Hyperion Hyperspectral Image Research Articles

Graph Convolutional Network Using Adaptive Neighborhood Laplacian Matrix for Hyperspectral Images with Application to Rice Seed Image Classification

Graph convolutional neural network architectures combine feature extraction and convolutional layers for hyperspectral image classification. An adaptive neighborhood aggregation method based on statistical variance integrating the spatial information along with the spectral signature of the pixels is proposed for improving graph convolutional network classification of hyperspectral images. The spatial-spectral information is integrated into the adjacency matrix and processed by a single-layer graph convolutional network. The algorithm employs an adaptive neighborhood selection criteria conditioned by the class it belongs to. Compared to fixed window-based feature extraction, this method proves effective in capturing the spectral and spatial features with variable pixel neighborhood sizes. The experimental results from the Indian Pines, Houston University, and Botswana Hyperion hyperspectral image datasets show that the proposed AN-GCN can significantly improve classification accuracy. For example, the overall accuracy for Houston University data increases from 81.71% (MiniGCN) to 97.88% (AN-GCN). Furthermore, the AN-GCN can classify hyperspectral images of rice seeds exposed to high day and night temperatures, proving its efficacy in discriminating the seeds under increased ambient temperature treatments.

Differentiating grazing-induced rangeland grass nutrition status in situ using near infrared reflectance

Assessing the nutrient content of rangeland grass using earth observation technologies presents opportunities for non-destructive, rapid and repetitive appraisals in support of rangeland management. The biochemical-related concentrations of macronutrients (N, P, K, Ca, Mg) are among the factors that influence near infrared reflectance (ρNIR) by a turgid leaf. High grazing intensity (GI) enhances nutrient recycling in rangelands, resulting in high concentrations in aboveground grass tissue. This study sought to establish whether grazing-induced macronutrient abundance in rangeland grass can be remotely sensed in situ through ρNIR in the multiple species natural settings. Sampling was conducted at peak grass growth stage in large savannah rangelands with similar grass species mixtures, in low moisture stress conditions. The sampling was widely distributed in GI-contrasted livestock and wild grazer rangelands, and in grazing-restricted control sites. Two species representing high and low nutrient grass species, respectively, were sampled. At each sampling site (N = 116), reflectance was measured in the 350–2500 nm range from leaf and stem tissue of healthy-looking specimens of the two species (≤10 m apart), using a 1.1 nm – 1.4 nm resolution spectroradiometer. Macronutrient concentrations (MNC) in the tissue were then determined in the laboratory. For each species, the hyperspectral NIR (λ700 – 1100 nm) reflectance was averaged per sampling site. Individual and total MNC, respectively, were correlated with the hyperspectral ρNIR, and then with atmospheric effect-corrected ρNIR from 10 m-resolution, field sampling-concurrent Sentinel-2 MSI multispectral images. For each sampling site, the two species’ hyperspectral ρNIR values, individual and total MNC, respectively, were then averaged. Respective models relating the paired hyperspectral ρNIR and averaged MNC were developed, by linear regression and partial least squares regression (PLSR). Tissue MNC were lowest in the control sites and higher in the grazed rangelands. Covariance in MNC in the two species suggested location-context similarities in all grasses. Individual and total MNC, respectively, had statistically significant (p < 0.01) negative correlations with both tissue level hyperspectral and multispectral ρNIR. The negative relationship was detected on empirical line-retrieved ρNIR on historical Hyperion hyperspectral images. PLSR yielded a more accurate predictive model (R2 = 0.760) than linear regression (R2 = 0.601, F = 138.415, p < 0.0001). The study shows that there are possibilities to remotely sense grazing-induced MNC in aboveground grass tissue through changes in ρNIR.

