Derivation of stress severities in wheat from hyperspectral data using support vector regression

ABSTRACTIn this article, an innovative classification framework for hyperspectral image data, based on both spectral and spatial information, is proposed. The main objective of this method is to improve the accuracy and efficiency of high-resolution land-cover mapping in urban areas. The spatial information is obtained by an enhanced marker-based minimum spanning forest (MMSF) algorithm. A pixel-based support vector machine (SVM) algorithm is first used to classify the hyperspectral image data, then the enhanced MMSF algorithm is applied in order to increase the accuracy of less accurately classified land-cover types. The enhanced MMSF algorithm is used as a binary classifier. These two classes are the low-accuracy class and remaining classes. Finally, the SVM algorithm is trained for classes with acceptable accuracy. In the proposed approach, namely MSF-SVM, the markers are extracted from the classification maps obtained by both SVM and watershed segmentation algorithms, and are then used to build the MSF. Three benchmark hyperspectral data sets are used for the assessment: Berlin, Washington DC Mall, and Quebec City. Experimental results demonstrate the superiority of the proposed approach compared with SVM and the original MMSF algorithms. It achieves approximately 5, 6, and 7% higher rates in kappa coefficients of agreement in comparison with the original MMSF algorithm for the Berlin, Washington DC Mall, and Quebec City data sets, respectively.

Discrimination of tropical forest types, dominant species, and mapping of functional guilds by hyperspectral and simulated multispectral Sentinel-2 data

: The goal of this project is to develop spectral analysis techniques for ocean color analysis that are explicitly designed for use with hyperspectral data. The CoBOP program offers a rare opportunity to test any spectral analysis techniques with a wealth of remote sensing and in situ spectral data. Our objective is to develop a set of spectral analysis methods that are appropriate for remote sensing and to adapt them to remote sensing of ocean color. Our eventual objective is to expand the capability to accurately classify water types and bottom types and to extract accurate bathymetry using hyperspectral image data. The procedures will be tested and evaluated using data collected during the CoBOP field programs. We have defined a three-pronged approach: (1) adapt laboratory spectroscopy techniques to remote sensing, (2) expand multispectral approaches where applicable, and (3) develop novel approaches where necessary.

A general framework for the integration of multi-sensor data for dry and fresh biomass retrieval is proposed and tested in Alpine meadows and pastures. To this purpose, hyperspectral spectroradiometer (as simulation of hyperspectral imagery) and biomass samples were collected in field campaigns and Copernicus Sentinel-1 Interferometric Wide (IW) swath SAR backscattering coefficients were used. First, a genetic algorithm feature selection was performed on hyperspectral data, and afterwards the resulting most sensitive bands where combined with SAR data within a support vector regression (SVR) model. The most sensitive hyperspectral bands were mainly located in different regions of the SWIR range for both fresh and dry biomass, and in the red and near-infrared regions mainly for dry biomass, but with less influence for fresh biomass. The R 2 correlation values between the sampled and the estimated biomass range from 0.24 to 0.71. The relatively low performances are mainly related to the saturation effect in the optical bands, as well as to the paucity of points for high values of biomass. The methodology allows a better understanding of the interaction between grassland systems and the electromagnetic spectrum by offering a model with a reduced number of narrow bands in the context of a multi-sensor integration.

The integration of spatial and spectral responses in hyperspectral image data analysis has been identified as a desirable objective by the remote sensing community. However, most available attempts are based on the consideration of spectral information separately from spatial information, and thus the two types of information are not treated simultaneously. In this paper, we describe our background in applying joint spatial/spectral techniques for full (pure)- and mixed-pixel classification of hyperspectral image data. Most of the techniques described in this work are based on classic mathematical morphology theory, which provides a remarkable framework to achieve the desired integration. The performance of the proposed methodologies is demonstrated by comparing them to other well-known pure- and mixed-pixel classifiers, using both simulated and real hyperspectral data collected by the NASA/JPL-AVIRIS and DLR-DAIS 7915 imaging spectrometers.

