Search Results (18)

Speech Emotion Recognition (SER) plays a vital role in supporting applications such as healthcare, human–computer interaction, and security. However, many existing approaches still face challenges in achieving robust generalization and maintaining high recall, particularly for emotions related to stress and anxiety. This study proposes a dual-stream hybrid model that combines prosodic features with spatio-temporal representations derived from the Multitaper Mel-Frequency Spectrogram (MTMFS) and the Constant-Q Transform Spectrogram (CQTS). Prosodic cues, including pitch, intensity, jitter, shimmer, HNR, pause rate, and speech rate, were processed using dense layers, while MTMFS and CQTS features were encoded with CNN and BiGRU. A Multi-Head Attention mechanism was then applied to adaptively fuse the two feature streams, allowing the model to focus on the most relevant emotional cues. Evaluations conducted on the RAVDESS dataset with subject-independent 5-fold cross-validation demonstrated an accuracy of 97.64% and a macro F1-score of 0.9745. These results confirm that combining prosodic and advanced spectrogram features with attention-based fusion improves precision, recall, and overall robustness, offering a promising framework for more reliable SER systems. Full article

Remote sensing technology has significant technical advantages over traditional geological methods in geological mapping and mineral resource exploration, especially in high-altitude and steep topography areas. Geochemical sampling and geological mapping methods in these areas are difficult to use directly in mountainous regions such as West Kunlun. Therefore, in the face of Li-Be-Nb-Ta mineralization of the Dahongliutan rare-metal pegmatite deposit in West Kunlun, remote sensing has become an effective means to identify areas of interest for exploration in the early stage of the exploration campaigns. Several methods have been developed to detect pegmatites. Still, in this study, this methodology is based on spectral analysis to select bands of the ASTER and Landsat-8 OLI satellites, and methods, such as principal component analysis (PCA) and mixture tuned matched filtering (MTMF), to delineate the prospective areas of pegmatite. The results proved that PCA could map the hydrothermal alteration and structure information for pegmatites. To define new locations of interest for exploration, we introduced the spectra of spodumene-bearing pegmatites and tourmaline-bearing pegmatites as endmembers for the MTMF approach. The results indicate that the location of pegmatite areas on the ASTER and Landsat-8 OLI images overlaps with the ore deposits, and the location of potential ore-bearing pegmatites is delineated using remote sensing and geological sampling. Although this does not guarantee that all prospective areas have the mining value of ore-bearing pegmatites, it can provide basic data and technical references for early exploration of Li. Full article

The direct effects of relative humidity and soil on aboveground biomass (AGB) versus the indirect effects mediated by stand structural diversity remain unclear in forest ecosystems across large-scale elevation gradients. Forest inventory data containing 15,260 individual trees and 104 tree species from 200 forest plots were collected. The result shows that the relative humidity, elevation, and Coefficient of Variation of Diameter at breast height (CVD) significantly influence AGB in the Tropical Thorn Forest (TTF). Regarding elevation, CVD was positive and significant, and relative humidity and SR negatively impacted AGB in sub-tropical broad-leaved forests (STBLF). In moist temperate mixed forests (MTMF), soil phosphorus and CVD have a significant positive impact, while relative humidity, elevation, and SR negatively influence AGB. Elevation and CVD have positive, while SR and soil phosphorus have a negative and insignificant effect on AGB in Dry Temperate Conifer Forests (DTCF). Soil phosphorus and relative humidity positively affected AGB (β = 0.021), while elevation, CVD, and SR negatively affect AGB in dry temperate, pure pine forests (DTPPF). Relative humidity and soil phosphorus have a positive direct effect on AGB in multi-species forests. The current study suggests that AGB primarily depends on relative humidity, soil phosphorus, and elevation in different forest types. Full article

