Multispectral Vegetation Indices Research Articles

Estimation of Relative Chlorophyll Content in Spring Wheat Based on Multi-Temporal UAV Remote Sensing

Relative chlorophyll content (SPAD) is an important index for characterizing the nitrogen nutrient status of plants. Continuous, rapid, nondestructive, and accurate estimation of SPAD values in wheat after heading stage can positively impact subsequent nitrogen fertilization management strategies, which regulate grain filling and yield quality formation. In this study, the estimation of SPAD of leaf relative chlorophyll content in spring wheat was conducted at the experimental base in Wuyuan County, Inner Mongolia in 2021. Multispectral images of different nitrogen application levels at 7, 14, 21, and 28 days after the wheat heading stage were acquired by DJI P4M UAV. A total of 26 multispectral vegetation indices were constructed, and the measured SPAD values of wheat on the ground were obtained simultaneously using a handheld chlorophyll meter. Four machine learning algorithms, including deep neural networks (DNN), partial least squares (PLS), random forest (RF), and Adaptive Boosting (Ada) were used to construct SPAD value estimation models at different time from heading growth stages. The model’s progress was evaluated by the coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAPE). The results showed that the optimal SPAD value estimation models for different periods of independent reproductive growth stages of wheat were different, with PLS as the optimal estimation model at 7 and 14 days after heading, RF as the optimal estimation model at 21 days after heading, and Ada as the optimal estimation model at 28 d after heading. The highest accuracy was achieved using the PLS model for estimating SPAD values at 14 d after heading (training set R2 = 0.767, RMSE = 3.205, MAPE = 0.060, and R2 = 0.878, RMSE = 2.405, MAPE = 0.045 for the test set). The combined analysis concluded that selecting multiple vegetation indices as input variables of the model at 14 d after heading stage and using the PLS model can significantly improve the accuracy of SPAD value estimation, provides a new technical support for rapid and accurate monitoring of SPAD values in spring wheat.

Model-Based Identification of Larix sibirica Ledeb. Damage Caused by Erannis jacobsoni Djak. Based on UAV Multispectral Features and Machine Learning

While unmanned aerial vehicle (UAV) remote sensing technology has been successfully used in crop vegetation pest monitoring, a new approach to forest pest monitoring that can be replicated still needs to be explored. The aim of this study was to develop a model for identifying the degree of damage to forest trees caused by Erannis jacobsoni Djak. (EJD). By calculating UAV multispectral vegetation indices (VIs) and texture features (TF), the features sensitive to the degree of tree damage were extracted using the successive projections algorithm (SPA) and analysis of variance (ANOVA), and a one-dimensional convolutional neural network (1D-CNN), random forest (RF), and support vector machine (SVM) were used to construct damage degree recognition models. The overall accuracy (OA), Kappa, Macro-Recall (Rmacro), and Macro-F1 score (F1macro) of all models exceeded 0.8, and the best results were obtained for the 1D-CNN based on the vegetation index sensitive feature set (OA: 0.8950, Kappa: 0.8666, Rmacro: 0.8859, F1macro: 0.8839), while the SVM results based on both vegetation indices and texture features exhibited the poorest performance (OA: 0.8450, Kappa: 0.8082, Rmacro: 0.8415, F1macro: 0.8335). The results for the stand damage level identified by the models were generally consistent with the field survey results, but the results of SVMVIs+TF were poor. Overall, the 1D-CNN showed the best recognition performance, followed by the RF and SVM. Therefore, the results of this study can serve as an important and practical reference for the accurate and efficient identification of the damage level of forest trees attacked by EJD and for the scientific management of forest pests.

