Mineral Mapping on Hyperspectral Imageries Using Cohesion-based Self Merging Algorithm

ABSTRACTAnomaly detection is an active research topic in hyperspectral remote sensing and has been applied in many areas including environmental monitoring, urban survey, mineral mapping, and national security. Usually, it makes a detection decision without any prior target information or background information. Several anomaly detection algorithms (e.g. Reed–Xiaoli detector, blocked adaptive computationally efficient outlier nominator and random-selection-based anomaly detector) have been developed, which rely on estimating background information only from a hyperspectral image without considering target information in making a detection decision. These methods may be efficient in general but sometimes with high false alarm rate (FAR). In order to reduce FAR, this study proposes a novel method that incorporates both background and target information, derived from the hyperspectral imagery, into anomaly detection algorithms. The target information is helpful to detect anomalies as outliers. With a scene of real airborne visible infrared imaging spectrometer data, the experimental results demonstrate that the proposed method has produced better detection results and higher time efficiency compared with those using the traditional algorithms that only consider background information.

ABSTRACTHyperspectral images have acquired an increasing interest in the scientific and civil community to detect or classify materials by their spectral signature in remote sensing applications. However, spectral signatures can vary because of lighting or atmospheric conditions. This phenomenon is known as spectral variability, and ignoring this variability is an important source of error in the analysis of hyperspectral images. Therefore, this work focuses on analysing different causes and effects of the spectral variability in hyperspectral images, by studying the latest advances in this area, including approaches that do not address the phenomenon and methods that address spectral variability. Experiments are executed with five different approaches to compare their accuracy in the estimation of abundances in synthetic data generated with spectral variability. Specifically, a case study is developed on hyperspectral data of oil palm crops in Colombia, which exhibit high spectral variability. The results of identification of stressed oil palms are compared by mapping the abundances of three classes (diseased oil palm, healthy oil palm, and background), evaluating the performance of the different approaches in terms of the root mean squared error (RMSE), reconstruction error (RE), and spectral angle mapping (SAM). Results show that the coordinate descent algorithm-mismodelling effects (CDA-ME) present the best performance, outperforming in up to 70% the other approaches with and without spectral variability since it can jointly model changes of illumination, effects of variability and outlier values present in the hyperspectral images.

The advent of new hyperspectral has improved the rapid surface mapping of minerals and earth materials. This research is creating the mineral maps using HyMap in Tick Hill Mount Isa Northwest Queensland as a guide for the regolith landform unit mapping .Tick Hill area is part of the Proterozoic Eastern and Western Fold Belt Province of Mt.Isa Inlier C omplex . The areas were covered by Mesozoic and Paleozoic litholog ies dominated by medium to coarse hornblende-biotite granite and gneiss intruded during 1760 – 1720Ma. Highly weathered landform covered the whole area. The Mesozoic sediments have experienced to deep weathering currently present in the form of mesas. The weathering profiles are dominated by kaolinite, smectite, and pedogenic carbonates with some secondary silicification. Part of the landform was covered by colluvium which varied in thickness from less than 1 meter to up to 12 meter in certain places.The general image processing for HyMap has been done for the area. In addition, ASD spectra laboratory has been applied to validate the remotely sensed mineral information. Iron Oxide and Al-OH ( k aolinite, illite, smectite) mineral maps have been successfully created through HyMap imagery. Those can easily identified through the band ratio with some mask application (relative band depth method) in HyMap . For final process, GIS method is used to overlay all the data producing regolith landform unit map . AL-OH mainly kaolinite mineral map is showing the usefulness for identification the surface regolith mapping (mottle zone) and its crystallinity maps can differentiate transported and in situ regolith materials. In addition, Iron oxide map is able to identify ferruginous and laterite surface materials. K ey w ords : HyMap,Regolith,Mineral Mapping, TickHill,Mt.Isa

As a new multi-sensor satellite, GaoFen-5 (GF-5) has gradually attracted more attention. Especially, the GF-5 hyperspectral sensor has shown good prospects in geological applications, such as mineral mapping, geological body identification, and mining environment analysis. Therefore, there is an urgent need to evaluate the effectiveness of GF-5 hyperspectral data relative to airborne hyperspectral images (HSI) in geological applications. In this paper, the characteristics and preprocessing steps of GF-5 HSI were introduced. The HyMap data in the Subei area was employed for comparative experiments to evaluate the application performance of GF-5 in gossan identification. The experimental results show that the diagnostic spectral characteristics of limonite can be observed through GF-5 data. The distribution trends of limonite in both hyperspectral data are consistent, and the concentration of the limonite area directly indicated the gossan information, indicating that GF-5 HSI has promising potential for mineral mapping and may have important significance in large-scale geological applications.

