# No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation

arXiv: https://arxiv.org/abs/2605.22248 · HTML: https://mlsanity.com/paper/2605.22248/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 80 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 29 of 29)

- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [ClimaX: A foundation model for weather and climate](https://mlsanity.com/paper/2301.10343/) (2023)
- [Inductive Biases for Deep Learning of Higher-Level Cognition](https://mlsanity.com/paper/2011.15091/) (2020)
- [Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization](https://mlsanity.com/paper/2107.04649/) (2021)
- [Neural General Circulation Models for Weather and Climate](https://mlsanity.com/paper/2311.07222/) (2023)
- [WeatherBench 2: A benchmark for the next generation of data-driven global weather models](https://mlsanity.com/paper/2308.15560/) (2023)
- [On the Binding Problem in Artificial Neural Networks](https://mlsanity.com/paper/2012.05208/) (2020)
- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responses](https://mlsanity.com/paper/2411.11268/) (2024)
- [Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High-Resolution Simulations](https://mlsanity.com/paper/1709.00037/) (2017)
- [ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling](https://mlsanity.com/paper/2307.01909/) (2023)
- [ClimateSet: A Large-Scale Climate Model Dataset for Machine Learning](https://mlsanity.com/paper/2311.03721/) (2023)
- [Climate-Invariant Machine Learning](https://mlsanity.com/paper/2112.08440/) (2021)
- [Marrying Causal Representation Learning with Dynamical Systems for Science](https://mlsanity.com/paper/2405.13888/) (2024)
- [ClimART: A Benchmark Dataset for Emulating Atmospheric Radiative Transfer in Weather and Climate Models](https://mlsanity.com/paper/2111.14671/) (2021)
- [Towards Physically-consistent, Data-driven Models of Convection](https://mlsanity.com/paper/2002.08525/) (2020)
- [Towards mechanistic understanding in a data-driven weather model: internal activations reveal interpretable physical features](https://mlsanity.com/paper/2512.24440/) (2025)
- [Robustness of AI-based weather forecasts in a changing climate](https://mlsanity.com/paper/2409.18529/) (2024)
- [Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation](https://mlsanity.com/paper/2406.19049/) (2024)
- [Multi-fidelity climate model parameterization for better generalization and extrapolation](https://mlsanity.com/paper/2309.10231/) (2023)
- [CERA: A Framework for Improved Generalization of Machine Learning Models to Changed Climates](https://mlsanity.com/paper/2509.00010/) (2025)
- [FloeNet: A mass-conserving global sea ice emulator that generalizes across climates](https://mlsanity.com/paper/2603.12449/) (2026)
- [Navigating the Noise: Bringing Clarity to ML Parameterization Design with O(100) Ensembles](https://mlsanity.com/paper/2309.16177/) (2023)
- [Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention](https://mlsanity.com/paper/2603.14483/) (2026)
- [Towards Physically Consistent Deep Learning For Climate Model Parameterizations](https://mlsanity.com/paper/2406.03920/) (2024)
- [Crowdsourcing the Frontier: Advancing Hybrid Physics-ML Climate Simulation via a 50,000 Kaggle Competition](https://mlsanity.com/paper/2511.20963/) (2025)
- [Assessing the Robustness of Climate Foundation Models under No-Analog Distribution Shifts](https://mlsanity.com/paper/2603.23043/) (2026)

## Abstract (arXiv)

Climate emulation is an out-of-distribution (OOD) projection task. This is precisely the challenge where modern Machine Learning (ML) methods are most prone to failure. Consequently, while current ML emulators trained on present climate achieve high in-distribution performance, their future reliability under the inevitable distribution shifts of a changing climate remains a critical, poorly understood blind spot. Addressing this challenge requires a fundamental shift in how we understand, evaluate, and design climate emulators. In this work, we first confirm that climate change drives a statistically significant and progressively growing shift in atmospheric state distributions, rendering standard evaluation protocols insufficient. We empirically establish that seasonal variation serves as an effective proxy for these long-term climate shifts, providing access to textitreal-world distribution shifts without recourse to heuristics like synthetic perturbations. Motivated by this link, we introduce a novel evaluation framework that leverages seasonal shifts as a rigorous, zero-overhead testbed for emulator robustness. Our systematic characterisation confirms that current state-of-the-art hybrid-ML emulators degrade significantly under these realistic shifts. Finally, we chart a path forward by identifying compositional generalisation, the ability to form novel combinations from observed elementary components, as a principled route towards robust climate emulation. We demonstrate that physically motivated decompositions substantially improve OOD performance with only modest trade-offs against in-distribution performance, providing an avenue towards ML-driven climate emulators robust to an unknown future.