Deep learning is a popular topic in machine learning and artificial intelligence research and has achieved remarkable results in various fields. In geological remote sensing, mineral mapping is an appealing application of hyperspectral remote sensing for geological surveyors. Whether deep learning can improve the mineral identification ability in hyperspectral remote sensing images, especially for the discrimination of spectrally similar and intimately mixed minerals, needs to be evaluated. In this study, shortwave airborne spectrographic imager (SASI) hyperspectral images of the Baiyanghe uranium deposit in Northwestern Xinjiang, China, were used as experimental data. Three deep neural network (DNN) models were designed: a fully connected neural network (FCNN), a one-dimensional convolutional neural network (1D CNN), and a one-dimensional and two-dimensional convolutional neural network (1D and 2D CNN). A sample dataset containing five minerals was constructed for model training and validation, which was divided into training, validation and test sets at a ratio of 6:2:2. The final test accuracies of the FCNN, 1D CNN, and 1D and 2D CNN were 91.24%, 93.67% and 94.77%, respectively. The three DNNs were used for mineral identification and mapping of SASI hyperspectral images of the Baiyanghe uranium mining area. The mapping results were compared with the mapping results of the support vector machine (SVM) and the mixture-tuned matched filtering (MTMF) method. Combined with the ground spectral data obtained by the spectrometer, spectral verification and interpretation were carried out on sections that the two kinds of methods identified differently. The verification results show that the mapping results of the 1D and 2D CNN were more accurate than those of the other methods. More importantly, for minerals with similar spectral characteristics, such as short-wavelength white mica and medium-wavelength white mica, the 1D and 2D CNN model had a more accurate discrimination effect than the other DNN models, indicating that the introduction of spatial information can improve the mineral identification ability in hyperspectral remote sensing images. In general, CNNs have good application prospects in geological mapping of hyperspectral remote sensing images and are worthy of further development in future work. Full article

Glacier surface facies are valuable indicators of changes experienced by a glacial system. The interplay of accumulation and ablation facies, followed by intermixing with dust and debris, as well as the local climate, all induce observable and mappable changes on the supraglacial terrain. In the absence or lag of continuous field monitoring, remote sensing observations become vital for maintaining a constant supply of measurable data. However, remote satellite observations suffer from atmospheric effects, resolution disparity, and use of a multitude of mapping methods. Efficient image-processing routines are, hence, necessary to prepare and test the derivable data for mapping applications. The existing literature provides an application-centric view for selection of image processing schemes. This can create confusion, as it is not clear which method of atmospheric correction would be ideal for retrieving facies spectral reflectance, nor are the effects of pansharpening examined on facies. Moreover, with a variety of supervised classifiers and target detection methods now available, it is prudent to test the impact of variations in processing schemes on the resultant thematic classifications. In this context, the current study set its experimental goals. Using very-high-resolution (VHR) WorldView-2 data, we aimed to test the effects of three common atmospheric correction methods, viz. Dark Object Subtraction (DOS), Quick Atmospheric Correction (QUAC), and Fast Line-of-Sight Atmospheric Analysis of Hypercubes (FLAASH); and two pansharpening methods, viz. Gram–Schmidt (GS) and Hyperspherical Color Sharpening (HCS), on thematic classification of facies using 12 supervised classifiers. The conventional classifiers included: Mahalanobis Distance (MHD), Maximum Likelihood (MXL), Minimum Distance to Mean (MD), Spectral Angle Mapper (SAM), and Winner Takes All (WTA). The advanced/target detection classifiers consisted of: Adaptive Coherence Estimator (ACE), Constrained Energy Minimization (CEM), Matched Filtering (MF), Mixture-Tuned Matched Filtering (MTMF), Mixture-Tuned Target-Constrained Interference-Minimized Filter (MTTCIMF), Orthogonal Space Projection (OSP), and Target-Constrained Interference-Minimized Filter (TCIMF). This experiment was performed on glaciers at two test sites, Ny-Ålesund, Svalbard, Norway; and Chandra–Bhaga basin, Himalaya, India. The overall performance suggested that the FLAASH correction delivered realistic reflectance spectra, while DOS delivered the least realistic. Spectra derived from HCS sharpened subsets seemed to match the average reflectance trends, whereas GS reduced the overall reflectance. WTA classification of the DOS subsets achieved the highest overall accuracy (0.81). MTTCIMF classification of the FLAASH subsets yielded the lowest overall accuracy of 0.01. However, FLAASH consistently provided better performance (less variable and generally accurate) than DOS and QUAC, making it the more reliable and hence recommended algorithm. While HCS-pansharpened classification achieved a lower error rate (0.71) in comparison to GS pansharpening (0.76), neither significantly improved accuracy nor efficiency. The Ny-Ålesund glacier facies were best classified using MXL (error rate = 0.49) and WTA classifiers (error rate = 0.53), whereas the Himalayan glacier facies were best classified using MD (error rate = 0.61) and WTA (error rate = 0.45). The final comparative analysis of classifiers based on the total error rate across all atmospheric corrections and pansharpening methods yielded the following reliability order: MXL > WTA > MHD > ACE > MD > CEM = MF > SAM > MTMF = TCIMF > OSP > MTTCIMF. The findings of the current study suggested that for VHR visible near-infrared (VNIR) mapping of facies, FLAASH was the best atmospheric correction, while MXL may deliver reliable thematic classification. Moreover, an extensive account of the varying exertions of each processing scheme is discussed, and could be transferable when compared against other VHR VNIR mapping methods. Full article