The hyperspectral and multispectral image fusion process, commonly known as the multisharpening process (also known as the hypersharpening process), results in the creation of unobservable high spectral and spatial resolution hyperspectral remote sensing data, by combining (or fusing) a hyperspectral image, characterized by a high spectral resolution, with, especially, a high spatial resolution multispectral one. There are several approaches in the literature performing such a process, in particular, those based on the spectral unmixing concept. The latter fusion methods aim to extract pure-material spectra from the high spectral resolution hyperspectral image and combine them with their corresponding proportions extracted from the high spatial resolution multispectral image. However, most of these methods, which mainly consider the standard linear mixing model, do not address the spectral variability phenomenon, precisely due to the considered data mixing model, which does not handle variations in illumination and atmospheric conditions or material composition inducing spectral variability. Neglecting such a phenomenon may lead to errors in the fusion process, thus decreasing the spatial and spectral qualities of sharpened products. In this paper, a new hyperspectral and multispectral data fusion method, based on the linear spectral unmixing concept that deals with spectral variability, is proposed. This approach, based on a multiplicative Nonnegative Matrix Factorization (NMF) technique, substantially extends the multiplicative Coupled NMF (CNMF) algorithm by considering a linear data mixing model that addresses the considered phenomenon. Indeed, the introduced approach minimizes new cost functions involving matrices with specific structures in order to deal with the spectral variability phenomenon. The proposed method is applied to synthetic and real data, and its effectiveness is evaluated with established performance criteria. Experimental results show that the designed algorithm globally yields sharpened hyperspectral data with fine spectral and spatial fidelities. Also, these results demonstrate that the proposed technique globally outperforms the tested literature approaches.

We developed a new method for mineral mapping based on the continuum-removal Modified Spectral Angle Mapper (MSAM) method to distinguish minerals, such as calcite and chlorite, which have diagnostic spectral features in the visible near infrared (VNIR) and shortwave infrared (SWIR) regions. This method was applied to the reflectance data obtained by HyMap, a hyperspectral airborne sensor with 126 spectral bands (0.44–2.48 μm) in Cuprite, Nevada, USA. Reflectance spectra in the VNIR and SWIR regions are characterized by a convex background (continuum). Continuum-removal processing results in emphasis of the shape and location of absorption peaks in reflectance spectra, and thus in recognition of the chemical species which are causing the absorption spectrum. On the other hand, the broad features in continuum spectra contain essential information for mineral classification as well. Therefore, we produced mineral index maps from both the continuum and continuum-removed images based on the MSAM method and then combined them to generate a mineral distribution map. This composite MSAM method was applied to remotely sensed hyperspectral data for the first time. It was confirmed that our mineral index maps were consistent with the existing mineral maps. We can conclude that the composite MSAM method has a great advantage over our previously developed method in discrimination between calcite and chlorite, in particular.

Mapping the wavelength position of deepest absorption features to explore mineral diversity in hyperspectral images

Laboratory-based hyperspectral imaging (HSI) is an optical non-destructive technology used to extract mineralogical information from bedrock drill cores. In the present study, drill core scanning in the long-wave infrared (LWIR; 8000–12,000 nm) wavelength region was used to map the dominant minerals in HSI pixels. Machine learning classification algorithms, including random forest (RF) and support vector machine, have previously been applied to the mineral characterization of drill core hyperspectral data. The objectives of this study are to expand semi-automated mineral mapping by investigating the mapping accuracy, generalization potential, and classification ability of cutting-edge methods, such as various ensemble machine learning algorithms and deep learning semantic segmentation. In the present study, the mapping of quartz, talc, chlorite, and mixtures thereof in HSI data was performed using the ENVINet5 algorithm, which is based on the U-net deep learning network and four decision tree ensemble algorithms, including RF, gradient-boosting decision tree (GBDT), light gradient-boosting machine (LightGBM), AdaBoost, and bagging. Prior to training the classification models, endmember selection was employed using the Sequential Maximum Angle Convex Cone endmember extraction method to prepare the samples used in the model training and evaluation of the classification results. The results show that the GBDT and LightGBM classifiers outperformed the other classification models with overall accuracies of 89.43% and 89.22%, respectively. The results of the other classifiers showed overall accuracies of 87.32%, 87.33%, 82.74%, and 78.32% for RF, bagging, ENVINet5, and AdaBoost, respectively. Therefore, the findings of this study confirm that the ensemble machine learning algorithms are efficient tools to analyze drill core HSI data and map dominant minerals. Moreover, the implementation of deep learning methods for mineral mapping from HSI drill core data should be further explored and adjusted.