Remote sensing and on-farm experiments for determining in-season nitrogen rates in winter wheat – Options for implementation, model accuracy and remaining challenges

Optimised nitrogen (N) fertilisation can be used to increase farm profits, to realise the achievement of quality goals for produce, and to reduce environmental risks in the form of leaching and/or volatilisation of N compounds from the fields. This study examined options and challenges for remote sensing-based variable rate supplemental N fertilisation in winter wheat ( Triticum aestivum L.). The models were based on data from ten field trials conducted in different regions across Sweden over three years. A two-step approach for modelling optimal N rates, suitable for practical implementation in precision agriculture, was developed and evaluated. The expected accuracies for new sites and years were assessed by leave-one-entire-trial-out cross-validation. In a first step, the average N rate was modelled from site-specific information, including data that can be obtained from on-farm experiments, i.e. N uptake in plots without N fertilisation (zero-plots) and N uptake in plots with non-limiting N supply (max-plots). In the second step, additions or subtractions from this average N rate was modelled based on vegetation indices (VIs) mapped by remote sensing. Mean absolute error of the best prediction was 14 kg N ha −1 . In a practical application, however, there will be additional uncertainty from several sources, e.g. uncertainty in the assessment of yield potential. The best mean N rate model was based on geographical region, cultivar, N uptake in zero-plots and yield potential, while the best model of relative N rate within the field used a new multispectral index (d 75 r 6 ), which was designed to give a standardized measure of the steepness of the red edge of reflectance of a crop canopy spectrum. Several other multispectral VIs also performed well but red-green-blue indices were less useful. We conclude that remote sensing (to capture within-field spatial variation patterns), on-farm experiments (to determine the field mean N rate), and the farmers’ experience and knowledge on local conditions (e.g. to assess the yield potential), is a useful combination of information sources in decision support systems for variable rate application of N. Options and remaining research needs for the setup of such a system are discussed. • Leave-one-entire-trial-out cross-validation of target N rate models in 10 field trials over 3 years. • Mean absolute error of supplemental N rate in winter wheat was at best 14 kg N ha −1 . • Yield potential and N uptake in zero-plots were best predictors of optimal average N rate. • A red edge remote sensing index was best predictor for optimal N rate adjustment. • Together, user knowledge, on-farm tests and remote sensing provide robust decision support.

Prediction of maize crop coefficient from UAV multisensor remote sensing using machine learning methods

In the upcoming irrigation management in agricultural production, accurate mapping of crop water consumption with a high spatial and temporal resolution at a farm scale is needed. In this study, we developed models for crop coefficients (Kc) estimation using unmanned aerial vehicle (UAV) remote sensing and machine learning (ML) techniques for irrigated maize in a semi-arid region in Northwest China. Kc values were calculated using a procedure given in FAO56 manual using field measurements. Multispectral vegetation indices (VIs), vegetation fraction (VF), thermal-based VIs, and texture information (TI) were derived from UAV-based multispectral, RGB, and thermal infrared imagery, respectively. These remotely sensed variables and their combinations were used to develop prediction models using six ML algorithms (linear regression-LR, polynomial regression-PR, exponential regression-ER, random forest regression-RFR, support vector regression-SVR, and deep neural network-DNN). Among these models, the RFR with the highest accuracy (R2 = 0.69, RMSE = 0.1019) was recommended to estimate maize Kc. The multispectral and thermal-based VIs and texture of the near-infrared band had greater contributions than RGB-based VF and TI in the Kc-RFR model under different irrigation treatments. Furthermore, the maize Kc-RFR prediction model had high accuracy in estimating cumulative evapotranspiration (R2 = 0.89, RMSE = 15.0 mm/stage) during different growth stages and daily soil water content (R2 = 0.85, RMSE = 0.0089 m3/m3) in the root zone. These results show that the integration of UAV remote sensing and ML provides a promising tool to help farmers make decisions using timely mapped crop water consumption, especially under water shortages or drought conditions.

Yield estimations in a vineyard based on high-resolution spatial imagery acquired by a UAV

Yield estimation in vineyards is an essential issue for performing cropping practices to reach the desired production quality or quantity. Sporadic manual measurements have been traditionally made. In the last decade, vegetation indices (VIs) and geometric parameters obtained from unmanned aerial vehicle (UAV) imagery have been related to different vine biophysical features. This research aimed to evaluate the potential of VIs and green canopy cover (GCC; as a measure of plant vigour) obtained from conventional (or red, green, blue; RGB) and multispectral sensors that monitor spatial intraplot variability for yield predictions. The yield components traditionally sampled in an early growth cycle stage (pea berry size) were combined with UAV imagery-based products. The proposed methodology was applied to a vineyard in southeastern Spain during the 2019 and 2020 growing seasons. Rain-fed and irrigated treatments were implemented. Flights were performed throughout the growth cycle using RGB and multispectral cameras mounted on a UAV. Orthoimages were generated. Computer vision techniques were used to segment these orthoimages to obtain vegetation-only masks. Simple and multiple linear regression techniques were evaluated by using VIs alone, VIs combined with GCC and yield components as predictors. The RMSE values ranged from 0.21 kg vine −1 to 0.39 kg vine −1 when yield components, RGB or multispectral VIs were employed. Therefore, with all the advantages that their use entails, RGB and multispectral sensors are a good option for estimating the final yield of vineyards despite calibration being required for each season and grapevine plot. • An approach was proposed to estimate yield in vineyards with UAVs. • Multispectral and RGB VIs and grapevine vigour were employed. • The method used yield components sampled in early growth cycle stages. • Estimations were made with small errors combining UAV data with yield components.

A Comparison of Analytical Approaches for the Spectral Discrimination and Characterisation of Mite Infestations on Banana Plants

This research investigates the capability of field-based spectroscopy (350–2500 nm) for discriminating banana plants (Cavendish subgroup Williams) infested with spider mites from those unaffected. Spider mites are considered a major threat to agricultural production, as they occur on over 1000 plant species, including banana plant varieties. Plants were grown under a controlled glasshouse environment to remove any influence other than the imposed treatment (presence or absence of spider mites). The spectroradiometer measurements were undertaken with a leaf clip over three infestation events. From the resultant spectral data, various classification models were evaluated including partial least squares discriminant analysis (PLSDA), K-nearest neighbour, support vector machines and back propagation neural network. Wavelengths found to have a significant response to the presence of spider mites were extracted using competitive adaptive reweighted sampling (CARS), sub-window permutation analysis (SPA) and random frog (RF) and benchmarked using the classification models. CARS and SPA provided high detection success (86% prediction accuracy), with the wavelengths found to be significant corresponding with the red edge and near-infrared portions of the spectrum. As there is limited access to operational commercial hyperspectral imaging and additional complexity, a multispectral camera (Sequoia) was assessed for detecting spider mite impacts on banana plants. Simulated multispectral bands were able to provide a high level of detection accuracy (prediction accuracy of 82%) based on a PLSDA model, with the near-infrared band being most important, followed by the red edge, green and red bands. Multispectral vegetation indices were trialled using a simple threshold-based classification method using the green normalised difference vegetation index (GNDVI), which achieved 82% accuracy. This investigation determined that remote sensing approaches can provide an accurate method of detecting mite infestations, with multispectral sensors having the potential to provide a more commercially accessible means of detecting outbreaks.

Remote Sensing Imaging as a Tool to Support Mulberry Cultivation for Silk Production

In recent decades there has been an increasing use of remotely sensed data for precision agricultural purposes. Sericulture, the activity of rearing silkworm (Bombyx mori L.) larvae to produce silk in the form of cocoons, is an agricultural practice that has rarely used remote sensing techniques but that could benefit from them. The aim of this work was to investigate the possibility of using satellite imaging in order to monitor leaf harvesting in mulberry (Morus alba L.) plants cultivated for feeding silkworms; additionally, quantitative parameters on silk cocoon production were related to the analyses on vegetation indices. Adopting PlanetScope satellite images, four M. alba fields were monitored from the beginning of the silkworm rearing season until its end in 2020 and 2021. The results of our work showed that a decrease in the multispectral vegetation indices in the mulberry plots due to leaf harvesting was correlated with the different parameters of silk cocoons spun by silkworm larvae; in particular, a decrease in the Normalized Difference Vegetation Index (NDVI) and Soil Adjusted Vegetation Index (SAVI) had high correlations with quantitative silk cocoon production parameters (R2 values up to 0.56, p < 0.05). These results led us to the conclusion that precision agriculture can improve sericultural practice, offering interesting solutions for estimating the quantity of produced silk cocoons through the remote analysis of mulberry fields.

