Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting

• URL: http://arxiv.org/abs/2605.00850v1
• Date: Mon, 20 Apr 2026 11:40:39 GMT
• Title: Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting
• Abstract summary: 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.
• Score: 52.53742727060265
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Foundation models (FMs) for the Earth system learn statistical relationships between physical variables across massive datasets to enable versatile downstream applications through finetuning, separating them from task-specific weather models. Here, we introduce Earth System Foundation Model (ESFM), a fully open model building on the 3D Swin UNet backbone of the pioneering Aurora model. ESFM introduces extensions that increase functionality and foster adoption in climate sciences. First, the encoding scheme and training protocols have been extended to handle diverse datasets, including those containing missing values across all spatio-temporal dimensions such as satellite data, as well as station data, all under one backbone. Axial attention is introduced to capture inter-variable dependencies. As a result ESFM skillfully predicts variables in regions or on pressure levels where no data is present at the initial time, while preserving inter-variable relationships, for example between temperature, pressure, and humidity. Individual variable tokenization enables different sets of variables to be shuffled during training and simplifies the process of building extensions for new downstream tasks. Adaptive layer norm-based ensembles allow for a simple yet effective way to transform deterministic ESFM to a probabilistic FM. We present findings using dense gridded data (ERA5, CMIP6), regionally masked dense data, sparse gridded MODIS satellite data, and station data. Results demonstrate competitive or superior performance relative to state-of-the-art benchmarks. Case studies of Super Typhoon Doksuri (2023) and 2024 sudden stratospheric warming events show accurate positional and magnitude estimations of extreme weather. ESFM retains the strengths of previous foundation models, such as long-term stability, but facilitates application to a variety of downstream tasks.

Related papers

• InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate [68.14572758582081]
  InfoAtlas is a foundation model-like architecture that eliminates the need for iterative optimization.<n>It learns to identify diverse dependence structures and predict MI directly from the dataset.<n>Experiments demonstrate that InfoAtlas matches state-of-the-art neural estimators in accuracy while achieving $100times$ speedup.
  arXiv  Detail & Related papers  (2026-05-29T18:16:51Z)
• Posterior Augmented Flow Matching [64.1559809786948]
  Posterior-Augmented Flow Matching (PAFM) is a generalization of flow matching (FM)<n>We show that PAFM improves over FM by up to 3.4 FID50K across different model scales.
  arXiv  Detail & Related papers  (2026-05-01T17:59:59Z)
• Parameter-Efficient Adaptation of Pre-Trained Vision Foundation Models for Active and Passive Seismic Data Denoising [4.127374559128319]
  The demand for high-resolution subsurface imaging and continuous Earth monitoring has driven rapid growth in active and passive seismic data.<n>This expansion makes complex noise suppression increasingly challenging, especially when signal fidelity must be preserved.<n>Pre-training seismic foundation models from scratch requires massive domain-specific data and substantial computation.<n>We propose an efficient framework that repurposes general-purpose Vision Foundation Models (VFMs) for geophysical tasks through Fine-Tuning.
  arXiv  Detail & Related papers  (2026-04-30T15:28:51Z)
• Tackling Data Heterogeneity in Federated Time Series Forecasting [61.021413959988216]
  Time series forecasting plays a critical role in various real-world applications, including energy consumption prediction, disease transmission monitoring, and weather forecasting. Most existing methods rely on a centralized training paradigm, where large amounts of data are collected from distributed devices to a central cloud server. We propose a novel framework, Fed-TREND, to address data heterogeneity by generating informative synthetic data as auxiliary knowledge carriers.
  arXiv  Detail & Related papers  (2024-11-24T04:56:45Z)
• Distributed Lag Transformer based on Time-Variable-Aware Learning for Explainable Multivariate Time Series Forecasting [4.572747329528556]
  Distributed Lag Transformer (DLFormer) is a novel Transformer architecture for explainable and scalable time series models.<n>DLFormer integrates a distributed lag embedding and a time variable aware learning (TVAL) mechanism to structurally model both local and global temporal dependencies.<n>Experiments show that DLFormer achieves predictive accuracy while offering robust, interpretable insights into variable wise and temporal dynamics.
  arXiv  Detail & Related papers  (2024-08-29T20:39:54Z)
• Generative Data Assimilation of Sparse Weather Station Observations at Kilometer Scales [5.427841765899196]
  We demonstrate the viability of score-based data assimilation in the context of realistically complex km-scale weather.<n>By incorporating observations from 40 weather stations, 10% lower RMSEs on left-out stations are attained.<n>It is a ripe time to explore extensions that combine increasingly ambitious regional state generators with an increasing set of in situ, ground-based, and satellite remote sensing data streams.
  arXiv  Detail & Related papers  (2024-06-19T10:28:11Z)
• Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models [36.229082478423585]
  LM-Weather is a generic approach to taming pre-trained language models (PLMs) We introduce a lightweight personalized adapter into PLMs and endow it with weather pattern awareness. Experiments show LM-Weather outperforms the state-of-the-art results by a large margin across various tasks.
  arXiv  Detail & Related papers  (2024-05-24T15:25:09Z)
• Observation-Guided Meteorological Field Downscaling at Station Scale: A Benchmark and a New Method [66.80344502790231]
  We extend meteorological downscaling to arbitrary scattered station scales and establish a new benchmark and dataset. Inspired by data assimilation techniques, we integrate observational data into the downscaling process, providing multi-scale observational priors. Our proposed method outperforms other specially designed baseline models on multiple surface variables.
  arXiv  Detail & Related papers  (2024-01-22T14:02:56Z)
• A Spatiotemporal Deep Neural Network for Fine-Grained Multi-Horizon Wind Prediction [3.2474405288441544]
  We propose a novel data-driven model for accurate and efficient fine-grained wind prediction. MHSTN integrates multiple deep neural networks targeting different factors in a sequence-to-sequence (Seq2Seq) backbone. MHSTN is already integrated into the scheduling platform of one of the busiest international airports of China.
  arXiv  Detail & Related papers  (2023-09-09T09:36:28Z)
• 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.