Improving Statistical Prediction of Subseasonal CONUS Precipitation Based on ENSO and the MJO by Training With Large Ensemble Climate Simulations

Abstract Previous studies have highlighted the significant impacts of El Niño–Southern Oscillation (ENSO) and the Madden–Julian Oscillation (MJO) on wintertime precipitation over the contiguous United States (CONUS). Here, we demonstrate skillful statistical prediction of subseasonal precipitation over the CONUS using the information of ENSO and the MJO. Simple statistical tools, such as multiple linear regression, exhibit significant improvement in prediction when trained with large ensemble climate simulations, surpassing those trained solely on observational data. Despite the biases in ENSO and MJO teleconnections in the climate simulations, the abundance of data, exceeding observational records by 100 times, allows more robust statistical relationships to be established, leading to such improvement. The utilization of machine learning tools yields additional gains in prediction skill beyond multiple linear regression. ENSO emerges as a dominant contributor to prediction skill, surpassing the influence of the MJO, whose impact diminishes with increasing forecast lead time.