Abstract:Green control technology is one of the important means to realize the green development of agriculture, but farmers, as direct users of technology, have low initiative and enthusiasm in adopting technology. Cooperatives play a radiating role and improve the adoption rate of farmers by providing them with a variety of services. Based on the data of 498 farmers in the Sichuan project area of IFAD project, Logit model and random forest model in machine learning were used to analyze the impact of cooperatives on the adoption of green control technology by members and non-members of cooperatives from the perspective of the number and type of services. The results showed that: (1) the numbers of cooperative services provided by cooperatives had significant positive impacts on the adoption of green control technology by farmers, and the probability of adoption of green control technology by members was higher than that of non-members. (2) The impact of agricultural services, technical services and sales services on the adoption of technology by members and non-members was complementary. (3) Sales service and technical training had the highest influence on the adoption of green control technology by members and non-members respectively. Therefore, cooperatives should give full play to their radiation-driven role, provide targeted services to members and non-members, promote the adoption rate of green control technology, and promote green agricultural production.