Machine learning based feature engineering for thermoelectric materials by design
U. S. Vaitesswar, Daniil Bash, Tan Huang, Jose Recatala‐Gomez, Tianqi Deng, Shuo‐Wang Yang, Xiaonan Wang, Kedar Hippalgaonkar
Abstract
We train several machine learning models on a dataset comprised by Materials Project and calculated thermoelectric power factor. We show that a random forest model outperforms more complex approaches for the dataset and allows for interpretability.
Topics & Concepts
InterpretabilityRandom forestFeature (linguistics)Computer scienceMachine learningFeature engineeringArtificial intelligenceThermoelectric effectPower (physics)Data miningDeep learningQuantum mechanicsPhysicsThermodynamicsPhilosophyLinguisticsMachine Learning in Materials ScienceAdvanced Thermoelectric Materials and DevicesThermography and Photoacoustic Techniques