Wavelength feature mapping as a proxy to mineral chemistry for investigating geologic systems: An example from the Rodalquilar epithermal system

Surface water is an essential carrier for the balance of ecosystems and human existence. As applied hyperspectral remote sensing has improved, the research into water extraction from the hyperspectral image gradually attracted more attention. However, delineating water from the hyperspectral image is challenging due to shadows of buildings and trees, and other dark pixels. Furthermore, water indexes that come from multispectral imagery are directly applied to hyperspectral imagery leads to some defects, such as underutilized abundant information and higher misclassifications. Here, we proposed a decision tree water index (DTWI) method to extract water bodies from hyperspectral imagery. Combining the threshold of the near-infrared reflectance and the magnitude of the difference between reflectance of 700 and 730 nm, the DTWI method could effectively extract water from hyperspectral imagery. Three hyperspectral images derived from the study areas within the city, a mixture of city and suburban zone, and suburban zone only, were applied to test the feasibility and flexibility of this method in various sensors and environments. Four alternative methods were used to verify the robustness of the proposed method, including hyperspectral difference water index, normalized difference water index, shaded building index, and support vector machine (SVM). Our results indicated that the proposed method was better suited to extracting water bodies from hyperspectral imagery when compared with other methods and could effectively capture water on different hyperspectral sensors, various heterogeneous surroundings, and multi-spatial scales. The proposed DTWI method has high stability in threshold and band selection, which is comparable to the SVM method in the mean overall accuracy and kappa coefficient (DTWI: 0.98 and 0.81; SVM: 0.98 and 0.82). For the view of elapsed time, calculation, and applicability, the proposed method has the potential of better utilization and rapid response for water extraction in hyperspectral imagery.

Suaeda Salsa (S. salsa), a pioneer species with short and red-purplish plants in the intertidal zones, has significant ecological, economic, recreational and tourism values. Timely monitoring of S. salsa is crucial for understanding its dynamics and sustainable management of coastal wetlands. Hyperspectral satellite offers valuable opportunities due to its detailed spectral information. This study proposed a Suaeda Salsa Hyperspectral Index (SSHI) for S. salsa mapping based on hyperspectral satellite imagery. SSHI was developed by considering the large within-class spectral variations of cover types at coastal wetlands, accounting for the spectral correlations in hyperspectral data, and employing dynamic band selection on a per-pixel basis to optimize the separation of S. salsa from other land covers. SSHI = Sgn ρ 620 − max ρ i ∗ ρ 860 − min ρ j ρ 860 + ρ 620 + L ∗ 1 + L , where i∈[499 nm, 611 nm], j∈[628 nm, 851 nm], L = 0.5 . We applied SSHI on ZY1-02D/E AHSI images over Yellow River Delta (YRD) and Liao River Delta (LRD), China during 2021–2023. To evaluate the performance of SSHI, a simple thresholding method and a random forest (RF) model were used to map S. salsa, respectively. Our results showed that the overall accuracies of S. salsa maps achieved 87.96~89.43% (YRD) and 92.03~93.36% (LRD) using thresholds, and 92.62~94.05% (YRD) and 94.74~94.79% (LRD) using RF. For RF, incorporating SSHI improves S. salsa producer’s accuracies (user’s accuracies) by 1.02~6.85% (2.26~6.25%) compared to those without SSHI, proving the effectiveness of SSHI. The S. salsa maps reveal notable temporal variations, reflecting the impacts of climate change and human activities. Compared to existing hyperspectral indices related to red pigments, SSHI depicts greater separability between S. salsa and non-S. salsa. Meanwhile, SSHI is also applicable to other hyperspectral images such as GF-5B and PRISMA. SSHI has shown good adaptability and robustness for different time periods, regions, and hyperspectral satellite images, indicating that SSHI presents significant potential in accurately and effectively detecting S. salsa to facilitate sustainable coastal wetland monitoring and management.

