Monitoring surface deformation in mining areas is a crucial technique for ensuring infrastructure safety. However, underground coal mining often causes large-gradient deformation, which appears as dense and aliased fringes in Interferometric Synthetic Aperture Radar (InSAR) interferograms. To address the limitations of traditional phase unwrapping methods in handling large-gradient deformation, this study proposes a novel InSAR phase unwrapping approach driven by a mining subsidence model. The main innovations are as follows: (1) An automatic detection algorithm for small-gradient interferometric phases is developed to accurately identify correctly unwrappable regions along the subsidence funnel edges. (2) To overcome the issue of poor fitting performance in existing subsidence models, a Boltzmann function-based prediction model with enhanced boundary fitting capability is constructed. Considering the highly nonlinear characteristics of the model, an improved Fireworks Algorithm (IFWA) is introduced for accurate modeling. (3) A comprehensive methodological framework is established using an iterative optimization strategy. Simulation experiments demonstrate that the proposed method accurately retrieves the absolute phase in scenarios with dense interferometric fringes, achieving higher unwrapping accuracy than several mainstream methods currently used for mining-induced deformation. The method was further applied to the Huaibei mining area in China, where experiments were conducted on eight typical subsidence zones. Comparison with leveling measurements shows a mean error of 19.3 mm, a Root Mean Square Error (RMSE) of 25.9 mm, and an R2 of 0.828 and 0.736 along the strike and dip directions. These experimental results verify the feasibility and effectiveness of the proposed method. (c) 2025 COSPAR. Published by Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.

Ground fissures induced by coal mining activities pose severe risks such as coal fires, water inrush, and environmental degradation. Efficient identification of these fissures is critical for disaster prevention and mining safety. However, the lack of publicly training data tailored to mining scenarios hinders progress in deep-learning-based fissure identification. This article presents the ground fissures in mining areas (GFM) dataset, the first publicly available high-resolution uncrewed aerial vehicle (UAV) image dataset for ground fissure segmentation in coal mining areas, comprising 7368 annotated images across diverse landscapes and introducing a structured fissure categorization scheme. Furthermore, we propose FS-YOLO, a specialized instance segmentation framework that incorporates the dynamic snake convolutional pyramid pooling and deformable large kernel attention modules to enhance learning multiscale morphological features for ground fissure segmentation. Experiments indicate that FS-YOLO outperforms YOLOv8 by 3.5% and 6.5% in box AP@0.5 and box AP@0.95, and by 4.8% and 3.6% in mask AP@0.5 and mask AP@0.95, respectively, and achieves competitive results against other state-of-the-art methods.

To effectively obtain effective spectral response sub intervals of maize leaves under heavy metal lead pollution, and support heavy metal monitoring of crops. This article used hyperspectral remote sensing as the core technology and set up a maize pot experiment to collect a complete set of hyperspectral remote sensing data for maize leaves under heavy metal lead pollution using the SVC land cover spectrometer. A Lead Detection Index (LDI) was designed based on an improved Red Edge Normalization Index to obtain effective spectral response sub intervals of maize leaves under heavy metal lead pollution. Firstly, the original reflectance spectral data of maize in the training set was denoised by using the Db5 wavelet in the Daubechies wavelet series, resulting in the d5 component of the high frequency component in the 5th layer of the wavelet decomposition. Then, we divided the entire spectral range of mazie leaves from 350 to 2 500 nm into 11 subband intervals and established LDI using the d5 wavelet coefficient values corresponding to the middle wavelength of each subband interval. Using the Pearson correlation coefficient r. LDI was compared with three conventional spectral indices (Photochemical Reflection Index, PRI; Meris Territorial Chlorophyll Index, MTCI; Modified Red Edge Simple Ratio Index, mSR). The effective spectral response sub intervals of maize leaves under heavy metal lead pollution obtained from the training set data are purple valley, green peak, near infrared platform, and near edge. The absolute values of Pearson correlation coefficients are all greater than 0.9, which are 0.911 0, 0.915 5. 0.905 1. and 0.907 6, respectively. In contrast, the absolute values of Pearson correlation coefficients between the three conventional spectral indices and the heavy metal lead content in the leaves are all less than 0.9, indicating high L.DI effectiveness. Finally, we used the validation set data to obtain the effective spectral response subintervals of maize leaves under heavy metal lead pollution; purple valley, green peak, near infrared platform, and near edge. The absolute Pearson correlation coefficients were all greater than 0.9. The Pearson correlation coefficients r for validation set one and validation set two were 0.9999,-0.973 0, 0.914 2.0.9057, and 0.9999,0.9117. 0.9146, and 0.9103, respectively. However, the absolute Pearson correlation coefficients between the three conventional spectral indices and the heavy metal lead content in the leaves were all less than 0.9. The results showed that under heavy metal lead pollution, the effective spectral response subhands of maize leaves were purple valley, green peak, near infrared platform, and near edge four subbands. The research results can provide technical support for monitoring heavy metal pollution in other crops.

