Search Results (84)

The crystallization of soluble salts is one of the most significant agents of deterioration affecting porous building materials in historical architecture. This process not only compromises the physical integrity of the materials but also results in considerable aesthetic, structural, and economic consequences. Soluble salts involved in these processes may originate from geogenic sources—including soil leachate, marine aerosols, and the natural weathering of parent rocks—or from anthropogenic factors such as air pollution, wastewater infiltration, and the use of incompatible restoration materials. This study examines the role of capillary rise as a primary mechanism responsible for the vertical migration of saline solutions from the soil profile into historic masonry structures, especially those constructed with calcareous stones. It describes how water retained or sustained within the soil matrix ascends via capillarity, carrying dissolved salts that eventually crystallize within the pore network of the stone. This phenomenon leads to a variety of damage types, ranging from superficial staining and efflorescence to more severe forms such as subflorescence, microfracturing, and progressive mass loss. By adopting a multidisciplinary approach that integrates concepts and methods from soil physics, hydrology, petrophysics, and conservation science, this paper examines the mechanisms that govern saline water movement, salt precipitation patterns, and their cumulative effects on stone durability. It highlights the influence of key variables such as soil texture and structure, matric potential, hydraulic conductivity, climatic conditions, and stone porosity on the severity and progression of deterioration. This paper also addresses regional considerations by focusing on the context of Spain, which holds one of the highest concentrations of World Heritage Sites globally and where many monuments are constructed from vulnerable calcareous materials such as fossiliferous calcarenites and marly limestones. Special attention is given to the types of salts most commonly encountered in Spanish soils—particularly chlorides and sulfates—and their thermodynamic behavior under fluctuating environmental conditions. Ultimately, this study underscores the pressing need for integrated, preventive conservation strategies. These include the implementation of drainage systems, capillary barriers, and the use of compatible materials in restoration, as well as the application of non-destructive diagnostic techniques such as electrical resistivity tomography and hyperspectral imaging. Understanding the interplay between soil moisture dynamics, salt crystallization, and material degradation is essential for safeguarding the cultural and structural value of historic buildings in the face of ongoing environmental challenges and climate variability. Full article

Plant species classification in semi-arid mining areas is of great significance in assessing the environmental impacts and ecological restoration effects of coal mining. However, in semi-arid mining areas characterized by mixed arbor–shrub–herb vegetation, the complex vegetation distribution patterns and spectral features render single-sensor approaches inadequate for achieving fine classification of plant species in such environments. How to effectively fuse hyperspectral images (HSI) data with light detection and ranging (LiDAR) to achieve better accuracy in classifying vegetation in semi-arid mining areas is worth exploring. There is a lack of precise evaluation regarding how these two data collection approaches impact the accuracy of fine-scale plant species classification in semi-arid mining environments. This study established two experimental scenarios involving the synchronous and asynchronous acquisition of HSI and LiDAR data. The results demonstrate that integrating LiDAR data, whether synchronously or asynchronously acquired, significantly enhances classification accuracy compared to using HSI data alone. The overall classification accuracy for target vegetation increased from 71.7% to 84.7% (synchronous) and 80.2% (asynchronous), respectively. In addition, the synchronous acquisition mode achieved a 4.5% higher overall accuracy than asynchronous acquisition, with particularly pronounced improvements observed in classifying vegetation with smaller canopies (Medicago sativa L.: 17.4%, Pinus sylvestris var. mongholica Litv.: 11.7%, and Artemisia ordosica Krasch.: 7.5%). This study can provide important references for ensuring classification accuracy and error analysis of land cover based on HSI-LiDAR fusion in similar scenarios. Full article

Growing awareness of the environmental cost of mining operations has led to increased research on monitoring and restoring legacy mine sites. Hyperspectral imaging (HSI) has emerged as a valuable tool in the mining life cycle, including post-mining environment. By detecting variations in crystal structure and physicochemical attributes on the surface of materials, HSI provides insights into site environmental and ecological conditions. Here, we explore the capabilities of drone-based HSI for mapping surface patterns related to contamination dispersal in a legacy uranium-rare earth element mine site. Hyperspectral data across the visible to near-infrared (VNIR) and short-wave infrared (SWIR) wavelength ranges (400–2500 nm) were collected over selected areas of the former Mary Kathleen mine site in Queensland, Australia. Analyses were performed using data-driven (Spectral Angle Mapper—SAM) and knowledge-based (Band Ratios—BRs) spectral processing techniques. SAM identifies contamination patterns and differentiates mineral compositions within visually similar areas. However, its accuracy is limited when mapping specific minerals, as most endmembers represent mineral groups or mixtures. BR highlights reactive surfaces and clay mixtures, reinforcing key patterns identified by SAM. The results indicate that drone-based HSI can capture and distinguish complex surface trends, demonstrating the technology’s potential to enhance the assessment and monitoring of environmental conditions at a mine site. Full article

Monitoring dust on plant canopies around open-pit coal mines is crucial to assessing environmental pollution and developing effective dust suppression strategies. This research focuses on the Ha’erwusu open-pit coal mine in Inner Mongolia, China, using measured dust content on plant canopies and UAV-borne VNIR hyperspectral data as the data sources. The study employed five spectral transformation forms—first derivative (FD), second derivative (SD), logarithm transformation (LT), reciprocal transformation (RT), and square root (SR)—alongside the competitive adaptive reweighted sampling (CARS) method to extract characteristic bands associated with canopy dust. Various regression models, including extreme learning machine (ELM), random forest (RF), partial least squares regression (PLSR), and support vector machine (SVM), were utilized to establish dust inversion models. The spatial distribution of canopy dust was then analyzed. The results demonstrate that the geometric and radiometric correction of the UAV-borne VNIR hyperspectral images successfully restored the true spatial information and spectral features. The spectral transformations significantly enhance the feature information for canopy dust. The CARS algorithm extracted characteristic bands representing 20 to 30% of the total spectral bands, evenly spread across the entire range, thereby reducing the estimation model’s computational complexity. Both feature extraction and model selection influence the inversion accuracy, with the LT-CARS and RF combination offering the best predictive performance. Canopy dust content decreases with increasing distance from the dust source. These findings offer valuable insights for canopy dust retention monitoring and offer a solid foundation for dust pollution management and the development of suppression strategies. Full article

Most current hyperspectral image compression methods rely on well-designed modules to capture image structural information and long-range dependencies. However, these modules tend to increase computational complexity exponentially with the number of bands, which limits their performance under constrained resources. To address these challenges, this paper proposes a novel triple-phase hybrid framework for hyperspectral image compression. The first stage utilizes an adaptive band selection technique to sample the raw hyperspectral image, which mitigates the computational burden. The second stage concentrates on high-fidelity compression, efficiently encoding both spatial and spectral information within the sampled band clusters. In the final stage, a reconstruction network compensates for sampling-induced losses to precisely restore the original spectral details. The proposed framework, known as ARM-Net, is evaluated on seven mixed hyperspectral datasets. Compared to state-of-the-art methods, ARM-Net achieves an overall improvement of approximately 1–2 dB in both the peak signal-to-noise ratio and multiscale structural similarity index measure, as well as a reduction in the average spectral angle mapper of approximately 0.1. Full article

Effectively handling mixed noise types and varying intensities is crucial for accurate information extraction and analysis, particularly in resource-limited edge computing scenarios. Conventional image denoising approaches struggle with unseen noise distributions, limiting their effectiveness in real-world applications such as object detection, classification, and change detection. To address these challenges, we introduce a novel image denoising framework that integrates asymmetric learning with symmetric fusion. It leverages a pretrained model trained only on clean images to provide semantic priors, while a supervised module learns direct noise-to-clean mappings using paired noisy–clean data. The asymmetry in our approach stems from its dual training objectives: a pretrained encoder extracts semantic priors from noise-free data, while a supervised module learns noise-to-clean mappings. The symmetry is achieved through a structured fusion of pretrained priors and supervised features, enhancing generalization across diverse noise distributions, including those in edge computing environments. Extensive evaluations across multiple noise types and intensities, including real-world remote sensing data, demonstrate the superior robustness of our approach. Our method achieves state-of-the-art performance in both in-distribution and out-of-distribution noise scenarios, significantly enhancing image quality for downstream tasks such as environmental monitoring and disaster response. Future work may explore extending this framework to specialized applications like hyperspectral imaging and nighttime analysis while further refining the interplay between symmetry and asymmetry in deep-learning-based image restoration. Full article

