Soil organic carbon (SOC) is a crucial indicator of soil quality and carbon cycling. While remote sensing and machine learning enable regional scale SOC prediction, most studies rely on vegetation indices (VIs) derived from bare-soil periods, potentially neglecting vegetation–soil interactions during crop growth. Given the bidirectional relationship between SOC and crop growth, we hypothesized that using crop-lush period VIs (VIs_lush) instead of bare-soil period VIs (VIs_bare) would increase the inversion accuracy. To test this hypothesis, we chose the cropland area in Liaoning Province as the study area and developed three modelling strategies (MS-1: VIs_lush + other features; MS-2: VIs_bare + other features; MS-3: without VIs) using Landsat 8 imagery, topographic and precipitation data, and ensemble learning models (XGBoost, RF, and AdaBoost), with SHapley Additive exPlanations (SHAP) analysis for variable interpretation. We found that 1) all models achieved their highest performance under MS-1, with XGBoost outperforming the others across all modelling strategies; 2) for XGBoost, MS-1 yielded the highest inversion accuracy (R² = 0.84, RMSE = 2.22 g·kg⁻¹, RPD = 2.49, and RPIQ = 3.25); compared with MS-2, MS-1 reduced the RMSE by 0.31 g·kg⁻¹, increased R² from 0.77 to 0.84, and reduced the RPD by 0.31 and the RPIQ by 0.40, and compared with MS-3, MS-1 reduced the RMSE by 0.41 g·kg⁻¹, increased R² from 0.79 to 0.84, and reduced the RPD by 0.39 and the RPIQ by 0.51; 2) SHAP analysis confirmed that VIs_lush contributed more than VIs_bare, supporting the rationale of using lush-period imagery; and 3) Liaoning Province exhibited distinct SOC spatial patterns (mean: 13.08 g·kg⁻¹), with values ranging from 2.19 g·kg⁻¹ (sandy central–western area) to 33.86 g·kg⁻¹ (eastern mountains/coast). This study demonstrates that integrating growth stage-specific VIs with ensemble learning can significantly enhance regional-scale SOC prediction.

Soil organic carbon (SOC) is a crucial indicator of soil quality and carbon cycling. While remote sensing and machine learning enable regional scale SOC prediction, most studies rely on vegetation indices (VIs) derived from bare-soil periods, potentially neglecting vegetation–soil interactions during crop growth. Given the bidirectional relationship between SOC and crop growth, we hypothesized that using crop-lush period VIs (VIs_lush) instead of bare-soil period VIs (VIs_bare) would increase the inversion accuracy. To test this hypothesis, we chose the cropland area in Liaoning Province as the study area and developed three modeling strategies (MS-1: VIs_lush + other features; MS-2: VIs_bare + other features; and MS-3: without VIs) using Landsat 8 imagery, topographic and precipitation data, and ensemble learning models (XGBoost, RF, and AdaBoost), with SHapley Additive exPlanations (SHAP) analysis for variable interpretation. We found that (1) all models achieved their highest performance under MS-1, with XGBoost outperforming the others across all modeling strategies; (2) for XGBoost, MS-1 yielded the highest inversion accuracy (R² = 0.84, RMSE = 2.22 g·kg⁻¹, RPD = 2.49, and RPIQ = 3.25); compared with MS-2, MS-1 reduced the RMSE by 0.31 g·kg⁻¹, increased R² from 0.77 to 0.84, and reduced the RPD by 0.31 and the RPIQ by 0.40, and compared with MS-3, MS-1 reduced the RMSE by 0.41 g·kg⁻¹, increased R² from 0.79 to 0.84, and reduced the RPD by 0.39 and the RPIQ by 0.51; (3) based on the SHAP analysis of the three modeling strategies, it is considered that precipitation, terrain and terrain analysis results are important indicators for SOC content inversion, and it is confirmed that VIs_lush contributed more than VIs_bare, supporting the rationale of using lush-period imagery; and (4) Liaoning Province exhibited distinct SOC spatial patterns (mean: 13.08 g·kg⁻¹), with values ranging from 2.19 g·kg⁻¹ (sandy central–western area) to 33.86 g·kg⁻¹ (eastern mountains/coast). This study demonstrates that integrating growth stage-specific VIs with ensemble learning can significantly enhance regional-scale SOC prediction.

