Rice yield is essential to global food security under increasingly frequent and severe climate change events. Spatial analysis of rice yields becomes more critical for regional action to ensure yields and reduce climate impacts. However, the understanding of the spatially varied geographical, climate, soil, and environmental factors of rice yields needs to be improved, leading to potentially biased local rice yield prediction and responses to climate change. This study develops a spatial machine learning-based approach that integrates machine learning and spatial stratified heterogeneity models to identify the determinants and spatial interactions of rice yields in the main rice-producing areas of China, the world’s largest rice-producing nation. A series of satellite remote sensing-derived variables are collected to characterize varied geographical, climate, soil, and environmental conditions and explain the spatial disparities of rice yields. The first step is to explore the spatial clustering patterns of the rice yield distributions using spatially global and local autocorrelation models. Next, a Geographically Optimal Zones-based Heterogeneity (GOZH) model, which integrates spatial stratified heterogeneity models and machine learning, is employed to explore the power of determinants (PD) of individual spatial variables in influencing the spatial disparities of rice yields. Third, geographically optimal zones are identified with the machine learning-derived optimal spatial overlay of multiple geographical variables. Finally, the overall PD of various variables affecting rice yield distributions is calculated using the multiple variables-determined geographically optimal zones and the GOZH model. The comparison between the developed spatial machine learning-based approach and previous related models demonstrates that the GOZH model is an effective and robust approach for identifying the spatial determinants and their spatial interactions with rice yields. The identified spatial determinants and their interactions are essential for enhancing regional agricultural management practices and optimizing resource allocation within diverse main rice-producing regions. The comprehensive understanding of the spatial determinants and heterogeneity of rice yields of this study has a broad impact on agricultural strategies and food security.

Mine tailings have shown viability as the fine–grained layer in a capillary barrier structure for controlling acid mine drainage in a circular economy. Their saturated hydraulic conductivities (k_sat) under wetting–drying cycles and freeze–thaw cycles remain unexplored. In this study, modified tailings with a weight ratio of 95:5 (tailings/hydrodesulfurization (HDS) clay from waste–water treatment) and an initial water content of 12% were used. The k_sat of specimens was measured after up to 15 wetting–drying cycles, each lasting 24 h, with a drying temperature of 105 °C. The k_sat for wetting–drying cycles decreased from 3.9 × 10⁻⁶ m/s to 9.5 × 10⁻⁷ m/s in the first three cycles and then stabilized in the subsequent wetting–drying cycles (i.e., 5.7 × 10⁻⁷ m/s–6.3 × 10⁻⁷ m/s). Increased fine particles due to particle breakage are the primary mechanism for the k_sat trend. In addition, the migration of fines and their preferential deposition near the pore throat area may also promote this decreasing trend through the shrinking and potentially clogging–up of pore throats. This could be explained by the movement of the meniscus, increased salinity, and, subsequently, the shrinkage of the electrical diffuse layer during the drying cycle. Similar specimens were tested to measure k_sat under up to 15 freeze–thaw cycles with temperatures circling between −20 °C and 20 °C at 12 h intervals. Compared to the untreated specimen (i.e., 3.8 × 10⁻⁶ m/s), the k_sat after three freeze–thaw cycles decreased by 77.6% (i.e., 8.5 × 10⁻⁷ m/s) and then remained almost unchanged (i.e., 5.6 × 10⁻⁷ m/s–8.9 × 10⁻⁷ m/s) in subsequent freeze–thaw cycles. The increased fine grain content (i.e., 3.1%) can be used to explain the decreased k_sat trend. Moreover, the migration of fines toward the pore throat area, driven by the advancing and receding of ice lens fronts and subsequent deposition at the pore throat, may also contribute to this trend.

Acid mine drainage (AMD) poses significant environmental and health risks due to its high acidity and elevated metal and sulfate contents. Previous studies have primarily focused on short-term AMD monitoring, with limited attention paid to long-term, spatially resolved datasets and predictive modeling. In this 3.5-year study, six wells down-stream of a mine waste rock pile were monitored, and 132 sets of associated water quality (AWQ), geological (GEO), and climate history (CH) parameters were compiled to develop predictive models for Fe, Cu, and Zn concentrations. Random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM) algorithms were applied using different combinations of input variables. The combined AWQ-GEO-CH dataset achieved the best overall performance, with XGBoost yielding the highest R² values for Fe (0.81) and Cu (0.77), and SVM performing best for Zn (0.94). CH variables, particularly precipitation and evaporation over 60-day periods, strongly influenced metal concentrations by driving hydrological and solute redistribution processes. AWQ parameters, especially F⁻ and S²⁻, were key predictors for Fe and Zn and ranked second for Cu, likely due to shared upstream sources and coupled geochemical processes such as FeF₃ dissolution. The most impactful GEO factor was the installation of a vertical barrier, which reduced metal concentrations by 73–80%. These findings highlight the value of integrating multi-source datasets with ML for long-term AMD prediction and management.