Deep multiphysics: Coupling discrete multiphysics with machine learning to attain self-learning in-silico models replicating human physiology

作者：

Highlights：

• First principle modelling and machine learning are coupled together.

• The resulting model has the ability to self-learn biological feedback loops.

• Peristalsis in the oesophagus is used as benchmark.

• The model learns by itself how to propagate the bolus in the oesophagus.

摘要

•First principle modelling and machine learning are coupled together.•The resulting model has the ability to self-learn biological feedback loops.•Peristalsis in the oesophagus is used as benchmark.•The model learns by itself how to propagate the bolus in the oesophagus.

论文关键词：Discrete multiphysics,Reinforcement Learning,Coupling first-principles models with machine learning,Particle-based computational methods

论文评审过程：Received 25 September 2018, Revised 30 May 2019, Accepted 24 June 2019, Available online 4 July 2019, Version of Record 10 July 2019.

论文官网地址：https://doi.org/10.1016/j.artmed.2019.06.005