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

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

Automated summary

Gravity waves (GWs) and their associated multi-scale dynamics are important in atmospheric energy and momentum processes. We present CAM-Net, an initial machine learning model trained on high-resolution simulations. Two applications to Kelvin-Helmholtz instability and mountain wave generation are described, showing CAM-Net's ability to capture key dynamics and spectral characteristics compared to CGCAM. CAM-Net demonstrates the potential for efficient and accurate descriptions of primary and secondary GWs in global atmospheric models.