A Study on Nonlinear Characteristics and Interaction Effects in Farmers’ Adoption of Agricultural Technologies Based on an Improved Technology Acceptance Model and Explainable Artificial Intelligence

Against the backdrop of China’s rural revitalization, understanding the factors influencing farmers’ agricultural technology adoption behavior is crucial for enhancing such adoption. Therefore, exploring the decision-making logic behind farmers’ agricultural technology adoption behavior is of paramount importance. This study, conducted among 482 typical farming households in the Chengdu Plain of Sichuan Province, China, introduced the Random Forest (RF) algorithm into an Improved TAM. Combined with SHAP and PDP techniques, it identified 21 influencing factors and their nonlinear interaction mechanisms. Key findings include the following: (1) Adoption rates stood at only 14.3%, exhibiting a pronounced “advantage-oriented” pattern favoring male farmers, middle-aged/young adults, and higher-income groups; (2) Level of agricultural production tools and technology (C1) and Agricultural product sales channels (C2) emerged as core drivers, with C1 presenting a significant “technology threshold effect”—adoption probability surged from 0.1 to over 0.35 during intelligent technology transitions; (3) Monthly household income level (B4) effectively mitigates risk aversion among elderly farmers, revealing the critical role of Age (A2) in decision-making and enabling a complementary relationship between experience and technology; (4) Self-learning and training proficiency in agricultural technology (F1) reflects that excessive technological complexity triggers resistance and blocks adoption, while Highest educational attainment in the household (B1) and Number of educated family members (B2) exhibit nonlinear peak characteristics influenced by “brain drain” due to labor migration. These findings not only expand the theoretical application of machine learning in studying farmer behavior but also provide granular insights for overcoming the “last mile” bottleneck in agricultural technology dissemination.