A maize pot experiment with different copper stress gradients was designed in an outdoor greenhouse to explore the sensitive leaf types and spectral ranges of crop pollution response under heavy metal stress. Taking maize leaves as the research. object, the hyperspectral reflectance data and heavy metal content data of maize leaves during the heading period were measured using instruments, providing basic data for research. This paper designed the Leaf Spectral Detection Method (LSDM) from the frequency domain perspective, combined with time-frequency analysis, to obtain sensitive leaf shapes and spectral hands under heavy metal copper stress, providing technical support for heavy metal monitoring in crops, Based on the growth process of maize, this study explores the full spectrum and sub-spectrum of the old leaf (O), middle leaf (M), and new leaf (N) spectra from 350 to 1 300 nm, Firstly, the hyperspectral reflectance data of maize leaves under copper stress were subjected to double differentiation (SOD) and envelope removal (CR) and transformed into the frequency domain, The Daubechies wavelet 6-layer decomposition was performed using time-frequency analysis methods. Then, based on the signal anomaly points, wavelet high value points, and SODCR curve high-value points, the spectral anomaly parameters SAP (Spectral Anomaly Parameters) of maize leaves are defined, namely, Abnormal Changes Reflectivity (ACR), which is the absolute value of the difference between the abnormal reflectance and the reflectance of the next adjacent band; Abnormal Wavelet Coefficients (AWC), which is the absolute value of the difference between the abnormal wavelet coefficients and the wavelet coefficients of the next adjacent band; Abnormal SODCR value (ASR), which is the absolute value of the difference between the abnormal point SOOCR value and the SODCR value of the next adjacent band, Finally, by examining the correlation between spectral anomaly parameters and heavy metal content in maize leaves, we aim to explore the leaf types and spectral segments sensitive to copper pollution, The results showed that the leaf spectral detection method LSDM can efficiently enhance weak information in maize leaves and accurately locate the spectral anomaly caused by heavy metal copper stress, with the anomaly range concentrated within 350 to 800 mm; Spectral anomaly parameters can quantitatively measure the spectral anomalies of maize leaves under heavy metal copper stress, Under different copper stress gradients, maize new leaves (N) exhibit sensitive leaf types, with sensitive spectral segments including blue edges, green peaks, yellow edges, and red valleys. This paper can provide technical support for monitoring heavy metals in other cercal crops and their canopy scales.

The stripe noise exists in the images acquired by the imaging spectrometer in orbit, which seriously restricts the subsequent high-precision quantitative application of hyperspectral images (HSIs). This article proposes the stripe removal method for HSIs, which can be applied to various scenes. It can remove the stripe noise of the images with large water area coverage, different stripe widths, and different stripe brightness to the greatest extent, without affecting the details of the image. The method uses the maximum between-class variance method adaptive threshold to extract the boundary of water and land areas in the image, and uses harmonic analysis to eliminate the cumulative stripe noise of image mean and variance in the frequency domain to obtain the theoretical true value of the image. Extensive experiments are carried out on GF5, ZY-1-02D, and Huanjing-2A (HJ-2A) satellite HSIs to compare the visualization effects of eight different algorithms for stripe removal, and the performance of the eight different algorithms is quantitatively evaluated by information entropy (IE) and noise estimation. The results show that the proposed algorithm has the most superior overall performance in terms of quantitative evaluation, processing efficiency, adaptability, and robustness, and is the best solution for engineering applications.