Grasslands play a crucial role in ecosystems, influencing key ecological functions such as biodiversity, climate regulation, and soil and water conservation. With the impacts of environmental changes and human activities, the functional status and health of grasslands are facing challenges. Therefore, efficient identification of grassland status is of great significance for the sustainable management, ecological protection, and restoration of grassland resources. To support the sustainable development of grasslands, the GRCNet network model is proposed. Grassland sweep photography was performed via a UAV-mounted hyperspectral imager to establish a 13-category grassland hyperspectral dataset. Then, Gaussian filter and principal component analysis (PCA) were used for noise reduction and dimensionality reduction in the hyperspectral images, and the GRCNet network model, which mainly consists of the GCA module, the RDC module, and the VIT-Base module, was established for the classification task. The experiments use the average accuracy, overall accuracy, F1 score, Kappa coefficient, and running time as the performance indexes, and the eight methods are compared with GRCNet. The results showed that the GRCNet network performed the best with AA reaching 92.84%, OA reaching 94.59%, F1 score reaching 97.22, and Kappa coefficient reaching 0.93. The GRCNet method is 10–20% more accurate than other methods. Comparative tests were also conducted using two public datasets, and GRCNet performed the best with a 2–20% improvement in accuracy. The results demonstrate the effectiveness of the GRCNet network model in hyperspectral grass classification tasks, which can be used as an efficient solution to the current problem of low hyperspectral accuracy and poor stability. Full article

Estuarine wetlands are the transition zone between marine, freshwater, and terrestrial ecosystems and are more ecologically fragile. In recent years, the spread of exotic vegetation, specifically Spartina alterniflora, in the Yellow River estuary wetlands has significantly encroached upon the habitats of native species such as Phragmites australis, Suaeda glauca Bunge, and Tamarix chinensis Lour. With advances in land prediction modeling, predicting wetland vegetation distribution can aid management and decision-making for ecological restoration. We selected the core area as the study object and coupled the hydrological model MIKE 21 with the PLUS model to predict the potential future distribution of invasive and dominant species in the region. (1) Based on the fine classification results from satellite images of GF1/G2/G5, we gained an understanding of the changes in wetland vegetation types in the core area of the reserve in 2018 and 2020. (2) Using public data such as ERA5 and GEO as input for basic environmental data, using MIKE 21 to provide high-spatial-resolution hydrodynamic parameters for the PLUS model as an environmental driver, we modeled the spatial distribution of various wetland vegetation in the Yellow River estuary wetland in Dongying under different artificial restoration measures. (3) We predicted the 2022 distribution of typical vegetation in the region, used the classification results of GF6 as the actual distribution, compared the spatial distribution with the actual distribution, and obtained a kappa coefficient of 0.78; the predicted values of the model are highly consistent with the true values. This study combines the fine classification results of vegetation based on hyperspectral remote sensing, the construction of a coupled model, and the prediction effect of typical species, providing a reference for constructing and optimizing the vegetation prediction model of estuarine wetlands. It also allows scientific and effective decision-making for the management of ecological restoration of delta wetlands. Full article

Hyperspectral Imaging (HSI) excels in material identification and capturing spectral details and is widely utilized in various fields, including remote sensing and environmental monitoring. However, in real-world applications, HSI is often affected by Stray Light Interference (SLI), which severely degrades both its spatial and spectral quality, thereby reducing overall image accuracy and usability. Existing hardware solutions are often expensive and add complexity to the system, and despite these efforts, they cannot fully eliminate SLI. Traditional algorithmic methods, on the other hand, struggle to capture the intricate spatial–spectral dependencies needed for effective restoration, particularly in complex noise scenarios. Deep learning methods present a promising alternative because of their flexibility in handling complex data and strong restoration capabilities. To tackle this challenge, we propose MambaHR, a novel State Space Model (SSM) for HSI restoration under SLI. MambaHR incorporates state space modules and channel attention mechanisms, effectively capturing and integrating global and local spatial–spectral dependencies while preserving critical spectral details. Additionally, we constructed a synthetic hyperspectral dataset with SLI by simulating light spots of varying intensities and shapes across spectral channels, thereby realistically replicating the interference observed in real-world conditions. Experimental results demonstrate that MambaHR significantly outperforms existing methods across multiple benchmark HSI datasets, exhibiting superior performance in preserving spectral accuracy and enhancing spatial resolution. This method holds great potential for improving HSI processing applications in fields such as remote sensing and environmental monitoring. Full article

