Assessing the Robustness of Climate Foundation Models under No-Analog Distribution Shifts

• URL: http://arxiv.org/abs/2603.23043v1
• Date: Tue, 24 Mar 2026 10:29:54 GMT
• Title: Assessing the Robustness of Climate Foundation Models under No-Analog Distribution Shifts
• Abstract summary: "No-analog" future climate states are regimes where external forcing drives the system into conditions outside the empirical range of the historical training data.<n>We benchmark the robustness of three state-of-the-art architectures: U-Net, ConvLSTM, and the ClimaX foundation model specifically restricted to a historical-only training regime.
• Score: 2.4329932351753114
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The accelerating pace of climate change introduces profound non-stationarities that challenge the ability of Machine Learning based climate emulators to generalize beyond their training distributions. While these emulators offer computationally efficient alternatives to traditional Earth System Models, their reliability remains a potential bottleneck under "no-analog" future climate states, which we define here as regimes where external forcing drives the system into conditions outside the empirical range of the historical training data. A fundamental challenge in evaluating this reliability is data contamination; because many models are trained on simulations that already encompass future scenarios, true out-of-distribution (OOD) performance is often masked. To address this, we benchmark the OOD robustness of three state-of-the-art architectures: U-Net, ConvLSTM, and the ClimaX foundation model specifically restricted to a historical-only training regime (1850-2014). We evaluate these models using two complementary strategies: (i) temporal extrapolation to the recent climate (2015-2023) and (ii) cross-scenario forcing shifts across divergent emission pathways. Our analysis within this experimental setup reveals an accuracy vs. stability trade-off: while the ClimaX foundation model achieves the lowest absolute error, it exhibits higher relative performance changes under distribution shifts, with precipitation errors increasing by up to 8.44% under extreme forcing scenarios. These findings suggest that when restricted to historical training dynamics, even high-capacity foundation models are sensitive to external forcing trajectories. Our results underscore the necessity of scenario-aware training and rigorous OOD evaluation protocols to ensure the robustness of climate emulators under a changing climate.

