Learning spatiotemporal dynamics with a pretrained generative model

Reconstructing spatiotemporal dynamics with sparse sensor measurement is an outstanding problem, commonly encountered in a wide spectrum of scientific and engineering applications. Such a problem is particularly challenging when the number and/or types of sensors (e.g., randomly placed) are extremely insufficient. Existing end-to-end learning models ordinarily suffer from the generalization issue for full-field reconstruction of spatiotemporal dynamics, especially in sparse data regimes typically seen in real-world applications. To this end, we propose a sparse-sensor-assisted score-based generative model (S³GM) to reconstruct and predict full-field spatiotemporal dynamics based on sparse measurements. Instead of learning directly the mapping between input and output pairs, an unconditioned generative model is firstly pretrained capturing the joint distribution of a vast group of pretraining data in a self-supervised manner, followed then by a sampling process conditioned on unseen sparse measurement. The efficacy of S³GM has been verified on multiple dynamical systems with various synthetic, real-world, and lab-test datasets (ranging from turbulent flow modeling to weather/climate forecasting). The results demonstrate the excellent performance of S³GM in zero-shot reconstruction and prediction of spatiotemporal dynamics even with high levels of data sparsity and noise. We find that S³GM exhibits high accuracy, generalizability, and robustness when handling different reconstruction tasks.