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

TL;DR

This paper introduces a machine learning-analog framework for multi-year to decadal temperature prediction, combining neural networks with analog forecasting to improve climate prediction accuracy.

Contribution

It presents a novel hybrid approach that integrates neural network-learned masks with analog forecasting, enhancing multi-year to decadal climate prediction performance.

Findings

Improved temperature prediction accuracy over traditional analog methods.

Effective use of neural networks to identify relevant analogs for climate prediction.

Demonstrated success with Berkeley Earth and CMIP6 datasets.

Abstract

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.