Satellite multispectral indices to estimate canopy parameters and within-field management zones in super-intensive almond orchards

Continuous canopy status monitoring is an essential factor to support and precisely apply orchard management actions such as pruning, pesticide and foliar treatment applications, or fertirrigation, among others. For that, this work proposes the use of multispectral vegetation indices to estimate geometric and structural orchard parameters from remote sensing images (high temporal and spatial resolution) as an alternative to more time-consuming processing techniques, such as LiDAR surveys or UAV photogrammetry. A super-intensive almond (Prunus dulcis) orchard was scanned using a mobile terrestrial laser (LiDAR) in two different vegetative stages (after spring pruning and before harvesting). From the LiDAR point cloud, canopy orchard parameters, including maximum height and width, cross-sectional area and porosity, were summarized every 0.5 m along the rows and interpolated using block kriging to the pixel centroids of PlanetScope (3 × 3 m) and Sentinel-2 (10 × 10 m) image grids. To study the association between the LiDAR-derived parameters and 4 different vegetation indices. A canonical correlation analysis was carried out, showing the normalized difference vegetation index (NDVI) and the green normalized difference vegetation index (GNDVI) to have the best correlations. A cluster analysis was also performed. Results can be considered optimistic both for PlanetScope and Sentinel-2 images to delimit within-field management zones, being supported by significant differences in LiDAR-derived canopy parameters.

Estimation of transpiration coefficient and aboveground biomass in maize using time-series UAV multispectral imagery

Estimating spatial variation in crop transpiration coefficients (CTc) and aboveground biomass (AGB) rapidly and accurately by remote sensing can facilitate precision irrigation management in semiarid regions. This study developed and assessed a novel machine learning (ML) method for estimating CTc and AGB using time-series unmanned aerial vehicle (UAV)-based multispectral vegetation indices (VIs) of maize under several irrigation treatments at the field scale. Four ML regression methods: multiple linear regression (MLR), support vector regression (SVR), random forest regression (RFR), and adaptive boosting regression (ABR), were used to address the complex relationship between CTc and VIs. AGB was then estimated using exponential, logistic, sigmoid, and linear equations because of their clear mathematical formulations based on the optimal CTc estimation model. The UAV VIs-derived CTc using the RFR estimation model yielded the highest accuracy (R2 = 0.91, RMSE = 0.0526, and nRMSE = 9.07%). The normalized difference red-edge index, transformed chlorophyll absorption in reflectance index, and simple ratio contributed significantly to the RFR-based CTc model. The accuracy of AGB estimation using nonlinear methods was higher than that using the linear method. The exponential method yielded the highest accuracy (R2 = 0.76, RMSE = 282.8 g m−2, and nRMSE = 39.24%) in both the 2018 and 2019 growing seasons. The study confirms that AGB estimation models based on cumulative CTc performed well under several irrigation treatments using high-resolution time-series UAV multispectral VIs and can support irrigation management with high spatial precision at a field scale.

Estimation of Maize LAI Using Ensemble Learning and UAV Multispectral Imagery under Different Water and Fertilizer Treatments

The leaf area index (LAI), commonly used as an indicator of crop growth and physiological development, is mainly influenced by the degree of water and fertilizer stress. Accurate assessment of the LAI can help to understand the state of crop water and fertilizer deficit, which is important for crop management and the precision agriculture. The objective of this study is to evaluate the unmanned aerial vehicle (UAV)-based multispectral imaging to estimate the LAI of maize under different water and fertilizer stress conditions. For this, multispectral imagery of the field was conducted at different growth stages (jointing, trumpet, silking and flowering) of maize under three water treatments and five fertilizer treatments. Subsequently, a stacking ensemble learning model was built with Gaussian process regression (GPR), support vector regression (SVR), random forest (RF), least absolute shrinkage and selection operator (Lasso) and cubist regression as primary learners to predict the LAI using UAV-based vegetation indices (VIs) and ground truth data. Results showed that the LAI was influenced significantly by water and fertilizer stress in both years’ experiments. Multispectral VIs were significantly correlated with maize LAI at multiple growth stages. The Pearson correlation coefficients between UAV-based VIs and ground truth LAI ranged from 0.64 to 0.89. Furthermore, the fusion of multiple stage data showed that the correlations were significantly higher between ground truth LAI and UAV-based VIs than that of single growth stage data. The ensemble learning algorithm with MLR as the secondary learner outperformed as a single machine learning algorithm with high prediction accuracy R2 = 0.967 and RMSE = 0.198 in 2020, and R2 = 0.897 and RMSE = 0.220 in 2021. We believe that the ensemble learning algorithm based on stacking is preferable to the single machine learning algorithm to build the LAI prediction model. This study can provide certain theoretical guidance for the rapid and precise management of water and fertilizer for large experimental fields.

