High-Throughput Screening of 6858 Compounds for Zinc-Ion Battery Cathodes via Hybrid Machine Learning Optimization

This work presents a machine-learning framework to explore cathode materials for zinc-ion batteries from a data set of 6858 zinc-containing compounds. Utilizing the extensive Materials Project (MP) database, we employed a two-step machine learning (ML) approach that uses transfer learning to compensate for missing electrochemical properties. Initially, a random forest regressor was used to fill in missing features in the zinc compounds, harnessing the full battery explorer in predictions. Two hybrid models were then developed: the sparrow search algorithm-light gradient boosting machine (SSA-LGBM), and Harris Hawk optimization-deep neural networks (HHO-DNN). The data set contains 107 feature vectors, which were minimized through principal component analysis. These features include descriptors related to structural, chemical, and electronic properties. Both models were trained using the 4351 known battery compounds from MP to predict key properties such as average voltage and gravimetric capacity. After initial prediction of 62 potential electrodes, further screening criteria were applied to identify 18 promising electrodes based on their voltage, specific capacity, electronic conductivity, safety, stability, cost, and abundance. The validation of our approach was carried out by applying the models to known cathode materials, verifying the accuracy of the predictions. This innovative approach significantly accelerates the discovery of efficient and stable cathode materials for zinc-ion batteries, paving the way for more sustainable and high-performance energy storage solutions. This method also provides a robust framework for future materials exploration across various battery technologies.