Detecting the linkage between arable land use and poverty using machine learning methods at global perspective

Eradicating extreme poverty is one of the UN's primary sustainable development goals (SDG). Arable land related to eradicating (SDG1) and hunger (SDG2). However, linkage between arable use reduction ambiguous has seldom been investigated globally. Six indicators agricultural inputs, crop intensification extensification were used explore relationship poverty. Non-parametric machine learning methods analyze agriculture at global scale, including classification regression tree (CART) random forest models. We found that yield gap, fertilizer consumption potential cropland ratio in protected areas correlated with Developing countries usually had a actual less than 0.33 7.31 kg/ha. Overall, extensification, inputs level.