Combined Optimization of Dynamics and Assimilation with End-to-End Learning on Sparse Observations
- URL: http://arxiv.org/abs/2409.07137v1
- Date: Wed, 11 Sep 2024 09:36:15 GMT
- Title: Combined Optimization of Dynamics and Assimilation with End-to-End Learning on Sparse Observations
- Authors: Vadim Zinchenko, David S. Greenberg,
- Abstract summary: CODA is an end-to-end optimization scheme for jointly learning dynamics and DA directly from sparse and noisy observations.
We introduce a novel learning objective that combines unrolled auto-regressive dynamics with the data- and self-consistency terms of weak-constraint 4Dvar DA.
- Score: 1.492574139257933
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Fitting nonlinear dynamical models to sparse and noisy observations is fundamentally challenging. Identifying dynamics requires data assimilation (DA) to estimate system states, but DA requires an accurate dynamical model. To break this deadlock we present CODA, an end-to-end optimization scheme for jointly learning dynamics and DA directly from sparse and noisy observations. A neural network is trained to carry out data accurate, efficient and parallel-in-time DA, while free parameters of the dynamical system are simultaneously optimized. We carry out end-to-end learning directly on observation data, introducing a novel learning objective that combines unrolled auto-regressive dynamics with the data- and self-consistency terms of weak-constraint 4Dvar DA. By taking into account interactions between new and existing simulation components over multiple time steps, CODA can recover initial conditions, fit unknown dynamical parameters and learn neural network-based PDE terms to match both available observations and self-consistency constraints. In addition to facilitating end-to-end learning of dynamics and providing fast, amortized, non-sequential DA, CODA provides greater robustness to model misspecification than classical DA approaches.
Related papers
- DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs [59.434893231950205]
Dynamic graph learning aims to uncover evolutionary laws in real-world systems.
We propose DyG-Mamba, a new continuous state space model for dynamic graph learning.
We show that DyG-Mamba achieves state-of-the-art performance on most datasets.
arXiv Detail & Related papers (2024-08-13T15:21:46Z) - eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling [9.52474299688276]
We introduce a low-rank structured variational autoencoder framework for nonlinear state-space graphical models.
We show that our approach consistently demonstrates the ability to learn a more predictive generative model.
arXiv Detail & Related papers (2024-03-03T02:19:49Z) - Semi-Supervised Learning of Dynamical Systems with Neural Ordinary
Differential Equations: A Teacher-Student Model Approach [10.20098335268973]
TS-NODE is the first semi-supervised approach to modeling dynamical systems with NODE.
We show significant performance improvements over a baseline Neural ODE model on multiple dynamical system modeling tasks.
arXiv Detail & Related papers (2023-10-19T19:17:12Z) - Learning Latent Dynamics via Invariant Decomposition and
(Spatio-)Temporal Transformers [0.6767885381740952]
We propose a method for learning dynamical systems from high-dimensional empirical data.
We focus on the setting in which data are available from multiple different instances of a system.
We study behaviour through simple theoretical analyses and extensive experiments on synthetic and real-world datasets.
arXiv Detail & Related papers (2023-06-21T07:52:07Z) - Decomposed Linear Dynamical Systems (dLDS) for learning the latent
components of neural dynamics [6.829711787905569]
We propose a new decomposed dynamical system model that represents complex non-stationary and nonlinear dynamics of time series data.
Our model is trained through a dictionary learning procedure, where we leverage recent results in tracking sparse vectors over time.
In both continuous-time and discrete-time instructional examples we demonstrate that our model can well approximate the original system.
arXiv Detail & Related papers (2022-06-07T02:25:38Z) - Learning Sparse Nonlinear Dynamics via Mixed-Integer Optimization [3.7565501074323224]
We propose an exact formulation of the SINDyDy problem using mixed-integer optimization (MIO) to solve the sparsity constrained regression problem to provable optimality in seconds.
We illustrate the dramatic improvement of our approach in accurate model discovery while being more sample efficient, robust to noise, and flexible in accommodating physical constraints.
arXiv Detail & Related papers (2022-06-01T01:43:45Z) - Gradient-Based Trajectory Optimization With Learned Dynamics [80.41791191022139]
We use machine learning techniques to learn a differentiable dynamics model of the system from data.
We show that a neural network can model highly nonlinear behaviors accurately for large time horizons.
In our hardware experiments, we demonstrate that our learned model can represent complex dynamics for both the Spot and Radio-controlled (RC) car.
arXiv Detail & Related papers (2022-04-09T22:07:34Z) - Capturing Actionable Dynamics with Structured Latent Ordinary
Differential Equations [68.62843292346813]
We propose a structured latent ODE model that captures system input variations within its latent representation.
Building on a static variable specification, our model learns factors of variation for each input to the system, thus separating the effects of the system inputs in the latent space.
arXiv Detail & Related papers (2022-02-25T20:00:56Z) - Continuous Forecasting via Neural Eigen Decomposition of Stochastic
Dynamics [47.82509795873254]
We introduce the Neural Eigen-SDE (NESDE) algorithm for sequential prediction with sparse observations and adaptive dynamics.
NESDE applies eigen-decomposition to the dynamics model to allow efficient frequent predictions given sparse observations.
We are the first to provide a patient-adapted prediction for blood coagulation following Heparin dosing in the MIMIC-IV dataset.
arXiv Detail & Related papers (2022-01-31T22:16:50Z) - Using Data Assimilation to Train a Hybrid Forecast System that Combines
Machine-Learning and Knowledge-Based Components [52.77024349608834]
We consider the problem of data-assisted forecasting of chaotic dynamical systems when the available data is noisy partial measurements.
We show that by using partial measurements of the state of the dynamical system, we can train a machine learning model to improve predictions made by an imperfect knowledge-based model.
arXiv Detail & Related papers (2021-02-15T19:56:48Z) - Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence.
This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time.
Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
arXiv Detail & Related papers (2020-02-21T05:00:01Z)
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.