# CERA: A Framework for Improved Generalization of Machine Learning Models to Changed Climates

## TL;DR

CERA is a machine learning framework that enhances climate model generalization to warmer climates by using latent-space alignment, reducing reliance on manual feature engineering, and improving predictions of moisture and energy processes.

## Contribution

The paper introduces CERA, a novel autoencoder-based framework with explicit latent-space alignment that improves climate model generalization without manual feature engineering.

## Key findings

- Outperforms baselines in predicting moisture and energy tendencies in warmer climates.
- Captures vertical, meridional, and intensity distribution shifts in precipitation.
- Latent alignment enhances accuracy and robustness across training seeds.

## Abstract

Robust generalization under climate change remains a major challenge for machine learning applications in climate science. Most existing approaches struggle to extrapolate beyond the climate they were trained on, leading to a strong dependence on training data from model simulations of warm climates. Use of climate-invariant inputs improves generalization but requires challenging manual feature engineering. Here, we present CERA (Climate-invariant Encoding through Representation Alignment), a machine learning framework consisting of an autoencoder with explicit latent-space alignment, followed by a predictor for downstream process estimation. We test CERA on the problem of parameterizing moist-physics processes. Without training on labeled data from a +4K climate, CERA leverages labeled control-climate data and unlabeled warmer-climate inputs to improve generalization to the warmer climate, outperforming both raw-input and physically informed baselines in predicting key moisture and energy tendencies. It captures not only the vertical and meridional structures of the moisture tendencies, but also shifts in the intensity distribution of precipitation including extremes. Ablation experiments show that latent alignment improves both accuracy and the robustness across random seeds used in training. While some reduced skill remains in the boundary layer, the framework offers a data-driven alternative to manual feature engineering of climate invariant inputs. Beyond parameterizations used in hybrid ML-physics systems, the approach holds promise for other climate applications such as statistical downscaling.