In this article, we used hyperspectral remote sensing as the core technology and set up a maize pot experiment to collect a complete set of hyperspectral remote sensing data for maize leaves under heavy metal lead pollution using the SVC (Spectra Vista Corporation) land cover spectrometer. We designed NLI (Novel Lead Index) based on an improved Red Edge Normalization Index to obtain effective spectral response sub intervals of maize leaves under heavy metal lead pollution. First, the original reflectance spectral data of maize in the training set was denoised by using the d5 (Daubechies wavelet 5-layer) wavelet in the Daubechies wavelet series, resulting in the d5 component of the high-frequency component in the 5th layer of wavelet decomposition. Then, we divided the entire spectral range of mazie leaves from 350 nm to 2500 nm into 11 sub band intervals, and established NLI using the d5 wavelet coefficient values corresponding to the middle wavelength of each sub band interval. Second, by using the Pearson correlation coefficient r (Pearson Correlation Coefficient), NLI was compared with three conventional spectral indices (Photochemical Reflection Index, PRI; Meris Territorial Chlorophyll Index, MTCI; Modified Red Edge Simple Ratio Index, mSR). Finally, we used the validation set data to verify the robustness of NLI. The results showed that under heavy metal lead pollution, the effective spectral response sub bands of maize leaves were purple valley, green peak, near-infrared platform, and near-edge four sub bands. The research results can provide technical support for monitoring heavy metal pollution in other crops.

When the PIM (Probability Integration Method) was applied to predicting surface subsidence for grouted backfill mining with overlying thick loose layers, it resulted in reduced accuracy, and the predicted values converged too rapidly at the edge of the subsidence basin. As a case study, this paper focuses on surface subsidence in grouted backfill mining at working face 1076 of Yangliu Coal Mine in the Huaibei Mining District. According to the principle of transferring the subsidence of grouted backfill mining, this study treated the bed separation cavity in the overburden strata as a semi-ellipsoid. It proposed an improved method for calculating the subsidence coefficient q in the PIM prediction model and established the surface subsidence dynamics prediction model called SEDC-Boltzmann (Semi-Ellipsoid Delamination Cavity-Boltzmann). The model was used for the dynamic prediction of surface subsidence in the grouting working face 1076 during the mining and grouting period. The prediction results were consistent with the monitored values from SBAS-InSAR (Small Baseline Subsets Interferometric Synthetic Aperture Radar) technology and leveling measurements. This model overcomes the flaw of predicted values converging too rapidly at the edge of the subsidence basin. Its prediction accuracy improved by 16.5

Drought impacts agricultural production and regional sustainable development. Accordingly, timely and accurate drought monitoring is essential for ensuring food security in rain-fed agricultural regions. Alternating drought and flood events frequently occur in the Heilongjiang River Basin, the largest grain-producing area in Far East Asia. However, spatiotemporal variability in drought is not well understood, in part owing to the limitations of the traditional Temperature Vegetation Dryness Index (TVDI). In this study, an Improved Temperature Vegetation Dryness Index (ITVDI) was developed by incorporating Digital Elevation Model data to correct land surface temperatures and introducing a constraint line method to replace the traditional linear regression for fitting dry–wet boundaries. Based on MODIS (Moderate-resolution Imaging Spectroradiometer) normalized vegetation index and land surface temperature products, the Heilongjiang River Basin, a cross-border basin between China, Mongolia, and Russia, exhibited pronounced spatiotemporal variability in drought conditions of the growing season from 2001 to 2023. Drought severity demonstrated clear geographical zonation, with a higher intensity in the western region and lower intensity in the eastern region. The Mongolian Plateau and grasslands were identified as drought hotspots. The Far East Asia forest belt was relatively humid, with an overall lower drought risk. The central region exhibited variation in drought characteristics. From the perspective of cross-national differences, the drought severity distribution in Northeast China and Inner Mongolia exhibits marked spatial heterogeneity. In Mongolia, regional drought levels exhibited a notable trend toward homogenization, with a higher proportion of extreme drought than in other areas. The overall drought risk in the Russian part of the basin was relatively low. A trend analysis indicated a general pattern of drought alleviation in western regions and intensification in eastern areas. Most regions showed relatively stable patterns, with few areas exhibiting significant changes, mainly surrounding cities such as Qiqihar, Daqing, Harbin, Changchun, and Amur Oblast. Regions with aggravation accounted for 52.29% of the total study area, while regions showing slight alleviation account for 35.58%. This study provides a scientific basis and data infrastructure for drought monitoring in transboundary watersheds and for ensuring agricultural production security.

