Improving the predictions of ML-corrected climate models with novelty detection

Autor:	Sanford, Clayton, Kwa, Anna, Watt-Meyer, Oliver, Clark, Spencer, Brenowitz, Noah, McGibbon, Jeremy, Bretherton, Christopher
Rok vydání:	2022
Předmět:	Physics - Atmospheric and Oceanic Physics
Druh dokumentu:	Working Paper
Popis:	While previous works have shown that machine learning (ML) can improve the prediction accuracy of coarse-grid climate models, these ML-augmented methods are more vulnerable to irregular inputs than the traditional physics-based models they rely on. Because ML-predicted corrections feed back into the climate model's base physics, the ML-corrected model regularly produces out of sample data, which can cause model instability and frequent crashes. This work shows that adding semi-supervised novelty detection to identify out-of-sample data and disable the ML-correction accordingly stabilizes simulations and sharply improves the quality of predictions. We design an augmented climate model with a one-class support vector machine (OCSVM) novelty detector that provides better temperature and precipitation forecasts in a year-long simulation than either a baseline (no-ML) or a standard ML-corrected run. By improving the accuracy of coarse-grid climate models, this work helps make accurate climate models accessible to researchers without massive computational resources. Comment: Appearing at Tackling Climate Change with Machine Learning Workshop at NeurIPS 2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2211.13354 Zobrazit plný text záznamu View this record from Arxiv