Performance comparison of RGB and multispectral vegetation indices based on machine learning for estimating Hopea hainanensis SPAD values under different shade conditions.

Reasonable cultivation is an important part of the protection work of endangered species. The timely and nondestructive monitoring of chlorophyll can provide a basis for the accurate management and intelligent development of cultivation. The image analysis method has been applied in the nutrient estimation of many economic crops, but information on endangered tree species is seldom reported. Moreover, shade control, as the common seedling management measure, has a significant impact on chlorophyll, but shade levels are rarely discussed in chlorophyll estimation and are used as variables to improve model accuracy. In this study, 2-year-old seedlings of tropical and endangered Hopea hainanensis were taken as the research object, and the SPAD value was used to represent the relative chlorophyll content. Based on the performance comparison of RGB and multispectral (MS) images using different algorithms, a low-cost SPAD estimation method combined with a machine learning algorithm that is adaptable to different shade conditions was proposed. The SPAD values changed significantly at different shade levels (p < 0.01), and 50% shade in the orthographic direction was conducive to chlorophyll accumulation in seedling leaves. The coefficient of determination (R2), root mean square error (RMSE), and average absolute percent error (MAPE) were used as indicators, and the models with dummy variables or random effects of shade greatly improved the goodness of fit, allowing better adaption to monitoring under different shade conditions. Most of the RGB and MS vegetation indices (VIs) were significantly correlated with the SPAD values, but some VIs exhibited multicollinearity (variance inflation factor (VIF) > 10). Among RGB VIs, RGRI had the strongest correlation, but multiple VIs filtered by the Lasso algorithm had a stronger ability to interpret the SPAD data, and there was no multicollinearity (VIF < 10). A comparison of the use of multiple VIs to estimate SPAD indicated that Random forest (RF) had the highest fitting ability, followed by Support vector regression (SVR), linear mixed effect model (LMM), and ordinary least squares regression (OLR). In addition, the performance of MS VIs was superior to that of RGB VIs. The R2 of the optimal model reached 0.9389 for the modeling samples and 0.8013 for the test samples. These findings reinforce the effectiveness of using VIs to estimate the SPAD value of H. hainanensis under different shade conditions based on machine learning and provide a reference for the selection of image data sources.

UAV-based remote sensing using visible and multispectral indices for the estimation of vegetation cover in an oasis of a desert

Natural vegetation is an important indicator for the maintenance of symbiosis in an oasis in extremely arid zones. Unmanned aerial vehicles have advantages of high resolution and multiple wavebands to obtain details of sparse vegetation cover. So far, studies on the selection of machine learning methods are relatively limited and usually focus on only a few selected methods. In this study, the natural vegetation of the Dariyabui Oasis in the hinterland of the Taklamakan Desert in China was mapped using 2,550 samples of data and 14 visible and multispectral vegetation indices as model variables. Six machine learning methods were used to construct fractional vegetation cover (FVC) predictive regression models. Coefficient of determination (R2), root-mean-square error (RMSE), and mean-absolute error (MAE) were used to evaluate the models. The regression models were divided into four components: visible (RF: R2 = 0.65, RMSE = 0.59 %, MAE = 0.41 %), multispectral (RF: R2 = 0.71, RMSE = 0.54 %, MAE = 0.36 %), visible and multispectral (RF: R2 = 0.69, RMSE = 0.55 %, MAE = 0.37 %), and the product of visible and multispectral vegetation indices (RF: R2 = 0.68, RMSE = 0.57 %, MAE = 0.39 %). Besides, the visible vegetation index results were validated using different years and different aerial height data. The results show that these four regression models can effectively obtain the FVC of sparse vegetation of the desert. This study applied the Random Forest model, which was selected based on a comparison of other models, to predict the status of desert vegetation cover based on spectral data to provide information for its conservation and management.

