Interpretable Climate Change Modeling With Progressive Cascade Networks

TL;DR

This paper introduces a progressive cascade network approach that builds interpretable climate models by incrementally increasing complexity, aiding understanding of climate change patterns from temperature and precipitation data.

Contribution

It presents a novel method that starts with simple linear models and adds complexity only as supported by data, enhancing interpretability in climate modeling.

Findings

Models successfully map climate variables to years, revealing meaningful patterns.

The approach improves interpretability over traditional deep learning models.

Incremental complexity addition aligns with data support, reducing overfitting.

Abstract

Typical deep learning approaches to modeling high-dimensional data often result in complex models that do not easily reveal a new understanding of the data. Research in the deep learning field is very actively pursuing new methods to interpret deep neural networks and to reduce their complexity. An approach is described here that starts with linear models and incrementally adds complexity only as supported by the data. An application is shown in which models that map global temperature and precipitation to years are trained to investigate patterns associated with changes in climate.