Enforcing Analytic Constraints in Neural Networks Emulating Physical Systems 论文

2021Physical Review Letters引用 404
Model Reduction and Neural NetworksNeural Networks and ApplicationsFault Detection and Control Systems

详细信息

发表期刊/会议
Physical Review Letters
发表日期
2021-03-04
发表年份
2021

关键词

Model Reduction and Neural NetworksNeural Networks and ApplicationsFault Detection and Control Systems

摘要

Neural networks can emulate nonlinear physical systems with high accuracy, yet they may produce physically inconsistent results when violating fundamental constraints. Here, we introduce a systematic way of enforcing nonlinear analytic constraints in neural networks via constraints in the architecture or the loss function. Applied to convective processes for climate modeling, architectural constraints enforce conservation laws to within machine precision without degrading performance. Enforcing constraints also reduces errors in the subsets of the outputs most impacted by the constraints.