Remote Sensing Survey of Altiplano-Puna Volcanic Complex Rocks and Minerals for Planetary Analog Use

The Altiplano-Puna Volcanic Complex (APVC) of the Central Andes is an arid region with extensive volcanism, possessing various geological features comparable to those of other solar system objects. The unique features of the APVC, e.g., hydrothermal fields and evaporite salars, have been used as planetary analogs before, but the complexity of the APVC presents a wealth of opportunities for more analog studies that have not been exploited previously. Motivated by the potential of using the APVC as an analog of the volcanic terrains of solar system objects, we mapped the mineralogy and silica content of the APVC up to ~100,000 km2 in northern Chile based on a combination of remote sensing data resembling those of the Moon and Mars. The band ratio indices of Landsat 8 Operational Land Imager multispectral images and mineral classifications based on spectral hourglass approach using Earth Observing-1 Hyperion hyperspectral images (both in the visible to shortwave infrared wavelengths) were used to map iron-bearing and alteration minerals. We also used Hyperion imagery to detect feldspar spectral signatures and demonstrated that feldspar minerals can be detected on non-anorthosites, which may influence interpretations of feldspar spectral signatures on Mars. From the Terra Advanced Spaceborne Thermal Emission and Reflection Radiometer Global Emissivity Dataset, we derived the silica percentage of non-evaporite rocks within errors of approximately 2–3 wt.% SiO2 for those in the 60–70 wt.% range (about 8 wt.% errors for the 50–60 wt.% range). Based on an integrated assessment of the three datasets, we highlighted three regions of particular interest worthy of further field investigation. We also evaluated the benefits and limitations of all three remote sensing methods for mapping key minerals and capturing rock diversity, based on available samples and existing geological maps.

Lithological mapping using EO-1 Hyperion hyperspectral data and semisupervised self-learning method

Hyperspectral remote sensing data have been widely used in lithological identification and mapping. In existing studies, sufficient training samples are required. However, collecting sufficient labeled training samples for lithological classification in remote and inaccessible areas is generally time consuming, expensive, and even hard to implement, which causes the insufficient training sample problems in lithological classification using hyperspectral data. The semisupervised self-learning (SSL) method provides an alternative way of addressing this ill-posed problem by enlarging the training set from unlabeled samples using the limited labeled samples as a priori. This study evaluates and analyzes the SSL method in lithological mapping using EO-1 Hyperion hyperspectral image over a remote area. The performance of SSL with limited training samples was validated by comparing with multinomial logistic regression (MLR) and random forest (RF) classification using full training samples. The experimental results indicate that SSL method with limited training samples can produce results comparable with the MLR with all the training samples and better results than those of the RF with all the training samples. Therefore, the SSL method provides a useful way for hyperspectral lithological mapping with limited training samples over remote and inaccessible areas.

A new method to detect targets in hyperspectral images based on principal component analysis

Target detection (TD) is a major task in hyperspectral image (HSI) processing which, due to the high spectral resolution, requires dealing with the curse of dimensionality. The integrated feature extraction and selection is a well-known solution for dimensionality reduction of HSIs. In this study, a new method is presented to improve the performance of TD algorithms based on principal component analysis (PCA) feature space. In this method, using the implantation of the target spectrum (TS) in the HSI and following the simulated targets in the PCA feature space, the best principal components (PCs) are selected. Then, using the mixing and unmixing coefficients of the PCs, a new TS and a new image in the PCA feature space are created. Afterwards, using the new spectrum of the target, the TD algorithm is run on the new HSI. The performance of the proposed method is compared to nine counterpart algorithms on Hymap and Hyperion HSI. All the comparisons are performed using adaptive coherence estimator (ACE) TD algorithm. Experimental results illustrate that the proposed method, compared to its counterparts, yields superior performance based on the false alarm rate (FAR) measure. It gives an average FAR value of about 16, which is approximately 9% better than that of its best counterparts.