The application of hyperspectral image (HSI) has expanded from Earth observation in large scenes to medical and industrial detection in small scenes. However, there are still many challenges in high-precision few-shot classification with high spectral similarity of targets. We have designed an end-to-end hyperspectral 3-D transformer (HSTR) semantic segmentation architecture based on multiscale spatial–spectral feature attention. This approach aims to simplify the model design and training processes through the end-to-end strategy while accurately capturing overall context and local detail information of spatial–spectral fusion feature. The HSTR can achieve high-precision HSI classification and transfer learning ability when training with limited small sample size, while enhancing efficiency through the utilization of the independent parallel computing advantage with 3-D shifted window strategy. Through three typical HSIs experiments, the evaluation of HSTR is conducted alongside nine other methods to assess its performance, and the advantages of HSTR are analyzed from the perspectives of end-to-end architecture, few-shot classification, spatial–spectral features combination, and multiscale features extraction. The HSTR algorithm effectively achieves the full extraction of multiscale features and spatial–spectral features fusion while demonstrating the most superior generalization performance and transfer learning ability in HSI classification tasks with insufficient samples.

In the interdisciplinary field of modern agriculture and environmental science, the study of changes in the spectral characteristics of crops contaminated with heavy metals is gradually becoming a hot topic, When crops are contaminated with heavy metals, their internal physiological structure and biochemical composition change, which is directly reflected in their spectral characteristics. The variation information generated by spectral changes becomes a crucial basis for monitoring heavy metal pollution. This study conducted pot experiments on maize plants contaminated with different concentrations of heavy metals, specifically copper and lead, in the laboratory. It measured the reflectance spectra of maize leaves under various 1 concentration gradients of copper and lead pollution, as well as key data such as the copper and lead content in maize leaves. A comprehensive, detailed, and specialized dataset was constructed for maize plants contaminated with heavy metals copper and lead. And focusing on the spectrum of maize leaves from a unique perspective in the frequency domain, we will conduct an in-depth exploration of its Full spectral range and sub-spectral range. By innovatively combining time-frequency analysis methods, a method called leaf-sensitive Spectral Interval Detection Method (SIDM) was proposed. Based on SIDM, spectral Variation Characteristic Parameters (SVCP) for leaf spectra were further proposed, which serve as "biomarkers" for crop contamination Status and are of great significance for studying the intrinsic correlation between variation characteristic parameters and leaf heavy metal content. Meanwhile, compare it with conventional spectral indices to explore the spectral range sensitive to copper and lead pollution. On this basis, a leaf Spectral Transformation Method (STM) was ingeniously constructed by combining a nonlinear time-frequency distribution, Through experimental verification, STM can clearly distinguish different types of copper and lead pollution, SIDM has successfully enhanced and accurately extracted weak information on copper and lead pollution in leaves, making the originally weak and difficult-to-detect pollution signals visible. More importantly, a highly specific spectral range for topper and lead pollution has been identified, laying a solid foundation for the development of more accurate and efficient heavy metal pollution monitoring technologies in the future, STM has advantages in distinguishing spectral differences between samples with and without heavy metal pollution, and can intuitively categorize the element types of maize contaminated with copper and 1 lead, effectively promoting the development of spectral technology for monitoring heavy metal pollution in crops.

Coal is the main mineral resource, but over-exploitation will cause a series of geological disasters. Interferometric synthetic aperture radar (InSAR) technology provides a superior monitoring method to compensate for the inadequacy of traditional measurements for mine surface deformation monitoring. In this study, the whole process of mining a working face in Huaibei Mining District, Anhui Province, is taken as the object of study. The ALOS PALSAR satellite radar image data and ground measurements were acquired, and the ISK-DPIM-InSAR deformation monitoring model with the dynamic probabilistic integral model (DPIM) was proposed by combining the probabilistic integral method (PIM) and the improved segmented Knothe time function (ISK). The ISK-DPIM-InSAR model constructs the inversion equations of InSAR line-of-sight deformation, north–south and east–west horizontal movement deformation, vertical deformation, inverts the optimal values of the predicted parameters of the workforce through the particle swarm algorithm, and substitutes it into the ISK-DPIM-InSAR model for predicting the three-dimensional dynamic deformation of a mining face. Simulated workface experiments determined the feasibility of the model, and by comparing the level observation results of the working face, it is confirmed that the ISK-DPIM-InSAR model can accurately monitor the three-dimensional deformation of the surface in the mining area.

