Work

Material insights for supercapacitor designs: A shapley additive explanatory study of critical temperature dependence on atomic properties

Year: 2026

Type: article

Abstract: The design of high-performance superconducting materials for energy storage applications relies on a deep understanding of the relationship between material properties and superconducting critical temperature ( T c ) dependence. This study employs a Shapley Additive Explanatory ( SHAP ) approach to investigate the impact of atomic properties on the T c of supercapacitors materials relevant to supercapacitor electrode applications. A vast dataset of crystalline supercapacitor materials is utilized to train a range of machine learning models, including Random Forest, Bagging Regressor, Extra Trees, and K-Nearest Neighbor. The top-performing models demonstrate high predictive accuracy, with R 2 values ranging from 0.50 to 0.56 and RMSE values between 17.74 and 18.90. The SHAP analysis reveals that Average Electronegativity has the most significant impact on the T c measurements, indicating its crucial role in determining the performance of supercapacitors. Furthermore, the descriptor impact study shows that the Target Property Function, f(x), also known as the T c Function, is equal to 8.199, while the Expected Value of the Target Property, E[f(X)], ranges from 8 to 22. This suggests that the T c of supercapacitors is highly dependent on the atomic properties of the materials, and that Average Electronegativity is a key factor in determining their performance.

Source: Next Materials

DOI: 10.1016/j.nxmate.2026.103103

Authors: Hussein A.K. Kyhoiesh, Islam H. El Azab, Hassan E. Abd Elsalam, Mahmoud Elsayed

Institutions: National University of Science and Technology, Ministry of Education, Taif University

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,280

Funder: Taif University