Spectral similarity algorithm-based image classification for oil spill mapping of hyperspectral datasets

In remote sensing, the compositional information of part of the earth’s surface is statistically evaluated by comparing known field or library spectra with the unknown image spectra, known as spectral matching or spectral similarity analysis. In this research, hybrid spectral similarity algorithms developed based on chi-square distance (CHI or χ2) are used to retrieve useful information from the Hyperion hyperspectral oil spill image covering the area near Liaodong Bay of the Bohai Sea, China. In order to evaluate the discriminability of spectral similarity algorithms, a pixel-level matching is carried out between the reference vectors, viz. Oil Slick (O), Sheen (H), Sea Water (S) and Ship Track (T), collected visually from known areas in the image. The hybrid spectral similarity algorithms are statistically assessed for their performance using the spectral discriminatory measures (i) relative spectral discriminatory power (RSDPW), (ii) relative spectral discriminatory probability (RSDPB) and (iii) relative spectral discriminatory entropy (RSDE). Additionally, the selected hybrid algorithms are used on the Hyperion image subset to perform a pixel-based classification. Classification results revealed that the CHI-based hybrid algorithms performed better than all other hybrid spectral similarity methods. Therefore, the CHI-based hybrid algorithms demonstrated their superior spectral discrimination capacity to classify marine spectral classes for oil spill mapping from the hyperspectral dataset.

Satellite imagery and spectral matching for improved estimation of calcium carbonate and iron oxide abundance in mine areas

This study attempts grade-wise mapping in a limestone mine in Ariyalur, Southern India, and in the iron ore mines of Noamundi, Eastern India. After noise removal in the Sentinel 2A (multispectral) and EO-1 Hyperion (hyperspectral) image datasets, spectral matching is performed using the Jeffries-Matusita (JM) distance, Spectral Correlation Mapper (SCM), and combined JM-SCM measure. Due to the specific absorption spectra for carbonates (1900 nm, 2000 nm, and 2160 nm) and iron oxide (865 nm), it is possible to identify and map such mineral deposits using the multispectral dataset (Sentinel 2A) and hyperspectral dataset (EO-1 Hyperion) respectively. The grade-wise mapping of carbonate in the Ariyalur mine using the Sentinel 2A dataset by the Jeffries-Matusita (JM) approach and Spectral Correlation Mapper (SCM) yielded R2 values of 0.44 and 0.77 respectively, whereas the combined JM-SCM approach resulted in a higher correlation with an R2 value of 0.87. The grade-wise mapping of iron oxide in Noamundi using the EO-1 Hyperion dataset by the Jeffries-Matusita (JM) approach and the Spectral Correlation Mapper (SCM) approach yielded R2 values of 0.15 and 0.76, respectively, whereas the combined JM-SCM approach resulted in a higher correlation with an R2 value of 0.90. Such an improved performance of the combined approach is primarily due to the simultaneous and effective utilization of band-wise information (by JM) and correlation aspects (by SCM) of the reference and target spectra considered in the matching algorithm. Thus, in this study, the proposed algorithm proved its compatibility and utility in extracting information on mineral abundance distribution for mine areas.

Supervised learning with convolutional neural networks for hyperspectral visualization

ABSTRACTThe Visualization for hyperspectral images is demanded by the ground processing system for quick view and information survey. Previous methods using band selection or dimension reduction fail to produce stable details and good colours as reasonable as corresponding multispectral images. In this paper, a mixed strategy is proposed which utilizes multi-band selection and supervised learning to integrate natural spatial details within hyperspectral bands for visualization. In the training stage, multispectral images are introduced as the reference, which are targeted by convolutional neural networks modelling the conversion from hyperspectral bands to multispectral bands. In order to preserve the colour, the hyperspectral band numbers are recorded for those with high correlation to the reference images, which are put into the network for dimension reduction. The proposed method is tested for the EO-1 Hyperion hyperspectral images with LandSat-8 images as the benchmark. The results are compared with five state-of-the-art algorithms. The comparison results show that the present method has good performance in maintaining both structures and colours.

Noise Removal from Remote Sensed Images by NonLocal Means with OpenCL Algorithm

We introduce a multi-platform portable implementation of the NonLocal Means methodology aimed at noise removal from remotely sensed images. It is particularly suited for hyperspectral sensors for which real-time applications are not possible with only CPU based algorithms. In the last decades computational devices have usually been a compound of cross-vendor sets of specifications (heterogeneous system architecture) that bring together integrated central processing (CPUs) and graphics processor (GPUs) units. However, the lack of standardization resulted in most implementations being too specific to a given architecture, eliminating (or making extremely difficult) code re-usability across different platforms. In order to address this issue, we implement a multi option NonLocal Means algorithm developed using the Open Computing Language (OpenCL) applied to Hyperion hyperspectral images. Experimental results demonstrate the dramatic speed-up reached by the algorithm on GPU with respect to conventional serial algorithms on CPU and portability across different platforms. This makes accurate real time denoising of hyperspectral images feasible.

