SPLTRAK Abstract Submission
Predicting Materials Parameters in Colloidal Quantum Dot Photovoltaic Devices Using Machine Learning Models Trained On Experimental Data
Hoon Jeong Lee, Ariana B. Hofelmann, Yida Lin, Susanna M. Thon
Johns Hopkins University, Baltimore, MD, United States

Experimentally measuring the underlying electronic materials parameters in photovoltaic devices is often an complex and time-consuming endeavor. Here, we explore several machine learning models that output materials, parameters such as electronic trap state density, solely using illuminated current-voltage curves, greatly reducing the complexity of the measurement process. Current-voltage curves were chosen to be the only input to our model because this type of measurement is relatively simple to perform. In addition, most photovoltaic research labs already collect this information on all devices. We compare several different network architectures, all of which are trained on experimental data from PbS colloidal quantum dot thin film solar cells. We predict values for underlying materials parameters and compare them to experimentally measured results.