This study aims to establish monitoring models for surface heavy metals in mining areas by utilizing multi-source remote sensing data and ensemble learning algorithms. By collecting heavy metal content data from soil and crop leaves within the study area, and combining it with data obtained from the Google Earth Engine platform, including Landsat 8, Sentinel-2 spectral data, vegetation indices, and VV and VH polarization information from Sentinel-1, along with terrain factors derived from the Digital Elevation Model such as elevation, hillshade, slope, and aspect, a total of 43 feature indicators were consolidated. Feature importance ranking (FI) and the successive projections algorithm (SPA) feature selection method were employed to filter feature factors, selecting different features for each type of heavy metal. In the soil, the optimal model for predicting Cr and Cd content is AdaBoost-MT, while the optimal model for inverting Zn, As, Hg, and Pb content is FISPA-AdaBoost-MT. In the crops, the optimal model for predicting the content of all six heavy metals is FISPA-AdaBoost-MT. This indicates that the combination of FI and SPA features effectively evaluates the heavy metal content in both soil and crops. Utilizing these multidimensional features, this study combines ensemble learning algorithms with multi-target regression techniques to construct inversion models for six types of heavy metals (Cr, Zn, As, Cd, Hg, and Pb) simultaneously. Based on the optimal prediction models, distribution maps of heavy metals in soil and crops within the study area were generated, achieving comprehensive, multidimensional monitoring of surface heavy metals in mining areas through overlay display.

When overlain by Longwall mining, the thick Quaternary loose layer of the working face produces a distinctive pattern of ground subsidence basins. The wide-area, multi-temporal, high-precision Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) time-series monitoring technique provides an accurate and efficient method of acquiring ground subsidence data, which can then be used in the dynamic inversion of ground subsidence basins. In this paper, 17 Sentinel 1-A microwave remote sensing images from the mining period of the 7225 inclined working face in the Huaibei Mining Area, Anhui Province, China, are used as the data source, and the results obtained by the SBAS-InSAR technique are used as the input values. The inversion model of the subsidence basin with thick, loose layers was constructed with reference to the heights of the caved zone and the fractured zone, as well as the mining distance and the mining depth. The parameters obtained from the inversion include the subsidence basin's length, width, centroid index, and spatial volume. The model inversion results follow the measured data, and the research results provide a theoretical basis and technical guidance for the subsequent exploration of Longwall mining in thick loose layers.

The technical theories of monitoring and preventing mining subsidence have long been key challenges and research priorities in the mining field. The rapid advancements in remote sensing technology and deep learning algorithms have enabled significant breakthroughs in monitoring and accurately identifying mining subsidence. In this article, a novel automatic detection method for mining subsidence is proposed using interferometric synthetic aperture radar (InSAR) wrapped interferograms. First, this study designs a VGG-UNet model enhanced by an attention mechanism module to learn and detect mining subsidence areas. This enhancement improves the feature representation and perception capabilities of the model. Second, to address the scarcity of real InSAR data in the training set, an efficient dataset simulation strategy is established. This strategy incorporates the realistic scenarios of monitoring the environment to improve the effect of model training. Finally, a complete workflow for model training and detection application is developed. The results demonstrate that the detection model achieves a precision of 92.55%, a recall of 90.43%, an accuracy of 93.37%, an F-1-score of 91.46%, and an intersection over union of 84.25% on the validation set. The model was applied to mining subsidence detection in the Huaibei-Yongcheng mining area, China, from June 2017 to July 2024. A total of 103 mining subsidence sites were identified, and their long-time series characteristics and the spatial distribution pattern of subsidence accumulation duration were analyzed. The findings offer critical technical support for sustainable mining management and land resource protection at the regional scale.

