Machine Learning for Ionic Thermoelectric Materials
Author Information
Author(s): Wu Yidan, Song Dongxing, An Meng, Chi Cheng, Zhao Chunyu, Yao Bing, Ma Weigang
Primary Institution: Tsinghua University
Hypothesis
Can machine learning accelerate the discovery of high-performance ionic thermoelectric materials?
Conclusion
The study successfully developed a machine learning model that predicts the Seebeck coefficients of ionic thermoelectric materials, identifying a promising material with a Seebeck coefficient of 41.39 mV/K.
Supporting Evidence
- The machine learning model achieved an R2 of 0.98 on the test dataset.
- Experimental validation identified a waterborne polyurethane/potassium iodide ionogel with a Seebeck coefficient of 41.39 mV/K.
- Interpretable analysis revealed key features affecting Seebeck coefficients.
Takeaway
This study uses computers to help find new materials that can turn heat into electricity better and faster.
Methodology
The study employed a machine learning model trained on a dataset of ionic thermoelectric materials to predict their Seebeck coefficients.
Potential Biases
Potential bias in the dataset due to reliance on previously published literature.
Limitations
The model's predictions may not be accurate for materials outside the training set range.
Statistical Information
P-Value
0.02
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website