Spatio-temporal characteristics and driving factor identification of precipitation use efficiency: Based on machine learning and SHAP analysis

Precipitation use efficiency (PUE) is a key indicator of the "carbon-water" coupling in ecosystems; research on its spatiotemporal distribution and the identification of its driving factors is of great significance for regional ecohydrological processes and resource management. This study focuses on the cold region of Northeast China, an important agricultural and natural ecological zone. Based on multi-source remote sensing data from 2001 to 2024, it employs the Theil-Sen trend estimation and Mann–Kendall significance tests to identify trends in PUE, and combined the Hurst index and coefficient of variation to analyze its future evolution. Furthermore, by integrating the SHAP explainable machine learning model framework, this study quantifies the multiscale driving contributions of climate, vegetation, and topographic factors to PUE and identifies the ecological thresholds of key factors. The results show that: (1) The spatial distribution of PUE exhibits a gradient pattern characterized by higher values in the northwest and lower values in the southeast. Interannual variations follow a three-phase pattern of “gradual increase, significant decline, and fluctuation at high levels,” with values ranging from 0.67 to 0.96 gC·m⁻²·mm⁻¹ . (2) Spatially, PUE is not only regulated by multiple individual factors, but the interactions among these factors further reinforce its patterns; temporally, PUE is jointly regulated by dynamic meteorological and vegetation factors, and key influencing factors exhibit significant nonlinear threshold responses. (3) The dominant driving mechanisms in regions with different PUE values exhibit significant heterogeneity: regions with low PUE values are primarily constrained by high evapotranspiration and weak water-holding capacity, whereas regions with high PUE values rely on efficient water conversion and utilization strategies under low-precipitation conditions. This study reveals the multiscale factors driving PUE in the cold regions of Northeast China and identifies key regulatory thresholds, providing quantitative evidence for regional “carbon-water” integrated management, precision-based vegetation restoration, and climate change adaptation strategies.