Physics-Informed Data-Driven Approach for Optimizing Electrocaloric Cooling

Electrocaloric (EC) cooling offers great potential to build efficient solid-state cooling devices that are quiet, low weight, and compact. However, the physics behind the EC temperature change are elusive. The current search for effective EC materials relies on the instincts of experts and brute force experimental synthesis of ceramics, polymers, and composites. There is no robust physical model to predict the EC temperature change based on material properties.
In this regard, we are developing a physics-informed machine learning model to predict the EC temperature change based on the material composition and easily-measured material properties. This work is the first application of machine learning to EC cooling. We gather experimental data of EC ceramics from literature and design the descriptors to account for the physical origins of the EC effect. These descriptors contain information from a macroscopic perspective and an atomic level. We build a random forest regression model on the data set. The resulting predictive model will help to accelerate the exploration of new EC materials by enabling the prediction of the EC temperature change from properties available in the literature.