New pre-print: *Advancing Building Energy Efficiency with Physics-Informed Neural Networks*.

I’m excited to share our latest research on using Physics-Informed Neural Networks (PINNs) to tackle a critical challenge in building energy efficiency: estimating thermophysical properties from real-world, non-invasive data.
In our new paper, "_Physics-Informed Neural Networks for Thermophysical Property Retrieval_", we introduce an iterative framework that estimates the thermal conductivity of building facades using thermographs and environmental data. This approach avoids invasive measurements and lengthy observation periods, making it practical for in-situ applications.

Read the full pre-print here: https://arxiv.org/abs/2511.23449
I’d love to hear your thoughts and discuss potential collaborations or applications!

#MachineLearning #EnergyEfficiency #PINNs #BuildingScience #Sustainability