Investigating the functional traits of Spartina alterniflora can provide insights towards understanding its invasion mechanism, and developing a method leaves can improve its management in coastal wetlands. Here, we examined the relationship between 11 leaf functional traits of S. alterniflora and hyperspectral data and investigated the feature bands through importance score analysis. Using original spectral and first-order differential conversion data of feature bands, we established four prediction models: random forest (RF), support vector machine (SVM), eXtreme Gradient Boosting (XGBoost), and back propagation neural network (BPNN). The study results showed that: (1) the SVM model based on Random Forest Importance Score is well-suited for S. alterniflora leaf functional trait inversion; (2) the importance score of leaf functional traits differed, and first-order differential spectral data produced more bands with high scores compared with the original hyperspectral reflectance data; (3) first-order differential data modelling effects were slightly better than those of the original spectral data. However, the first-order differential treatment did not show a significant improvement in the validation accuracy compared with the original data, and the accuracy of some traits decreased. Our study provides a new methodological approach for improving the monitoring and management of S. alterniflora in coastal wetlands.

Encoding of multispectral and hyperspectral image data using wavelet transform and gain shape vector quantization

Identifying objects by its color name is an essential capability for a service robot to understand and interact with the physical world and be of use in everyday life scenarios. The robot uses an image for the identification, but the image is strongly affected by lightning environment while human does not affected by the environment when they decide its color name. We present lightning environment estimation and perceptual color classification based on the estimation using hyperspectral data. Support Vector Machine (SVM) or Multiple Kernel Learning SVM is used for the estimation and classification. Originality of our paper is that the hyperspectral data is used for both lightning environment estimation and perceptual color classification of an object. Suppose that the lightning environment is given, the perceptual color of the object is classified in each environment. Additionally, perceptual color is estimated by using result of the lightning environment estimation. A novel dataset which consists of the hyperspectral image of 15 objects taken in 4 different lightning environments is constructed in our experiment. Experimental result of the hyperspectral data are compared by those of common color spaces, such as RGB and L*a*b. The estimation and classification with SVM and MKL SVM are compared in the experiments. From the experimental results, hyperspectral data enabled us to present a separated scheme which consists of the lightning environment estimation and perceptual color classification while previous color spaces could not.

Chlorophyll content is one of the essential parameters to assess the growth process of the fruit trees. This present study developed a model for estimation of canopy averaged chlorophyll content (CACC) of pear trees using the convolutional autoencoder (CAE) features of hyperspectral (HS) data. This study also demonstrated the inspection of anomaly among the trees by employing multidimensional scaling on the CAE features and detected outlier trees prior to fit nonlinear regression models. These outlier trees were excluded from the further experiments that helped in improving the prediction performance of CACC. Gaussian process regression (GPR) and support vector regression (SVR) techniques were investigated as nonlinear regression models and used for prediction of CACC. The CAE features were proven to be providing better prediction of CACC when compared with the direct use of HS bands or vegetation indices as predictors. The CACC prediction performance was improved with the exclusion of the outlier trees during training of the regression models. It was evident from the experiments that GPR could predict the CACC with better accuracy compared to SVR. In addition, the reliability of the tree canopy masks, which were utilized for averaging the features' values for a particular tree, was also evaluated.

