Band Priority Index: A Feature Selection Framework for Hyperspectral Imagery

BSDR: A Data-Efficient Deep Learning-Based Hyperspectral Band Selection Algorithm Using Discrete Relaxation

Hyperspectral band selection algorithms are crucial for processing high-dimensional data, which enables dimensionality reduction, improves data analysis, and enhances computational efficiency. Among these, attention-based algorithms have gained prominence by ranking bands based on their discriminative capability. However, they require a large number of model parameters, which increases the need for extensive training data. To address this challenge, we propose Band Selection through Discrete Relaxation (BSDR), a novel deep learning-based algorithm. BSDR reduces the number of learnable parameters by focusing solely on the target bands, which are typically far fewer than the original bands, thus resulting in a data-efficient configuration that minimizes training data requirements and reduces training time. The algorithm employs discrete relaxation, transforming the discrete problem of band selection into a continuous optimization task, which enables gradient-based search across the spectral dimension. Through extensive evaluations on three benchmark datasets with varying spectral dimensions and characteristics, BSDR demonstrates superior performance for both regression and classification tasks, achieving up to 25% and 34.6% improvements in overall accuracy, compared to the latest attention-based and traditional algorithms, respectively, while reducing execution time by 96.8% and 97.18%. These findings highlight BSDR's effectiveness in addressing key challenges in hyperspectral band selection.

Geochemical and remote sensing integrated with satellite gravity data of Darhib and Atshan talc deposits, South Eastern Desert, Egypt

The current contribution conducted new geochemical, remote sensing integrated with gravity detailed studies of talc deposits to identify the talc protolith as well as its extension, depth, and structures. There are two examined areas, distributed from north to south, Atshan and Darhib and both belong to the southern sector of the Egyptian Eastern Desert. They occur as individual lenses or pocket bodies in ultramafic-metavolcanics following NNW-SSE and E-W shear zones. Geochemically, among the investigated talc, Atshan samples have high contents of SiO₂ (av. 60.73 wt.%), and higher concentrations of transition elements such as Co (av. 53.92 ppm), Cr (781 ppm), Ni (av. 1303.6 ppm), V (av. 16.67 ppm), and Zn (av. 55.7 ppm). Notably, the examined talc deposits contain low contents of CaO (av. 0.32 wt.%), TiO₂ (av. 0.04 wt.%), SiO₂/MgO (av. 2.15), and Al₂O₃ (av. 0.72 wt.%), which is comparable with ophiolitic peridotite and forearc setting. False color composite (FCC), principal component analysis (PCA), minimum noise fraction (MNF), and band ratio (BR) have been used to distinguish talc deposits in the investigated areas. Two new proposed band ratios were created to separate talc deposits. FCC band ratios (2/4, 4/7, 6/5) and (4 + 3/5, 5/7, 2 + 1/3) have been derived to focus on talc deposits in two case studies, Atshan and Darhib areas. The application of regional, residual, horizontal gradient (HG), and analytical signal (AS) techniques to gravity data are used in interpreting the structural directions of the study area. The analysis of this technique displays several notable faults trending in NW-SE, NE-SW, NNW-SSE, and E-W directions. Two techniques of gravity depth calculation were applied in the study areas, namely source parameter image (SPI), and Euler deconvolution (EU). The analysis of these techniques reflects that the depth of subsurface sources ranges between 383 and 3560 m. Talc deposits may be attributed to greenschist facies metamorphism or to a magmatic solution that is (associated with granitic intrusions) interacted with the surrounding volcanic rocks forming metasomatic minerals.

Classifying Crop Types Using Two Generations of Hyperspectral Sensors (Hyperion and DESIS) with Machine Learning on the Cloud

Advances in spaceborne hyperspectral (HS) remote sensing, cloud-computing, and machine learning can help measure, model, map and monitor agricultural crops to address global food and water security issues, such as by providing accurate estimates of crop area and yield to model agricultural productivity. Leveraging these advances, we used the Earth Observing-1 (EO-1) Hyperion historical archive and the new generation DLR Earth Sensing Imaging Spectrometer (DESIS) data to evaluate the performance of hyperspectral narrowbands in classifying major agricultural crops of the U.S. with machine learning (ML) on Google Earth Engine (GEE). EO-1 Hyperion images from the 2010–2013 growing seasons and DESIS images from the 2019 growing season were used to classify three world crops (corn, soybean, and winter wheat) along with other crops and non-crops near Ponca City, Oklahoma, USA. The supervised classification algorithms: Random Forest (RF), Support Vector Machine (SVM), and Naive Bayes (NB), and the unsupervised clustering algorithm WekaXMeans (WXM) were run using selected optimal Hyperion and DESIS HS narrowbands (HNBs). RF and SVM returned the highest overall producer’s, and user’s accuracies, with the performances of NB and WXM being substantially lower. The best accuracies were achieved with two or three images throughout the growing season, especially a combination of an earlier month (June or July) and a later month (August or September). The narrow 2.55 nm bandwidth of DESIS provided numerous spectral features along the 400–1000 nm spectral range relative to smoother Hyperion spectral signatures with 10 nm bandwidth in the 400–2500 nm spectral range. Out of 235 DESIS HNBs, 29 were deemed optimal for agricultural study. Advances in ML and cloud-computing can greatly facilitate HS data analysis, especially as more HS datasets, tools, and algorithms become available on the Cloud.

Low-Cost Multispectral System Design for Pigment Analysis in Works of Art

To better understand and preserve works of art, knowledge is needed about the pigments used to create the artwork. Various noninvasive techniques have been used previously to create pigment maps, such as combining X-ray fluorescence and hyperspectral imaging data. Unfortunately, most museums have limited funding for the expense of specialized research equipment, such as hyperspectral reflectance imaging systems. However, many museums have hand-held point X-ray fluorescence systems attached to motorized easels for scanning artwork. To assist museums in acquiring data that can produce similar results to that of HSI systems, while minimizing equipment costs, this study designed and modeled a prototype system to demonstrate the expected performance of a low-cost multispectral system that can be attached to existing motorized easels. We show that multispectral systems with a well-chosen set of spectral bands can often produce classification maps with value on par with hyperspectral systems. This study analyzed the potential for capturing data with a point scanning system through predefined filters. By applying the system and noise modeling parameters to HSI data captured from a 14th-Century illumination, the study reveals that the proposed multispectral imaging system is a viable option for this need.

Tensor Discriminant Analysis via Compact Feature Representation for Hyperspectral Images Dimensionality Reduction

Dimensionality reduction is of great importance which aims at reducing the spectral dimensionality while keeping the desirable intrinsic structure information of hyperspectral images. Tensor analysis which can retain both spatial and spectral information of hyperspectral images has caused more and more concern in the field of hyperspectral images processing. In general, a desirable low dimensionality feature representation should be discriminative and compact. To achieve this, a tensor discriminant analysis model via compact feature representation (TDA-CFR) was proposed in this paper. In TDA-CFR, the traditional linear discriminant analysis was extended to tensor space to make the resulting feature representation more informative and discriminative. Furthermore, TDA-CFR redefines the feature representation of each spectral band by employing the tensor low rank decomposition framework which leads to a more compact representation.

Selection of Optimal Hyperspectral Wavebands for Detection of Discolored, Diseased Rice Seeds

The inspection of rice grain that may be infected by seedborne disease is important for ensuring uniform plant stands in production fields as well as preventing proliferation of some seedborne diseases. The goal of this study was to use a hyperspectral imaging (HSI) technique to find optimal wavelengths and develop a model for detecting discolored, diseased rice seed infected by bacterial panicle blight (Burkholderia glumae), a seedborne pathogen. For this purpose, the HSI data spanning the visible/near-infrared wavelength region between 400 and 1000 nm were collected for 500 sound and discolored rice seeds. For selecting optimal wavelengths to use for detecting diseased seed, a sequential forward selection (SFS) method combined with various spectral pretreatments was employed. To evaluate performance based on optimal wavelengths, support vector machine (SVM) and linear and quadratic discriminant analysis (LDA and QDA) models were developed for detection of discolored seeds. As a result, the violet and red regions of the visible spectrum were selected as key wavelengths reflecting the characteristics of the discolored rice seeds. When using only two or only three selected wavelengths, all of the classification methods achieved high classification accuracies over 90% for both the calibration and validation sample sets. The results of the study showed that only two to three wavelengths are needed to differentiate between discolored, diseased and sound rice, instead of using the entire HSI wavelength regions. This demonstrates the feasibility of developing a low cost multispectral imaging technology based on these selected wavelengths for non-destructive and high-throughput screening of diseased rice seed.