesis from leaf reflectance spectra. The performance of four machine-learning algorithms were assessed, and RF algorithm yielded the highest predictive power for predicting photosynthetic parameters (R2 was 0.92, 0.89, and 0.88 for Pn, Cond, and Trmmol, respectively). Our results indicated that leaf hyperspectral reflectance is a reliable and stable method for monitoring water stress and yield increase, with great potential to be applied in large-scale orchards.

Predicting photosynthetic capacity in tobacco using shortwave infrared spectral reflectance

Plateauing yield and stressful environmental conditions necessitate selecting crops for superior physiological traits with untapped potential to enhance crop performance. Plant productivity is often limited by carbon fixation rates that could be improved by increasing maximum photosynthetic carboxylation capacity (Vcmax). However, Vcmax measurements using gas exchange and biochemical assays are slow and laborious, prohibiting selection in breeding programs. Rapid hyperspectral reflectance measurements show potential for predicting Vcmax using regression models. While several hyperspectral models have been developed, contributions from different spectral regions to predictions of Vcmax have not been clearly identified or linked to biochemical variation contributing to Vcmax. In this study, hyperspectral reflectance data from 350-2500 nm were used to build partial least squares regression models predicting in vivo and in vitro Vcmax. Wild-type and transgenic tobacco plants with antisense reductions in Rubisco content were used to alter Vcmax independent from chlorophyll, carbon, and nitrogen content. Different spectral regions were used to independently build partial least squares regression models and identify key regions linked to Vcmax and other leaf traits. The greatest Vcmax prediction accuracy used a portion of the shortwave infrared region from 2070 nm to 2470 nm, where the inclusion of fewer spectral regions resulted in more accurate models.

Data management challenges for artificial intelligence in plant and agricultural research

Artificial Intelligence (AI) is increasingly used within plant science, yet it is far from being routinely and effectively implemented in this domain. Particularly relevant to the development of novel food and agricultural technologies is the development of validated, meaningful and usable ways to integrate, compare and visualise large, multi-dimensional datasets from different sources and scientific approaches. After a brief summary of the reasons for the interest in data science and AI within plant science, the paper identifies and discusses eight key challenges in data management that must be addressed to further unlock the potential of AI in crop and agronomic research, and particularly the application of Machine Learning (AI) which holds much promise for this domain.

Data management challenges for artificial intelligence in plant and agricultural research

Artificial Intelligence (AI) is increasingly used within plant science, yet it is far from being routinely and effectively implemented in this domain. Particularly relevant to the development of novel food and agricultural technologies is the development of validated, meaningful and usable ways to integrate, compare and visualise large, multi-dimensional datasets from different sources and scientific approaches. After a brief summary of the reasons for the interest in data science and AI within plant science, the paper identifies and discusses eight key challenges in data management that must be addressed to further unlock the potential of AI in crop and agronomic research, and particularly the application of Machine Learning (AI) which holds much promise for this domain.

The effect of increasing temperature on crop photosynthesis: from enzymes to ecosystems

As global land surface temperature continues to rise and heatwave events increase in frequency, duration, and/or intensity, our key food and fuel cropping systems will likely face increased heat-related stress. A large volume of literature exists on exploring measured and modelled impacts of rising temperature on crop photosynthesis, from enzymatic responses within the leaf up to larger ecosystem-scale responses that reflect seasonal and interannual crop responses to heat. This review discusses (i) how crop photosynthesis changes with temperature at the enzymatic scale within the leaf; (ii) how stomata and plant transport systems are affected by temperature; (iii) what features make a plant susceptible or tolerant to elevated temperature and heat stress; and (iv) how these temperature and heat effects compound at the ecosystem scale to affect crop yields. Throughout the review, we identify current advancements and future research trajectories that are needed to make our cropping systems more resilient to rising temperature and heat stress, which are both projected to occur due to current global fossil fuel emissions.

Effect of leaf temperature on the estimation of photosynthetic and other traits of wheat leaves from hyperspectral reflectance

A growing number of leaf traits can be estimated from hyperspectral reflectance data. These include structural and compositional traits, such as leaf mass per area (LMA) and nitrogen and chlorophyll content, but also physiological traits such a Rubisco carboxylation activity, electron transport rate, and respiration rate. Since physiological traits vary with leaf temperature, how does this impact on predictions made from reflectance measurements? We investigated this with two wheat varieties, by repeatedly measuring each leaf through a sequence of temperatures imposed by varying the air temperature in a growth room. Leaf temperatures ranging from 20 °C to 35 °C did not alter the estimated Rubisco capacity normalized to 25 °C (Vcmax25), or chlorophyll or nitrogen contents per unit leaf area. Models estimating LMA and Vcmax25/N were both slightly influenced by leaf temperature: estimated LMA increased by 0.27% °C-1 and Vcmax25/N increased by 0.46% °C-1. A model estimating Rubisco activity closely followed variation associated with leaf temperature. Reflectance spectra change with leaf temperature and therefore contain a temperature signal.