The eastern plains of China are home to numerous "coal-grain composite regions," where extensive underground coal mining has led to widespread land subsidence and cropland destruction, profoundly affecting regional ecological environments, agricultural production, and food security. This study proposes an automatic method for detecting cropland destruction and reclamation. The Normalized Difference Vegetation Index (NDVI) derived from long-term Landsat imagery was selected as the primary factor. First, by extracting a substantial number of NDVI samples from the mining areas, the threshold for cropland destruction due to mining disturbances was determined. Various types and scales of NDVI change templates were constructed based on the mechanisms of cropland disturbance. Subsequently, the Fast Dynamic Time Warping algorithm was employed to match the time-series curves and identify disturbance types, along with formulating detection rule for the year and magnitude of the cropland disturbance. Finally, patch indicators for disturbed croplands were established, and a random forest model was utilized to eliminate the disturbance noise induced by anthropogenic construction. The proposed method was applied to the Huaibei coal base, mapping cropland destruction and reclamation due to mining activities from 1987 to 2022, with overall accuracies of 0.85 and 0.81, respectively. This study revealed that the total area of cropland destroyed by mining activities amounted to 10179.71 ha during the monitoring period. From 1987 to 2005, the area of cropland destruction was small, accounting for 27.51% of the entire period. Between 2006 and 2018, the area of cropland destruction significantly increased, totaling 6102.01 ha and accounting for 59.94% of the entire period. The area of cropland destruction rapidly decreased and stabilized after 2018. Reclamation efforts began roughly in 1995, achieving a total reclaimed area of 2734.83 ha, with a reclamation rate of 26.86%. This study provides a crucial reference for monitoring the environmental impacts of mining and assessing the effectiveness of ecological restoration.

The application of hyperspectral image (HSI) has expanded from earth observation in large scenes to medical and industrial detection in small scenes. However, there are still many challenges in high-precision few-shot classification with high spectral similarity of targets. We have designed an end-to-end hyperspectral 3D Transformer (HSTR) semantic segmentation architecture based on multiscale spatial-spectral feature attention. This approach aims to simplify the model design and training processes through the end-to-end strategy while accurately capturing overall context and local detail information of spatial-spectral fusion feature. The HSTR can achieve high-precision HSI classification and transfer learning ability when training with limited small sample size, while enhancing efficiency through the utilization of the independent parallel computing advantage with 3D shifted window strategy. Through three typical HSIs experiments, the evaluation of HSTR is conducted alongside nine other methods to assess its performance, and the advantages of HSTR are analyzed from the perspectives of end-to-end architecture, few-shot classification, spatial-spectral features combination and multiscale features extraction. The HSTR algorithm effectively achieves the full extraction of multiscale features and spatial-spectral features fusion while demonstrating the most superior generalization performance and transfer learning ability in HSI classification tasks with insufficient samples.

Coal mining significantly affects vegetation evolution, but the patterns of vegetation change and the driving factors behind them in shaft mining mines are less explored. The Zhahe mining area in Huaibei City, China, was used as the study area to extract the vegetation cover （FVC） between 1987 and 2023 and explore the deep-seated drivers. Relying on the Google Earth Engine cloud platform, a total of 734 scenes of Landsat-5, Landsat-7, and Landsat-8 satellite image data were acquired from 1987 to 2023. Based on the image element dichotomous model, the spatial and temporal changes in FVC in the Zhahe mining area during the 37 years period were quantitatively analyzed by using trend analysis and stability analysis, and the impacts of nine driving factors on FVC in three aspects, namely, climate, topography, and human activities, were analyzed by using the geodetic detector. The results showed that： ① FVC in the Zhahe mining area has been decreasing over the past 37 years, with an average rate of change of 0.02%·a-1. The average FVC level in the area was high, and the area with medium coverage and above accounted for 81.8%, with a spatial distribution characterized by "high in the northeast and low in the southwest." ② The FVC of each coal mine in the Zhahe mining area was dominated by high stability areas, accounting for more than 30% of the area, and the land use type was dominated by cultivated land and construction land, while the areas of lower stability were mainly concentrated in the Shuoxi Lake, the collapse zone of Zhong Lake, and the areas close to the town roads in the study area. ③ In the exploration of the influence of the nine driving factors on FVC, the order of the influence of each factor on FVC was as follows： land use type （0.41） > precipitation （0.164） > nighttime light （0.12） > temperature （0.095） > GDP （0.079） > population density （0.048） > elevation （0.043） > slope （0.040） > slope （0.021）. The interaction between land use type and other factors had the strongest effect on the spatial variability of FVC.

