A Hybrid Approach to Atmospheric Modeling That Combines Machine Learning With a Physics‐Based Numerical Model. (28th February 2022)

• Record Type: Journal Article
• Authors: Arcomano, Troy; Szunyogh, Istvan; Wikner, Alexander; Pathak, Jaideep; Hunt, Brian R.; Ott, Edward
• Is Part Of: Journal of advances in modeling earth systems. Volume 14:Number 3(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-02-28
• Subjects: Geological modeling -- Periodicals; Climatology -- Periodicals; Geochemical modeling -- Periodicals; 551.5011
• DOI: 10.1029/2021MS002712
• Languages: English
• ISSNs: 1942-2466

Abstract

Abstract: This paper describes an implementation of the combined hybrid‐parallel prediction (CHyPP) approach of Wikner et al. (2020), https://doi.org/10.1063/5.0005541 on a low‐resolution atmospheric global circulation model (AGCM). The CHyPP approach combines a physics‐based numerical model of a dynamical system (e.g., the atmosphere) with a computationally efficient type of machine learning (ML) called reservoir computing to construct a hybrid model. This hybrid atmospheric model produces more accurate forecasts of most atmospheric state variables than the host AGCM for the first 7–8 forecast days, and for even longer times for the temperature and humidity near the earth's surface. It also produces more accurate forecasts than a model based only on ML, or a model that combines linear regression, rather than ML, with the AGCM. The potential of the CHyPP approach for climate research is demonstrated by a 10‐year long hybrid model simulation of the atmospheric general circulation, which shows that the hybrid model can simulate the general circulation with substantially smaller systematic errors and more realistic variability than the host AGCM. Plain Language Summary: This paper presents a computationally efficient novel approach to construct a hybrid model of the atmosphere by combining a physics‐based model of the global atmospheric circulation with a machine learning component. The primary purpose of the hybrid model is to produce quantitative weather forecasts on the same grid as the physics‐based model. It is found that the hybrid model produces more accurate forecasts than the host physics‐based model for the first 7–8 forecast days for most forecast variables, and for even longer times for the temperature and humidity near the Earth's surface. Furthermore, the hybrid model is found to simulate the climate with substantially smaller systematic errors and more realistic temporal variability than the host model. Key Points: A hybrid model incorporating machine learning produces more accurate forecasts and more realistic climate than the host physics‐based model The hybrid model states are more realistically balanced and have substantially lower biases than the host model The hybrid model produces more realistic atmospheric variability than the host model at time scales shorter than about a week