Remote Sensing Applied to the Extraction of Road Geometric Features Based on Optimum Path Forest Classifiers, Northeastern Brazil

One of the principal difficulties related to road safety management in Brazil is the lack of data on road projects, especially those on rural roads, which makes it difficult to use road safety studies and models from other countries as a reference. Updating road networks through the use of hyperspectral remote sensing images can be a good alternative. However, accurately recognizing and extracting hyperspectral images from roads has been recognized as a challenging task in the processing of hyperspectral data. In order to solve the aforementioned challenges, Hyperion hyperspectral images were combined with the Optimum Forest Path (OPF) algorithm for supervised classification of rural roads and the effectiveness of the OPF and SVM classifiers when applied to these areas was compared. Both classifiers produced reasonable results, however, the OPF algorithm outperformed SVM. The higher classification accuracy obtained by the OPF was mainly attributed to the ability to better distinguish between regions of exposed soil and unpaved roads.

GLAM Bio-Lith RT: A Tool for Remote Sensing Reflectance Simulation and Water Components Concentration Retrieval in Glacial Lakes

A new open--source software tool, called GLAM BioLith--RT (Glacier Lakes Assisted Melting Biological Lithological Radiative Transfer), has been developed for modeling of Radiative Transfer (RT) in water bodies containing suspended lithic particles , phytoplankton, dissolved salts, and colored dissolved organic matter. Although our objective is an application to glacial lakes of High Mountain Asia, the model has potential application for the study of seawater, organic-rich lakes, rivers, etc. The tool is built on a solid foundation of an existing published open-source code called WASI, which has been reviewed and augmented with new capabilities, notably the addition of a suspended lithic particle grain size parameterization. GLAM BioLith-RT operates in both a forward modeling and inverse modeling mode. The forward mode is specifically designed to compute the reflectance spectra of glacier lakes from inherent optical water properties. Conversely, in the inverse mode, measured spectral reflectance is employed with other inputs to derive best fitting water component properties (e.g., suspended particles concentration). The inverse modeling includes Bayesian Optimization of the output which is a significant advance over the existing software. We have tested the code for sensitivity to noise, and uncertainties in input parameters. The model succeeds in nearly reproducing the hyperspectral reflectance of some glacial lakes in Nepal as observed by the EO-1 Hyperion hyperspectral imager. The inverse modeling approach, when supported up by validated forward modeling, offers a means for remote sensing characterization of suspended sediment load in glacial lakes and rivers and hence, use of suspended sediment as a proxy for glacial activity; and many other potential applications in other thematic areas.

Reconstructing Cloud Contaminated Pixels Using Spatiotemporal Covariance Functions and Multitemporal Hyperspectral Imagery

One of the major challenges in optical-based remote sensing is the presence of clouds, which imposes a hard constraint on the use of multispectral or hyperspectral satellite imagery for earth observation. While some studies have used interpolation models to remove cloud affected data, relatively few aim at restoration via the use of multi-temporal reference images. This paper proposes not only the use of image time-series, but also the implementation of a geostatistical model that considers the spatiotemporal correlation between them to fill the cloud-related gaps. Using Hyperion hyperspectral images, we demonstrate a capacity to reconstruct cloud-affected pixels and predict their underlying surface reflectance values. To do this, cloudy pixels were masked and a parametric family of non-separable covariance functions was automated fitted, using a composite likelihood estimator. A subset of cloud-free pixels per scene was used to perform a kriging interpolation and to predict the spectral reflectance per each cloud-affected pixel. The approach was evaluated using a benchmark dataset of cloud-free pixels, with a synthetic cloud superimposed upon these data. An overall root mean square error (RMSE) of between 0.5% and 16% of the reflectance was achieved, representing a relative root mean square error (rRMSE) of between 0.2% and 7.5%. The spectral similarity between the predicted and reference reflectance signatures was described by a mean spectral angle (MSA) of between 1° and 11°, demonstrating the spatial and spectral coherence of predictions. The approach provides an efficient spatiotemporal interpolation framework for cloud removal, gap-filling, and denoising in remotely sensed datasets.

