ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing

• URL: http://arxiv.org/abs/2605.14285v1
• Date: Thu, 14 May 2026 02:34:33 GMT
• Title: ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing
• Abstract summary: We introduce ForcingDAS, a unified and robust data assimilation framework.<n>ForcingDAS learns a joint-trajectory prior instead of frame-to-frame transitions.<n>We evaluate ForcingDAS on 2D Navier-Stokes vorticity, precipitation nowcasting, and global atmospheric state estimation.
• Score: 24.41363445015799
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Data assimilation (DA) estimates the state of an evolving dynamical system from noisy, partial observations, and is widely used in scientific simulation as well as weather and climate science. In practice, filtering methods rely on frame-to-frame transition models. However, these models are fragile when observations are non-Markovian (when they form only a partial slice of a higher-dimensional latent state as in real-world weather data): they tend to accumulate errors over long horizons. At the same time, learned DA methods typically commit to a single regime, either filtering (nowcasting, real-time forecasting) or smoothing (retrospective reanalysis), which splits what should be a shared prior across application-specific pipelines. To address both issues, we introduce ForcingDAS, a unified and robust DA framework. Built on Diffusion Forcing with an independent noise level assigned to each frame, ForcingDAS learns a joint-trajectory prior instead of frame-to-frame transitions. This allows it to capture long-horizon temporal dependencies and reduce error accumulation. In addition, the same trained model spans the full filtering to smoothing spectrum at inference time. Specifically, nowcasting, fixed-lag smoothing, and batch reanalysis are selected through the inference schedule alone, without retraining. We evaluate ForcingDAS on 2D Navier-Stokes vorticity, precipitation nowcasting, and global atmospheric state estimation. Across all settings, a single model is competitive with or outperforms both learned and classical baselines that are specialized for individual regimes, with the largest gains observed on real-world weather benchmarks.

Related papers

• Multimodal Spatiotemporal Atmospheric Data Assimilation with Latent Video Flow-matching [2.225353152447347]
  We propose a fundamentally different, unified approach to atmospheric data assimilation.<n>We use latent video flow-matching to sample temporally consistent trajectories from a prior trained.<n>We generate full-state ensemble forecasts directly from sparse observations.
  arXiv  Detail & Related papers  (2026-08-05T17:42:29Z)
• Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights [1.7767466724342065]
  A temporally drifting data stream may pass through discrete regimes rather than changing continuously.<n>We ask whether such regimes are recoverable from the weights of models trained on the stream using a hidden Markov model (HMM)<n>We study this question in two domains known to drift over time: multimodal misinformation detection, using the Fakeddit dataset; and sentiment analysis, using the Yelp dataset.
  arXiv  Detail & Related papers  (2026-07-29T21:51:29Z)
• 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)
• STIPP: Space-time in situ postprocessing over the French Alps using proper scoring rules [1.887852744008007]
  Space-time in situ postprocessing (STIPP) is a machine learning model that generates consistent weather forecasts for a network of station locations.<n>By leveraging a proper scoring rule for training, STIPP contributes to ongoing work-driven atmospheric models supervised only with distribution marginals.
  arXiv  Detail & Related papers  (2026-01-06T10:07:20Z)
• DDTime: Dataset Distillation with Spectral Alignment and Information Bottleneck for Time-Series Forecasting [28.005308500582405]
  Time-series forecasting is fundamental across many domains, yet training accurate models often requires large-scale datasets and computational resources.<n>We propose DDTime, a lightweight and plug-in distillation framework built upon first-order condensation decomposition.<n> DDTime consistently outperforms existing distillation methods, achieving about 30% relative accuracy gains while introducing about 2.49% computational overhead.
  arXiv  Detail & Related papers  (2025-11-20T16:50:09Z)
• SynCast: Synergizing Contradictions in Precipitation Nowcasting via Diffusion Sequential Preference Optimization [62.958457694151384]
  We introduce preference optimization into precipitation nowcasting for the first time, motivated by the success of reinforcement learning from human feedback in large language models.<n>In the first stage, the framework focuses on reducing FAR, training the model to effectively suppress false alarms.
  arXiv  Detail & Related papers  (2025-10-22T16:11:22Z)
• WaveGNN: Modeling Irregular Multivariate Time Series for Accurate Predictions [3.489870763747715]
  Real-world time series often exhibit irregularities such as misaligned timestamps, missing entries, and variable sampling rates.<n>Existing approaches often rely on imputation, which can introduce biases.<n>We present WaveGNN, a novel framework designed to embed irregularly sampled time series data for accurate predictions.
  arXiv  Detail & Related papers  (2024-12-14T00:03:44Z)
• Hierarchically Disentangled Recurrent Network for Factorizing System Dynamics of Multi-scale Systems: An application on Hydrological Systems [4.634606500665259]
  We propose a novel hierarchical recurrent neural architecture that factorizes the system dynamics at multiple temporal scales.<n> Experiments on several catchments from the National Weather Service North Central River Forecast Center show that FHNN outperforms standard baselines.<n>We show that FHNN can maintain accuracy even with limited training data through effective pre-training strategies and training global models.
  arXiv  Detail & Related papers  (2024-07-29T16:25:43Z)
• FreDF: Learning to Forecast in the Frequency Domain [54.2091536822376]
  Time series modeling presents unique challenges due to autocorrelation in both historical data and future sequences.<n>We propose the Frequency-enhanced Direct Forecast (FreDF) which mitigates label autocorrelation by learning to forecast in the frequency domain.
  arXiv  Detail & Related papers  (2024-02-04T08:23:41Z)
• OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning [67.07363529640784]
  We propose OpenSTL to categorize prevalent approaches into recurrent-based and recurrent-free models. We conduct standard evaluations on datasets across various domains, including synthetic moving object trajectory, human motion, driving scenes, traffic flow and forecasting weather. We find that recurrent-free models achieve a good balance between efficiency and performance than recurrent models.
  arXiv  Detail & Related papers  (2023-06-20T03:02:14Z)
• Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement [51.55157852647306]
  Time series forecasting has been a widely explored task of great importance in many applications. It is common that real-world time series data are recorded in a short time period, which results in a big gap between the deep model and the limited and noisy time series. We propose to address the time series forecasting problem with generative modeling and propose a bidirectional variational auto-encoder equipped with diffusion, denoise, and disentanglement.
  arXiv  Detail & Related papers  (2023-01-08T12:20:46Z)
• Deep Convolution for Irregularly Sampled Temporal Point Clouds [39.51507835155255]
  We consider the problem of modeling the dynamics of continuous spatial-temporal processes represented by irregular samples through both space and time. We propose a new deep model that is able to directly learn and predict over this irregularly sampled data, without voxelization. We present experiments on real-world weather station data and battles between large armies in StarCraft II.
  arXiv  Detail & Related papers  (2021-05-01T00:54:32Z)
• Consistency Guided Scene Flow Estimation [159.24395181068218]
  CGSF is a self-supervised framework for the joint reconstruction of 3D scene structure and motion from stereo video. We show that the proposed model can reliably predict disparity and scene flow in challenging imagery. It achieves better generalization than the state-of-the-art, and adapts quickly and robustly to unseen domains.
  arXiv  Detail & Related papers  (2020-06-19T17:28:07Z)

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.