Hydrothermal alteration minerals are an effective prospecting indicator. Advanced spaceborne thermal emission and reflection radiometer (ASTER) satellite data are some of the most commonly adopted multispectral data for the mapping of hydrothermal alteration minerals. Compared to multispectral data, hyperspectral data have stronger ground object recognition ability. Chinese Gaofen-5 (GF-5) is the first hyperspectral satellite independently developed by China that has the advantages of both wide-width and high-spectral-resolution technology. However, the mapping ability of GF5 data for hydrothermal alteration minerals requires further study. In this study, ASTER and GF-5 satellite data were implemented to map hydrothermal alteration minerals in the Longtoushan Pb-Zn deposit, SW China. Selective principal component analysis (SPCA) technology was employed to map iron oxide/hydroxides, argillic, quartz, and carbonate minerals at the pixel level using ASTER data, and the mixture tuned matched filtering (MTMF) method was implemented for the extracted hematite, kaolinite, calcite, and dolomite at the sub-pixel level using GF-5 data. When mapping the hydrothermal alteration minerals, the distribution features of the hydrothermal alteration minerals from the Longtoushan Pb-Zn deposit were systematically revealed. A comprehensive field investigation and petrographic study were conducted to verify the extraction accuracy of the hydrothermal alteration minerals. The results showed that the overall accuracies for the ASTER and GF-5 data were 82.6 and 92.9 and that the kappa coefficients were 0.78 and 0.90, respectively. This indicates that the GF-5 data are able to map hydrothermal alteration minerals well and that they can be promoted as a hyperspectral data source for mapping systematic hydrothermal alteration minerals in the future. Full article

The present work aims to map kaolin occurrences on the Kefalos peninsula, SW Kos Island, Greece, through the elaboration of ASTER satellite imagery. The island of Kos is located on the eastern edge of the South Aegean Active Volcanic Arc (SAAVA) and is characterised by its complex geologic structure. During Plio-Pleistocene, the voluminous eruption of the Kos Plateau Tuff was recorded on Kefalos; the largest quaternary eruption in the Mediterranean. Kaolin is the product of hydrothermal alteration of the Pliocene volcanic rocks with rhyolitic composition. Our study emphasises the usefulness of satellite imagery combined with the Mixture Tuned Matched Filtering (MTMF) technique to detect occurrences of industrial minerals, kaolin-group minerals in this case, either in terms of raw mineral exploitation or by mapping hydrothermal alteration. Full article