Rust diseases are considered to be responsible for significant qualitative and quantitative damages on wheat. However, the severity of rust diseases can be managed through development of resistant lines. The present study was aimed to scrutinize existing wheat germplasm against leaf rust and stripe rust of wheat. For this purpose 30 wheat genotypes were assessed for disease resistance under artificial inoculation conditions and 16 genotypes were evaluated under natural conditions at Nuclear Institute for Agriculture (NIA), Tandojam, Pakistan. The disease severity ratings were taken according to Cobs’scale. The studies revealed that wheat genotypes were markedly differed in their resistance to leaf and stripe rust. Among the tested wheat lines / varieties, 6 were rated as resistant, 6 moderately resistant, 13 showed MRMS type response, 2 showed moderately susceptible reaction, 3 lines/varieties displayed susceptible response against leaf rust under artificial conditions. Moreover, under natural conditions 1 was rated as resistant, 2 showed MRMS type response against leaf rust and all were found resistant or immune against stripe rusts under both the conditions. Hence, it was suggested that resistant genotypes evaluated from these studies can be deployed in the future breeding strategies to evolve the resistant varieties against leaf & stripe rusts of wheat

Monitoring grape nutrient status, from flowering to veraison, is important for viticulturists when implementing vineyard management strategies, in order to produce quality wines. However, traditional methods for measuring nutrient elements incur high labour costs. The aim of this study is to explore the potential of predicting grapevine leaf blade nutrient concentration based on hyperspectral data. Leaf blades were collected at two Pinot Noir commercial vineyards at Martinborough, New Zealand. The leaf blade spectral data were obtained with a handheld spectroradiometer, to evaluate surface reflectance and derivative spectra in the spectrum range between 400 and 2400 nm. Afterwards, leaf blades nutrient concentrations (N, P, K, Ca, and Mg) were measured, and their relationships with the hyperspectral data were modelled by machine learning models; partial least squares regression (PLSR), random forest regression (RFR), and support vector regression (SVR) were used. Pearson correlation and recursive feature elimination, based on cross-validation, were used as feature selection methods for RFR and SVR, to improve the model’s performance. The variable importance score of PLSR, and permutation variable importance of RFR and SVR, were used to determine the most sensitive wavelengths, or spectral regions related to each biochemical variable. The results showed that the best predictive performance for leaf blade N concentration was based on PLSR to raw reflectance data (R2 = 0.66; RMSE = 0.15%). The combination of support vector regression with the Pearson correlation selected method and second derivative reflectance provided a high accuracy for K and Ca modelling (R2 = 0.7; RMSE = 0.06%; R2 = 0.62; RMSE = 0.11%, respectively). However, the modelling performance for P and Mg, by different feature groups and variable selection methods, was poor (R2 = 0.15; RMSE = 0.02%; R2 = 0.43; RMSE = 0.43%, respectively). Thus, a larger dataset is needed for improving the prediction of P and Mg. The results indicated that for Pinot Noir leaf blades, raw reflectance data had potential for the prediction of N concentration, while the second-derivative spectra were more suitable to predict K and Ca. This study led to the provision of rapid and non-destructive measurements of grapevine leaf nutrient status.

Urban reservoirs are important for drinking water services and urban living. However, potentially toxic cyanobacteria blooms are frequently present due to human pollution and might threaten the urban water supply. Conveniently, cyanobacteria can be monitored by remote sensing-based approaches based on the spectral features of C-Phycocyanin (PC). Furthermore, methods leveraging Machine Learning Algorithms (MLA) for PC estimation from hyperspectral data have highlighted the potential to estimate PC more accurately - even at low concentrations. Since relatively few methodologies for PC retrieval in tropical environments have been developed or validated, this research evaluated PRISMA hyperspectral data processed with three MLA (Random Forest, Extreme Gradient Boost, and Support Vector Machines) to estimate PC concentrations in the Billings reservoir, Brazil. The same MLA were used to generate PC models using Wordview-3 and Landsat-8/OLI simulated data to assess the potential gain of using hyperspectral over multispectral data. A PRISMA image was processed with three atmospheric correction methods and validated with co-located in-situ data, where the best atmospherically corrected product was used to generate synthetic Landsat-8/OLI and Worldview-3 images. The PC models were calibrated and validated through Monte Carlo simulation using field radiometric and biological data (Chlorophyll-a, PC, and phytoplankton taxonomy) collected in eight field campaigns (N = 115). The PRISMA and the synthetic multispectral images were used for a second round of models’ validation using co-located PC measurements (match-up window ± 4 h). The global PC Mixture Density Network was also applied to the PRISMA data, and the estimates were compared with the other MLA. The results showed that the standard PRISMA surface reflectance product provided the best atmospheric correction (MAE < 20% for the 500–700 nm bands), while ACOLITE and 6SV underperformed it from two to more than ten-fold. Cyanobacteria species were abundant in 96% of the taxonomical samples, even though relatively low PC concentrations were found (PC from 0 to 301.81 μg/L and median PC = 2.9 μg/L). The global Mixture Density Network sharply overestimated PC (MAE = 280% and Bias = 280%), potentially due to Billings reservoir’s low PC:Chlorophyll-a ratio relative to the original training dataset. PRISMA/Random Forest (MAE = 45%) achieved the lowest error for orbital PC estimate, while Extreme Gradient Boost outperformed the other MLA using Worldview-3 (MAE = 49%) and Landsat-8 (MAE = 74%) synthetic imagery. Therefore, the results suggest hyperspectral and multispectral orbital data aligned with MLA are feasible for monitoring PC, even for waters containing low PC concentrations and reduced PC:Chlorophyll-a ratios.

