Tree species classification in an extensive forest area using airborne hyperspectral data under varying light conditions

Although airborne hyperspectral data with detailed spatial and spectral information has demonstrated significant potential for tree species classification,it has not been widely used over large areas.A comprehensive process based on multi-flightline airborne hyperspectral data is lacking over large,forested areas influenced by both the effects of bidirectional reflectance distribution function(BRDF)and cloud shadow contamination.In this study,hyperspectral data were collected over the Mengjiagang Forest Farm in Northeast China in the summer of 2017 using the Chinese Academy of Forestry's LiDAR,CCD,and hyperspectral systems(CAF-LiCHy).After BRDF correction and cloud shadow detection processing,a tree species classification workflow was developed for sunlit and cloud-shaded forest areas with input features of minimum noise fraction reduced bands,spectral vegetation indices,and texture information.Results indicate that BRDF-corrected sunlit hyperspectral data can provide a stable and high classification accuracy based on representative training data.Cloud-shaded pixels also have good spectral separability for species classification.The red-edge spectral information and ratio-based spectral indices with high importance scores are recommended as input features for species classification under varying light conditions.According to the classification accuracies through field survey data at multiple spatial scales,it was found that species classification within an extensive forest area using airborne hyperspectral data under various illuminations can be successfully carried out using the effective radiometric consistency process and feature selection strategy.

CNN coal and rock recognition method based on hyperspectral data

Aiming at the problem of coal gangue identifcation in the current fully mechanized mining face and coal washing,this article proposed a convolution neural network(CNN)coal and rock identifcation method based on hyperspectral data.First,coal and rock spectrum data were collected by a near-infrared spectrometer,and then four methods were used to flter 120 sets of collected data:frst-order diferential(FD),second-order diferential(SD),standard normal variable transformation(SNV),and multi-style smoothing.The coal and rock refectance spectrum data were pre-processed to enhance the intensity of spectral refectance and absorption characteristics,as well as efectively remove the spectral curve noise generated by instrument performance and environmental factors.A CNN model was constructed,and its advantages and disadvantages were judged based on the accuracy of the three parameter combinations(i.e.,the learning rate,the number of feature extraction layers,and the dropout rate)to generate the best CNN classifer for the hyperspectral data for rock recognition.The experiments show that the recognition accuracy of the one-dimensional CNN model proposed in this paper reaches 94.6%.Verifcation of the advantages and efectiveness of the method were proposed in this article.

Evaluation of atmospheric corrections on hyperspectral data with special reference to mineral mapping

Hyperspectral images have wide applications in the fields of geology,mineral exploration,agriculture,forestry and environmental studies etc.due to their narrow band width with numerous channels.However,these images commonly suffer from atmospheric effects,thereby limiting their use.In such a situation,atmospheric correction becomes a necessary pre-requisite for any further processing and accurate interpretation of spectra of different surface materials/objects.In the present study,two very advance atmospheric approaches i.e.QUAC and FLAASH have been applied on the hyperspectral remote sensing imagery.The spectra of vegetation,man-made structure and different minerals from the Gadag area of Karnataka,were extracted from the raw image and also from the QUAC and FLAASH corrected images.These spectra were compared among themselves and also with the existing USGS and JHU spectral library.FLAASH is rigorous atmospheric algorithm and requires various parameters to perform but it has capability to compensate the effects of atmospheric absorption.These absorption curves in any spectra play an important role in identification of the compositions.Therefore,the presence of unwanted absorption features can lead to wrong interpretation and identification of mineral composition.FLAASH also has an advantage of spectral polishing which provides smooth spectral curves which helps in accurate identification of composition of minerals.Therefore,this study recommends that FLAASH is better than QUAC for atmospheric correction and correct interpretation and identification of composition of any object or minerals.

Research on Estimation Models of Chlorophyll Content in Apple Leaves Based on Imaging Hyperspectral Data

In view of the shortage of using traditional methods to monitor chlorophyll content, hyperspectral technology was used to estimate the chlorophyll content of apple leaves rapidly, accurately and non-destructively. Based on the data of hyperspectral reflectivity and SPAD value of normal apple leaves and the leaves under the stress of red spiders collected from the Wanjishan base in Tai an, the correlations of SPAD value with the original spectral reflectivity of apple leaves and its first derivative and between SPAD value and high spectral value were analyzed to select sensitive bands, and the estimation models of chlorophyll content in apple leaves based on hyperspectral reflectivity were established. The sensitive bands of chlorophyll content in normal apple leaves were 513-539, 564-585, 694, 699 and 720 nm , and the best estimation model of chlorophyll content was SPAD =152.450-1 884.851 R 377 . The sensitive bands of chlorophyll content in the leaves under the stress of red spiders were 961, 972 and 720 nm, and the best estimation model of chlorophyll content was SPAD =49.371-46 428.473 R 972.

