Examining Spatiotemporal Trends Of Drought In The Conterminous United States Using Self-Organizing Maps

Droughts can inflict long-lasting devastation on natural ecosystems and socio-economic sectors. In this study, we examine the spatiotemporal trends of drought using self-organizing maps (SOM), SOMs are a competitive learning subset of artificial neural networks (ANN) requiring unsupervised training of inputs. We used monthly Palmer Drought Severity Index (PDSI) values to identify existing clusters of wetting and drying patterns from 1895-2016. We created cartographic visualizations of the SOM output and conducted a subsequent time-series analysis to link with our spatial observations. Across most SOM patterns, we identified no significant changes of drying or wetting patterns over the last century for the greater part of the CONUS., however, we noted a statistically significant increase in drought patterns in Southwestern and Western U.S. over the study period. Our findings inform novel methods for quantification of historical drought and further support the notion that drought is region-specific.