Background: Rodents severely damage the ecological environment of grasslands, and rodent mounds of different ages require distinct management strategies. Understanding the age of these mounds aids in formulating targeted restoration measures, which can enhance grassland productivity and biodiversity. Current surveys of rodent mounds rely on ground exposure and mound height to determine their age, which is time-consuming and labor-intensive. Remote sensing methods can quickly and easily identify the distribution of rodent mounds. Existing remote sensing images use ground exposure and mound height for identification but do not distinguish between mounds of different ages, such as one-year-old and two-year-old mounds. According to the existing literature, rodent mounds of different ages exhibit significant differences in vegetation structure, soil background, and plant diversity. Utilizing a combination of vegetation indices and hyperspectral data to determine the age of rodent mounds aims to provide a better method for extracting rodent hazard information. This experiment investigates and analyzes the age, distribution, and vegetation characteristics of rodent mounds, including total coverage, height, biomass, and diversity indices such as Patrick, Shannon–Wiener, and Pielou. Spectral data of rodent mounds of different ages were collected using an Analytical Spectral Devices field spectrometer. Correlation analysis was conducted between vegetation characteristics and spectral vegetation indices to select key indices, including NDVI₆₇₀, NDVI₇₀₅, EVI, TCARI, Ant, and SR. Multiple stepwise regression and Random Forest (RF) inversion models were established using vegetation indices, and the most suitable model was selected through comparison. Random Forest modeling was conducted to classify plateau zokor rat mounds of different ages, using both vegetation characteristic indicators and vegetation indices for comparison. The rodent mound classification models established using vegetation characteristic indicators and vegetation indices through Random Forest could distinguish rodent mounds of different ages, with out-of-bag error rates of 36.96% and 21.74%, respectively. The model using vegetation indices performed better. Conclusions: (1) Rodent mounds play a crucial ecological role in alpine meadow ecosystems by enhancing plant diversity, biomass, and the stability and vitality of the ecosystem. (2) The vegetation indices SR and TCARI are the most influential in classifying rodent mounds. (3) Incorporating vegetation indices into Random Forest modeling facilitates a precise and robust remote sensing interpretation of rodent mound ages, which is instrumental for devising targeted restoration strategies. Full article

The fusion of low-resolution hyperspectral images (LR-HSI) with high-resolution multispectral images (HR-MSI) provides a cost-effective approach to obtaining high-resolution hyperspectral images (HR-HSI). Existing methods primarily based on convolutional neural networks (CNNs) struggle to capture global features and do not adequately address the significant scale and spectral resolution differences between LR-HSI and HR-MSI. To tackle these challenges, our novel FCSwinU network leverages the spectral fast Fourier convolution (SFFC) module for spectral feature extraction and utilizes the Swin Transformer’s self-attention mechanism for multi-scale global feature fusion. FCSwinU employs a UNet-like encoder–decoder framework to effectively merge spatiospectral features. The encoder integrates the Swin Transformer feature abstraction module (SwinTFAM) to encode pixel correlations and perform multi-scale transformations, facilitating the adaptive fusion of hyperspectral and multispectral data. The decoder then employs the Swin Transformer feature reconstruction module (SwinTFRM) to reconstruct the fused features, restoring the original image dimensions and ensuring the precise recovery of spatial and spectral details. Experimental results from three benchmark datasets and a real-world dataset robustly validate the superior performance of our method in both visual representation and quantitative assessment compared to existing fusion methods. Full article

The value of the Buddhist cave lies not only in the Buddha statues but also in the surface painting. Hyperspectral imaging technology, as an emerging and effective method for component identification, offers a non-contact and non-destructive approach to the preservation and restoration of oil paintings. This study employed hyperspectral cameras to capture common pigments on the surfaces of Buddhist caves. Then, the results were processed and used as a database to identify the paintings. Additionally, a series of experiments were conducted to examine the impact of binder, substrate types, and pigment sizes on the reflectance spectrum of the paints. The Spectral Angle Matching (SAM) algorithm was then used to analyze the Yuanjue Cave and Qiqushan Stone Carvings of the Tang Dynasty in China. The findings revealed that the position of absorption peaks in the reflectance spectra is not significantly influenced by the substrate but is affected by the binder. Moreover, the absorption depth varies regularly with particle size. Furthermore, the spectral matching results demonstrate that components can be accurately identified even for similar colors. Based on the pigment distribution, the study also inferred specific details of ancient paintings, including the painting steps and hidden information in the manuscript layout. These findings hold significant implications for the restoration of representative surface paintings of the Tang Dynasty Buddhist cave, providing a reference for the selection of restoration materials and methods. Full article