This study produces alteration mineral maps based on WorldView-3 (WV-3) data and field shortwave-infrared (SWIR) spectroscopy. It is supported by conventional analytical methods such as X-ray diffraction, X-ray fluorescence, and electron probe X-ray micro analyzer as an initial step for mineral exploration in eastern Tsogttsetsii, Mongolia, where access is limited. Distributions of advanced argillic minerals (alunite, dickite, and kaolinite), illite/smectite (illite, smectite, and mixed-layered illite-smectite), and ammonium minerals (buddingtonite and NH4-illite) were mapped using the decorrelation stretch, band math, and mixture-tuned-matched filter (MTMF) techniques. The accuracy assessment of the WV-3 MTMF map using field SWIR data showed good WV-3 SWIR data accuracy for spectrally predominant alteration minerals such as alunite, kaolinite, buddingtonite, and NH4-illite. The combination of WV-3 SWIR mineral mapping and a drone photogrammetric-derived digital elevation model contributed to an understanding of the structural development of the hydrothermal system through visualization of the topographic and spatial distribution of surface alteration minerals. Field SWIR spectroscopy provided further detailed information regarding alteration minerals such as chemical variations of alunite, crystallinity of kaolinite, and aluminum abundance of illite that was unavailable in WV-3 SWIR data. Combining WV-3 SWIR data and field SWIR spectroscopy with conventional exploration methods can narrow the selection between deposit models and facilitate mineral exploration. Full article

In Antarctica, spectral mapping of altered minerals is very challenging due to the remoteness and inaccessibility of poorly exposed outcrops. This investigation evaluates the capability of Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) satellite remote sensing imagery for mapping and discrimination of phyllosilicate mineral groups in the Antarctic environment of northern Victoria Land. The Mixture-Tuned Matched-Filtering (MTMF) and Constrained Energy Minimization (CEM) algorithms were used to detect the sub-pixel abundance of Al-rich, Fe³⁺-rich, Fe²⁺-rich and Mg-rich phyllosilicates using the visible and near-infrared (VNIR), short-wave infrared (SWIR) and thermal-infrared (TIR) bands of ASTER. Results indicate that Al-rich phyllosilicates are strongly detected in the exposed outcrops of the Granite Harbour granitoids, Wilson Metamorphic Complex and the Beacon Supergroup. The presence of the smectite mineral group derived from the Jurassic basaltic rocks (Ferrar Dolerite and Kirkpatrick Basalts) by weathering and decomposition processes implicates Fe³⁺-rich and Fe²⁺-rich phyllosilicates. Biotite (Fe²⁺-rich phyllosilicate) is detected associated with the Granite Harbour granitoids, Wilson Metamorphic Complex and Melbourne Volcanics. Mg-rich phyllosilicates are mostly mapped in the scree, glacial drift, moraine and crevasse fields derived from weathering and decomposition of the Kirkpatrick Basalt and Ferrar Dolerite. Chlorite (Mg-rich phyllosilicate) was generally mapped in the exposures of Granite Harbour granodiorite and granite and partially identified in the Ferrar Dolerite, the Kirkpatrick Basalt, the Priestley Formation and Priestley Schist and the scree, glacial drift and moraine. Statistical results indicate that Al-rich phyllosilicates class pixels are strongly discriminated, while the pixels attributed to Fe³⁺-rich class, Fe²⁺-rich and Mg-rich phyllosilicates classes contain some spectral mixing due to their subtle spectral differences in the VNIR+SWIR bands of ASTER. Results derived from TIR bands of ASTER show that a high level of confusion is associated with mafic phyllosilicates pixels (Fe³⁺-rich, Fe²⁺-rich and Mg-rich classes), whereas felsic phyllosilicates (Al-rich class) pixels are well mapped. Ground truth with detailed geological data, petrographic study and X-ray diffraction (XRD) analysis verified the remote sensing results. Consequently, ASTER image-map of phyllosilicate minerals is generated for the Mesa Range, Campbell and Priestley Glaciers, northern Victoria Land of Antarctica. Full article

This study presents a new approach for detection and mapping of ancient slag heaps using 16-band multispectral satellite imagery. Understanding the distribution of slag (a byproduct of metal production) is of great importance for understanding how metallurgy shaped long-term economic and political change across the ancient Near East. This study presents results of slag mapping in Oman using WorldView-3 (WV3) satellite imagery. A semi-automated target detection routine using a mixed tuned matched filtering (MTMF) algorithm with scene-derived spectral signatures was applied to 16-band WV3 imagery. Associated field mapping at two copper production sites indicates that WorldView-3 satellite data can differentiate slag and background materials with a relatively high (>90%) overall accuracy. Although this method shows promise for future initiatives to discover and map slag deposits, difficulties in dark object spectral differentiation and underestimation of total slag coverage substantially limit its use. Resulting lower estimations of combined user’s (61%) and producer’s (45%) accuracies contextualize these limitations for slag specific classification. Accordingly, we describe potential approaches to address these challenges in future studies. As sites of ancient metallurgy in Oman are often located in areas of modern exploration and mining, detection and mapping of ancient slag heaps via satellite imagery can be helpful for discovery and monitoring of vulnerable cultural heritage sites. Full article

