<p>Identifying the key influencing factors of IWUE and formulating industrial water-saving policies are crucial for promoting green transformation and upgrading in the region. Existing studies mostly employ linear models to analyze the influencing factors of IWUE, which struggle to capture complex nonlinear relationships, interaction effects, and spatial heterogeneity among variables, resulting in an insufficient understanding of the underlying mechanisms. To address these gaps, this study uses panel data for 41 prefecture-level cities (leagues) in Northeast China from 2000 to 2022. It integrates the Super-SBM model, interpretable machine learning methods, and GTWR to construct an analytical framework that systematically reveals the spatiotemporal patterns, nonlinear driving mechanisms, and spatial differentiation characteristics of IWUE. Key findings show that IWUE increased from 0.25 in 2000 to 0.63 in 2022, rising from a medium-low to a medium-high efficiency level, with cumulative growth of 152%. Spatially, the region has shifted from being dominated by medium-low efficiency cities to one primarily composed of medium-high and high efficiency cities. Among all influencing factors, the IUI is the most critical and consistently positive driver, exhibiting an almost monotonically increasing effect. Furthermore, significant synergistic effects exist among the various factors. The magnitude and direction of each factor’s influence exhibit clear spatial heterogeneity, shaped primarily by local industrial structure, development stage, and resource endowment.</p>