DeepAI AI Chat
Log In Sign Up

Theory-guided hard constraint projection (HCP): a knowledge-based data-driven scientific machine learning method

by   Yuntian Chen, et al.

Machine learning models have been successfully used in many scientific and engineering fields. However, it remains difficult for a model to simultaneously utilize domain knowledge and experimental observation data. The application of knowledge-based symbolic AI represented by an expert system is limited by the expressive ability of the model, and data-driven connectionism AI represented by neural networks is prone to produce predictions that violate physical mechanisms. In order to fully integrate domain knowledge with observations, and make full use of the prior information and the strong fitting ability of neural networks, this study proposes theory-guided hard constraint projection (HCP). This model converts physical constraints, such as governing equations, into a form that is easy to handle through discretization, and then implements hard constraint optimization through projection. Based on rigorous mathematical proofs, theory-guided HCP can ensure that model predictions strictly conform to physical mechanisms in the constraint patch. The performance of the theory-guided HCP is verified by experiments based on the heterogeneous subsurface flow problem. Due to the application of hard constraints, compared with fully connected neural networks and soft constraint models, such as theory-guided neural networks and physics-informed neural networks, theory-guided HCP requires fewer data, and achieves higher prediction accuracy and stronger robustness to noisy observations.


page 10

page 13

page 16

page 20

page 22


A Lagrangian Dual-based Theory-guided Deep Neural Network

The theory-guided neural network (TgNN) is a kind of method which improv...

Physics-informed ConvNet: Learning Physical Field from a Shallow Neural Network

Big-data-based artificial intelligence (AI) supports profound evolution ...

Constraint Guided Gradient Descent: Guided Training with Inequality Constraints

Deep learning is typically performed by learning a neural network solely...

On the application of Physically-Guided Neural Networks with Internal Variables to Continuum Problems

Predictive Physics has been historically based upon the development of m...

Constraint-Aware Neural Networks for Riemann Problems

Neural networks are increasingly used in complex (data-driven) simulatio...