The prompt acquisition of precise land cover categorization data is indispensable for the strategic development of contemporary farming practices, especially within the realm of forestry oversight and preservation. Forests are complex ecosystems that require precise monitoring to assess their health, biodiversity, and response to environmental changes. The existing methods for classifying remotely sensed imagery often encounter challenges due to the intricate spacing of feature classes, intraclass diversity, and interclass similarity, which can lead to weak perceptual ability, insufficient feature expression, and a lack of distinction when classifying forested areas at various scales. In this study, we introduce the DASR-Net algorithm, which integrates a dual attention network (DAN) in parallel with the Residual Network (ResNet) to enhance land cover classification, specifically focusing on improving the classification of forested regions. The dual attention mechanism within DASR-Net is designed to address the complexities inherent in forested landscapes by effectively capturing multiscale semantic information. This is achieved through multiscale null attention, which allows for the detailed examination of forest structures across different scales, and channel attention, which assigns weights to each channel to enhance feature expression using an improved BSE-ResNet bilinear approach. The two-channel parallel architecture of DASR-Net is particularly adept at resolving structural differences within forested areas, thereby avoiding information loss and the excessive fusion of features that can occur with traditional methods. This results in a more discriminative classification of remote sensing imagery, which is essential for accurate forest monitoring and management. To assess the efficacy of DASR-Net, we carried out tests with 10m Sentinel-2 multispectral remote sensing images over the Heshan District, which is renowned for its varied forestry. The findings reveal that the DASR-Net algorithm attains an accuracy rate of 96.36%, outperforming classical neural network models and the transformer (ViT) model. This demonstrates the scientific robustness and promise of the DASR-Net model in assisting with automatic object recognition for precise forest classification. Furthermore, we emphasize the relevance of our proposed model to hyperspectral datasets, which are frequently utilized in agricultural and forest classification tasks. DASR-Net’s enhanced feature extraction and classification capabilities are particularly advantageous for hyperspectral data, where the rich spectral information can be effectively harnessed to differentiate between various forest types and conditions. By doing so, DASR-Net contributes to advancing remote sensing applications in forest monitoring, supporting sustainable forestry practices and environmental conservation efforts. The findings of this study have significant practical implications for urban forestry management. The DASR-Net algorithm can enhance the accuracy of forest cover classification, aiding urban planners in better understanding and monitoring the status of urban forests. This, in turn, facilitates the development of effective forest conservation and restoration strategies, promoting the sustainable development of the urban ecological environment. Full article

Restored wetlands should be closely monitored to fully evaluate the effectiveness of restoration efforts. However, regular post-restoration monitoring can be time-consuming and expensive, and is often absent or inadequate. Satellite and airborne remote sensing systems have proven to be cost-effective tools in many fields, but they have not been widely used to monitor ecological restoration. This study assessed the potential of airborne hyperspectral remote sensing to monitor water mass characteristics of experimental temporary ponds in the Mediterranean region. These ponds were created during marsh restoration in Doñana National Park (south-west Spain). We used hyperspectral images acquired by the CASI-1500 hyperspectral airborne sensor to estimate and map water depth, turbidity and chlorophyll a in a subset of the 96 new ponds. The high spatial and spectral resolution of the CASI sensor allowed us to detect differences between ponds in water depth, turbidity and chlorophyll a, providing accurate mapping of these three variables, and a useful method to assess restoration success. High levels of spatial variation were recorded between different ponds, which likely generates high diversity in the animal and plant species that they contain. These results highlight the great potential of hyperspectral sensors for the long-term monitoring of wetland complexes in the Mediterranean region and elsewhere. Full article

Painted cultural relics hold significant historical value and are crucial in transmitting human culture. However, mold is a common issue for paper or silk-based relics, which not only affects their preservation and longevity but also conceals the texture, patterns, and color information, hindering cultural value and heritage. Currently, the virtual restoration of painting relics primarily involves filling in the RGB based on neighborhood information, which might cause color distortion and other problems. Another approach considers mold as noise and employs maximum noise separation for its removal; however, eliminating the mold components and implementing the inverse transformation often leads to more loss of information. To effectively acquire virtual restoration for mold removal from ancient paintings, the spectral characteristics of mold were analyzed. Based on the spectral features of mold and the cultural relic restoration philosophy of maintaining originality, a 3D CNN artifact restoration network was proposed. This network is capable of learning features in the near-infrared spectrum (NIR) and spatial dimensions to reconstruct the reflectance of visible spectrum, achieving the virtual restoration for mold removal of calligraphic and art relics. Using an ancient painting from the Qing Dynasty as a test subject, the proposed method was compared with the Inpainting, Criminisi, and inverse MNF transformation methods across three regions. Visual analysis, quantitative evaluation (the root mean squared error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MEA), and a classification application were used to assess the restoration accuracy. The visual results and quantitative analyses demonstrated that the proposed 3D CNN method effectively removes or mitigates mold while restoring the artwork to its authentic color in various backgrounds. Furthermore, the color classification results indicated that the images restored with 3D CNN had the highest classification accuracy, with overall accuracies of 89.51%, 92.24%, and 93.63%, and Kappa coefficients of 0.88, 0.91, and 0.93, respectively. This research provides technological support for the digitalization and restoration of cultural artifacts, thereby contributing to the preservation and transmission of cultural heritage. Full article