The inverse relationship between solar-induced fluorescence yield and photosynthetic capacity: benefits for field phenotyping

Improving photosynthesis is considered a promising way to increase crop yield to feed a growing population. Realizing this goal requires non-destructive techniques to quantify photosynthetic variation among crop cultivars. Despite existing remote sensing-based approaches, it remains a question whether solar-induced fluorescence (SIF) can facilitate screening crop cultivars of improved photosynthetic capacity in plant breeding trials. Here we tested a hypothesis that SIF yield rather than SIF had a better relationship with the maximum electron transport rate (Jmax). Time-synchronized hyperspectral images and irradiance spectra of sunlight under clear-sky conditions were combined to estimate SIF and SIF yield, which were then correlated with ground-truth Vcmax and Jmax. With observations binned over time (i.e. group 1: 6, 7, and 12 July 2017; group 2: 31 July and 18 August 2017; and group 3: 24 and 25 July 2018), SIF yield showed a stronger negative relationship, compared with SIF, with photosynthetic variables. Using SIF yield for Jmax (Vcmax) predictions, the regression analysis exhibited an R2 of 0.62 (0.71) and root mean square error (RMSE) of 11.88 (46.86) μmol m-2 s-1 for group 1, an R2 of 0.85 (0.72) and RMSE of 13.51 (49.32) μmol m-2 s-1 for group 2, and an R2 of 0.92 (0.87) and RMSE of 15.23 (30.29) μmol m-2 s-1 for group 3. The combined use of hyperspectral images and irradiance measurements provides an alternative yet promising approach to characterization of photosynthetic parameters at plot level.

Proximal Hyperspectral Imaging Detects Diurnal and Drought-Induced Changes in Maize Physiology

Hyperspectral imaging is a promising tool for non-destructive phenotyping of plant physiological traits, which has been transferred from remote to proximal sensing applications, and from manual laboratory setups to automated plant phenotyping platforms. Due to the higher resolution in proximal sensing, illumination variation and plant geometry result in increased non-biological variation in plant spectra that may mask subtle biological differences. Here, a better understanding of spectral measurements for proximal sensing and their application to study drought, developmental and diurnal responses was acquired in a drought case study of maize grown in a greenhouse phenotyping platform with a hyperspectral imaging setup. The use of brightness classification to reduce the illumination-induced non-biological variation is demonstrated, and allowed the detection of diurnal, developmental and early drought-induced changes in maize reflectance and physiology. Diurnal changes in transpiration rate and vapor pressure deficit were significantly correlated with red and red-edge reflectance. Drought-induced changes in effective quantum yield and water potential were accurately predicted using partial least squares regression and the newly developed Water Potential Index 2, respectively. The prediction accuracy of hyperspectral indices and partial least squares regression were similar, as long as a strong relationship between the physiological trait and reflectance was present. This demonstrates that current hyperspectral processing approaches can be used in automated plant phenotyping platforms to monitor physiological traits with a high temporal resolution.

Emerging approaches to measure photosynthesis from the leaf to the ecosystem

Measuring photosynthesis is critical for quantifying and modeling leaf to regional scale productivity of managed and natural ecosystems. This review explores existing and novel advances in photosynthesis measurements that are certain to provide innovative directions in plant science research. First, we address gas exchange approaches from leaf to ecosystem scales. Leaf level gas exchange is a mature method but recent improvements to the user interface and environmental controls of commercial systems have resulted in faster and higher quality data collection. Canopy chamber and micrometeorological methods have also become more standardized tools and have an advanced understanding of ecosystem functioning under a changing environment and through long time series data coupled with community data sharing. Second, we review proximal and remote sensing approaches to measure photosynthesis, including hyperspectral reflectance- and fluorescence-based techniques. These techniques have long been used with aircraft and orbiting satellites, but lower-cost sensors and improved statistical analyses are allowing these techniques to become applicable at smaller scales to quantify changes in the underlying biochemistry of photosynthesis. Within the past decade measurements of chlorophyll fluorescence from earth-orbiting satellites have measured Solar Induced Fluorescence (SIF) enabling estimates of global ecosystem productivity. Finally, we highlight that stronger interactions of scientists across disciplines will benefit our capacity to accurately estimate productivity at regional and global scales. Applying the multiple techniques outlined in this review at scales from the leaf to the globe are likely to advance understanding of plant functioning from the organelle to the ecosystem.

Genebank Phenomics: A Strategic Approach to Enhance Value and Utilization of Crop Germplasm

Genetically diverse plant germplasm stored in ex-situ genebanks are excellent resources for breeding new high yielding and sustainable crop varieties to ensure future food security. Novel alleles have been discovered through routine genebank activities such as seed regeneration and characterization, with subsequent utilization providing significant genetic gains and improvements for the selection of favorable traits, including yield, biotic, and abiotic resistance. Although some genebanks have implemented cost-effective genotyping technologies through advances in DNA technology, the adoption of modern phenotyping is lagging. The introduction of advanced phenotyping technologies in recent decades has provided genebank scientists with time and cost-effective screening tools to obtain valuable phenotypic data for more traits on large germplasm collections during routine activities. The utilization of these phenotyping tools, coupled with high-throughput genotyping, will accelerate the use of genetic resources and fast-track the development of more resilient food crops for the future. In this review, we highlight current digital phenotyping methods that can capture traits during annual seed regeneration to enrich genebank phenotypic datasets. Next, we describe strategies for the collection and use of phenotypic data of specific traits for downstream research using high-throughput phenotyping technology. Finally, we examine the challenges and future perspectives of genebank phenomics.

