Search

The accurate prediction of the spatial variability for soil water content (SWC) in farmland is essential for water resource management and sustainable agricultural development. However, natural factors introduce uncertainty and result in poor alignment when predicting farmland SWC, leading to low accuracy. To address this, this study introduced a novel indicator: landscape indices. These indices include the largest patch index (LPI), edge density (ED), aggregation index (AI), patch cohesion index (COH), contagion index (CON), landscape division index (DIV), percentage of like adjacencies (PLA), Shannon evenness index (SHEI), and Shannon diversity index (SHDI). A Bayesian optimization–deep forest (BO–DF) model was developed to leverage these indices for predicting the spatial variability of SWC. Statistical analysis revealed that landscape indices exhibited skewed distributions and weak linear correlations with SWC (r < 0.2). Despite this, incorporating landscape index variables into the BO–DF model significantly improved prediction accuracy, with R2 increasing by 35.85%. This model demonstrated a robust nonlinear fitting capability for the spatial variability of SWC. Spatial mapping of SWC using the BO–DF model indicated that high-value areas were predominantly located in the eastern and southern regions of the Yellow River Delta in China. Furthermore, the SHapley additive explanation (SHAP) analysis highlighted that landscape indices were key drivers in predicting SWC. These findings underscore the potential of landscape indices as valuable variables for spatial SWC prediction, supporting regional strategies for sustainable agricultural development. [ABSTRACT FROM AUTHOR]

The spatial prediction of soil CO2 flux is of great significance for assessing regional climate change and high-quality agricultural development. Using a single satellite to predict soil CO2 flux is limited by climatic conditions and land cover, resulting in low prediction accuracy. To this end, this study proposed a strategy of multi-source spectral satellite coordination and selected seven optical satellite remote sensing data sources (i.e., GF1-WFV, GF6-WFV, GF4-PMI, CB04-MUX, HJ2A-CCD, Sentinel 2-L2A, and Landsat 8-OLI) to extract auxiliary variables (i.e., vegetation indices and soil texture features). We developed a tree-structured Parzen estimator (TPE)-optimized extreme gradient boosting (XGBoost) model for the prediction and spatial mapping of soil CO2 flux. SHapley additive explanation (SHAP) was used to analyze the driving effects of auxiliary variables on soil CO2 flux. A scatter matrix correlation analysis showed that the distributions of auxiliary variables and soil CO2 flux were skewed, and the linear correlations between them (r < 0.2) were generally weak. Compared with single-satellite variables, the TPE-XGBoost model based on multiple-satellite variables significantly improved the prediction accuracy (RMSE = 3.23 kg C ha−1 d−1, R2 = 0.73), showing a stronger fitting ability for the spatial variability of soil CO2 flux. The spatial mapping results of soil CO2 flux based on the TPE-XGBoost model revealed that the high-flux areas were mainly concentrated in eastern and northern farmlands. The SHAP analysis revealed that PC2 and the TCARI of Sentinel 2-L2A and the TVI of HJ2A-CCD had significant positive driving effects on the prediction accuracy of soil CO2 flux. The above results indicate that the integration of multiple-satellite data can enhance the reliability and accuracy of spatial predictions of soil CO2 flux, thereby supporting regional agricultural sustainable development and climate change response strategies. [ABSTRACT FROM AUTHOR]