Geochemical measurements of stream sediments are practical for small-scale mineral exploration. However, traditional grid interpolation methods cause element concentrations to diffuse and smooth out anomalies, particularly in complex terrains, making it challenging to reflect the actual distribution of elements accurately. We applied the Dynamic Enhanced Weighted Drainage Catchment Basin (DE-WDCB) method to enhance the retention and identification of local anomalies by limiting the scope of analysis to specific drainage units. This method reduces interference from varying background values across different watersheds, effectively enhancing geochemical element anomalies and aligning better with geomorphic conditions. The DE-WDCB method was tested in the Duobaoshan–Heihe area, a significant copper polymetallic mineral district in northeastern China. Compared with traditional grid interpolation methods, the DE-WDCB method retained and strengthened low and weak abnormal information of favorable mineralization elements, particularly in the Luotuowaizi area. The method demonstrated a higher spatial coverage rate with mineral points and a more vital ore-indicating ability. Specifically, the DE-WDCB method identified anomalies with a mean accuracy of 63.57% (p < 0.05, 95% CI: 47.64%–79.50%), compared to 50.53% for traditional methods. In conclusion, in regions with a complex topography and watershed differences, the DE-WDCB method effectively reduces local geochemical background interference, accurately identifies low and weak geochemical anomalies, and better reflects the actual distribution of elements. This makes it a significantly advantageous method for geochemical anomaly extraction, delineating higher-confidence exploration targets in the Sandaowan–Luotuowaizi area in the east and the triangular area between Duobaoshan, Yubaoshan, Sankuanggou, and the midstream highlands of the Guanbird River in the west.

Land-use change substantially contributes to carbon emissions, yet systematic research on complex human–environment interactions in old industrial bases remains scarce. Here, we integrated multi-temporal land-use data and socio-economic statistics from 1990 to 2023 to analyze the spatiotemporal dynamics and drivers of land-use carbon emissions in Northeast China. The land-use transfer matrix, the carbon emission coefficient, exploratory spatiotemporal data analysis (ESTDA), standard deviational ellipses, and modified Kaya–LMDI models were applied. Construction land area expanded by 120%, with its share of total emissions increasing from 87% to 95%. Meanwhile, forest and grassland shrank, reducing their carbon sink capacity and increasing their net carbon emissions 1.9-fold. Spatially, emissions showed a weak global correlation but strong local lock-in (i.e., persistent stability of local spatial patterns over time), with the emission center of gravity shifting southwestward. Economic development was the dominant positive driver (provincial contribution rates: 275–529%), whereas energy intensity was the main mitigating factor (up to −409%). Population loss exerted a slight negative contribution, while energy structure showed only a weak inhibitory effect (−9.1%), reflecting the region’s path-dependent lock-in to fossil fuels. This study provides a scientific basis for differentiated carbon management strategies in Northeast China and analogous regions.

Urban spatial patterns regulate microclimates, yet those nonlinear interactive actions of 2D landscape patterns and 3D building morphology on land surface temperature (LST) among diverse urban functional zones (UFZs) remain insufficiently quantified. Using Shenyang as the case study, this study coupled Bayesian-optimized LightGBM and GeoShapley to disentangle these driving mechanisms. The models demonstrated high predictive accuracy (R² > 0.84 across all UFZs). Results show high-temperature zone proportions ranking as: commercial (17.93%) > public service (11.40%) > residential (8.70%) > industrial (3.97%). Further factor analysis reveals that while geographic location is the predominant overall driver, after removing this baseline effect, residential, public service, and commercial zones are mainly regulated by MNDWI and NDVI, while industrial zones are dominated by Spatial Congestion Degree (SCD) and Floor Area Ratio (FAR). Morphological metrics exhibit clear ecological thresholds: residential zones show turning points at FAR 1.19 and NDVI 0.13; commercial zones see SCD’s cooling effect reverse to warming beyond 0.27; industrial zones experience sharp deterioration when SCD and FAR exceed 0.09 and 0.51, respectively. These findings demonstrate the necessity of UFZ-based differentiated spatial regulation and provide actionable thresholds for climate-adaptive urban planning.