Accelerating Atmospheric Gravity Wave Simulations Using Machine Learning: Kelvin‐Helmholtz Instability and Mountain Wave Sources Driving Gravity Wave Breaking and Secondary Gravity Wave Generation

Abstract Gravity waves (GWs) and their associated multi‐scale dynamics are known to play fundamental roles in energy momentum transport deposition processes throughout the atmosphere. We describe an initial machine learning model—the Compressible Atmosphere Model Network (CAM‐Net). CAM‐Net is trained on high‐resolution simulations by state‐of‐the‐art model Complex Geometry (CGCAM). Two applications a Kelvin‐Helmholtz instability source mountain wave generation, propagation, breaking, Secondary GW (SGW) generation two wind environments described here. Results show that can capture key 2‐D modeled CGCAM with high precision. Spectral characteristics of primary SGWs estimated agree well those from CGCAM. Our results achieve several order‐of‐magnitude acceleration relative without sacrificing accuracy suggests potential for enable efficient accurate descriptions secondary GWs global atmospheric models.