Polymetallic vein-type ores are important sources of precious metal and a principal type of orebody for various base-metals. In this research, Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) remote sensing data were used for mapping hydrothermal alteration zones associated with epithermal polymetallic vein-type mineralization in the Toroud–Chahshirin Magmatic Belt (TCMB), North of Iran. The TCMB is the largest known goldfield and base metals province in the central-north of Iran. Propylitic, phyllic, argillic, and advanced argillic alteration and silicification zones are typically associated with Au-Cu, Ag, and/or Pb-Zn mineralization in the TCMB. Specialized image processing techniques, namely Selective Principal Component Analysis (SPCA), Band Ratio Matrix Transformation (BRMT), Spectral Angle Mapper (SAM) and Mixture Tuned Matched Filtering (MTMF) were implemented and compared to map hydrothermal alteration minerals at the pixel and sub-pixel levels. Subtle differences between altered and non-altered rocks and hydrothermal alteration mineral assemblages were detected and mapped in the study area. The SPCA and BRMT spectral transformation algorithms discriminated the propylitic, phyllic, argillic and advanced argillic alteration and silicification zones as well as lithological units. The SAM and MTMF spectral mapping algorithms detected spectrally dominated mineral groups such as muscovite/montmorillonite/illite, hematite/jarosite, and chlorite/epidote/calcite mineral assemblages, systematically. Comprehensive fieldwork and laboratory analysis, including X-ray diffraction (XRD), petrographic study, and spectroscopy were conducted in the study area for verifying the remote sensing outputs. Results indicate several high potential zones of epithermal polymetallic vein-type mineralization in the northeastern and southwestern parts of the study area, which can be considered for future systematic exploration programs. The approach used in this research has great implications for the exploration of epithermal polymetallic vein-type mineralization in other base metals provinces in Iran and semi-arid regions around the world. Full article

Mixture tuned matched filtering (MTMF) image classification capitalizes on the increasing spectral and spatial resolutions of available hyperspectral image data to identify the presence, and potentially the abundance, of a given cover type or endmember. Previous studies using MTMF have relied on extensive user input to obtain a reliable classification. In this study, we expand the traditional MTMF classification by using a selection of supervised learning algorithms with rigorous cross-validation. Our approach removes the need for subjective user input to finalize the classification, ultimately enhancing replicability and reliability of the results. We illustrate this approach with an MTMF classification case study focused on leafy spurge (Euphorbia esula), an invasive forb in Western North America, using free 30-m hyperspectral data from the National Aeronautics and Space Administration’s (NASA) Hyperion sensor. Our protocol shows for our data, a potential overall accuracy inflation between 18.4% and 30.8% without cross-validation and according to the supervised learning algorithm used. We propose this new protocol as a final step for the MTMF classification algorithm and suggest future researchers report a greater suite of accuracy statistics to affirm their classifications’ underlying efficacies. Full article

This study develops a site specific burn severity modelling using remote sensing techniques to develop severity patterns on vegetation and soil in the fire prone region of the Palo Verde National Park in Guanacaste, Costa Rica. Terrain physical features, soil cover, and scorched vegetation characteristics were examined to develop a fire risk model and to quantify probable burned areas. Spectral signatures of affected areas were captured through multi-spectral analysis; i.e., Normalized Burn Ratio (NBR), Landsat derived differenced Normalized Burn Ratio (dNBR) and relativized dNBR (RdNBR). A partial unmixing algorithm, Mixture Tuned Matched Filtering (MTMF) was used to isolate endmembers for scorched vegetation and soil. The performance of dNBR and RdNBR for predicting ground cover components was acceptable with an overall accuracy of 84.4% and Cohen’s Kappa 0.82 for dNBR and an overall accuracy of 89.4% and Cohen’s Kappa 0.82 for RdNBR. Landsat derived RdNBR showed a strong correlation with scorched vegetation (r² = 0.76) and moderate correlation with soil cover (r² = 0.53), which outperformed dNBR. The ecologically diverse and unique park area is threatened by wetland fires, which pose a potential threat to various species. Human induced fires by poachers are a common occurrence in such areas to gain access to these species. This paper aims to prioritize areas that are at a higher risk from fire and model spatial adaptations in relation to the direction of fire within the affected wetlands. This assessment will help wildlife personnel in managing disturbed wetland ecosystems. Full article

