Influence of Irrigation Drivers Using Boosted Regression Trees: Kansas High Plains

Groundwater levels across parts of western Kansas have been declining at unsustainable rates due to pumping for agricultural irrigation despite water-saving efforts. Accelerating this decline is the complex landscape, consisting both categorical (e.g., management boundaries) and numerical crop prices) factors that drive decisions, making integrated water budget a challenge. Furthermore, these frequently change through time, rendering strategies outdated within relatively short time scales. This study uses boosted regression trees simultaneously analyze data against annual determine relative influence each factor on groundwater space time. In all, 45 key use variables covering approximately 19,000 wells were tested from 2006 2016 five categories: (1) management/policy, (2) hydrology, (3) weather, (4) land/agriculture, (5) economics. Study results showed all categories included among top 10 drivers irrigation, greatest came such as irrigated area per well, saturated thickness, soil permeability, summer precipitation, costs (depth table). Variables had little regional boundaries technology. The are further used target statistically lead volumes help develop robust strategy suggestions achieve goals region.