Land cover data are important basic data for earth system science and other fields. Multi-source remote sensing images have become the main data source for land cover classification. There are still many uncertainties in the scale effect of image spatial resolution on land cover classification. Since it is difficult to obtain multiple spatial resolution remote sensing images of the same area at the same time, the main current method to study the scale effect of land cover classification is to use the same image resampled to different resolutions, however errors in the resampling process lead to uncertainty in the accuracy of land cover classification. To study the land cover classification scale effect of different spatial resolutions of multi-source remote sensing data, we selected 1 m and 4 m of GF-2, 6 m of SPOT-6, 10 m of Sentinel-2, and 30 m of Landsat-8 multi-sensor data, and explored the scale effect of image spatial resolution on land cover classification from two aspects of mixed image element decomposition and spatial heterogeneity. For the study area, we compared the classification obtained from GF-2, SPOT-6, Sentinel-2, and Landsat-8 images at different spatial resolutions based on GBDT and RF. The results show that (1) GF-2 and SPOT-6 had the best classification results, and the optimal scale based on this classification accuracy was 4–6 m; (2) the optimal scale based on linear decomposition depended on the study area; (3) the optimal scale of land cover was related to spatial heterogeneity, i.e., the more fragmented and complex was the space, the smaller the scale needed; and (4) the resampled images were not sensitive to scale and increased the uncertainty of the classification. These findings have implications for land cover classification and optimal scale selection, scale effects, and landscape ecology uncertainty studies.

Soil texture is one of the important physical and natural properties of soil. Much of the current research focuses on soil texture monitoring using non-imaging geophysical spectrometers. However there are fewer studies utilizing unmanned aerial vehicle (UAV) hyperspectral data for soil texture monitoring. UAV mounted hyperspectral cameras can be used for quickly and accurately obtaining high-resolution spatial information of soil texture. A foundation has been laid for the realization of rapid soil texture surveys using unmanned airborne hyperspectral data without field sampling. This study selected three typical farmland areas in Huangshui Basin of Qinghai as the study area, and a total of 296 soil samples were collected. Data calibration of UAV spectra using laboratory spectra and field in situ spectra to explore the feasibility of applying laboratory soil texture models directly to field conditions. This results show that UAV hyperspectral imagery combined with machine learning can obtain a set of ideal processing methods. The pre-processing of the spectral data can obtain high accuracy of soil texture estimation and good mapping effect. The results of this study can provide effective technical support and decision-making assistance for future agricultural land planning on the Tibetan Plateau. The main innovation of this study is to establish a set of processing procedures and methods applicable to UAV hyperspectral imagery to provide data reference for monitoring soil texture in agricultural fields on the Tibetan Plateau.

Land cover data are important basic data for earth system science and other fields. Multi-source remote sensing images have become the main data source for land cover classification. There are still many uncertainties in the scale effect of image spatial resolution on land cover classification. Since it is difficult to obtain multiple spatial resolution remote sensing images of the same area at the same time, the main current method to study the scale effect of land cover classification is to use the same image resampled to different resolutions, however errors in the resampling process lead to uncertainty in the accuracy of land cover classification. To study the land cover classification scale effect of different spatial resolutions of multi-source remote sensing data, we selected 1 m and 4 m of GF-2, 6 m of SPOT-6, 10 m of Sentinel-2 and 30 m of Landsat-8 multi-sensor data, and explored the scale effect of image spatial resolution on land cover classification from two aspects of mixed image element decomposition and spatial heterogeneity. For the study area, we compared the classification obtained from GF-2, SPOT-6, Sentinel-2, and Landsat-8 images at different spatial resolutions based on GBDT and RF. The results show that (1) GF-2 and SPOT-6 had the best classification results, and the optimal scale based on this classification accuracy was 4–6 m; (2) the optimal scale based on linear decomposition depended on the study area; (3) the optimal scale of land cover was related to spatial heterogeneity, i.e., the more fragmented and complex was the space, the smaller the scale needed; and (4) the resampled images were not sensitive to scale and increase the uncertainty of the classification. These findings have implications for land cover classification and optimal scale selection, scale effects and landscape ecology uncertainty studies.

