mlsanityData to 7 Oct 2026

Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate Models

arXiv 2204.03497 ↗First posted 7 Apr 2022cs.LG nlin.CD physics.comp-phcited by 24

Not on the map. Why?

Abstract (arXiv)

Reduced-order modelling and low-dimensional surrogate models generated using machine learning algorithms have been widely applied in high-dimensional dynamical systems to improve the algorithmic efficiency. In this paper, we develop a system which combines reduced-order surrogate models with a novel data assimilation (DA) technique used to incorporate real-time observations from different physical spaces. We make use of local smooth surrogate functions which link the space of encoded system variables and the one of current observations to perform variational DA with a low computational cost. The new system, named Generalised Latent Assimilation can benefit both the efficiency provided by the reduced-order modelling and the accuracy of data assimilation. A theoretical analysis of the difference between surrogate and original assimilation cost function is also provided in this paper where an upper bound, depending on the size of the local training set, is given. The new approach is tested on a high-dimensional CFD application of a two-phase liquid flow with non-linear observation operators that current Latent Assimilation methods can not handle. Numerical results demonstrate that the proposed assimilation approach can significantly improve the reconstruction and prediction accuracy of the deep learning surrogate model which is nearly 1000 times faster than the CFD simulation.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 21 of its 71 references that are in the map. First posted on arXiv 7 Apr 2022.

Builds on

21 of 71 references.

References · 21

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  2. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  3. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  4. 2020Combining data assimilation and machine learning to emulate a dynamical model from sparse and noisy observations: a case study with the Lorenz 96 modelcited by 72
  5. 2019Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spacescited by 64
  6. 2020Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernelscited by 53
  7. 2020Using machine learning to correct model error in data assimilation and forecast applicationscited by 40
  8. 2021Latent Space Data Assimilation by using Deep Learningcited by 29
  9. 2018Data-driven polynomial chaos expansion for machine learning regressioncited by 25
  10. 2018Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalizationcited by 21
  11. 2020An autoencoder-based reduced-order model for eigenvalue problems with application to neutron diffusioncited by 19
  12. 2020A Modified Perturbed Sampling Method for Local Interpretable Model-agnostic Explanationcited by 13
9 more
  1. 2020Data Assimilation in the Latent Space of a Neural Networkcited by 9
  2. 2020Applying Convolutional Neural Networks to Data on Unstructured Meshes with Space-Filling Curvescited by 8
  3. 2021Observation Error Covariance Specification in Dynamical Systems for Data assimilation using Recurrent Neural Networkscited by 7
  4. 2019Background Error Covariance Iterative Updating with Invariant Observation Measures for Data Assimilationcited by 6
  5. 2020Neural Networks and Polynomial Regression. Demystifying the Overparametrization Phenomenacited by 5
  6. 2020Incremental Training of a Recurrent Neural Network Exploiting a Multi-Scale Dynamic Memorycited by 4
  7. 2021Adversarial autoencoders and adversarial LSTM for improved forecasts of urban air pollution simulationscited by 4
  8. 2021Data Assimilation Predictive GAN (DA-PredGAN): applied to determine the spread of COVID-19cited by 4
  9. 2021UCNN: A Convolutional Strategy on Unstructured Meshcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 8; 2024: 7; 2025: 2; 2026: 6.

24 papers.

Sort:

By area:

  1. 2023Machine learning with data assimilation and uncertainty quantification for dynamical systems: a reviewcited by 74
  2. 2024Deep Generative Data Assimilation in Multimodal Settingcited by 28
  3. 2022Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks in Scientific Computingcited by 24
  4. 2023Towards an end-to-end artificial intelligence driven global weather forecasting systemcited by 20
  5. 2024Latent-EnSF: A Latent Ensemble Score Filter for High-Dimensional Data Assimilation with Sparse Observation Datacited by 20
  6. 2023Efficient deep data assimilation with sparse observations and time-varying sensorscited by 14
  7. 2025Machine learning for modelling unstructured grid data in computational physics: a reviewcited by 12
  8. 2024LD-EnSF: Synergizing Latent Dynamics with Ensemble Score Filters for Fast Data Assimilation with Sparse Observationscited by 10
  9. 2023A generative model for surrogates of spatial-temporal wildfire nowcastingcited by 8
  10. 2023Latent assimilation with implicit neural representations for unknown dynamicscited by 8
  11. 2024State-observation augmented diffusion model for nonlinear assimilation with unknown dynamicscited by 7
  12. 2024Multi-fidelity physics constrained neural networks for dynamical systemscited by 5
12 more
  1. 2024TorchDA: A Python package for performing data assimilation with deep learning forward and transformation functionscited by 5
  2. 2025Bridging Idealized and Operational Models: An Explainable AI Framework for Earth System Emulatorscited by 3
  3. 2026Latent Autoencoder Ensemble Kalman Filter for Nonlinear Data assimilationcited by 3
  4. 2023On the uncertainty analysis of the data-enabled physics-informed neural network for solving neutron diffusion eigenvalue problemcited by 2
  5. 2026AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modelingcited by 2
  6. 2023Hierarchical Autoencoder-based Lossy Compression for Large-scale High-resolution Scientific Datacited by 1
  7. 2023Estimating fire Duration using regression methodscited by 1
  8. 2024The Deep Latent Space Particle Filter for Real-Time Data Assimilation with Uncertainty Quantificationcited by 1
  9. 2026Spatiotemporal System Forecasting with Irregular Time Steps via Masked Autoencodercited by 0
  10. 2026Ensemble Controlled-Flow Filtering for Implicit Data Assimilationcited by 0
  11. 2026Variational Parameter Calibration with Physics-Aware Latent-Space Surrogatescited by 0
  12. 2026Diffusion Distillation for Efficient Weather Ensemblescited by 0