Scientific Machine Learning: Principles, Methods and Applications

A recent report by the US Department of Energy defines the area of scientific machine learning as “a core component of artificial intelligence (AI) and a computational technology that can be trained, with scientific data, to augment or automate human skills”, which has “the potential to transform science and energy research”. We explore the potential of scientific machine learning methods to problems in computational electromagnetics starting from standard microwave structure design and multiphysics modeling, employing an unsupervised learning strategy based on Physics-Informed Neural Networks (PINN). PINNs directly integrate physical laws into their loss function, so that the training process does not rely on the generation of ground truth data from a large number of simulations (as in typical neural networks).