Journal ArticleTechnical note: Deep learning for creating surrogate models of precipitation in Earth system modelsWeber, Theodore; Corotan, Austin; Hutchinson, Brian; Kravitz, Ben; Link, RobertnullAbstract. We investigate techniques for using deep neural networks to produce surrogatemodels for short-term climate forecasts. A convolutional neural network istrained on 97 years of monthly precipitation output from the 1pctCO2 run (theCO2 concentration increases by 1 % per year) simulated by the second-generation Canadian Earth System Model (CanESM2). The neural network clearly outperforms a persistence forecast anddoes not show substantially degraded performance even when the forecast lengthis extended to 120 months. The model is prone to underpredicting precipitationin areas characterized by intense precipitation events. Scheduled sampling(forcing the model to gradually use its own past predictions rather than groundtruth) is essential for avoiding amplification of early forecasting errors.However, the use of scheduled sampling also necessitates preforecasting(generating forecasts prior to the first forecast date) to obtain adequateperformance for the first few prediction time steps. We document the trainingprocedures and hyperparameter optimization process for researchers who wish toextend the use of neural networks in developing surrogate models.2020-01-0110249444Atmospheric Chemistry and Physics2042303 to 23171680-7324https://doi.org/10.5194/acp-20-2303-20201931641National Science Foundation