The present study aims to quantitatively assess soil erosion intensity (SEI) and amounts in the Qinghai Lake Basin (QLB) over the 1990–2020 period using the Integrated Valuation Ecosystem Services and Tradeoffs (InVEST) model based on multi-source data. In addition, the changing trends and driving factors of soil erosion (SE) in the study area were systematically analyzed. The result showed: (1) An increasing-decreasing trend in the total soil erosion amount (SEA) in the QLB over the 1990–2020 period, with an average SEI of 579.52 t/km². In addition, very low and low erosion classes covered 94.49% of the total surface area, while areas with high SEI were mainly distributed in alpine areas with low vegetation coverage (VC). (2) The highest average SEI was observed in bare land, while grassland and unused land were the main land use (LU) types where SE mainly occurred, with the ratio of the two being 95.78%. (3) The average value of SEI was positively correlated with altitude values below 4800 m. In addition, areas with altitude ranges of 4000–4400 m, 3600–4000 m, and 4400–4800 m were the main areas where SE occurred, with an average total soil erosion ratio (SER) value of 88.73%. (4) The average SEI was directly proportional to the slope degrees. SE occurred mainly in the areas with slope degree ranges of 15–25°, 25–35°, 8–15°, and >35°, accounting for 93.16% of the average total SER value. (5) The q value of the two-factor interaction was greater than that of the single-factor interaction. In addition, the areas with a high SE risk were mainly those with 1220–2510 m rainfall, 35°. The interaction between rainfall, VC, LULC, elevation, and slope had a significant impact on the spatial distribution of SEI.

The effective monitoring and early warning capability of metal mine tailings ponds can improve the associated safety risk management level. The infiltration line is an important core index of tailings pond stability. In this paper, a tailings pond monitoring and early warning system, which provides technical support for the design and daily management of tailings reservoir early warning systems, is constructed. Based on a deep learning bidirectional recurrent long and short memory network, an infiltration line prediction model with univariate input and an infiltration line prediction model with multivariate input are proposed. The data adopted are those from four monitoring points of the same cross-section at different positions and data from one adjacent internal lateral displacement and internal vertical displacement monitoring point. Using the adaptive moment estimation (Adam) optimization algorithm and the root mean square error (RMSE) model evaluation metric, the multilayer perceptron model, univariate input model, and multivariate input model are compared. This work shows that their RMSEs are 0.10611, 0.09966, and 0.11955, respectively.

The Qinghai Lake Basin (QLB), as a key component of the ecological security barrier on the Tibetan Plateau, is crucial for regional sustainable development due to the stability of its alpine agro-pastoral ecosystems. This study aims to systematically analyze the spatiotemporal evolution patterns and underlying driving mechanisms of eco-environmental quality (EEQ) in the QLB from 2001 to 2022. Based on Google Earth Engine (GEE) and long-term MODIS data, we constructed a Remote Sensing Ecological Index (RSEI) model to evaluate the EEQ dynamics. Geodetector (GD) was applied to quantitatively identify key driving factors and their interactions. The findings reveal: (1) The mean RSEI value increased from 0.46 in 2001 to 0.51 in 2022, showing a fluctuating improvement trend with significant transitions toward higher ecological quality grades; (2) spatially, a distinct “high-north-south, low-center” pattern emerged, with excellent-grade areas (4.77%) concentrated in alpine meadows and poor-grade areas (5.10%) mainly in bare rock regions; (3) 47.81% of the region experienced ecological improvement, whereas 16.34% showed degradation, predominantly above 3827 m elevation; and (4) GD analysis indicated natural factors dominated EEQ differentiation, with temperature (q = 0.340) and elevation (q = 0.332) being primary drivers. The interaction between temperature and precipitation (q = 0.593) exerted decisive control on ecological pattern evolution. This study provides an efficient monitoring framework and a spatially explicit governance paradigm for maintaining differentiated management and ecosystem stability in alpine agro-pastoral regions.