Adaptive Reduction of Multicollinearity for Machine Learning Prediction of CO Adsorption Energies on Single Atoms
Precision Chemistry · 27.07.2026 · 4 (7) · 1016-1030
DOI: 10.1021/prechem.5c00411 ↗Kurz gefasst
Fachartikel in der Zeitschrift Precision Chemistry, online erschienen am 03.03.2026. Verfasst von Kyoichi Sawabe und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Materials Chemistry, Graduate School of Engineering, Nagoya University, Nagoya 464-8603, Japan. Die Arbeit nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Japan Society for the Promotion of Science.
Abstract (Originalsprache)
Data-driven approaches are pivotal for optimizing single-atom catalysts. However, when the training data size is limited, the prevalence of multicollinearity among physicochemical features frequently destabilizes statistical models and obscures chemical interpretation. To address this challenge, we developed a wrapper-based feature selection algorithm termed adaptive reduction of multicollinearity with retention (ARMR). This method iteratively identifies feature subsets that satisfy strict multicollinearity constraints while minimizing cross-validated prediction error. The features selected by ARMR yielded robust predictive performance in both linear and nonlinear models, clearly outperforming baselines derived from univariate correlations or standard importance rankings. The efficacy of ARMR was validated through machine learning predictions using a density functional theory dataset of CO adsorption energies on 11 transition metals embedded as a single atom on three TiO2 polymorphs (rutile, anatase, and brookite). Specifically, a gradient boosting regression model trained on ARMR-selected features achieved high predictive accuracy with a test root-mean-square error of 0.087 eV. Furthermore, analysis of selected features identified s-orbital charge density as an important electronic feature correlating with CO binding strength. By removing multicollinearity, ARMR eliminates redundant properties intrinsically correlated with metal-specific characteristics like oxidation state, retaining only robust features. ARMR provides valuable insights into metal–support interactions and offers an effective strategy for accelerating rational design of single-atom catalysts through interpretable structure–property relationships.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Materials Chemistry, Graduate School of Engineering, Nagoya University, Nagoya 464-8603, Japan.
- Institute for Catalysis, Hokkaido University, Sapporo 001-0021, Japan.
ORCID-Profile: Kyoichi Sawabe, Atsushi Satsuma
Förderung
- Japan Society for the Promotion of Science
Zitieren
APA
Sawabe, K., Tsukiyama, T., Oda, A., & Satsuma, A. (2026). Adaptive Reduction of Multicollinearity for Machine Learning Prediction of CO Adsorption Energies on Single Atoms. Precision Chemistry, 4(7), 1016-1030. https://doi.org/10.1021/prechem.5c00411
Vancouver
Sawabe K, Tsukiyama T, Oda A, Satsuma A. Adaptive Reduction of Multicollinearity for Machine Learning Prediction of CO Adsorption Energies on Single Atoms. Precision Chemistry. 2026;4(7):1016-1030. doi:10.1021/prechem.5c00411
BibTeX
@article{Sawabe2026,
author = {Sawabe, Kyoichi and Tsukiyama, Takumi and Oda, Akira and Satsuma, Atsushi},
title = {Adaptive Reduction of Multicollinearity for Machine Learning Prediction of CO Adsorption Energies on Single Atoms},
journal = {Precision Chemistry},
year = {2026},
volume = {4},
number = {7},
pages = {1016--1030},
doi = {10.1021/prechem.5c00411}
}
EUVIMED