Feasibility of Estimating Heavy Metal Contaminations in Floodplain Soils Using Laboratory-Based Hyperspectral Data—A Case Study Along Le’an River, China

It is necessary to estimate heavy metal concentrations within soils for understanding heavy metal contaminations and for keeping the sustainable developments of ecosystems.This study,with the floodplain along Le'an River and its two branches in Jiangxi Province of China as a case study,aimed to explore the feasibility of estimating concentrations of heavy metal lead(Pb),copper(Cu) and zinc(Zn) within soils using laboratory-based hyperspectral data.Thirty soil samples were collected,and their hyperspectral data,soil organic matters and Pb,Cu and Zn concentrations were measured in the laboratory.The potential relations among hyperspectral data,soil organic matter and Pb,Cu and Zn concentrations were explored and further used to estimate Pb,Cu and Zn concentrations from hyperspectral data with soil organic matter as a bridge.The results showed that the ratio of the first-order derivatives of spectral absorbance at wavelengths 624 and 564 nm could explain 52% of the variation of soil organic matter;the soil organic matter could ex-plain 59%,51% and 50% of the variation of Pb,Cu and Zn concentrations with estimated standard errors of 1.41,48.27 and 45.15 mg·kg-1;and the absolute estimation errors were 8%-56%,12%-118% and 2%-22%,and 50%,67% and 100% of them were less than 25% for Pb,Cu and Zn concentration estimations.We concluded that the laboratory-based hyperspectral data hold potentials in esti-mating concentrations of heavy metal Pb,Cu and Zn in soils.More sampling points or other potential linear and non-linear regression methods should be used for improving the stabilities and accuracies of the estimation models.

Spectral-spatial target detection based on data field modeling for hyperspectral data

Target detection is always an important application in hyperspectral image processing field. In this paper, a spectral-spatial target detection algorithm for hyperspectral data is proposed.The spatial feature and spectral feature were unified based on the data filed theory and extracted by weighted manifold embedding. The novelties of the proposed method lie in two aspects. One is the way in which the spatial features and spectral features were fused as a new feature based on the data field theory, and the other is that local information was introduced to describe the decision boundary and explore the discriminative features for target detection. The extracted features based on data field modeling and manifold embedding techniques were considered for a target detection task.Three standard hyperspectral datasets were considered in the analysis. The effectiveness of the proposed target detection algorithm based on data field theory was proved by the higher detection rates with lower False Alarm Rates（FARs） with respect to those achieved by conventional hyperspectral target detectors.

Detection of scab in wheat ears using in situ hyperspectral data and support vector machine optimized by genetic algorithm

A new method was proposed to extract sensitive features and to construct a monitoring model for wheat scab based on in situ hyperspectral data of wheat ears to achieve effective prevention and control and provide theoretical support for its large-scale monitoring.Eight sensitive features were selected through correlation analysis and wavelet transform.These features were as follows:three original bands of 350-400 nm,500-600 nm,and 720-1000 nm;three vegetation indices of modified simple ratio(MSR),normalized difference vegetation index,and structural independent pigment index;and two wavelet features of WF01 and WF02.By combining the selected sensitive features with support vector machine(SVM)and SVM optimized by genetic algorithm(GASVM),a total of 16 monitoring models were built,and the monitoring accuracies of the two types of models were compared.The ability of the monitoring models built by GASVM to identify scab was better than that of SVM algorithm under the same characteristic variables.Among the 16 models,MSR combined with GASVM had an overall accuracy of 75%and a Kappa coefficient of 0.47.GASVM can be used to monitor wheat scab and its application can improve the accuracy of disease monitoring.

Kinetic models of peroxidase activity in potato leaves infected with late blight based on hyperspectral data

Potato late blight,which is caused by Phytophthorainfestans(Mont.)de Bary,is a worldwide devastating disease for potato.It decreased yields of potato and caused unpredictable losses all over the world.Various simple statistical methods and forecasting models have been developed to predict and manage potato late blight.Meanwhile,there is a rising need to develop prediction models reflecting peroxidase(POD)activity,which is an important health index that varies with infection and correlated with stress resistance in plants.Thus,the aim of this research was to develop kinetic models to predict POD activity.Infection-induced changes in potato leaves stored in an artificial climate chest at 25°C were analyzed using hyperspectroscopy.Four prediction models were developed by using linear partial least squares(PLS)and nonlinear support vector machine(SVM)methods based on the full spectrum and effective wavelengths.The effective wavelengths were selected by the successive projection algorithm(SPA).In this study,the prediction model developed by means of SPA-SVM method obtained the best performance,with a Rp(correlation coefficient of prediction)value of 0.923 and a RMSEp(root mean square error of prediction)value of 24.326.Five-order kinetics models according to the prediction model were developed,and late blight disease can be predicted using this model.This study provided a theoretical basis for the prediction of latencies of late blight.

Mining hyperspectral data for non-destructive and rapid prediction of nitrite content in ham sausages

Accurate and rapid determination of nitrite contents is an important step for guaranteeing sausage quality.This study attempted to mine hyperspectral data in the range of 900-1700 nm for non-destructive and rapid prediction of nitrite contents in sausages.The average spectra of 156 samples were collected to relate to the measured nitrite values by partial least squares(PLS)regression.Optimal wavelengths were respectively selected by successive projections algorithm(SPA)and regression coefficients(RC)to simplify the PLS model.The results indicated that PLS model established with 15 optimal wavelengths(900.5 nm,907.1 nm,908.8 nm,912.1 nm,915.4 nm,920.3 nm,922.0 nm,941.7 nm,979.6 nm,1083.2 nm,1213.2 nm,1353.0 nm,1460.2 nm,1595.6 nm and 1699.9 nm)selected by SPA had better performance with r C,r CV,r P of 0.92,0.89,0.89 and RMSEC,RMSECV,RMSEP of 0.41 mg/kg,0.89 mg/kg,0.49 mg/kg,respectively,for calibration set,cross-validation and prediction set.It was concluded that hyperspectral data could be mined by PLS&SPA for realizing the rapid evaluation of nitrite content in ham sausages.

Monitoring nitrogen concentration of oilseed rape from hyperspectral data using radial basis function

Remote sensing technology is the important tool of digital earth,it can facilitate nutrient management in sustainable cropping systems.In the study,two types of radial basis function(RBF)neural network approaches,the standard radial basis function(SRBF)neural networks and the modified type of RBF,generalized regression neural networks(GRNN),were investigated in estimating the nitrogen concentrations of oilseed rape canopy using vegetation indices(VIs)and hyperspectral reflectance.Comparison analyses were performed to the spectral variables and the approaches.The Root Mean Square Error(RMSE)and determination coefficients(R2)were used to assess their predictability of nitrogen concentrations.For all spectral variables(VIs and hyperspectral reflectance),the GRNN method produced more accurate estimates of nitrogen concentrations than did the SRBF method at all ranges of nitrogen concentrations,and the better agreements between the measured and the predicted nitrogen concentration were obtained with the GRNN method.This indicated that the GRNN method is prior to the SRBF method in estimation of nitrogen concentrations.Among the VIs,the Modified Chlorophyll Absorption in Reflectance Index(MCARI),MCARI1510,and Transformed Chlorophyll Absorption in Reflectance Index are better than the others in estimating oilseed rape canopy nitrogen concentrations.Compared to the results from VIs,the hyperspectral reflectance data also gave an acceptable estimation.The study showed that nitrogen concentrations of oilseed rape canopy could be monitored using remotely sensed data and the RBF method,especially the GRNN method,is a useful explorative tool for oilseed rape nitrogen concentration monitoring when applied on hyperspectral data.

Impact of spectral interval on wavelet features for detecting wheat yellow rust with hyperspectral data

Detection of yellow rust using hyperspectral data is of practical importance for disease control and prevention.As an emerging spectral analysis method,continuous wavelet analysis(CWA)has shown great potential for the detection of plant diseases and insects.Given the spectral interval of airborne or spaceborne hyperspectral sensor data differ greatly,it is important to understand the impact of spectral interval on the performance of CWA in detecting yellow rust in winter wheat.A field experiment was conducted which obtained spectral measurements of both healthy and disease-infected plants.The impacts of the mother wavelet type and spectral interval on disease detection were analyzed.The results showed that spectral features derived from all four mother wavelet types exhibited sufficient sensitivity to the occurrence of yellow rust.The Mexh wavelet slightly outperformed the others in estimating disease severity.Although the detecting accuracy generally declined with decreasing of spectral interval,relatively high accuracy levels were maintained(R^(2)>0.7)until a spectral interval of 16 nm.Therefore,it is recommended that the spectral interval of hyperspectral data should be no larger than 16 nm for the detection of yellow rust.The relatively loose spectral interval requirement permits extensive applications for disease detection with hyperspectral imagery.

3D-CNNHSR: A 3-Dimensional Convolutional Neural Network for Hyperspectral Super-Resolution

Hyperspectral images can easily discriminate different materials due to their fine spectral resolution.However,obtaining a hyperspectral image(HSI)with a high spatial resolution is still a challenge as we are limited by the high computing requirements.The spatial resolution of HSI can be enhanced by utilizing Deep Learning(DL)based Super-resolution(SR).A 3D-CNNHSR model is developed in the present investigation for 3D spatial super-resolution for HSI,without losing the spectral content.The 3DCNNHSR model was tested for the Hyperion HSI.The pre-processing of the HSI was done before applying the SR model so that the full advantage of hyperspectral data can be utilized with minimizing the errors.The key innovation of the present investigation is that it used 3D convolution as it simultaneously applies convolution in both the spatial and spectral dimensions and captures spatial-spectral features.By clustering contiguous spectral content together,a cube is formed and by convolving the cube with the 3D kernel a 3D convolution is realized.The 3D-CNNHSR model was compared with a 2D-CNN model,additionally,the assessment was based on higherresolution data from the Sentinel-2 satellite.Based on the evaluation metrics it was observed that the 3D-CNNHSR model yields better results for the SR of HSI with efficient computational speed,which is significantly less than previous studies.

Progress of Geological Survey Using Airborne Hyperspectral Remote Sensing Data in the Gansu and Qinghai Regions

Hyperspectral remote sensing is now a frontier of the remote sensing technology. Airborne hyperspectral remote sensing data have hundreds of narrow bands to obtain complete and continuous ground-object spectra. Therefore, they can be effectively used to identify these grotmd objects which are difficult to discriminate by using wide-band data, and show much promise in geological survey. At the height of 1500 m, have 36 bands in visible to the CASI hyperspectral data near-infrared spectral range, with a spectral resolution of 19 nm and a space resolution of 0.9 m. The SASI data have 101 bands in the shortwave infrared spectral range, with a spectral resolution of 15 nm and a space resolution of 2.25 m. In 2010, China Geological Survey deployed an airborne CASI/SASI hyperspectral measurement project, and selected the Liuyuan and Fangshankou areas in the Beishan metallogenic belt of Gansu Province, and the Nachitai area of East Kunlun metallogenic belt in Qinghai Province to conduct geological survey. The work period of this project was three years.

Hyperspectral estimation model of soil Pb content and its applicability in different soil types

In order to obtain Pb content in soil quickly and efficiently,a multivariate linear regression(MLR) and a principal component regression(PCR) Pb content estimation model were established on the basis of hyperspectral techniques,and their applicability in different soil types was evaluated.Results indicated that Pb exhibited strong spatial heterogeneity in the study area,and more than 82% of the samples exceeded the background value.In addition,the pollution range was large.Pb was sensitive in the nearinfrared band,and the correlation of absorbance(AB) was most significant of all the transformed forms.Both models achieved optimal stability and reliability when AB was used as an independent variable.Compared with the PCR model,the stability,fitting accuracy,and predictive power of the MLR model were superior with a coefficient of determination,root mean square error,and mean relative error of 0.724%,24.92%,and 28.22%,respectively.Both models could be applied to different soil types;however,MLR had better applicability compared with PCR.The PCR model that distinguished different soil types had better reliability than one that did not.Thus,the model established via hyperspectral techniques can achieve largearea,rapid,and efficient soil Pb content monitoring,which can provide technical support for the treatment of heavy metal pollution in soil.

Robust Deep 3D Convolutional Autoencoder for Hyperspectral Unmixing with Hypergraph Learning

Hyperspectral unmixing aims to acquire pure spectra of distinct substances(endmembers)and fractional abundances from highly mixed pixels.In this paper,a deep unmixing network framework is designed to deal with the noise disturbance.It contains two parts:a three⁃dimensional convolutional autoencoder(denoising 3D CAE)which recovers data from noised input,and a restrictive non⁃negative sparse autoencoder(NNSAE)which incorporates a hypergraph regularizer as well as a l2,1⁃norm sparsity constraint to improve the unmixing performance.The deep denoising 3D CAE network was constructed for noisy data retrieval,and had strong capacity of extracting the principle and robust local features in spatial and spectral domains efficiently by training with corrupted data.Furthermore,a part⁃based nonnegative sparse autoencoder with l2,1⁃norm penalty was concatenated,and a hypergraph regularizer was designed elaborately to represent similarity of neighboring pixels in spatial dimensions.Comparative experiments were conducted on synthetic and real⁃world data,which both demonstrate the effectiveness and robustness of the proposed network.

One-Dimensional Variational Retrieval of Temperature and Humidity Profiles from the FY4A GIIRS

A physical retrieval approach based on the one-dimensional variational(1 D-Var) algorithm is applied in this paper to simultaneously retrieve atmospheric temperature and humidity profiles under both clear-sky and partly cloudy conditions from FY-4 A GIIRS(geostationary interferometric infrared sounder) observations. Radiosonde observations from upper-air stations in China and level-2 operational products from the Chinese National Satellite Meteorological Center(NSMC)during the periods from December 2019 to January 2020(winter) and from July 2020 to August 2020(summer) are used to validate the accuracies of the retrieved temperature and humidity profiles. Comparing the 1 D-Var-retrieved profiles to radiosonde data, the accuracy of the temperature retrievals at each vertical level of the troposphere is characterized by a root mean square error(RMSE) within 2 K, except for at the bottom level of the atmosphere under clear conditions. The RMSE increases slightly for the higher atmospheric layers, owing to the lack of temperature sounding channels there.Under partly cloudy conditions, the temperature at each vertical level can be obtained, while the level-2 operational products obtain values only at altitudes above the cloud top. In addition, the accuracy of the retrieved temperature profiles is greatly improved compared with the accuracies of the operational products. For the humidity retrievals, the mean RMSEs in the troposphere in winter and summer are both within 2 g kg^(–1). Moreover, the retrievals performed better compared with the ERA5 reanalysis data between 800 h Pa and 300 h Pa both in summer and winter in terms of RMSE.

Multi-Class Support Vector Machine Classifier Based on Jeffries-Matusita Distance and Directed Acyclic Graph

Based on the framework of support vector machines( SVM) using one-against-one( OAO) strategy, a new multi-class kernel method based on directed acyclic graph( DAG) and probabilistic distance is proposed to raise the multi-class classification accuracies. The topology structure of DAG is constructed by rearranging the nodes' sequence in the graph. DAG is equivalent to guided operating SVM on a list,and the classification performance depends on the nodes' sequence in the graph. Jeffries-Matusita distance( JMD) is introduced to estimate the separability of each class,and the implementation list is initialized with all classes organized according to certain sequence in the list. To testify the effectiveness of the proposed method,numerical analysis is conducted on UCI data and hyperspectral data. Meanwhile,comparative studies using standard OAO and DAG classification methods are also conducted and the results illustrate better performance and higher accuracy of the proposed JMD-DAG method.

A new approach based on orthogonal bases of data space to decomposition of mixed pixels for hyperspectral imagery

A new algorithm for decomposition of mixed pixels based on orthogonal bases of data space is proposed in this paper. It is a simplex-based method which extracts endmembers sequentially using computations of largest simplex volumes. At each searching step of this extraction algorithm, searching for the simplex with the largest volume is equivalent to searching for a new orthogonal basis which has the largest norm. The new endmember corresponds to the new basis with the largest norm. This algorithm runs very fast and can also avoid the dilemma in traditional simplex-based endmember extraction algorithms, such as N-FINDR, that it generally produces different sets of final endmembers if different initial conditions are used. Moreover, with this set of orthogonal bases, the proposed algorithm can also determine the proper number of endmembers and finish the unmixing of the original images which the traditional simplex-based algorithms cannot do by themselves. Experimental results of both artificial simulated images and practical remote sensing images demonstrate the algorithm proposed in this paper is a fast and accurate algorithm for the decomposition of mixed pixels.