Physics-Coupled Spatio-Temporal Active Learning for Dynamical Systems

08/11/2021
by   Yu Huang, et al.
0

Spatio-temporal forecasting is of great importance in a wide range of dynamical systems applications from atmospheric science, to recent COVID-19 spread modeling. These applications rely on accurate predictions of spatio-temporal structured data reflecting real-world phenomena. A stunning characteristic is that the dynamical system is not only driven by some physics laws but also impacted by the localized factor in spatial and temporal regions. One of the major challenges is to infer the underlying causes, which generate the perceived data stream and propagate the involved causal dynamics through the distributed observing units. Another challenge is that the success of machine learning based predictive models requires massive annotated data for model training. However, the acquisition of high-quality annotated data is objectively manual and tedious as it needs a considerable amount of human intervention, making it infeasible in fields that require high levels of expertise. To tackle these challenges, we advocate a spatio-temporal physics-coupled neural networks (ST-PCNN) model to learn the underlying physics of the dynamical system and further couple the learned physics to assist the learning of the recurring dynamics. To deal with data-acquisition constraints, an active learning mechanism with Kriging for actively acquiring the most informative data is proposed for ST-PCNN training in a partially observable environment. Our experiments on both synthetic and real-world datasets exhibit that the proposed ST-PCNN with active learning converges to near optimal accuracy with substantially fewer instances.

READ FULL TEXT

page 3

page 7

research
08/12/2021

ST-PCNN: Spatio-Temporal Physics-Coupled Neural Networks for Dynamics Forecasting

Ocean current, fluid mechanics, and many other spatio-temporal physical ...
research
06/21/2023

Learning Latent Dynamics via Invariant Decomposition and (Spatio-)Temporal Transformers

We propose a method for learning dynamical systems from high-dimensional...
research
12/20/2021

Learning Spatio-Temporal Specifications for Dynamical Systems

Learning dynamical systems properties from data provides important insig...
research
11/02/2017

Bayesian Recurrent Neural Network Models for Forecasting and Quantifying Uncertainty in Spatial-Temporal Data

Recurrent neural networks (RNNs) are nonlinear dynamical models commonly...
research
01/16/2020

Identification of Chimera using Machine Learning

Coupled dynamics on the network models have been tremendously helpful in...
research
02/24/2023

Deep active learning for nonlinear system identification

The exploding research interest for neural networks in modeling nonlinea...
research
11/01/2022

Combined space-time reduced-order model with 3D deep convolution for extrapolating fluid dynamics

There is a critical need for efficient and reliable active flow control ...

Please sign up or login with your details

Forgot password? Click here to reset