Identification of Male and Female Parents for Hybrid Rice Seed Production Using UAV-Based Multispectral Imagery

Identifying and extracting male and female parent of hybrid rice and then accurately judging the spikelet flowering of male parents is the basis of hybrid rice pollination. Currently, male parent flowering information extraction for hybrid rice is basically obtained by manual recognition. In this study, remote sensing images of parental rice fields were obtained with a multispectral camera carried by a UAV (Umanned Aerial Vehicle). Six kinds of visible light vegetation indices and four kinds of multispectral vegetation indices, together with two classification methods, pixel-based supervised classification and sample-based object-oriented classification, were applied to identify the male and female parents of hybrid rice, after which the accuracies of the methods were compared. The results showed that the visible vegetation index had a better effect in pixel-based supervised classification. The kappa coefficient of ExGR (Excess Green minus Excess Red index) classification was 0.9256 and the total accuracy was 0.9552. The extraction accuracy was higher than that of the other vegetation indices and object-oriented classification. In pixel-based supervised classification, the maximum likelihood method achieved the highest identification accuracy and shortest calculation time. Taking the remote sensing images obtained with a UAV as a data source, maximum likelihood supervised classification based on ExGR index can more effectively and quickly identify the field information of male and female parents of hybrid rice so as to provide a reference for determining optimal pollination timing for hybrid rice in large-scale seed production farms.

Improving Wheat Yield Prediction Accuracy Using LSTM-RF Framework Based on UAV Thermal Infrared and Multispectral Imagery

Yield prediction is of great significance in agricultural production. Remote sensing technology based on unmanned aerial vehicles (UAVs) offers the capacity of non-intrusive crop yield prediction with low cost and high throughput. In this study, a winter wheat field experiment with three levels of irrigation (T1 = 240 mm, T2 = 190 mm, T3 = 145 mm) was conducted in Henan province. Multispectral vegetation indices (VIs) and canopy water stress indices (CWSI) were obtained using an UAV equipped with multispectral and thermal infrared cameras. A framework combining a long short-term memory neural network and random forest (LSTM-RF) was proposed for predicting wheat yield using VIs and CWSI from multi-growth stages as predictors. Validation results showed that the R2 of 0.61 and the RMSE value of 878.98 kg/ha was achieved in predicting grain yield using LSTM. LSTM-RF model obtained better prediction results compared to the LSTM with n R2 of 0.78 and RMSE of 684.1 kg/ha, which is equivalent to a 22% reduction in RMSE. The results showed that LSTM-RF considered both the time-series characteristics of the winter wheat growth process and the non-linear characteristics between remote sensing data and crop yield data, providing an alternative for accurate yield prediction in modern agricultural management.

Vineyard classification using OBIA on UAV-based RGB and multispectral data: A case study in different wine regions

Vineyard classification is an important process within viticulture-related decision-support systems. Indeed, it improves grapevine vegetation detection, enabling both the assessment of vineyard vegetative properties and the optimization of in-field management tasks. Aerial data acquired by sensors coupled to unmanned aerial vehicles (UAVs) may be used to achieve it. Flight campaigns were conducted to acquire both RGB and multispectral data from three vineyards located in Portugal and in Italy. Red, green, blue and near infrared orthorectified mosaics resulted from the photogrammetric processing of the acquired data. They were then used to calculate RGB and multispectral vegetation indices, as well as a crop surface model (CSM). Three different supervised machine learning (ML) approaches—support vector machine (SVM), random forest (RF) and artificial neural network (ANN)—were trained to classify elements present within each vineyard into one of four classes: grapevine, shadow, soil and other vegetation. The trained models were then used to classify vineyards objects, generated from an object-based image analysis (OBIA) approach, into the four classes. Classification outcomes were compared with an automatic point-cloud classification approach and threshold-based approaches. Results shown that ANN provided a better overall classification performance, regardless of the type of features used. Features based on RGB data showed better performance than the ones based only on multispectral data. However, a higher performance was achieved when using features from both sensors. The methods presented in this study that resort to data acquired from different sensors are suitable to be used in the vineyard classification process. Furthermore, they also may be applied in other land use classification scenarios.

