CAM-NET: An AI Model for Whole Atmosphere with Thermosphere and Ionosphere Extension

2025-06-24

AI Summary

This study addresses the challenge of high-fidelity, computationally efficient prediction of neutral atmospheric states from the surface to the ionosphere (0–600 km) to investigate upward-propagating gravity wave impacts on atmospheric dynamics and interlayer coupling. To this end, we propose the first all-atmosphere AI model: a modular architecture that decouples tracer evolution from core dynamical processes, enabling rapid adaptation to multiple tracer scenarios without retraining; it employs the Spherical Fourier Neural Operator (SFNO) to intrinsically encode Earth’s spherical geometry and global-scale dynamics, trained on a decade of WACCM-X simulations. The model achieves over 1,000× faster inference than conventional GCMs—completing one-year simulations in minutes—while matching WACCM-X accuracy for key atmospheric variables. This establishes a scalable, high-efficiency paradigm for gravity wave propagation and multi-sphere coupling research.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Computer Vision: Diffusion Models for Vision
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

We present Compressible Atmospheric Model-Network (CAM-NET), an AI model designed to predict neutral atmospheric variables from the Earth's surface to the ionosphere with high accuracy and computational efficiency. Accurate modeling of the entire atmosphere is critical for understanding the upward propagation of gravity waves, which influence upper-atmospheric dynamics and coupling across atmospheric layers. CAM-NET leverages the Spherical Fourier Neural Operator (SFNO) to capture global-scale atmospheric dynamics while preserving the Earth's spherical structure. Trained on a decade of datasets from the Whole Atmosphere Community Climate Model with thermosphere and ionosphere eXtension (WACCM-X), CAM-NET demonstrates accuracy comparable to WACCM-X while achieving a speedup of over 1000x in inference time, can provide one year simulation within a few minutes once trained. The model effectively predicts key atmospheric parameters, including zonal and meridional winds, temperature, and time rate of pressure. Inspired by traditional modeling approaches that use external couplers to simulate tracer transport, CAM-NET introduces a modular architecture that explicitly separates tracer prediction from core dynamics. The core backbone of CAM-NET focuses on forecasting primary physical variables (e.g., temperature, wind velocity), while tracer variables are predicted through a lightweight, fine-tuned model. This design allows for efficient adaptation to specific tracer scenarios with minimal computational cost, avoiding the need to retrain the entire model. We have validated this approach on the $O^2$ tracer, demonstrating strong performance and generalization capabilities.

Problem

• Predicts neutral atmospheric variables from surface to ionosphere accurately
• Models entire atmosphere to study gravity waves propagation and coupling
• Achieves high-speed simulations with modular tracer prediction architecture

Innovation

• Uses Spherical Fourier Neural Operator for global dynamics
• Achieves 1000x speedup with modular tracer prediction
• Trains on WACCM-X data for accurate atmospheric modeling