Dissection of hyperspectral reflectance to estimate nitrogen and chlorophyll contents in tea leaves based on machine learning algorithms

Advances in the tea plants phenotyping using hyperspectral imaging technology

Rapid detection of plant phenotypic traits is crucial for plant breeding and cultivation. Traditional measurement methods are carried out by rich-experienced agronomists, which are time-consuming and labor-intensive. However, with the increasing demand for rapid and high-throughput testing in tea plants traits, digital breeding and smart cultivation of tea plants rely heavily on precise plant phenotypic trait measurement techniques, among which hyperspectral imaging (HSI) technology stands out for its ability to provide real-time and rich-information. In this paper, we provide a comprehensive overview of the principles of hyperspectral imaging technology, the processing methods of cubic data, and relevant algorithms in tea plant phenomics, reviewing the progress of applying hyperspectral imaging technology to obtain information on tea plant phenotypes, growth conditions, and quality indicators under environmental stress. Lastly, we discuss the challenges faced by HSI technology in the detection of tea plant phenotypic traits from different perspectives, propose possible solutions, and envision the potential development prospects of HSI technology in the digital breeding and smart cultivation of tea plants. This review aims to provide theoretical and technical support for the application of HSI technology in detecting tea plant phenotypic information, further promoting the trend of developing high quality and high yield tea leaves.

Prediction of leaf nitrogen in sugarcane (Saccharum spp.) by Vis-NIR-SWIR spectroradiometry

Nitrogen is one of the essential nutrients for the production of agricultural crops, participating in a complex interaction among soil, plant and the atmosphere. Therefore, its monitoring is important both economically and environmentally. The aim of this work was to estimate the leaf nitrogen contents in sugarcane from hyperspectral reflectance data during different vegetative stages of the plant. The assessments were performed from an experiment designed in completely randomized blocks, with increasing nitrogen doses (0, 60, 120 and 180 kg ha-1). The acquisition of the spectral data occurred at different stages of crop development (67, 99, 144, 164, 200, 228, 255 and 313 days after cutting; DAC). In the laboratory, the hyperspectral responses of the leaves and the Leaf Nitrogen Contents (LNC) were obtained. The hyperspectral data and the LNC values were used to generate spectral models employing the technique of Partial Least Squares Regression (PLSR) Analysis, also with the calculation of the spectral bands of greatest relevance, by the Variable Importance in Projection (VIP). In general, the increase in LNC promoted a smaller reflectance in all wavelengths in the visible (400-680 nm). Acceptable models were obtained (R2 > 0.70 and RMSE <1.41 g kg-1), the most robust of which were those generated from spectra in the visible (400-680 nm) and red-edge (680-750 nm), with values of R2 > 0.81 and RMSE <1.24 g kg-1. An independent validation, leave-one-date-out cross validation (LOOCV), was performed using data from other collections, which confirmed the robustness and the possibility of LNC prediction in new data sets, derived, for instance, from samplings subsequent to the period of study.

Review - Plant nutritional status analysis employing the visible and near-infrared spectroscopy spectral sensor

Experiments demonstrated that visible and near-infrared (Vis-NIR) spectroscopy is a highly reliable tool for determining the nutritional status of plants. Although numerous studies on various kinds of plants have been conducted, there are only a few summaries of the research findings regarding the absorbance bands in the visible and near-infrared region and how they relate to the nutritional status of plants. This article will discuss the application of Vis-NIR spectroscopy for monitoring the nutrient conditions of plants, with a particular emphasis on three major components required by plants, namely nitrogen (N), phosphorus (P), and potassium (K), or NPK. Each section discussed different topics, for instance, the essential nutrients needed by plants, the application of Vis-NIR spectroscopy in nutrient status analysis, chemometrics tools, and absorbance bands related to the nutrient status, respectively. Deduction made concluded that factors affecting the plant's structure are contributed by several circumstances like the age of leaves, concentration of pigments, and water content. These factors are intertwined, strongly correlated, and can be observed in the visible and near-infrared regions. While the visible region is commonly utilised for nutritional analysis in plants, the literature review performed in this paper shows that the near-infrared region as well contains valuable information about the plant's nutritional status. A few wavelengths related to the direct estimation of nutrients in this review explained that information on nutrients can be linked with chlorophyll and water absorption bands such that N and P are the components of chlorophyll and protein; on the other hand, K exists in the form of cationic carbohydrates which are sensitive to water region.

