Machine Learning-Driven Discovery of Key Descriptors for CO2 Activation over Two-Dimensional Transition Metal Carbides and Nitrides - research article

Aug 6, 2026

High-throughput quantum mechanical screening fused with modern artificial intelligence is applied to identify key descriptors governing CO2 activation on two-dimensional transition metal carbides/nitrides (MXenes). Machine learning models evaluate more than 114 pristine and defective MXenes, with the random forest regressor delivering the strongest prediction of CO2 adsorption energy. Feature-importance analysis highlights d-band center, surface metal electronegativity, and valence electron number of metal atoms as the most influential descriptors, supporting rational MXene catalyst design via targeted prediction and validation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Abstract

Introduction

CO2 background and catalyst challenges

Need for rational descriptor-based catalyst design

ML Workflow and Data Strategy

[www.acsami.org](www.acsami.org) Research Article Machine Learning-Driven Discovery of Key Descriptors for CO2 Activation over Two-Dimensional Transition Metal Carbides and Nitrides B. Moses Abraham, Oriol Piqué, Mohd Aamir Khan, Francesc Vĩnes, * Francesc Illas, and Jayant K. Singh * Cite This: ACS Appl. Mater. Interfaces 2023, 15, 30117−30126 Read Online Downloaded via 16 1.1 16.162.34 on January 16, 2025 at 17:25:32 (UTC) . See [https://pubs.acs.org/sharingguidelines](https://pubs.acs.org/sharingguidelines) for options on how to legitimately share published articles. ACCESS Metrics & More Article Recommendations *sı Supporting Information ABSTRACT: Fusing high-throughput quantum mechanical screening techniques with modern artificial intelligence strategies is among the most fundamental 􀀁yet revolutionary 􀀁 science activities, capable of opening new horizons in catalyst discovery. Here, we apply this strategy to the process of finding appropriate key descriptors for CO2 activation over two-dimensional transition metal (TM) carbides/ nitrides (MXenes). Various machine learning (ML) models are developed to screen over 114 pure and defective MXenes, where the random forest regressor (RFR) ML scheme exhibits the best predictive performance for the CO2 adsorption energy, with a mean absolute error ± standard deviation of 0.16 ± 0.01 and 0.42 ± 0.06 eV for training and test data sets, respectively. Feature importance analysis revealed d-band center (εd), surface metal electronegativity (χM), and valence electron number of metal atoms (MV) as key descriptors for CO2 activation. These findings furnish a fundamental basis for designing novel MXene-based catalysts through the prediction of potential indicators for CO2 activation and their posterior usage. KEYWORDS: MXenes, CO2 activation, machine learning, density functional calculations, descriptors 1. INTRODUCTION The excessive carbon dioxide (CO2) concentration in Earth’s atmosphere has become a large threat to the environment given its main role in global warming; therefore, a lot of efforts have been taken worldwide to remove it. The rise of CO2 concentration in the atmosphere is mainly due to the massive destruction of forests as well as the extensive exploitation of fossil fuels, which led to a increase of CO2 concentration, that will reach 590 ppm by the year 2100, causing an expected global temperature raise by 1.9 °C, with the concomitant acidification of oceans and devastating consequences for the marine ecosystems.1 At present, the increasing CO2 emissions are partly controlled through either converting it into useful carbon-based fuels/chemicals or by storing it in a stabilized media. To attain a valid impact on both environment and economy, it is necessary to utilize CO2 instead of just storing it, to thus unlock its potential and trigger profitable industrial applications. Hitherto, several types of catalysts were investigated aimed at CO2 activation and reduction, including different metal oxides, pure metals and alloys, organometallics, single-atom catalysts, non-metals, and nano-metals.2−4 Typically, metals such as Cd, Sn, In, Pd, and Bi mediate the formation of formic acid from CO2,5−8 while Ti, Zn, and Au can efficiently convert CO2 into CO.9−11 These studies demonstrated that the CO2 molecule can interact with metal surfaces through either strong or weak binding modes. In the case of strong interactions, the metal−carbon (M−C) overbonding may poison the catalyst surface, making the active sites inaccessible for further reduction of CO2 with a concomitant reduction of product formation. In contrast, a weak bonding between CO2 and a given metal surface does not allow for the CO2 C−O bond dissociation, as desorption prevails over this bond scission chemical step, which would favor the formation of the desired products. It should be borne in mind that the C−O bond enthalpy in the CO2 molecule is very large, of 803 kJ·mol−1, 12 a

FAQs

What is the main goal of the study?

To identify key descriptors that predict CO2 activation performance on two-dimensional transition metal carbides and nitrides (MXenes) using machine learning.

Which machine learning model performed best for CO2 adsorption energy prediction?

The random forest regressor showed the best predictive performance for CO2 adsorption energy on both training and test data sets.

What descriptors were found to be most important for CO2 activation?

The d-band center (εd), surface metal electronegativity (χM), and the valence electron number of metal atoms (MV) were identified as key descriptors.

Aug 6, 2026

Upload by Emma Wilson