With the development of industrialization, environmental heavy metal pollution has become increasingly serious, and the growth of crops has been seriously affected by heavy metal pollution in the soil environment. Therefore, it is necessary to establish methods for distinguishing and monitoring heavy metal pollution. The application of hyperspectral remote sensing in heavy metal pollution monitoring demonstrates the great potential of using crop leaf spectra to accurately distinguish heavy metal pollution elements. At the same time, new spectral processing methods and models are required to provide support for accurate identification. In this study, greenhouse experiments were conducted to simulate the growth of corn plants under heavy metal Cu and Pb stress. Collect hyperspectral data from different leaf layers of maize plants during the heading stage. Multivariate empirical mode decomposition (MEMD) was introduced, and the spectral data were preprocessed using MEMD, First derivative (FD), and second derivative (SD). At the same time, chemical analysis was used to examine the changes in copper (Cu), lead (Pb), and chlorophyll content in corn leaves. Competitive adaptive reweighted sampling (CARS) and iteratively retaining informative variables (IRIV) were used to screen characteristic bands that were sensitive to copper and lead. Finally, machine learning SVM, ELM, and XGBoost were utilized to construct and propose a series of models such as MEMD-CARS-ELM for accurate discrimination of Cu and Pb pollution elements. The results indicated that the discriminative model established after the MEMD transformation of the spectrum exhibited the best performance. Among them, whether it is tender leaves, functional leaves, or basal leaves, the accuracy of the MEMD-CARS-SVM and MEMD-CARS-ELM models in the training group and validation group for distinguishing Cu and Pb elements is greater than 80%. Other models established by MEMD spectral transformation are also significantly better at identifying Cu and Pb than those established by FD and SD transformations. The signal time-frequency analysis method MEMD is feasible and excellent for hyperspectral data processing. Based on this method, the Cu and Pb pollution element identification method proposed in this study was reliable. The research results provide a new method for the preprocessing of hyperspectral data and a new perspective for the accurate identification of soil heavy metal contamination elements. This study showed that corn leaf spectra can be used to accurately identify heavy metal pollution elements, providing a powerful scientific reference for hyperspectral remote sensing to monitor heavy metal pollution in large areas.

The Isolated Overburden Grout Injection Technology is employed for the "Three down" coal resource mining, ground subsidence management, and fly ash waste treatment, exemplifying the concept of environmentally friendly mining. The analysis of Isolated Overburden Grout Injection Technology can be effectively conducted utilizing the large-deflection inclined thin plate combined with the slurry model. However, differences in stratigraphic parameters, such as main roof and principal key strata (PKS), among different mines, as well as variations in design parameters like working face dimensions, mining height, coal seam angle of inclination, mining speed, and grouting parameters such as the number of grouting holes, start and finish times. These parameters lead to variations in outcomes such as PKS deflection and Bed-separation development, as well as the maximum subsidence and extent of the ground subsidence basin. To guarantee accurate and effective safeguarding of village structures, exploitation of coal resources, and appropriate management of fly ash waste, it is crucial to assess each parameter's influence in the model thoroughly. This analysis aims to clarify the mining and grouting process and enhance the logical design of the essential parameters. This paper classifies and examines the influence of each parameter on the results, utilizing the case study of the 7221 work face grouting operations in Huaibei, Anhui Province, China. The mining and grouting parameters were re-optimized to meet the protection requirements of the Gaochangying and Houlou Gaojia villages. The changes assessed the possible advantages of enhancing the initial design of coal seam resources and including fly ash backfill.

This paper designed CSSDM (Copper Stress Spectral Diagnosis Method) from the perspective of frequency domain, combined with time-frequency analysis, to obtain sensitive leaf types and spectral segments under heavy metal copper stress, providing technical support for heavy metal monitoring in crops. Firstly, the hyperspectral reflectance data of maize leaves under copper stress were subjected to DD (Double Differentiation) and EE (Envelope Elimination), and transformed into the frequency domain. The d6 (Daubechies wavelet 6-layer) decomposition was performed using time-frequency analysis methods. Then, based on the signal anomaly points, wavelet high value points and DDEE (Double Differentiation Envelope Elimination) curve high value points, the SRVP (Spectral Reflectance Variation Parameters) of maize leaves are defined. Finally, by examining the correlation between spectral reflectance variation parameters and heavy metal content in maize leaves, we aim to explore the leaf types and spectral segments that are sensitive to copper pollution. The results showed that CSSDM can efficiently enhance weak information in maize leaves and accurately locate the spectral anomaly caused by heavy metal copper stress, with the anomaly range concentrated within 350 nm-800 nm. Spectral reflectance variation parameters can quantitatively measure the spectral anomalies of maize leaves under heavy metal copper stress. Under different copper stress gradients, maize new leaves exhibit sensitive leaf types, with sensitive spectral segments including Blue Edges, Green Peaks, Yellow Edges and Red Valleys.