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.

Transcriptome Analysis of Maize Ear Leaves Treated with Long-Term Straw Return plus Nitrogen Fertilizer under the Wheat-Maize Rotation System

Straw return (SR) plus nitrogen (N) fertilizer has become a practical field management mode to improve soil fertility and crop yield in North China. This study aims to explore the relationship among organic waste, mineral nutrient utilization, and crop yield under SRN mode. The fertilizer treatments included unfertilized (CK), SR (straws from wheat and corn), N fertilizer (N), and SR plus N fertilizer (SRN). SRN treatment not only significantly increased the grain yield, net photosynthetic rate, and transpiration rate but also enhanced the contents of chlorophyll, soluble sugar, and soluble protein and increased the activities of antioxidant enzymes but reduced intercellular CO2 concentration and malondialdehyde (MDA) content when compared to other treatments. There were 2572, 1258, and 3395 differentially expressed genes (DEGs) identified from the paired comparisons of SRvsCK, NvsCK, and SRNvsCK, respectively. The transcript levels of many promising genes involved in the transport and assimilation of potassium, phosphate, and nitrogen, as well as the metabolisms of sugar, lipid, and protein, were down-regulated by straw returning under N treatment. SRN treatment maintained the maximum maize grain yield by regulating a series of genes' expressions to reduce nutrient shortage stress and to enhance the photosynthesis of ear leaves at the maize grain filling stage. This study would deepen the understanding of complex molecular mechanisms among organic waste, mineral nutrient utilization, crop yield, and quality.

Modeling the spatial-spectral characteristics of plants for nutrient status identification using hyperspectral data and deep learning methods

Sustainable fertilizer management in precision agriculture is essential for both economic and environmental reasons. To effectively manage fertilizer input, various methods are employed to monitor and track plant nutrient status. One such method is hyperspectral imaging, which has been on the rise in recent times. It is a remote sensing tool used to monitor plant physiological changes in response to environmental conditions and nutrient availability. However, conventional hyperspectral processing mainly focuses on either the spectral or spatial information of plants. This study aims to develop a hybrid convolution neural network (CNN) capable of simultaneously extracting spatial and spectral information from quinoa and cowpea plants to identify their nutrient status at different growth stages. To achieve this, a nutrient experiment with four treatments (high and low levels of nitrogen and phosphorus) was conducted in a glasshouse. A hybrid CNN model comprising a 3D CNN (extracts joint spectral-spatial information) and a 2D CNN (for abstract spatial information extraction) was proposed. Three pre-processing techniques, including second-order derivative, standard normal variate, and linear discriminant analysis, were applied to selected regions of interest within the plant spectral hypercube. Together with the raw data, these datasets were used as inputs to train the proposed model. This was done to assess the impact of different pre-processing techniques on hyperspectral-based nutrient phenotyping. The performance of the proposed model was compared with a 3D CNN, a 2D CNN, and a Hybrid Spectral Network (HybridSN) model. Effective wavebands were selected from the best-performing dataset using a greedy stepwise-based correlation feature selection (CFS) technique. The selected wavebands were then used to retrain the models to identify the nutrient status at five selected plant growth stages. From the results, the proposed hybrid model achieved a classification accuracy of over 94% on the test dataset, demonstrating its potential for identifying nitrogen and phosphorus status in cowpea and quinoa at different growth stages.

Proximal hyperspectral sensing of abiotic stresses in plants

Recent attempts, advances and challenges, as well as future perspectives regarding the application of proximal hyperspectral sensing (where sensors are placed within 10 m above plants, either on land-based platforms or in controlled environments) to assess plant abiotic stresses have been critically reviewed. Abiotic stresses, caused by either physical or chemical reasons such as nutrient deficiency, drought, salinity, heavy metals, herbicides, extreme temperatures, and so on, may be more damaging than biotic stresses (affected by infectious agents such as bacteria, fungi, insects, etc.) on crop yields. The proximal hyperspectral sensing provides images at a sub-millimeter spatial resolution for doing an in-depth study of plant physiology and thus offers a global view of the plant's status and allows for monitoring spatio-temporal variations from large geographical areas reliably and economically. The literature update has been based on 362 research papers in this field, published from 2010, most of which are from four years ago and, in our knowledge, it is the first paper that provides a comprehensive review of the applications of the technique for the detection of various types of abiotic stresses in plants.

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.

