Abstract
Global water cycling plays a fundamental role in the climate system, with the majority of terrestrial water ultimately sourced from the ocean. As oceanic moisture evaporates, it leaves a signature on sea surface salinity, allowing the salinity fields to be a predictor of terrestrial precipitation. This research is among the first in the published literature to assess the role of sea surface salinity for predictions on low-skill summertime subseasonal timescales for terrestrial precipitation predictions. Neural networks are trained with the CESM2 Large Ensemble using North Atlantic salinity anomalies to quantify predictability of U.S. Midwest summertime heavy rainfall events at 0- to 56-day leads. Using explainable artificial intelligence, salinity anomalies in the Caribbean Sea and Gulf of Mexico are shown to provide skill for subseasonal forecasts of opportunity. Further, to independently validate the CESM2-based findings, a moisture-tracking algorithm applied to ERA5 reanalysis data demonstrates that the regions of evaporation identified by neural networks directly provide moisture that precipitates in the Midwest.