Novel Structural Feature-descriptor Platform for Machine Learning to Accelerate the Development of Organic Photovoltaics

<Novel Structural Feature-descriptor Platform for Machine Learning to Accelerate the Development of Organic Photovoltaics> - Nano Energy 106 (2023) 108108 - https://doi.org/10.1016/j.nanoen.2022.108108 The training/evaluating process of the Lightgbm model combined with leave-one-group-out cross-validation is described. Also, we attach a dataset including structural feature-descriptors and photovoltaic parameters to run the machine learning model.