Target detection is a key issue in processing hyperspectral images (HSIs). Spectral-identification-based algorithms are sensitive to spectral variability and noise in acquisition. In most cases, both the target spatial distributions and the spectral signatures are unknown, so each pixel is separately tested and appears as a target when it significantly differs from the background. In this paper, we propose two algorithms to improve the signal-to-noise ratio (SNR) of hyperspectral data, leading to detectors that are robust to noise. These algorithms consist in integrating adaptive spatial/spectral filtering into the adaptive matched filter and adaptive coherence estimator. Considering the HSIs as tensor data, our approach introduces a data representation involving multidimensional processing. It combines the advantages of spatial and spectral information using an alternating least square algorithm. To estimate the signal subspace dimension in each spatial mode, we extend the Akaike information criterion, and we develop an iterative algorithm for spectral-mode rank estimation. We demonstrate the interest of integrating the quadtree decomposition to perform an adaptive 3-D filtering and thereby preserve the local image characteristics. This leads to a significant improvement in terms of denoised tensor SNR and, consequently, in terms of detection probability. The performance of our method is exemplified using simulated and real-world HYperspectral Digital Imagery Collection Experiment images.

Hyperspectral image (HSI) classification has become a core task in hyperspectral remote sensing interpretation, with deep learning dominating due to its ability to learn hierarchical features without manual engineering. As the model complexity has grown, manual design limitations have prompted a shift to automated approaches such as differentiable architecture search (DARTS), where the architectures are optimized for greater accuracy and efficiency. However, applying gradient-based neural architecture search (NAS) methods directly to hyperspectral classification presents several challenges. Regarding search space design, there is a lack of lightweight operators that can mitigate the spectral variability, spatial heterogeneity, and scale differences inherent in hyperspectral imagery. In terms of search strategy, the traditional DARTS approach directly derives the topology from operation weights, which can lead to suboptimal topological structures, and thus affects the performance of the network in HSI classification. In this article, to address these issues, we propose L3M, which is a lightweight multiscale and multiattention HSI classification network based on multistage search. The proposed approach introduces a novel lightweight operator to address the spectral variability, spatial heterogeneity, and scale differences in HSIs. The operation search and topology search are also decomposed into a multistage process to prevent a suboptimal network by searching for and determining the topological order of the candidate operations in a predefined operation space. L3M was validated on four public datasets, where the proposed model demonstrated a superior classification performance, compared to other lightweight models, while maintaining a low parameter count, low model complexity, and high inference speed.

Spectral variability inevitably presents in hyperspectral images (HSIs), resulting in significant unmixing errors when using the conventional linear mixture model (LMM). Though several variants of LMM have been proposed to encounter such spectral variability, they cannot well model the complex characteristics of spectral variability, and the performance of these variants strongly depends on the prior knowledge of the scene. In this article, spectral variability within an image is classified into class-dependent variability and class-independent one, which can be tackled by a novel fully linear mixture model (FLMM) introducing a class-dependent multiplicative scaling term, a class-dependent additive perturbation term, and a class-independent variability term into the conventional LMM. Moreover, a spectral variability-aware cascaded autoencoder (SVACA) is designed to realize the automatic learning and representation of unmixing targets and spectral variability in different hyperspectral scenarios, which consists of a class-independent variability autoencoder and a cascaded class-dependent variability autoencoder. Such a network is able to handle different spectral variability autonomously without any scene prior by parallel inference structure. Experimental results over synthetic and real hyperspectral datasets demonstrate that the proposed SVACA network not only outperforms several state-of-the-art unmixing networks but also presents a stronger capability to handle spectral variability within HSIs.

Image segmentation is one of the most important and difficult tasks in digital image processing. It represents a key stage of automated image analysis and interpretation. Segmentation algorithms for gray-scale images utilize basic properties of intensity values such as discontinuity and similarity. However, it is possible to enhance edge-detection capability by means of using spectral information provided by multispectral (MS) or hyperspectral (HS) imagery. In this paper we consider image segmentation algorithms for multispectral images with particular emphasis on detection of multi-color or multispectral edges. More specifically, we report on an algorithm for joint spatio-spectral (JSS) edge detection. By joint we mean simultaneous utilization of spatial and spectral characteristics of a given MS or HS image. The JSSbased edge-detection approach, termed Spectral Ratio Contrast (SRC) edge-detection algorithm, utilizes the novel concept of matching edge signatures. The edge signature represents a combination of spectral ratios calculated using bands that enhance the spectral contrast between the two materials. In conjunction with a spatial mask, the edge signature give rise to a multispectral operator that can be viewed as a threedimensional extension of the mask. In the extended mask, the third (spectral) dimension of each hyper-pixel can be chosen independently. The SRC is verified using MS and HS imagery from a quantum-dot in a well infrared (IR) focal plane array, and the Airborne Hyperspectral Imager.