Green-NAS: A Global-Scale Multi-Objective Neural Architecture Search for Robust and Efficient Edge-Native Weather Forecasting
This work addresses the need for robust and efficient AI models for edge-native weather forecasting, particularly in low-resource environments, though it is incremental as it builds on existing NAS and Green AI principles.
The paper tackles the problem of developing efficient and sustainable neural networks for weather forecasting by introducing Green-NAS, a multi-objective neural architecture search framework that minimizes computational energy and carbon footprint. The best model achieved an RMSE of 0.0988 with only 153k parameters, which is 239 times fewer than other global models like GraphCast, and transfer learning improved accuracy by approximately 5.2% in data-limited scenarios.
We introduce Green-NAS, a multi-objective NAS (neural architecture search) framework designed for low-resource environments using weather forecasting as a case study. By adhering to 'Green AI' principles, the framework explicitly minimizes computational energy costs and carbon footprints, prioritizing sustainable deployment over raw computational scale. The Green-NAS architecture search method is optimized for both model accuracy and efficiency to find lightweight models with high accuracy and very few model parameters; this is accomplished through an optimization process that simultaneously optimizes multiple objectives. Our best-performing model, Green-NAS-A, achieved an RMSE of 0.0988 (i.e., within 1.4% of our manually tuned baseline) using only 153k model parameters, which is 239 times fewer than other globally applied weather forecasting models, such as GraphCast. In addition, we also describe how the use of transfer learning will improve the weather forecasting accuracy by approximately 5.2%, in comparison to a naive approach of training a new model for each city, when there is limited historical weather data available for that city.