Analyzing land use changes (LUC) in both past and future scenarios is critical to optimize local ecology and formulate policies for sustainable development. We analyzed LUC characteristics in Huaibei City, China from 1985 to 2020, and used the CLUE-S and PLUS models to simulate LU in 2020. Then, we compared the accuracy of the simulation phase and chose the PLUS model to project LU under four scenarios in 2025. The results showed the following: (1) Farmland and grassland areas decreased from 1985 to 2020, while forestland, water, and construction land increased. (2) The LU types in the region are explained well by the driving factors, with all receiver operation characteristic (ROC) values greater than 0.8. (3) The kappa indices for CLUE-S and PLUS analog modeling were 0.727 and 0.759, respectively, with figure of merit (FOM) values of 0.109 and 0.201. (4) Under the farmland and ecological protection scenario (FEP), farmland and forestland areas are protected, increasing by 1727.91 hm² and 86.22 hm², respectively, while construction land decreases by 2001.96 hm². These results confirm that PLUS is significantly better than the CLUE-S model in modeling forestland and water, and slightly better than the CLUE-S model in modeling the rest of the LU type. Urban sustainability is strong in the scenario FEP.

Soil organic matter (SOM) is a key index of soil fertility. Visible and near-infrared (VNIR, 350–2500 nm) reflectance spectroscopy is an effective method for modeling SOM content. Characteristic wavelength screening and spectral transformation may improve the performance of SOM prediction. This study aimed to explore the optimal combination of characteristic wavelength selection and spectral transformation for hyperspectral modeling of SOM. A total of 219 topsoil (0–20 cm) samples were collected from two soil types in the East China. VNIR reflectance spectra were measured in the laboratory. Firstly, after spectral transformation (inverse-log reflectance (LR), continuum removal (CR) and first-order derivative reflectance (FDR)) of VNIR spectra, characteristic wavelengths were selected by competitive adaptive reweighted sampling (CARS) and uninformative variables elimination (UVE) algorithms. Secondly, the SOM prediction models were constructed based on the partial least squares regression (PLSR), random forest (RF) and support vector regression (SVR) methods using the full spectra and selected wavelengths, respectively. Finally, optimal SOM prediction models were selected for two soil types. The results were as follows: (1) The CARS algorithm screened 40–125 characteristic wavelengths from the full spectra. The UVE algorithm screened 105–884 characteristic wavelengths. (2) For two soil types and full spectra, CARS and UVE improved the SOM modeling precision based on the PLSR and SVR methods. The coefficient of determination (R²) value in the validation of the CARS-PLSR (PLSR model combined with CARS) and CARS-SVR (SVR model combined CARS) models ranged from 0.69 to 0.95, and the relative percent deviation (RPD) value ranged from 1.74 to 4.31. Lin’s concordance correlation coefficient (LCCC) values ranged from 0.83 to 0.97. The UVE-PLSR and UVE-SVR models showed moderate precision. (3) The PLSR and SVR modeling accuracies of Paddy soil were better than those for Shajiang black soil. RF models performed worse for both soil types, with the R² values of validation ranging from 0.22 to 0.68 and RPD values ranging from 1.01 to 1.60. (4) For Paddy soil, the optimal SOM prediction models (highest R² and RPD, lowest root mean square error (RMSE)) were CR-CARS-PLSR (R² and RMSE: 0.97 and 1.21 g/kg in calibration sets, 0.95 and 1.72 g/kg in validation sets, RPD: 4.31) and CR-CARS-SVR (R² and RMSE: 0.98 and 1.04 g/kg in calibration sets, 0.91 and 2.24 g/kg in validation sets, RPD: 3.37). For Shajiang black soil, the optimal SOM prediction models were LR-CARS-PLSR (R² and RMSE: 0.95 and 0.93 g/kg in calibration sets, 0.86 and 1.44 g/kg in validation sets, RPD: 2.62) and FDR-CARS-SVR (R² and RMSE: 0.99 and 0.45 g/kg in calibration sets, 0.83 and 1.58 g/kg in validation sets, RPD: 2.38). The results suggested that the CARS algorithm combined CR and FDR can significantly improve the modeling accuracy of SOM content.