Accuracies Achieved in Classifying Five Leading World Crop Types and their Growth Stages Using Optimal Earth Observing-1 Hyperion Hyperspectral Narrowbands on Google Earth Engine

As the global population increases, we face increasing demand for food and nutrition. Remote sensing can help monitor food availability to assess global food security rapidly and accurately enough to inform decision-making. However, advances in remote sensing technology are still often limited to multispectral broadband sensors. Although these sensors have many applications, they can be limited in studying agricultural crop characteristics such as differentiating crop types and their growth stages with a high degree of accuracy and detail. In contrast, hyperspectral data contain continuous narrowbands that provide data in terms of spectral signatures rather than a few data points along the spectrum, and hence can help advance the study of crop characteristics. To better understand and advance this idea, we conducted a detailed study of five leading world crops (corn, soybean, winter wheat, rice, and cotton) that occupy 75% and 54% of principal crop areas in the United States and the world respectively. The study was conducted in seven agroecological zones of the United States using 99 Earth Observing-1 (EO-1) Hyperion hyperspectral images from 2008–2015 at 30 m resolution. The authors first developed a first-of-its-kind comprehensive Hyperion-derived Hyperspectral Imaging Spectral Library of Agricultural crops (HISA) of these crops in the US based on USDA Cropland Data Layer (CDL) reference data. Principal Component Analysis was used to eliminate redundant bands by using factor loadings to determine which bands most influenced the first few principal components. This resulted in the establishment of 30 optimal hyperspectral narrowbands (OHNBs) for the study of agricultural crops. The rest of the 242 Hyperion HNBs were redundant, uncalibrated, or noisy. Crop types and crop growth stages were classified using linear discriminant analysis (LDA) and support vector machines (SVM) in the Google Earth Engine cloud computing platform using the 30 optimal HNBs (OHNBs). The best overall accuracies were between 75% to 95% in classifying crop types and their growth stages, which were achieved using 15–20 HNBs in the majority of cases. However, in complex cases (e.g., 4 or more crops in a Hyperion image) 25–30 HNBs were required to achieve optimal accuracies. Beyond 25–30 bands, accuracies asymptote. This research makes a significant contribution towards understanding modeling, mapping, and monitoring agricultural crops using data from upcoming hyperspectral satellites, such as NASA’s Surface Biology and Geology mission (formerly HyspIRI mission) and the recently launched HysIS (Indian Hyperspectral Imaging Satellite, 55 bands over 400–950 nm in VNIR and 165 bands over 900–2500 nm in SWIR), and contributions in advancing the building of a novel, first-of-its-kind global hyperspectral imaging spectral-library of agricultural crops (GHISA: www.usgs.gov/WGSC/GHISA).

A New Low-Rank Representation Based Hyperspectral Image Denoising Method for Mineral Mapping

Hyperspectral imaging technology has been used for geological analysis for many years wherein mineral mapping is the dominant application for hyperspectral images (HSIs). The very high spectral resolution of HSIs enables the identification and the diagnosis of different minerals with detection accuracy far beyond that offered by multispectral images. However, HSIs are inevitably corrupted by noise during acquisition and transmission processes. The presence of noise may significantly degrade the quality of the extracted mineral information. In order to improve the accuracy of mineral mapping, denoising is a crucial pre-processing task. By leveraging on low-rank and self-similarity properties of HSIs, this paper proposes a state-of-the-art HSI denoising algorithm that implements two main steps: (1) signal subspace learning via fine-tuned Robust Principle Component Analysis (RPCA); and (2) denoising the images associated with the representation coefficients, with respect to an orthogonal subspace basis, using BM3D, a self-similarity based state-of-the-art denoising algorithm. Accordingly, the proposed algorithm is named Hyperspectral Denoising via Robust principle component analysis and Self-similarity (HyDRoS), which can be considered as a supervised version of FastHyDe. The effectiveness of HyDRoS is evaluated in a series of mineral mapping experiments using noise-reduced AVIRIS and Hyperion HSIs. In these experiments, the proposed denoiser yielded systematically state-of-the-art performance.

