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 Furthermore, these factors frequently change through time, rendering management strategies outdated or irrelevant within relatively short timescales.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