Spectral Preprocessing Combined with Deep Transfer Learning to Evaluate Chlorophyll Content in Cotton Leaves

Rapid determination of chlorophyll content is significant for evaluating cotton's nutritional and physiological status. Hyperspectral technology equipped with multivariate analysis methods has been widely used for chlorophyll content detection. However, the model developed on one batch or variety cannot produce the same effect for another due to variations, such as samples and measurement conditions. Considering that it is costly to establish models for each batch or variety, the feasibility of using spectral preprocessing combined with deep transfer learning for model transfer was explored. Seven different spectral preprocessing methods were discussed, and a self-designed convolutional neural network (CNN) was developed to build models and conduct transfer tasks by fine-tuning. The approach combined first-derivative (FD) and standard normal variate transformation (SNV) was chosen as the best pretreatment. For the dataset of the target domain, fine-tuned CNN based on spectra processed by FD + SNV outperformed conventional partial least squares (PLS) and squares-support vector machine regression (SVR). Although the performance of fine-tuned CNN with a smaller dataset was slightly lower, it was still better than conventional models and achieved satisfactory results. Ensemble preprocessing combined with deep transfer learning could be an effective approach to estimate the chlorophyll content between different cotton varieties, offering a new possibility for evaluating the nutritional status of cotton in the field.

Transcriptome and hyperspectral profiling allows assessment of phosphorus nutrient status in rice under field conditions

Phosphorus (P) is one of the macronutrients indispensable for crop production, and therefore it is important to understand the potential of plants to adapt to low P conditions. We compared growth and leaf genome-wide transcriptome of four rice cultivars during growth between two fields with different amount of available phosphate and further analysed the acceptable range of P levels for normal growth from the view of both appearance traits and internal P nutrient status, which was measured by profiling the expression of the P indicator gene. This demonstrated that rice plants have a robustness to moderate P-deficient conditions expressing a system for P acquisition and usage without any effects on yield potential and that P indicator gene expression could be a useful index for early diagnosis of P status in plants. To develop a simple method for assessment of P status, we tried to predict the expression level using reflectance spectroscopy and hyperspectral imaging, thereby providing models with good performance. Our findings suggest that rice plants have the potential to adapt to moderate low P conditions in the field and showed that the hyperspectral technique is one of the useful tools for simple measurement of molecular-level dynamics reflecting internal nutrient conditions.

Evaluation of a One-Dimensional Convolution Neural Network for Chlorophyll Content Estimation Using a Compact Spectrometer

Leaf chlorophyll content is used as a major indicator of plant stress and growth, and hyperspectral remote sensing is frequently used to monitor the chlorophyll content. Hyperspectral reflectance has been used to evaluate vegetation properties such as pigment content, plant structure and physiological features using portable spectroradiometers. However, the prices of these devices have not yet decreased to consumer-affordable levels, which prevents widespread use. In this study, a system based on a cost-effective fingertip-sized spectrometer (Colorcompass-LF, a total price for the proposed solution was approximately 1600 USD) was evaluated for its ability to estimate the chlorophyll contents of radish and wasabi leaves and was compared with the Analytical Spectral Devices FieldSpec4. The chlorophyll contents per leaf area (cm2) of radish were generally higher than those of wasabi and ranged from 42.20 to 94.39 μg/cm2 and 11.39 to 40.40 μg/cm2 for radish and wasabi, respectively. The chlorophyll content was estimated using regression models based on a one-dimensional convolutional neural network (1D-CNN) that was generated after the original reflectance from the spectrometer measurements was de-noised. The results from an independent validation dataset confirmed the good performance of the Colorcompass-LF after spectral correction using a second-degree polynomial, and very similar estimation accuracies were obtained for the measurements from the FieldSpec4. The coefficients of determination of the regression models based on 1D-CNN were almost same (with R2 = 0.94) and the ratios of performance to deviation based on reflectance after spectral correction using a second-degree polynomial for the Colorcompass-LF and the FieldSpec4 were 4.31 and 4.33, respectively.

