Digital‐Green Collaborative Transformation and Agricultural Economic Resilience: Evidence From a Double Machine Learning Model

Industrial pollution governance and the strengthening of agricultural resilience are typically pursued in parallel rather than in coordination. This study argues that the digital‐green collaborative transformation (DGCT) of heavily polluting enterprises can enhance agricultural economic resilience (AER) through cross‐sector spillover effects arising from more efficient factor allocation. Using panel data on Chinese A‐share listed heavily polluting enterprises from 2011 to 2023, we employ a double machine learning approach to estimate the impact of DGCT on AER. The results indicate that DGCT significantly improves AER, and the finding remains robust across multiple specification checks, including alternative machine learning algorithms, alternative dependent variables, and changes in sample size. Further analysis identifies three underlying channels: reduced financing constraints, regional industrial upgrading, and higher total factor productivity. The positive effect is particularly strong in non‐coastal regions, areas outside major economic circles, and major grain‐producing and grain‐producing‐marketing‐balanced regions. In addition, government subsidies and more developed factor markets strengthen the resilience‐enhancing effect of DGCT. Overall, this study broadens understanding of digital‐green integration and provides empirical support for policies aimed at promoting coordinated industrial and agricultural resilience.