Machine learning to extend and understand the sources and limits of water cycle predictability on subseasonal-to-decadal timescales in the Earth system

Abstract

Katherine Dagon\u200b1\u200b, Maria J. Molina\u200b1\u200b, Gerald A. Meehl\u200b1\u200b, Jadwiga H. Richter\u200b1\u200b, Elizabeth A. Barnes\u200b2\u200b, Judith Berner\u200b1\u200b, Julie M. Caron\u200b1\u200b, Will Chapman\u200b3\u200b, Gokhan Danabasoglu\u200b1\u200b, David John Gagne\u200b1\u200b, Sasha Glanville\u200b1\u200b, Sue Ellen Haupt\u200b1\u200b, Aixue Hu\u200b1\u200b, Zane Martin\u200b2\u200b, Kirsten Mayer\u200b2\u200b, Kathy Pegion\u200b4\u200b, Kevin Raeder\u200b1\u200b, Isla Simpson\u200b1\u200b, Aneesh Subramanian\u200b5\u200b, and Steve Yeager\u200b1 National Center for Atmospheric Research, Boulder, Colorado, \u200bColorado State University, Fort Collins, Colorado, \u200bScripps Institution of Oceanography, San Diego, California, \u200bGeorge Mason University, Fairfax, Virginia, \u200bUniversity of Colorado, Boulder, Colorado