AO-PHLGFeb 24, 2025

Multi-Year-to-Decadal Temperature Prediction using a Machine Learning Model-Analog Framework

arXiv:2502.17583v11 citationsh-index: 1
Originality Incremental advance
AI Analysis

This work addresses climate prediction for regional and global futures, representing an incremental advancement in combining existing techniques.

The authors tackled multi-year-to-decadal temperature prediction by developing a machine learning model-analog framework that combines neural networks with analog forecasting, resulting in improved performance over traditional analog methods and initialized decadal predictions.

Multi-year-to-decadal climate prediction is a key tool in understanding the range of potential regional and global climate futures. Here, we present a framework that combines machine learning and analog forecasting for predictions on these timescales. A neural network is used to learn a mask, specific to a region and lead time, with global weights based on relative importance as precursors to the evolution of that prediction target. A library of mask-weighted model states, or potential analogs, are then compared to a single mask-weighted observational state. The known future of the best matching potential analogs serve as the prediction for the future of the observational state. We match and predict 2-meter temperature using the Berkeley Earth Surface Temperature dataset for observations, and a set of CMIP6 models as the analog library. We find improved performance over traditional analog methods and initialized decadal predictions.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes