Fusing a machine learning strategy with density functional theory to hasten the discovery of 2D MXene-based catalysts for hydrogen generation

Abstract

The complexity of topological and combinatorial configuration space of MXenes can give rise to gigantic design challenges that cannot be addressed through traditional experimental or routine theoretical portfolios. To this...

Accelerating the Discovery of g-C3N4-Supported Single Atom Catalysts for Hydrogen Evolution Reaction: A Combined DFT and Machine Learning Strategy

“…In recent years, data-driven approaches applied to materials design have shown potential to overcome such stumbling blocks. Machine learning (ML) techniques − simplify the understanding of complex configurational spaces through readily available physical properties. For example, ML models predicted the identification of aggregation trends compromising single atom stability, explored the impact of surface modifications on MgO(100) supports, and predicted the binding energies of SACs on various oxides .…”

Machine Learning-Driven Discovery of Key Descriptors for CO2Activation over Two-Dimensional Transition Metal Carbides and Nitrides

“…Ultimately, choosing suitable descriptors is essential in any ML to regulate the prediction power and the learning efficiency. 32 In this work, ML models are developed to mine and map the CO 2 activation over pure and defective MXenes based solely on their pristine properties and the features of gas-phase atoms that enter in the MXene chemical composition. Note in passing by that for CO 2 activation, we refer here to a strong interaction between the CO 2 molecule and the MXene surfaces, leading to significant changes in the adsorbed CO 2 geometry, including a bent geometry with elongated C−O bonds and a molecular negative charge, resulting from a charge transfer from the MXene surface to CO 2 .…”

“…More advanced techniques are currently available to handle multiple features such as non-linear relationships, − including kernel ridge regression, neural networks, random forest regression, and Gaussian processes regression, to name a few. Ultimately, choosing suitable descriptors is essential in any ML to regulate the prediction power and the learning efficiency …”

MXene-Based Single-Atom Catalysts for Electrochemical Reduction of CO2 to Hydrocarbon Fuels

“…MXenes, being a recently developed family of 2D transition metal carbides, carbonitrides, and nitrides with the general formula M n +1 X n T x ( n = 1–3), M = TM, X is carbon or nitrogen, and T stands for the terminations (H, O, OH, F, or Cl), − have a wide range of applications in energy storage, − CO 2 conversion, − oxygen reduction, the HER, − electrochemistry, and biosensors . Morales-García et al employed DFT calculations to examine the impact of the number of atomic layers on CO 2 adsorption across various MXene surfaces, revealing a consistent trend of favorable interaction where the adsorption energy decreases as the transition metal electronic configuration shifts from d 2 to d 3 and d 4 .…”