Remote Sensing, Geophysics, and Modeling to Support Precision Agriculture—Part 2: Irrigation Management

Food and water security are considered the most critical issues globally due to the projected population growth placing pressure on agricultural systems. Because agricultural activity is known to be the largest consumer of freshwater, the unsustainable irrigation water use required by crops to grow might lead to rapid freshwater depletion. Precision agriculture has emerged as a feasible concept to maintain farm productivity while facing future problems such as climate change, freshwater depletion, and environmental degradation. Agriculture is regarded as a complex system due to the variability of soil, crops, topography, and climate, and its interconnection with water availability and scarcity. Therefore, understanding these variables’ spatial and temporal behavior is essential in order to support precision agriculture by implementing optimum irrigation water use. Nowadays, numerous cost- and time-effective methods have been highlighted and implemented in order to optimize on-farm productivity without threatening the quantity and quality of the environmental resources. Remote sensing can provide lateral distribution information for areas of interest from the regional scale to the farm scale, while geophysics can investigate non-invasively the sub-surface soil (vertically and laterally), mapping large spatial and temporal domains. Likewise, agro-hydrological modelling can overcome the insufficient on-farm physicochemical dataset which is spatially and temporally required for precision agriculture in the context of irrigation water scheduling.

VIS-NIR Modeling of Hydrangenol and Phyllodulcin Contents in Tea-Hortensia (Hydrangea macrophylla subsp. serrata)

Hyperspectral data are commonly used for the fast and inexpensive quantification of plant constituent estimation and quality control as well as in research and development applications. Based on chemical analysis, different models for dihydroisocoumarins (DHCs), namely hydrangenol (HG) and phyllodulcin (PD), were built using a partial least squares regression (PLSR). While HG is common in Hydrangea macrophylla, PD only occurs in cultivars of Hydrangea macrophylla subsp. serrata, also known as ‘tea-hortensia’. PD content varies significantly over the course of the growing period. For maximizing yield, a targeted estimation of PD content is needed. Nowadays, DHC contents are determined via UPLC, a time-consuming and a destructive method. In this research article we investigated PLSR-based models for HG and PD using three different spectrometers. Two separate trials were conducted to test for model quality. Measurement conditions, namely fresh or dried leaves and black or white background, did not influence model quality. While highly accurate modeling of HG and PD for single plants was not possible, the determination of the mean content on a larger scale was successful. The results of this study show that hyperspectral modeling as a decision support for farmers is feasible and provides accurate results on a field scale.

Detection of apple proliferation disease in Malus × domestica by near infrared reflectance analysis of leaves

In this study near infrared spectroscopical analysis of dried and ground leaves was performed and combined with a multivariate data analysis to distinguish 'Candidatus Phytoplasma mali' infected from non-infected apple trees (Malus × domestica). The bacterium is the causative agent of Apple Proliferation, one of the most threatening diseases in commercial apple growing regions. In a two-year study, leaves were sampled from three apple orchards, at different sampling events throughout the vegetation period. The spectral data were analyzed with a principal component analysis and classification models were developed. The model performance for the differentiation of Apple Proliferation diseased from non-infected trees increased throughout the vegetation period and gained best results in autumn. Even with asymptomatic leaves from infected trees a correct classification was possible indicating that the spectral-based method provides reliable results even if samples without visible symptoms are analyzed. The wavelength regions that contributed to the differentiation of infected and non-infected trees could be mainly assigned to a reduction of carbohydrates and N-containing organic compounds. Wet chemical analyses confirmed that N-containing compounds are reduced in leaves from infected trees. The results of our study provide a valuable indication that spectral analysis is a promising technique for Apple Proliferation detection in future smart farming approaches.

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.

Potential of spectroscopic analyses for non-destructive estimation of tea quality-related metabolites in fresh new leaves

Spectroscopic sensing provides physical and chemical information in a non-destructive and rapid manner. To develop non-destructive estimation methods of tea quality-related metabolites in fresh leaves, we estimated the contents of free amino acids, catechins, and caffeine in fresh tea leaves using visible to short-wave infrared hyperspectral reflectance data and machine learning algorithms. We acquired these data from approximately 200 new leaves with various status and then constructed the regression model in the combination of six spectral patterns with pre-processing and five algorithms. In most phenotypes, the combination of de-trending pre-processing and Cubist algorithms was robustly selected as the best combination in each round over 100 repetitions that were evaluated based on the ratio of performance to deviation (RPD) values. The mean RPD values were ranged from 1.1 to 2.7 and most of them were above the acceptable or accurate threshold (RPD = 1.4 or 2.0, respectively). Data-based sensitivity analysis identified the important hyperspectral regions around 1500 and 2000 nm. Present spectroscopic approaches indicate that most tea quality-related metabolites can be estimated non-destructively, and pre-processing techniques help to improve its accuracy.