Estimating photosynthetic traits from reflectance spectra: A synthesis of spectral indices, numerical inversion, and partial least square regression

The lack of efficient means to accurately infer photosynthetic traits constrains understanding global land carbon fluxes and improving photosynthetic pathways to increase crop yield. Here, we investigated whether a hyperspectral imaging camera mounted on a mobile platform could provide the capability to help resolve these challenges, focusing on three main approaches, that is, reflectance spectra-, spectral indices-, and numerical model inversions-based partial least square regression (PLSR) to estimate photosynthetic traits from canopy hyperspectral reflectance for 11 tobacco cultivars. Results showed that PLSR with inputs of reflectance spectra or spectral indices yielded an R2 of ~0.8 for predicting V cmax and J max , higher than an R2 of ~0.6 provided by PLSR of numerical inversions. Compared with PLSR of reflectance spectra, PLSR with spectral indices exhibited a better performance for predicting V cmax (R2 = 0.84 ± 0.02, RMSE = 33.8 ± 2.2 μmol m-2  s-1 ) while a similar performance for J max (R2 = 0.80 ± 0.03, RMSE = 22.6 ± 1.6 μmol m-2  s-1 ). Further analysis on spectral resampling revealed that V cmax and J max could be predicted with ~10 spectral bands at a spectral resolution of less than 14.7 nm. These results have important implications for improving photosynthetic pathways and mapping of photosynthesis across scales.

Plot-level rapid screening for photosynthetic parameters using proximal hyperspectral imaging

Photosynthesis is currently measured using time-laborious and/or destructive methods which slows research and breeding efforts to identify crop germplasm with higher photosynthetic capacities. We present a plot-level screening tool for quantification of photosynthetic parameters and pigment contents that utilizes hyperspectral reflectance from sunlit leaf pixels collected from a plot (~2 m×2 m) in <1 min. Using field-grown Nicotiana tabacum with genetically altered photosynthetic pathways over two growing seasons (2017 and 2018), we built predictive models for eight photosynthetic parameters and pigment traits. Using partial least squares regression (PLSR) analysis of plot-level sunlit vegetative reflectance pixels from a single visible near infra-red (VNIR) (400-900 nm) hyperspectral camera, we predict maximum carboxylation rate of Rubisco (Vc,max, R2=0.79) maximum electron transport rate in given conditions (J1800, R2=0.59), maximal light-saturated photosynthesis (Pmax, R2=0.54), chlorophyll content (R2=0.87), the Chl a/b ratio (R2=0.63), carbon content (R2=0.47), and nitrogen content (R2=0.49). Model predictions did not improve when using two cameras spanning 400-1800 nm, suggesting a robust, widely applicable and more 'cost-effective' pipeline requiring only a single VNIR camera. The analysis pipeline and methods can be used in any cropping system with modified species-specific PLSR analysis to offer a high-throughput field phenotyping screening for germplasm with improved photosynthetic performance in field trials.

A Machine Learning Framework to Predict Nutrient Content in Valencia-Orange Leaf Hyperspectral Measurements

This paper presents a framework based on machine learning algorithms to predict nutrient content in leaf hyperspectral measurements. This is the first approach to evaluate macro- and micronutrient content with both machine learning and reflectance/first-derivative data. For this, citrus-leaves collected at a Valencia-orange orchard were used. Their spectral data was measured with a Fieldspec ASD FieldSpec® HandHeld 2 spectroradiometer and the surface reflectance and first-derivative spectra from the spectral range of 380 to 1020 nm (640 spectral bands) was evaluated. A total of 320 spectral signatures were collected, and the leaf-nutrient content (N, P, K, Mg, S, Cu, Fe, Mn, and Zn) was associated with them. For this, 204,800 (320 × 640) combinations were used. The following machine learning algorithms were used in this framework: k-Nearest Neighbor (kNN), Lasso Regression, Ridge Regression, Support Vector Machine (SVM), Artificial Neural Network (ANN), Decision Tree (DT), and Random Forest (RF). The training methods were assessed based on Cross-Validation and Leave-One-Out. The Relief-F metric of the algorithms’ prediction was used to determine the most contributive wavelength or spectral region associated with each nutrient. This approach was able to return, with high predictions (R2), nutrients like N (0.912), Mg (0.832), Cu (0.861), Mn (0.898), and Zn (0.855), and, to a lesser extent, P (0.771), K (0.763), and S (0.727). These accuracies were obtained with different algorithms, but RF was the most suitable to model most of them. The results indicate that, for the Valencia-orange leaves, surface reflectance data is more suitable to predict macronutrients, while first-derivative spectra is better linked to micronutrients. A final contribution of this study is the identification of the wavelengths responsible for contributing to these predictions.