A novel framework for generalization of deep hidden physics models
This addresses a key economic viability issue for engineering and industrial applications where retraining models for small changes is impractical.
The paper tackles the problem of model generalizability in deep hidden physics models, which struggle with changes in system inputs, parameters, and domains, by presenting a novel enhancement that enables generalization across these variations and aids in system discovery.
Modelling of systems where the full system information is unknown is an oft encountered problem for various engineering and industrial applications, as it's either impossible to consider all the complex physics involved or simpler models are considered to keep within the limits of the available resources. Recent advances in greybox modelling like the deep hidden physics models address this space by combining data and physics. However, for most real-life applications, model generalizability is a key issue, as retraining a model for every small change in system inputs and parameters or modification in domain configuration can render the model economically unviable. In this work we present a novel enhancement to the idea of hidden physics models which can generalize for changes in system inputs, parameters and domains. We also show that this approach holds promise in system discovery as well and helps learn the hidden physics for the changed system inputs, parameters and domain configuration.