The US Great Plains, spanning over 1,300 miles from the US-Canada border to Texas, plays a vital role in supporting human livelihoods, wildlife, and natural resources. Water availability, largely driven by seasonal precipitation, is crucial for ecosystems and agriculture in this region. Pluvial years in the Great Plains are influenced by synoptic-scale processes, with distinct patterns in the southern and northern regions. Wet periods are enhanced when the Pacific decadal oscillation (PDO) and El Niño–Southern Oscillation (ENSO) are both in their warm phases. The Pacific jet stream and the Great Plains Low Level Jet (GPLLJ) are significant drivers of precipitation, influenced by ENSO, Pacific–North American teleconnection pattern, and Atlantic SST anomalies. Despite these known influences, robust predictions of precipitation on seasonal and longer timescales remain challenging. To address this gap, our research aims to improve mechanistic understanding of important large-scale forcing and regional moisture transport and thereby improving predictability. We identify distinct spatial clusters of seasonal precipitation with similar variability for the Great Plains region and examine large-scale drivers like sea surface temperatures, and atmospheric flow and moisture transport patterns for these clusters. Our analysis aims to unravel causal linkages, particularly during the warm and cold seasons, to enhance precipitation forecasts and assess predictability across timescales. Using a Classification and Regression Trees (CART) approach, we seek to understand the mechanisms driving regional moisture transport which will inform the development of a modeling framework for improved predictions.