Physics-Constrained Adaptive Flow Matching for Climate Downscaling

• URL: http://arxiv.org/abs/2604.03459v1
• Date: Fri, 03 Apr 2026 21:09:13 GMT
• Title: Physics-Constrained Adaptive Flow Matching for Climate Downscaling
• Abstract summary: We present Physics-Constrained Adaptive Flow Matching (PC-AFM) as a generative downscaling model.<n>We train the model on Central Europe climate data, evaluate it on a 10-time downscaling task, and test the generalization on two held-out climate regions.<n>Results indicate that physical consistency is a practical requirement for deploying generative downscaling models in real-world applications.
• Score: 20.06043414924976
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Regional climate information at kilometer scales is essential for assessing the impacts of climate change, but generating it with global climate models is too expensive due to their high computational costs. Machine learning models offer a fast alternative, yet they often violate basic physical laws and degrade when applied to climates outside of their training distribution. We present Physics-Constrained Adaptive Flow Matching (PC-AFM), a generative downscaling model that addresses both problems. Building on the Adaptive Flow Matching (AFM) model of Fotiadis et al. (2025) as our baseline, we add soft conservation constraints that keep the downscaled output consistent with the large-scale input for precipitation and humidity, and use gradient surgery via the ConFIG algorithm to prevent these constraints from interfering with the generative objective. We train the model on Central Europe climate data, evaluate it on a 10-time downscaling task (63km to 6.3km) over six variables (near-surface temperature, precipitation, specific humidity, surface pressure, and horizontal wind components) across a comprehensive set of metrics including bias, ensemble skill scores, power spectra, and conservation error, and test the generalization on two held-out climate regions. Within the training distribution, PC-AFM reduces conservation errors and improves ensemble calibration while matching the baseline on standard skill metrics. Outside the training distribution, where unconstrained models develop large systematic errors by extrapolating learned statistics, PC-AFM halves precipitation wet bias, reduces conservation error and improves extreme-quantile accuracy, all without any information about the target climate at inference time. These results indicate that physical consistency is a practical requirement for deploying generative downscaling models in real-world applications.

Related papers

• EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting [50.31500063307306]
  We introduce EO-WM, a video diffusion transformer for multispectral Earth Observation forecasting.<n> EO-WM incorporates a physically informed conditioning framework that represents meteorological forcing through a climatological baseline, weather anomalies, and cumulative physical stress signals.<n>Experiments show that EO-WM reduces the error in predicted Normalized Difference Vegetation Index (NDVI) decline amplitude by a relative 5.63% and improves directional hit rate by a relative 7.80%.
  arXiv  Detail & Related papers  (2026-06-25T16:53:30Z)
• Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting [52.53742727060265]
  Foundation models (FMs) for the Earth system learn statistical relationships between physical variables across massive datasets.<n>Here, we introduce Earth System Foundation Model (ESFM), a fully open model building on the 3Dwin UNet backbone of the pioneering model.<n>We present findings using dense gridded data (ERA5, CMIP6), regionally masked dense data, sparse gridded MODIS satellite data, and station data.<n>Results demonstrate competitive or superior performance relative to state-of-the-art benchmarks.
  arXiv  Detail & Related papers  (2026-04-20T11:40:39Z)
• 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)
• CERA: A Framework for Improved Generalization of Machine Learning Models to Changed Climates [1.205087107092304]
  Robust generalization under climate change remains a major challenge for machine learning applications in climate science.<n>We present CERA (Climate-invariant climate representation through Representation), a machine learning framework consisting of an autoencoder with explicit latent-space alignment.<n>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.
  arXiv  Detail & Related papers  (2025-08-15T20:28:04Z)
• PACER: Physics Informed and Uncertainty Aware Climate Emulator [0.6372261626436676]
  We propose PACER, a relatively lightweight 2.1M parameter Physics Informed Uncertainty Aware Climate EmulatoR.<n> PACER is trained across is trained across varying spatial resolutions and physics based climate models.<n>We show PACER's emulation performance across 20 climate models outperforming relevant baselines.
  arXiv  Detail & Related papers  (2024-10-29T01:53:40Z)
• 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)
• Embedding machine-learnt sub-grid variability improves climate model biases [0.44998333629984877]
  Under-representation of cloud formation is a long-standing bias associated with climate simulations. We overcome these biases by embedding a Multi-Output Gaussian Process (MOGP) trained on high resolution Unified Model simulations. Ten-year predictions are generated for both control and ML-hybrid models.
  arXiv  Detail & Related papers  (2024-06-13T19:35:58Z)
• 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)
• 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)
• Multi-scale Digital Twin: Developing a fast and physics-informed surrogate model for groundwater contamination with uncertain climate models [53.44486283038738]
  Climate change exacerbates the long-term soil management problem of groundwater contamination. We develop a physics-informed machine learning surrogate model using U-Net enhanced Fourier Neural Contaminated (PDENO) In parallel, we develop a convolutional autoencoder combined with climate data to reduce the dimensionality of climatic region similarities across the United States.
  arXiv  Detail & Related papers  (2022-11-20T06:46:35Z)

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.