Learning Space-Time Continuous Neural PDEs from Partially Observed States
This advances data-driven PDE modeling for complex partially-observed dynamic processes, though it is incremental in improving upon existing neural PDE methods.
The paper tackles the problem of learning partial differential equations (PDEs) from noisy and partial observations on irregular grids by introducing a space-time continuous latent neural PDE model, achieving state-of-the-art performance on synthetic and real-world datasets.
We introduce a novel grid-independent model for learning partial differential equations (PDEs) from noisy and partial observations on irregular spatiotemporal grids. We propose a space-time continuous latent neural PDE model with an efficient probabilistic framework and a novel encoder design for improved data efficiency and grid independence. The latent state dynamics are governed by a PDE model that combines the collocation method and the method of lines. We employ amortized variational inference for approximate posterior estimation and utilize a multiple shooting technique for enhanced training speed and stability. Our model demonstrates state-of-the-art performance on complex synthetic and real-world datasets, overcoming limitations of previous approaches and effectively handling partially-observed data. The proposed model outperforms recent methods, showing its potential to advance data-driven PDE modeling and enabling robust, grid-independent modeling of complex partially-observed dynamic processes.