Estimation of above-ground biomass in tropical afro-montane forest using Sentinel-2 derived indices

Empirical analyses were common methods for forest biomass estimation. Lately, satellite images are popularly used to study different attributes of forest vegetation. Sentinel-2 image provides a significant improvement in spectral coverage, spatial resolution and temporal frequency in assessing forest biomass. This study examined the potential use of multispectral (MS) bands, vegetation indices and biophysical variables derived from Sentinel-2 images in modeling above-ground biomass (AGB) in tropical afro-montane forest of the Yayu biosphere reserve. A coupled method of remote sensing and statistics was applied to establish a biomass estimation model using spectral data generated from Sentinel-2 image and AGB data measured from the field. Multispectral bands, vegetation indices and biophysical variables were extracted from the Sentinel-2 image. Forest stand parameters such as DBH and tree height were measured from sampling plots to calculate AGB using allometric equations. The strength of correlation between the measured biomass and the MS bands, indices and biophysical variables were examined using Pearson’s product-moment correlation coefficients. A regression analysis was iteratively applied to identify the determinant variables for predicting AGB. The prediction results were validated based on the magnitude of coefficients of determination between the observed and the predicted values and the magnitude of the Root Mean Square Error (RMSE). A strong correlation (r ranging from 0.65 to 0.74) was observed between the biophysical variables from Sentinel-2 image and the measured AGB from the field. The MS Band 4 (red band), vegetation variables LAI, FCOVER and FAPAR, and band combination index IRECI yielded better results and are good predictor variables for forest AGB. The model goodness of fit between the observed and predicted AGB showed a coefficient of determination (r2) of 0.74 and RMSE of 0.16 ton C/pixel, which shows strong performance of the prediction model. Vegetation indices derived from Sentinel-2 imagery are good predictors of AGB in tropical afro-montane forests. Sentinel-2 image has improved the reliability of biomass estimation from remotely sensed data. Since field sampling plots were few in this study, the level of accuracy will likely improve with more number of field sample measurements.

UAV-based multispectral vegetation indices for assessing the interactive effects of water and nitrogen in irrigated horticultural crops production under tropical sub-humid conditions: A case of African eggplant

UAV-based multispectral vegetation indices are often used to assess crop performance and water consumptive use. However, their ability to assess the interaction between water, especially deficit irrigation, and nitrogen application rates in irrigated agriculture has been less explored. Understanding the effect of water-nitrogen interactions on vegetation indices could further support optimal water and N management. Therefore, this study used a split plot design with water being the main factor and N being the sub-factor. African eggplants were drip irrigated at 100% (I100), 80% (I80) or 60% (I60) of the crop water requirements and received 100% (F100), 75% (F75), 50% (F50) or 0% (F0) of the crop N requirements. Results showed that the transformed difference vegetation index (TDVI) was best in distinguishing differences in leaf moisture content (LMC) during the vegetative stage irrespective of the N treatment. The green normalized difference vegetation index (GNDVI) worked well to distinguish leaf N during vegetative and full vegetative stages. However, the detection of the interactive effect of water and N on crop performance required a combination of GNDVI, NDVI and OSAVI across both stages as each of these 3 VI showed an ability to detect some but not all treatments. The fact that a certain amount of irrigation water can optimize the efficiency of N uptake by the plant is an important criterion to consider in developing crop specific VI based decision trees for crop performance assessments and yield prediction.

