Model discovery in the sparse sampling regime
arXiv:2105.00400
Abstract
To improve the physical understanding and the predictions of complex dynamic systems, such as ocean dynamics and weather predictions, it is of paramount interest to identify interpretable models from coarsely and off-grid sampled observations. In this work, we investigate how deep learning can improve model discovery of partial differential equations when the spacing between sensors is large and the samples are not placed on a grid. We show how leveraging physics informed neural network interpolation and automatic differentiation, allow to better fit the data and its spatiotemporal derivatives, compared to more classic spline interpolation and numerical differentiation techniques. As a result, deep learning-based model discovery allows to recover the underlying equations, even when sensors are placed further apart than the data's characteristic length scale and in the presence of high noise levels. We illustrate our claims on both synthetic and experimental data sets where combinations of physical processes such as (non)-linear advection, reaction, and diffusion are correctly identified.
References in corpus (19)
- Scikit-learn: Machine Learning in Python
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
- Data-driven discovery of coordinates and governing equations
- Physics-informed learning of governing equations from scarce data
- Hamiltonian Neural Networks
- Graph networks as learnable physics engines for inference and control
- Weak SINDy For Partial Differential Equations
- Deep learning of dynamics and signal-noise decomposition with time-stepping constraints
- Discovery of Nonlinear Multiscale Systems: Sampling Strategies and Embeddings
- Data-driven discovery of PDEs in complex datasets
- DeepMoD: Deep learning for Model Discovery in noisy data
- Lagrangian Neural Networks
- Differentiable Physics-informed Graph Networks
- Optimal Sensor Placement and Enhanced Sparsity for Classification
- Stability selection enables robust learning of partial differential equations from limited noisy data
- Machine Discovery of Partial Differential Equations from Spatiotemporal Data
- Sparsely constrained neural networks for model discovery of PDEs