Applying Decision Trees to Examine the Nonlinear Effects of Multiscale Transport Accessibility on Rural Poverty in China

Accessibility plays an important role in alleviating rural poverty. Previous studies have explored the relationship between accessibility and poverty, but they offer limited evidence of collective influence multiscale transport (town-level, county-level, prefecture-level accessibility) its nonlinear effects on This study adopted gradient-boosting decision tree model to explore association threshold poverty incidence (RPI). We selected Huining, a poverty-stricken county China, as case study. The results show that collectively has larger predictive power than other variables. Specifically, town-level (12.97%) dominant predicting RPI, followed by county-level (9.50%) (7.38%). further identified effective ranges guide poverty-alleviation policy. Our help inform policy planning sustainable reduction vitalization.