Machine-Learning-Assisted Accurate Band Gap Predictions of Functionalized MXene

MXenes are two-dimensional (2D) transition metal carbides and nitrides, and are invariably metallic in pristine form. While spontaneous passivation of their reactive bare surfaces lends unprecedented functionalities, consequently a many-folds increase in number of possible functionalized MXene makes their characterization difficult. Here, we study the electronic properties of this vast class of materials by accurately estimating the band gaps using statistical learning. Using easily available properties of the MXene, namely, boiling and melting points, atomic radii, phases, bond lengths, etc., as input features, models were developed using kernel ridge (KRR), support vector (SVR), Gaussian process (GPR), and bootstrap aggregating regression algorithms. Among these, the GPR model predicts the band gap with lowest root-mean-squared error (rmse) of 0.14 eV, within seconds. Most importantly, these models do not involve the Perdew–Burke–Ernzerhof (PBE) band gap as a feature. Our results demonstrate that machin...

[1]  Mohammad Khazaei,et al.  Topological insulators in the ordered double transition metals M 2 ′ M ″ C 2 MXenes ( M ′ = Mo , W; M ″ = Ti , Zr, Hf) , 2016, 1609.03649.

[2]  Y. Gogotsi,et al.  Calorimetric Determination of Thermodynamic Stability of MAX and MXene Phases , 2016 .

[3]  Felix A Faber,et al.  Machine Learning Energies of 2 Million Elpasolite (ABC_{2}D_{6}) Crystals. , 2015, Physical review letters.

[4]  I. Tanaka,et al.  Atomistic Origin of Phase Stability in Oxygen-Functionalized MXene: A Comparative Study , 2017 .

[5]  V. Presser,et al.  Two‐Dimensional Nanocrystals Produced by Exfoliation of Ti3AlC2 , 2011, Advanced materials.

[6]  Stefano Curtarolo,et al.  How the Chemical Composition Alone Can Predict Vibrational Free Energies and Entropies of Solids , 2017, 1703.02309.

[7]  S. Elahi,et al.  Electronic and optical properties of 2D graphene-like compounds titanium carbides and nitrides: DFT calculations , 2014 .

[8]  Yoshiyuki Kawazoe,et al.  Novel Electronic and Magnetic Properties of Two‐Dimensional Transition Metal Carbides and Nitrides , 2013 .

[9]  Engineering,et al.  Prediction model of band gap for inorganic compounds by combination of density functional theory calculations and machine learning techniques , 2016 .

[10]  G. Kresse,et al.  Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set , 1996 .

[11]  W. Kohn,et al.  Self-Consistent Equations Including Exchange and Correlation Effects , 1965 .

[12]  F. Aryasetiawan,et al.  The GW method , 1997, cond-mat/9712013.

[13]  Kristof T. Schütt,et al.  How to represent crystal structures for machine learning: Towards fast prediction of electronic properties , 2013, 1307.1266.

[14]  J. Vybíral,et al.  Big data of materials science: critical role of the descriptor. , 2014, Physical review letters.

[15]  David Barber,et al.  Bayesian reasoning and machine learning , 2012 .

[16]  H. Mizuseki,et al.  Isolation of pristine MXene from Nb₄AlC₃ MAX phase: a first-principles study. , 2016, Physical chemistry chemical physics : PCCP.

[17]  Chiho Kim,et al.  From Organized High-Throughput Data to Phenomenological Theory using Machine Learning: The Example of Dielectric Breakdown , 2016 .

[18]  James Theiler,et al.  Accelerated search for materials with targeted properties by adaptive design , 2016, Nature Communications.

[19]  Avanish Mishra,et al.  Mechanistic Insight into the Chemical Exfoliation and Functionalization of Ti3C2 MXene. , 2016, ACS applied materials & interfaces.

[20]  Matthias Scheffler,et al.  Defect formation energies without the band-gap problem: combining density-functional theory and the GW approach for the silicon self-interstitial. , 2008, Physical review letters.

[21]  Anand Chandrasekaran,et al.  Ferroelectricity, Antiferroelectricity, and Ultrathin 2D Electron/Hole Gas in Multifunctional Monolayer MXene. , 2017, Nano letters.

[22]  H. Mizuseki,et al.  Mechanistic Insight into the Chemical Exfoliation and Functionalization of Ti 3 C 2 MXene , 2018 .

[23]  Atsuto Seko,et al.  Representation of compounds for machine-learning prediction of physical properties , 2016, 1611.08645.

[24]  Sang-Hoon Park,et al.  Oxidation Stability of Colloidal Two-Dimensional Titanium Carbides (MXenes) , 2017 .

[25]  Cormac Toher,et al.  Universal fragment descriptors for predicting properties of inorganic crystals , 2016, Nature Communications.

[26]  G. Pilania,et al.  Machine learning bandgaps of double perovskites , 2016, Scientific Reports.

[27]  Miguel A. L. Marques,et al.  The optimal one dimensional periodic table: a modified Pettifor chemical scale from data mining , 2016 .

[28]  Linggang Zhu,et al.  MXene: a promising photocatalyst for water splitting , 2016 .

[29]  Sanguthevar Rajasekaran,et al.  Accelerating materials property predictions using machine learning , 2013, Scientific Reports.

[30]  Aijun Du,et al.  Ti3C2 MXene co-catalyst on metal sulfide photo-absorbers for enhanced visible-light photocatalytic hydrogen production , 2017, Nature Communications.

[31]  Paul Raccuglia,et al.  Machine-learning-assisted materials discovery using failed experiments , 2016, Nature.

[32]  Thomas Hammerschmidt,et al.  Three-Parameter Crystal-Structure Prediction for sp-d-Valent Compounds , 2016 .

[33]  Luca M. Ghiringhelli,et al.  SISSO: a compressed-sensing method for systematically identifying efficient physical models of materials properties , 2017 .

[34]  G. Kresse,et al.  From ultrasoft pseudopotentials to the projector augmented-wave method , 1999 .

[35]  Feng Liu,et al.  Large-Gap Quantum Spin Hall State in MXenes: d-Band Topological Order in a Triangular Lattice. , 2016, Nano letters.

[36]  Jamil Tahir-Kheli,et al.  Resolution of the Band Gap Prediction Problem for Materials Design. , 2016, The journal of physical chemistry letters.

[37]  Yury Gogotsi,et al.  Dye adsorption and decomposition on two-dimensional titanium carbide in aqueous media , 2014 .