Using a Feature Subset Selection method and Support Vector Machine to address curse of dimensionality and redundancy in Hyperion hyperspectral data classification

The curse of dimensionality resulted from insufficient training samples and redundancy is considered as an important problem in the supervised classification of hyperspectral data. This problem can be handled by Feature Subset Selection (FSS) methods and Support Vector Machine (SVM). The FSS methods can manage the redundancy by removing redundant spectral bands. Moreover, kernel based methods, especially SVM have a high ability to classify limited-sample data sets. This paper mainly aims to assess the capability of a FSS method and the SVM in curse of dimensional circumstances and to compare results with the Artificial Neural Network (ANN), when they are used to classify alteration zones of the Hyperion hyperspectral image acquired from the greatest Iranian porphyry copper complex. The results demonstrated that by decreasing training samples, the accuracy of SVM was just decreased 1.8% while the accuracy of ANN was highly reduced i.e. 14.01%. In addition, a hybrid FSS was applied to reduce the dimension of Hyperion. Accordingly, among the 165 useable spectral bands of Hyperion, 18 bands were only selected as the most important and informative bands. Although this dimensionality reduction could not intensively improve the performance of SVM, ANN revealed a significant improvement in the computational time and a slightly enhancement in the average accuracy. Therefore, SVM as a low-sensitive method respect to the size of training data set and feature space can be applied to classify the curse of dimensional problems. Also, the FSS methods can improve the performance of non-kernel based classifiers by eliminating redundant features.

Mangrove above-ground carbon stock mapping of multi-resolution passive remote-sensing systems

ABSTRACTThis research address several issues related to mangrove above-ground carbon stock (AGC) mapping using the integration of remote-sensing images and field data. These issues are (1) remote-sensing image availability for specific mangrove AGC mapping scale and precision, (2) the impact on mangrove AGC modelling due to the difference between images spatial resolution and plot size of field mangrove AGC measurement, which follow the standardized procedure and not specially developed to be integrated with remote-sensing data, and (3) the accuracy of performing mangrove AGC mapping using image at different spatial resolutions using similar field size mangrove AGC data. Four multispectral data sets, namely Worldview-2, Advanced Land Observation System Advanced Visible and Near-Infrared Radiometer-2 (ALOS AVNIR-2), Advanced Spectral and Thermal Radiometer (ASTER) Visible Near-Infrared (VNIR) and Landsat 8 Operational Land Imager (OLI), and a Hyperion hyperspectral image were tested for their performance for mangrove AGC mapping. These images represent various spatial, spectral, and radiometric resolutions of remote-sensing data available to date. The mapping was performed using their original spatial resolution, and for Worldview-2 the mapping was also conducted using 10 m spatial resolution. Image radiometric corrections, vegetation indices, principal component analysis and minimum noise fraction were applied to each image. These were used as input in the empirical modelling of mangrove AGC. The results indicate that (1) it is not possible to perform empirical modelling of mangrove AGC using image with sub-canopy spatial resolution, (2) decreasing the spatial resolution may be beneficial to obtaining a significant correlation with mangrove AGC, and (3) it is possible to perform empirical modelling of mangrove AGC mapping using field data not specially intended to be integrated with remote-sensing data, along with some adjustments. This opens up the possibility of utilizing the available field mangrove AGC data collected by stakeholders, that is, government institutions, NGOs, academics, private sector, to assist mangrove AGC mapping across the nation.