Deep Semantic Segmentation of Trees Using Multispectral Images

Forests can be efficiently monitored by automatic semantic segmentation of trees using satellite and/or aerial images. Still, several challenges can make the problem difficult, including the varying spectral signature of different trees, lack of sufficient labelled data, and geometrical occlusions. In this paper, we address the tree segmentation problem using multispectral imagery. While we carry out large-scale experiments on several deep learning architectures using various spectral input combinations, we also attempt to explore whether hand-crafted spectral vegetation indices can improve the performance of deep learning models in the segmentation of trees. Our experiments include benchmarking a variety of multispectral remote sensing image sets, deep semantic segmentation architectures, and various spectral bands as inputs, including a number of hand-crafted spectral vegetation indices. From our large-scale experiments, we draw several useful conclusions. One particularly important conclusion is that, with no additional computation burden, combining different categories of multispectral vegetation indices, such as NVDI, ARVI, and SAVI, within a single three-channel input, and using the state-of-the-art semantic segmentation architectures, tree segmentation accuracy can be improved under certain conditions, compared to using high-resolution visible and/or nearinfrared input.

Entropy Weight Ensemble Framework for Yield Prediction of Winter Wheat Under Different Water Stress Treatments Using Unmanned Aerial Vehicle-Based Multispectral and Thermal Data.

Crop breeding programs generally perform early field assessments of candidate selection based on primary traits such as grain yield (GY). The traditional methods of yield assessment are costly, inefficient, and considered a bottleneck in modern precision agriculture. Recent advances in an unmanned aerial vehicle (UAV) and development of sensors have opened a new avenue for data acquisition cost-effectively and rapidly. We evaluated UAV-based multispectral and thermal images for in-season GY prediction using 30 winter wheat genotypes under 3 water treatments. For this, multispectral vegetation indices (VIs) and normalized relative canopy temperature (NRCT) were calculated and selected by the gray relational analysis (GRA) at each growth stage, i.e., jointing, booting, heading, flowering, grain filling, and maturity to reduce the data dimension. The elastic net regression (ENR) was developed by using selected features as input variables for yield prediction, whereas the entropy weight fusion (EWF) method was used to combine the predicted GY values from multiple growth stages. In our results, the fusion of dual-sensor data showed high yield prediction accuracy [coefficient of determination (R2) = 0.527–0.667] compared to using a single multispectral sensor (R2 = 0.130–0.461). Results showed that the grain filling stage was the optimal stage to predict GY with R2 = 0.667, root mean square error (RMSE) = 0.881 t ha–1, relative root-mean-square error (RRMSE) = 15.2%, and mean absolute error (MAE) = 0.721 t ha–1. The EWF model outperformed at all the individual growth stages with R2 varying from 0.677 to 0.729. The best prediction result (R2 = 0.729, RMSE = 0.831 t ha–1, RRMSE = 14.3%, and MAE = 0.684 t ha–1) was achieved through combining the predicted values of all growth stages. This study suggests that the fusion of UAV-based multispectral and thermal IR data within an ENR-EWF framework can provide a precise and robust prediction of wheat yield.

Damage assessment of chilli thrips using high resolution multispectral satellite data

&#x0D; Remote sensing technology offers an effective, rapid and reliable tool for assessing pest severity in vegetation. Ground based hyperspectral radiometry studies revealed significant difference in the reflectance spectra between healthy and thrip damaged vegetation. Space borne multispectral reflectance from Sentinel 2A satellite data of chilli thrip infested canopy has significant differences in red region (Band 4 – 664.6 nm), NIR region (Bands 5, 6, 7, 8 &amp; 8A having central wavelengths at 704.1, 740.5, 782.8 &amp; 832.8 nm, respectively) and SWIR region (Bands 11 &amp; 12 having central wavelengths at 1613.7 and 2202.4 nm). In this study, an attempt was made to discriminate healthy and pest affected chilli crop in the multispectral satellite imagery using several multispectral vegetation indices. Of these, land surface water index, LSWI (p=0.018) and normalized difference water index, NDWI (p=0.001) were found significant. These indices were used to classify chilli fields in the satellite imagery into severe, moderate and healthy classes. Superior performance of LSWI over NDWI with overall accuracy of 93.80 and Kappa Coefficient of 0.89 was observed. Moran's Index was used to study the spatial distribution of chilli thrips and observed strong clustering (I= 0.9073, p=0.0001).&#x0D;