Topographic relief is a key factor limiting population distribution and economic development in mountainous areas, especially in the transition zone from mountains to plains. Taking the southern Anhui mountainous area as an example, based on the digital elevation model (DEM) with a resolution of 30 m, we used ‘quadratic’ mean change-point analysis to calculate the optimal statistical unit, and then extracted the topographic relief. Taking the county as the unit of analysis, two indicators of population density and economic density were selected. Spatial statistics and correlation analysis were used to quantitatively analyze the impact of topographic relief on population and economy. Finally, the impact of slope and elevation was analyzed. The following results were obtained. (1) The topography of the study area was dominated by medium relief (200–500 m), followed by small relief (70–200 m), flat (0–30 m), and slight relief (30–70 m), and a small proportion of large relief (≥500 m). (2) The impact of topographic relief on population and economy was slightly stronger than that of slope and elevation. The impact on population distribution was stronger than that on economic development. The impact on primary industry was stronger than that on secondary and tertiary industries. (3) In the southern Anhui mountainous area, 72.35% of the population and 76.72% of GDP were distributed in the area with a topographic relief of 155 m or less, while the land area only accounted for 43.93%. The area with a topographic relief greater than 245 m accounted for 28.76%, but only 10.69% of the population, and only 8.34% of GDP. The population distribution and economic development were obviously concentrated in the low topographic relief area. However, the characteristics of high topographic relief not only hindered the agricultural mechanization and limited the development of the primary industry, but also had a significant impact on infrastructure development, investment, and industrial layout, thus weakening regional economic advantages. In the future, the economic level of these areas needs to be improved.

This study aimed to evaluate and compare the performances of the random forest (RF) and support vector regression (SVR) models combined with different feature selection methods, including recursive feature elimination (RFE), simulated annealing feature selection (SAFS), and selection by filtering (SBF) in predicting soil pH in Anhui Province, East China. We also used the ALL original features to build the RF and SVR models as a comparison. A total of 140 samples were selected, following the principles of randomness, uniformity, and representativeness, to consider the combination of landscape elements, such as topography, parent material, and land use. Auxiliary data, including climatic, topographic, and vegetation indexes, were used for predicting soil pH. The results showed that compared with the use the ALL original modeling features (ALL-RF, ALL-SVR), the combination of the three feature selection algorithms with RF and SVR can eliminate some redundant features and effectively improve the prediction accuracy of the soil pH model. For the RF model, the RMSE and the MAE of the calibration of the RFE-RF model were 0.73 and 0.57 and had the highest R² in four different RF models. The testing set of the RFE-RF model had an R² of 0.61, which was better than that of the ALL-RF (R² = 0.45) model and lower than those of the SAFS-RF (R² = 0.71) and SBF-RF (R² = 0.69) models. For the SVR model, the RFE-RF model was more robust and had better generalization ability. The accuracy of digital soil mapping can be improved through feature selection.

Monitoring the spatio-temporal dynamics of desertification is critical for desertification control. Using the Urat front flag as the study area, Landsat remote sensing images between 2010 and 2020 were selected as data sources, along with MOD17A3H as auxiliary data. Additionally, RS and GIS theories and methods were used to establish an Albedo–NDVI feature space based on the normalized difference vegetation index (NDVI) and land surface albedo. The desertification difference index (DDI) was developed to investigate the dynamic change and factors contributing to desertification in the Urat front banner. The results show that: ① the Albedo–NDVI feature space method is effective and precise at extracting and classifying desertification information, which is beneficial for quantitative analysis and monitoring of desertification; ② from 2010 to 2020, the spatial distribution of desertification degree in the Urat front banner gradually decreased from south to north; ③ throughout the study period, the area of moderate desertification land increased the most, at an annual rate of 8.2%, while the area of extremely serious desertification land decreased significantly, at an annual rate of 9.2%, indicating that desertification degree improved during the study period; ④ the transformation of desertification types in Urat former banner is mainly from very severe to moderate, from severe to undeserted, and from mild to undeserted, with respective areas of 22.5045 km², 44.0478 km², and 319.2160 km². Over a 10-year period, the desertification restoration areas in the study area ranged from extremely serious desertification to moderate desertification, from serious desertification to non-desertification, and from weak desertification to non-desertification, while the desertification aggravation areas ranged mainly from serious desertification to moderate desertification; ⑤ NPP dynamic changes in vegetation demonstrated a zonal increase in distribution from west to east, and significant progress was made in desertification control. The change in desertification has accelerated significantly over the last decade. Climate change and irresponsible human activities have exacerbated desertification in the eastern part of the study area.

Soil organic matter (SOM) is an important component of soil and plays an important role in improving the soil’s physical and chemical properties. Ascertaining the spatial distribution of soil organic matter and its main controlling factors in the context of provincial scale farming is of important guiding significance for soil carbon sequestration, emission reduction and sustainable utilization. Using 257 soil profiles from the second soil survey in Shandong Province, GIS, we applied geostatistical methods to study the spatial distribution characteristics of SOM in topsoil. In addition, correlation and regression analyses were used to explore the main controlling factors over the spatial variation of SOM. The results showed that the mean amount of SOM in Shandong province ranged from 1.20–74.90 g·kg⁻¹, with a coefficient of variation of 73.52%, which is a medium level of variation. The distribution of SOM in the study area was patchy, with higher levels of organic matter in the central, eastern, and northern parts, and lower levels of organic matter in the south-west. The comprehensive explanatory ability of all factors reached 52.30%. Soil type and parent material were the main controlling factors for the spatial variability of SOM in the Shandong Province, followed by soil texture and land use type, with topography and climatic factors having relatively little influence.