Mapping evaporite minerals and associated sediments in Lake Magadi, Kenya, using Hyperspectral Hyperion data

Hyperion hyperspectral (VNIR-SWIR) satellite image data was used to map the spatial distribution of mineral precipitates at Lake Magadi area, in the southernmost part of the eastern Kenya rift, Kenya. Mapping was coupled with laboratory analysis, including visible near infrared diffuse reflectance spectroscopy (VNIR) measurements and X-ray diffraction for selected rock and soil samples. The VNIR spectral responses of 92 rock and soil samples including trona, chert, diatomite, basalt/trachyte, erionite, Green bed and High Magadi bed were studied and identified. The spectral signatures of Chert samples show the broad Si-OH absorption feature at 2.2 μm while, Green bed, High Magadi bed and diatomite exhibit carbonate absorption feature at 2.35 μm with broad Si-OH absorption feature at 2.2 μm. Trona exhibits six common absorption features at 1.50, 1.74, 1.94, 2.03, 2.22 and 2.39 μm. These characteristics spectral absorption features together with the general shape of the spectral curve are used to identify the surface minerals of the area. In the mapping of different stages of evaporites and other surface minerals using Hyperion data, various image processing techniques including, the Minimum Noise Fraction (MNF), Pixel Purity Index (PPI) and Mixture Tuned Matched Filtering (MTMF) were applied. These spectral mapping methods coupled with geochemical knowledge of the area substantially improved the existing geological knowledge and enhanced the capability to derive substantial information related to the distribution and formation of precipitates and evaporites in the area.

Evaluating EO1-Hyperion capability for mapping conifer and broadleaved forests

The objective of the present study is the comparison of the combined use of Earth Observation-1 (EO-1) Hyperion Hyperspectral images with the Random Forest (RF), Support Vector Machines (SVM) and Multivariate Adaptive Regression Splines (MARS) classifiers for discriminating forest cover groups, namely broadleaved and coniferous forests. Statistics derived from classification confusion matrix were used to assess the accuracy of the derived thematic maps. We demonstrated that Hyperion data can be effectively used to obtain rapid and accurate large-scale mapping of main forest types (conifers-broadleaved). We also verified higher capability of Hyperion imagery with respect to Landsat data to such an end. Results demonstrate the ability of the three tested classification methods, with small improvements given by SVM in terms of overall accuracy and kappa statistic.

LAND COVER CHANGE DETECTION BASED ON GENETICALLY FEATURE AELECTION AND IMAGE ALGEBRA USING HYPERION HYPERSPECTRAL IMAGERY

Abstract. The Earth has always been under the influence of population growth and human activities. This process causes the changes in land use. Thus, for optimal management of the use of resources, it is necessary to be aware of these changes. Satellite remote sensing has several advantages for monitoring land use/cover resources, especially for large geographic areas. Change detection and attribution of cultivation area over time present additional challenges for correctly analyzing remote sensing imagery. In this regards, for better identifying change in multi temporal images we use hyperspectral images. Hyperspectral images due to high spectral resolution created special placed in many of field. Nevertheless, selecting suitable and adequate features/bands from this data is crucial for any analysis and especially for the change detection algorithms. This research aims to automatically feature selection for detect land use changes are introduced. In this study, the optimal band images using hyperspectral sensor using Hyperion hyperspectral images by using genetic algorithms and Ratio bands, we select the optimal band. In addition, the results reveal the superiority of the implemented method to extract change map with overall accuracy by a margin of nearly 79% using multi temporal hyperspectral imagery.

Solar-induced fluorescence of terrestrial chlorophyll derived from the O2-A band of Hyperion hyperspectral images

Satellite-based detection of solar-induced chlorophyll fluorescence, an important remote sensing tool for the assessment of plant physiology and environmental monitoring, is growing popular nowadays. The present work proposes a methodology for the estimation of chlorophyll fluorescence from the existing hyperspectral images acquired by the Hyperion sensor on Earth Observing-1 satellite over the last decade. The principle is to compare the radiation ratio of the O2-A band to that of its adjacent bands for vegetated and non-vegetated regions of the same image. The process is demonstrated with three different images of different years and seasons, and the results are compared with earlier reported values. A simulation with leaf-level data affirms the capability of an instrument with Hyperion’s characteristics to detect chlorophyll fluorescence from O2-A band absorption.