mlsanityData to 14 Oct 2026

ADDA: a Modular Framework for Representing, Simulating and Assimilating Dynamics with End-to-end Differentiability

arXiv 2608.23297 ↗First posted 24 Aug 2026cs.MS cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Data assimilation (DA) is an essential tool for prediction and understanding in the geosciences. DA combines simulation programs representing scientific knowledge with observations that constrain system dynamics, resulting in analyses and forecasts that incorporate both knowledge and data. DA tasks can be addressed with a diverse toolset, including variational, ensemble and learning-based methods. In particular, many recent works have proposed using automatic differentiation tools for variational, learning-based or hybrid methods. However, comprehensive comparisons across algorithms and dynamical systems remain challenging, due to the incompatibility of simulation and assimilation codes, inflexible handling of spatial and temporal discretizations, specialization of DA methods to specific simulations, and limited support for automatic differentiation and parallel computation in simulations. To address this challenge, we introduce Automatic Differentiation for Data Assimilation (ADDA), a software framework for defining and working with system states, simulations, observation schemes and DA methods. ADDA provides a powerful and flexible set of base classes for representing dynamical systems and observation operators, with support for collocated and staggered grids, unstructured meshes, Lagrangian state variables and irregular or continuous-time observations. Parallel processing and differentiability are first-class features, with support for batch axes and automatic differentiation throughout. ADDA is implemented in PyTorch library, but supports DA for JAX-based computation of dynamics and their gradients. To demonstrate its features, we further provide differentiable, ADDA-compatible implementations of 10 dynamical systems of various dimensionalities and scales, from which we design multiple illustrative DA examples. All of our code is publicly available at https://github.com/m-dml/ADDA.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 48 of its 139 references that are in the map. First posted on arXiv 24 Aug 2026.

Builds on

48 of 139 references.

References · 48

  1. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  2. 2021Machine learning accelerated computational fluid dynamicscited by 471
  3. 2023Score-based Data Assimilationcited by 96
  4. 2023Machine learning with data assimilation and uncertainty quantification for dynamical systems: a reviewcited by 75
  5. 2024DiffDA: a Diffusion Model for Weather-scale Data Assimilationcited by 61
  6. 2024Learning Diffusion Priors from Observations by Expectation Maximizationcited by 61
  7. 2023TorchRL: A data-driven decision-making library for PyTorchcited by 60
  8. 2024On conditional diffusion models for PDE simulationscited by 60
  9. 2024APEBench: A Benchmark for Autoregressive Neural Emulators of PDEscited by 60
  10. 2024ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responsescited by 54
  11. 2020Combining data assimilation and machine learning to infer unresolved scale parametrisationcited by 40
  12. 2020Learning Variational Data Assimilation Models and Solverscited by 36
36 more
  1. 2022JAX-FLUIDS: A fully-differentiable high-order computational fluid dynamics solver for compressible two-phase flowscited by 36
  2. 2021Latent Space Data Assimilation by using Deep Learningcited by 30
  3. 2024Deep Generative Data Assimilation in Multimodal Settingcited by 29
  4. 2021Variational Data Assimilation with a Learned Inverse Observation Operatorcited by 28
  5. 2024Samudra: An AI Global Ocean Emulator for Climatecited by 27
  6. 2023FengWu-4DVar: Coupling the Data-driven Weather Forecasting Model with 4D Variational Assimilationcited by 23
  7. 2022Differentiable Programming for Earth System Modelingcited by 22
  8. 2021Integrating Recurrent Neural Networks with Data Assimilation for Scalable Data-Driven State Estimationcited by 21
  9. 2024Differentiable Programming for Differential Equations: A Reviewcited by 21
  10. 2025Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilationcited by 20
  11. 2024Fuxi-DA: A Generalized Deep Learning Data Assimilation Framework for Assimilating Satellite Observationscited by 18
  12. 2025FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilationcited by 18
  13. 2020Online learning of both state and dynamics using ensemble Kalman filterscited by 15
  14. 20224DVarNet-SSH: end-to-end learning of variational interpolation schemes for nadir and wide-swath satellite altimetrycited by 10
  15. 2023Neural Koopman prior for data assimilationcited by 10
  16. 2020Data Assimilation in the Latent Space of a Neural Networkcited by 9
  17. 2024AI enhanced data assimilation and uncertainty quantification applied to Geological Carbon Storagecited by 7
  18. 20244D-Var using Hessian approximation and backpropagation applied to automatically-differentiable numerical and machine learning modelscited by 6
  19. 2025Neural Emulator Superiority: When Machine Learning for PDEs Surpasses its Training Datacited by 6
  20. 2023Gradient-free online learning of subgrid-scale dynamics with neural emulatorscited by 5
  21. 2024Proof-of-concept: Using ChatGPT to Translate and Modernize an Earth System Model from Fortran to Python/JAXcited by 5
  22. 2024TorchDA: A Python package for performing data assimilation with deep learning forward and transformation functionscited by 5
  23. 2025Ensemble Kalman filter in latent space using a variational autoencoder paircited by 5
  24. 2025Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferencescited by 5
  25. 2022Inversion of sea surface currents from satellite-derived SST-SSH synergies with 4DVarNetscited by 4
  26. 2023Training neural mapping schemes for satellite altimetry with simulation datacited by 4
  27. 2024KODA: A Data-Driven Recursive Model for Time Series Forecasting and Data Assimilation using Koopman Operatorscited by 4
  28. 2025Augmented Invertible Koopman Autoencoder for long-term time series forecastingcited by 4
  29. 2024Combined Optimization of Dynamics and Assimilation with End-to-End Learning on Sparse Observationscited by 3
  30. 2026Latent Autoencoder Ensemble Kalman Filter for Nonlinear Data assimilationcited by 3
  31. 2014On the Convergence of a Non-linear Ensemble Kalman Smoothercited by 2
  32. 2025Observation-only learning of neural mapping schemes for gappy satellite-derived ocean colour parameterscited by 2
  33. 2025An uncertainty-aware framework for data-efficient multi-view animal pose estimationcited by 2
  34. 2025Towards fully differentiable neural ocean model with Veroscited by 2
  35. 2025Uncertainty-aware data assimilation through variational inferencecited by 1
  36. 2026FESOM2-JAX v1.0: a differentiable shadow of the ocean-sea-ice model FESOM2, cast onto GPUscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Variational Augmented Invertible Koopman Autoencoder for probabilistic time series forecastingcited by 0