Environmental variables have a substantial effect on the reliability of soil organic carbon (SOC) mapping. However, it is still challenging to identify which environmental variables are effective in cropland SOC prediction in sandy, saline, and black soil regions. To address this issue, we used the principal component analysis (PCA) method for the feature selection of bands, spectral indexes, and terrain factors for each region. Based on the selection feature, we used global RF and local RF for SOC prediction for these three regions. Our results indicated that (1) climate factors, particularly mean annual precipitation and mean annual temperature, were the most effective predictors in SOC mapping across sandy, saline, and black soil regions, as indicated by their significant contribution to RF model performance (R² > 0.63); (2) followed by climate factors, the Transformed Vegetation Index (TVI) was consistently identified as the most influential variable for SOC prediction among spectral indexes in all three regions; (3) a local regression method based on RF models showed good performance compared to a global model; (4) desertification and salinization were the main reasons for the spatial differences in AH and DM&LD, respectively. The SOC of HL in black soil regions was consistent with the climate change trend because of the latitude difference. This study provides valuable information for constructing a more precise soil prediction strategy for cultivated land in sandy, saline, and black soil regions.

The accuracy of forest canopy height estimation is crucial for forest resource management and ecosystem carbon sequestration. However, existing approaches often face limitations in effectively integrating multisource remote sensing data, feature representation, and model learning strategies. To enhance the prediction performance of the model in complex terrain and multisource data environments, this study comprehensively used ICESat-2/ATLAS photon point clouds, Sentinel-2/MSI multispectral imagery, and SRTM-DEM to construct a remote sensing-driven multisource feature system, which eliminated redundant interference using permutation feature importance analysis. Additionally, a self-attention (SA) mechanism was introduced to strengthen high-dimensional feature representation. Three heterogeneous models, incorporating deep neural network (DNN), extreme gradient boosting (XGBoost), and residual network (ResNet), were independently applied for forest canopy height estimation and were further used as base learners, with a random forest as the meta-learner, and an SA-Blending heterogeneous ensemble model that combines a blending technique with an SA mechanism was proposed to enhance the accuracy of forest canopy height estimation. To evaluate the SA optimization strategy and the role of multisource fusion, this study used the original features, SA-optimized features, and multisource fusion features (i.e., the concatenation and fusion of original features and self-attention mechanism features) as inputs to comprehensively compare the performance of each single model and the integrated model. The results show that: (1) The self-attention mechanism significantly improves the prediction performance of heterogeneous models. Compared with original features inputs, the R² of DNN (SA-Only) and XGBoost (SA-Only) increased to 0.706 and 0.708, respectively, and the RMSE decreased to 1.691 m and 1.613 m. Although the R² for ResNet (SA-Only) decreased slightly to 0.699 and the RMSE increased to 1.712 m, the overall impact was not significant. (2) Under the condition of multisource fusion feature input, DNN+SA, XGBoost+SA, and ResNet+SA all demonstrated higher fitting accuracy and stability, verifying the enhancing effect of the SA mechanism on the association expression of multisource information. (3) The SA-Blending model achieved the best overall performance, with R² of 0.766 and RMSE of 1.510 m. It outperformed individual models and the SA-optimized model in terms of overall accuracy, stability, and robustness. The results can provide technical support for high-precision forest canopy height mapping and are of great significance for ecological monitoring applications.

Soil health is essential for food security, ecosystem stability, and sustainable development, yet its spatial heterogeneity and driving mechanisms remain insufficiently understood at regional scales. This study investigates soil health in Heilongjiang Province, China. A Soil Health Index (SHI) was constructed using eight indicators covering physical, chemical, and biological properties based on multi-source datasets at 1 km spatial resolution. A random forest (RF) model was applied to identify key environmental drivers, and Moran’s I and Getis–Ord Gi* statistics were used to analyze spatial clustering. The results showed that SHI values ranged from 0.19 to 0.70, with a mean of 0.45. The RF model achieved strong performance (R² = 0.6666, RMSE = 0.03184, MAE = 0.02372), significantly outperforming linear regression (R² ≈ 0.17). Significant spatial clustering was observed, where “hotspots” refer to statistically significant clusters of high SHI values, and “coldspots” indicate clusters of low SHI values based on Getis–Ord Gi* analysis. Climate factors (temperature and precipitation) and elevation were the dominant drivers. Significant spatial clustering was observed, with clear hotspot and coldspot patterns. These findings provide spatial evidence for sustainable land-use planning and zonal soil management. However, the analysis is limited by data resolution and model interpretability, which may affect the representation of fine-scale variability.