Continuous PDE Dynamics Forecasting with Implicit Neural Representations
arXiv:2209.14855
Abstract
Effective data-driven PDE forecasting methods often rely on fixed spatial and / or temporal discretizations. This raises limitations in real-world applications like weather prediction where flexible extrapolation at arbitrary spatiotemporal locations is required. We address this problem by introducing a new data-driven approach, DINo, that models a PDE's flow with continuous-time dynamics of spatially continuous functions. This is achieved by embedding spatial observations independently of their discretization via Implicit Neural Representations in a small latent space temporally driven by a learned ODE. This separate and flexible treatment of time and space makes DINo the first data-driven model to combine the following advantages. It extrapolates at arbitrary spatial and temporal locations; it can learn from sparse irregular grids or manifolds; at test time, it generalizes to new grids or resolutions. DINo outperforms alternative neural PDE forecasters in a variety of challenging generalization scenarios on representative PDE systems.
References in corpus (10)
- Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
- Fourier Neural Operator for Parametric Partial Differential Equations
- VideoGPT: Video Generation using VQ-VAE and Transformers
- Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting
- Message Passing Neural PDE Solvers
- From data to functa: Your data point is a function and you can treat it like one
- Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction
- CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural Representations
- Long-time integration of parametric evolution equations with physics-informed DeepONets
- Variable-Input Deep Operator Networks