Is it possible to discern Striga weed (Striga hermonthica) infestation levels in maize agro-ecological systems using in-situ spectroscopy?

Mapping the spatial distribution of plant species in savannas provides insight into the roles of competition, fire, herbivory, soils and climate in maintaining the biodiversity of these ecosystems. This study focuses on the challenges facing large-scale species mapping using a fusion of Light Detection and Ranging (LiDAR) and hyperspectral imagery. Here we build upon previous work on airborne species detection by using a two-stage support vector machine (SVM) classifier to first predict species from hyperspectral data at the pixel scale. Tree crowns are segmented from the lidar imagery such that crown-level information, such as maximum tree height, can then be combined with the pixel-level species probabilities to predict the species of each tree. An overall prediction accuracy of 76% was achieved for 15 species. We also show that bidirectional reflectance distribution (BRDF) effects caused by anisotropic scattering properties of savanna vegetation can result in flight line artifacts evident in species probability maps, yet these can be largely mitigated by applying a semi-empirical BRDF model to the hyperspectral data. We find that confronting these three challenges—reflectance anisotropy, integration of pixel- and crown-level data, and crown delineation over large areas—enables species mapping at ecosystem scales for monitoring biodiversity and ecosystem function.

Invasive plants are causing massive economic and environmental troubles for our societies worldwide. The aim of this study is to employ a set of machine learning classifiers for detecting invasive plant species using remote sensing data. The target species is Kudzu vine, which mostly grows in the south-eastern states of the US and quickly outcompetes other plants, making it a relevant and threatening species to consider. Our study area is Atlanta, Georgia and the surrounding area. Five different algorithms: Boosted Logistic Regression (BLR), Naive Bayes (NB), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM) were tested with the aim of testing their performance and identifying the most optimal one. Furthermore, the influence of temporal, spectral and spatial resolution in detecting Kudzu was also tested and reviewed. Our finding shows that random forest, neural network and support vector machine classifiers outperformed. While the achieved internal accuracies were about 97%, an external validation conducted over an expanded area of interest resulted in 79.5% accuracy. Furthermore, the study indicates that high accuracy classification can be achieved using multispectral Sentinel-2 imagery and can be improved while integrating with airborne visible/infrared imaging spectrometer (AVIRIS) hyperspectral data. Finally, this study indicates that dimensionality reduction methods such as principal component analysis (PCA) should be applied cautiously to the hyperspectral AVIRIS data to preserve its utility. The applied approach and the utilized set of methods can be of interest for detecting other kinds of invasive species as part of fulfilling UN sustainable development goals, particularly number 12: responsible consumption and production, 13: climate action, and 15: life on land.