Calibration of dynamic models to data is an important step in building building digital twins of HVAC equipment, thermal loads and control systems. Sometimes, when a model fails to calibrate to data, a possible cause is that the model has made too many sim- plifying assumptions and is missing physics. In this paper we propose a semi-automated approach, called Dyad Model Discovery, that can augment the physical equations of the model with symbolic expressions discovered from the data. We demonstrate this method on a digital twin of a transportation refrigeration unit to improve its predictive performance, trained using telemetry data. An engineer-in-the-loop workflow is proposed, which provides suggestions to the user which can then be accepted or rejected. This is the first AI-assisted engineering design workflow to our knowledge.
@article{arxiv.2603.15943,
title = {Scientific Machine Learning-assisted Model Discovery from Telemetry Data},
author = {Sebastian Micluta-Campeanu and Avinash Subramanian and Anas Abdelrehim and Ranjan Anantharaman and Rohit Dhumane and Brad Carman and Chris Rackauckas},
journal= {arXiv preprint arXiv:2603.15943},
year = {2026}
}