Related papers

• Temporal Coverage over Density: Parsimonious Training-Set Design for ML Climate Downscaling [6.383771493909507]
  High-resolution regional climate simulations provide critical information for climate impacts assessments.<n>Findings provide practical guidance for regional climate downscaling and large-ensemble projection.
  arXiv  Detail & Related papers  (2026-06-05T23:16:38Z)
• No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation [13.032406275216557]
  We show that climate change drives a statistically significant and progressively growing shift in atmospheric state distributions.<n>We introduce a novel evaluation framework that leverages seasonal shifts as a rigorous, zero-overhead testbed for emulator.<n>Our systematic characterisation confirms that current state-of-the-art hybrid-ML emulators degrade significantly under these realistic shifts.
  arXiv  Detail & Related papers  (2026-05-21T09:54:57Z)
• High-Resolution Climate Projections Using Diffusion-Based Downscaling of a Lightweight Climate Emulator [1.9367648935513015]
  We introduce a deep learning-based downscaling framework to generate climate models at 28km resolution.<n>These models are trained on approximately 14,000 ERA5 timesteps spanning 2000-2009 and evaluated on LUCIE predictions from 2010 to 2020.<n>We observe that the proposed approach is able to preserve the coarse-grained dynamics from LUCIE while generating fine-scaled climatological statistics at 28km resolution.
  arXiv  Detail & Related papers  (2026-02-13T19:36:46Z)
• Toward generative machine learning for boosting ensembles of climate simulations [0.0]
  We develop a conditional Variational Autoencoder (cVAE) trained on a limited sample of climate simulations to generate arbitrary large ensembles.<n>We show that the cVAE model learns the underlying distribution of the data and generates physically consistent samples that reproduce realistic low and high moment statistics.
  arXiv  Detail & Related papers  (2026-02-06T00:54:19Z)
• Do machine learning climate models work in changing climate dynamics? [3.912757881247533]
  This research systematically evaluates state-of-the-art ML-based climate models in diverse out-of-distribution (OOD) scenarios.<n>Experiments on large-scale datasets reveal notable performance variability across scenarios, shedding light on the strengths and limitations of current models.
  arXiv  Detail & Related papers  (2025-09-15T17:12:49Z)
• TianQuan-S2S: A Subseasonal-to-Seasonal Global Weather Model via Incorporate Climatology State [23.8714341737652]
  Accurate Subseasonal-to-Seasonal (S2S) forecasting is vital for decision-making in agriculture, energy production, and emergency management.<n>Recent data-driven studies have shown promising results, but their performance is limited by the inadequate incorporation of climate states and a model tendency to degrade.<n>We propose TianQuan-S2S, a global S2S forecasting model that integrates initial weather states with climatological means via climatology into patch embedding and enhancing variability capture through an uncertainty-augmented Transformer.
  arXiv  Detail & Related papers  (2025-04-14T07:02:34Z)
• On conditional diffusion models for PDE simulations [53.01911265639582]
  We study score-based diffusion models for forecasting and assimilation of sparse observations. We propose an autoregressive sampling approach that significantly improves performance in forecasting. We also propose a new training strategy for conditional score-based models that achieves stable performance over a range of history lengths.
  arXiv  Detail & Related papers  (2024-10-21T18:31:04Z)
• Efficient Localized Adaptation of Neural Weather Forecasting: A Case Study in the MENA Region [62.09891513612252]
  We focus on limited-area modeling and train our model specifically for localized region-level downstream tasks. We consider the MENA region due to its unique climatic challenges, where accurate localized weather forecasting is crucial for managing water resources, agriculture and mitigating the impacts of extreme weather events. Our study aims to validate the effectiveness of integrating parameter-efficient fine-tuning (PEFT) methodologies, specifically Low-Rank Adaptation (LoRA) and its variants, to enhance forecast accuracy, as well as training speed, computational resource utilization, and memory efficiency in weather and climate modeling for specific regions.
  arXiv  Detail & Related papers  (2024-09-11T19:31:56Z)
• Probabilistic Emulation of a Global Climate Model with Spherical DYffusion [15.460280166612119]
  We present the first conditional generative model that produces accurate and physically consistent global climate ensemble simulations. Our model integrates the dynamics-informed diffusion framework (DYffusion) with the Spherical Fourier Neural Operator (SFNO) architecture. The model achieves near gold-standard performance for climate model emulation, outperforming existing approaches and demonstrating promising ensemble skill.
  arXiv  Detail & Related papers  (2024-06-21T00:16:55Z)
• Weather Prediction with Diffusion Guided by Realistic Forecast Processes [49.07556359513563]
  We introduce a novel method that applies diffusion models (DM) for weather forecasting. Our method can achieve both direct and iterative forecasting with the same modeling framework. The flexibility and controllability of our model empowers a more trustworthy DL system for the general weather community.
  arXiv  Detail & Related papers  (2024-02-06T21:28:42Z)
• ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast [57.6987191099507]
  We introduce Exloss, a novel loss function that performs asymmetric optimization and highlights extreme values to obtain accurate extreme weather forecast. We also introduce ExBooster, which captures the uncertainty in prediction outcomes by employing multiple random samples. Our solution can achieve state-of-the-art performance in extreme weather prediction, while maintaining the overall forecast accuracy comparable to the top medium-range forecast models.
  arXiv  Detail & Related papers  (2024-02-02T10:34:13Z)
• Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling [58.456404022536425]
  State of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• Long-term drought prediction using deep neural networks based on geospatial weather data [75.38539438000072]
  High-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. We tackle drought data by introducing an end-to-end approach that adopts a systematic end-to-end approach. Key findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts.
  arXiv  Detail & Related papers  (2023-09-12T13:28:06Z)
• ClimaX: A foundation model for weather and climate [51.208269971019504]
  ClimaX is a deep learning model for weather and climate science. It can be pre-trained with a self-supervised learning objective on climate datasets. It can be fine-tuned to address a breadth of climate and weather tasks.
  arXiv  Detail & Related papers  (2023-01-24T23:19:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.