Geological mapping and mineral exploration programs in the High Arctic have been naturally hindered by its remoteness and hostile climate conditions. The Franklinian Basin in North Greenland has a unique potential for exploration of world-class zinc deposits. In this research, multi-sensor remote sensing satellite data (e.g., Landsat-8, Phased Array L-band Synthetic Aperture Radar (PALSAR) and Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER)) were used for exploring zinc in the trough sequences and shelf-platform carbonate of the Franklinian Basin. A series of robust image processing algorithms was implemented for detecting spatial distribution of pixels/sub-pixels related to key alteration mineral assemblages and structural features that may represent potential undiscovered Zn–Pb deposits. Fusion of Directed Principal Component Analysis (DPCA) and Independent Component Analysis (ICA) was applied to some selected Landsat-8 mineral indices for mapping gossan, clay-rich zones and dolomitization. Major lineaments, intersections, curvilinear structures and sedimentary formations were traced by the application of Feature-oriented Principal Components Selection (FPCS) to cross-polarized backscatter PALSAR ratio images. Mixture Tuned Matched Filtering (MTMF) algorithm was applied to ASTER VNIR/SWIR bands for sub-pixel detection and classification of hematite, goethite, jarosite, alunite, gypsum, chalcedony, kaolinite, muscovite, chlorite, epidote, calcite and dolomite in the prospective targets. Using the remote sensing data and approaches, several high potential zones characterized by distinct alteration mineral assemblages and structural fabrics were identified that could represent undiscovered Zn–Pb sulfide deposits in the study area. This research establishes a straightforward/cost-effective multi-sensor satellite-based remote sensing approach for reconnaissance stages of mineral exploration in hardly accessible parts of the High Arctic environments. Full article

Implying the prosperity and development of the city, impervious surface area (ISA) is playing an increasingly important role in ecological processes, microclimate, material and energy flows, and urban flood. The free sub-meter resolution Google Earth image, which is integrated by several high spatial resolution data, appears to have potential for high-resolution ISA extraction, where present study is rare and performances remain to be improved. Due to the high spatial and spectral variation of the urban environment as well as confusion between ISA and soil, the accurate delineating of ISA with traditional (direct) methods can be costly and time-consuming, which is in a word resource-intensive. However, this paper presents a novel indirect ISA extraction conceptual model and a new detecting and masking background land cover (DMBLC) approach that: uses a freely available, high-resolution dataset; requires a reduced set of training samples; and consists of relatively simple, common, and feasible image processing steps. The key characteristic of DMBLC is to detect the background of ISA (vegetation, soil, and water) accurately and obtain the ISA by masking the background. The approach relies on background detection to avoid the predicaments of direct ISA extraction. Water can be directly gained by water body vector data, in DMBLC; mixture tuned matched filtering (MTMF) is exploited to detect vegetation and soil, image segmentation is used to mitigate the spectral variation problem within the same land cover, and segment rectangularity reduces the confusion between ISA and soil. From experiments in a core area of Fuzhou, China, the DMBLC approach reached high performance and outperformed the powerful traditional support vector machines (SVM) method (overall accuracy of 94.45% and Kappa coefficient of 0.8885, compared to 86.44% and 0.7329, respectively). From the comparison of different levels of complexity within the inner processing steps, it is confirmed that the DMBLC approach is a powerful and flexible changed framework for indirect ISA extraction, which can be improved by using more advanced inner methods. Full article