Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

MLTB: Enhancing Transferability and Extensibility of Density Functional Tight-Binding Theory with Many-body Interaction Corrections

Journal Article · · Journal of Chemical Theory and Computation
We present a hybrid semiempirical density functional tight-binding (DFTB) model with a machine learning neural network potential as a correction to the repulsive term. This hybrid model, termed machine learning tight-binding (MLTB), employs the standard self-consistent charge (SCC) DFTB formalism as a baseline, enhanced by the HIP-NN potential as an effective many-body correction for short-range pairwise repulsive interactions. The MLTB model demonstrates significantly improved transferability and extensibility compared to the SCC-DFTB and HIP-NN models. This work provides a practical computational framework for developing reliable SCC-DFTB models with additional many-body corrections that more closely approach the DFT level of accuracy. We illustrate this method with the development of an accurate model for the thorium–oxygen system, applied to the study of its nanocluster structures (ThO2)n.
Research Organization:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Organization:
USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA); USDOE Office of Science (SC), Basic Energy Sciences (BES)
Grant/Contract Number:
89233218CNA000001
OSTI ID:
2507345
Alternate ID(s):
OSTI ID: 2568701
Report Number(s):
LA-UR--24-27467; 10.1021/acs.jctc.4c00858; 1549-9626
Journal Information:
Journal of Chemical Theory and Computation, Journal Name: Journal of Chemical Theory and Computation Journal Issue: 3 Vol. 21; ISSN 1549-9626; ISSN 1549-9618
Publisher:
American Chemical SocietyCopyright Statement
Country of Publication:
United States
Language:
English

References (55)

Optimized Slater-type basis sets for the elements 1-118 journal May 2003
Chemistry with ADF journal January 2001
Density-functional tight binding-an approximate density-functional theory method: DFTB-an approximate DFT method journal January 2012
Density functional tight binding: application to organic and biological molecules: Density functional tight binding journal June 2013
A new active learning approach for global optimization of atomic clusters journal May 2021
Density-functional tight-binding for beginners journal November 2009
Global minimum search via annealing: Nanoscale gold clusters journal February 2015
Environmental dependence of bonding: A challenge for modelling of intermetallics and fusion materials journal February 2007
Machine Learning Force Fields journal March 2021
Bond Covalency and Oxidation State of Actinide Ions Complexed with Therapeutic Chelating Agent 3,4,3-LI(1,2-HOPO) journal April 2018
Curvature Constrained Splines for DFTB Repulsive Potential Parametrization journal February 2021
Efficient Parameterization of Density Functional Tight-Binding for 5f-Elements: A Th–O Case Study journal July 2024
Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach journal April 2015
Numerical Optimization of Density Functional Tight Binding Models: Application to Molecules Containing Carbon, Hydrogen, Nitrogen, and Oxygen journal November 2017
Generalized Density-Functional Tight-Binding Repulsive Potentials from Unsupervised Machine Learning journal March 2018
A Density Functional Tight Binding Layer for Deep Learning of Chemical Hamiltonians journal October 2018
Development of Density Functional Tight-Binding Parameters Using Relative Energy Fitting and Particle Swarm Optimization journal February 2020
Learning to Use the Force: Fitting Repulsive Potentials in Density-Functional Tight-Binding with Gaussian Process Regression journal March 2020
DFTB Modeling of Lithium-Intercalated Graphite with Machine-Learned Repulsive Potential journal January 2021
Considering Density Functional Approaches for Actinide Species: The An66 Molecule Set journal August 2021
Accurate Many-Body Repulsive Potentials for Density-Functional Tight Binding from Deep Tensor Neural Networks journal July 2020
The Rise of Neural Networks for Materials and Chemical Dynamics journal July 2021
Experimental and Theoretical Comparison of Actinide and Lanthanide Bonding in M[N(EPR 2 ) 2 ] 3 Complexes (M = U, Pu, La, Ce; E = S, Se, Te; R = Ph, i Pr, H) journal January 2008
Quantum-chemical insights from deep tensor neural networks journal January 2017
δ and φ back-donation in AnIV metallacycles journal March 2020
Revisiting complexation thermodynamics of transplutonium elements up to einsteinium journal January 2018
Unraveling the structural stability and the electronic structure of ThO2 clusters journal January 2020
Density functional investigations of the properties and thermochemistry of UF6 and UF5 using valence-electron and all-electron approaches journal August 2004
Representing molecule-surface interactions with symmetry-adapted neural networks journal July 2007
A note on the Pulay force at finite electronic temperatures journal December 2008
Atom-centered symmetry functions for constructing high-dimensional neural network potentials journal February 2011
Geometry optimizations in the zero order regular approximation for relativistic effects journal May 1999
Hierarchical modeling of molecular energies using a deep neural network journal June 2018
Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansions journal June 2018
TBMaLT, a flexible toolkit for combining tight-binding and machine learning journal January 2023
Lightweight and effective tensor sensitivity for atomistic neural networks journal May 2023
Atomistic modelling of TiAl I. Bond-order potentials with environmental dependence journal January 2003
Density-functional tight-binding: basic concepts and applications to molecules and clusters journal January 2020
The tight-binding bond model journal January 1988
Tight-binding modelling of materials journal December 1997
Enhancing classical gold nanoparticle simulations with electronic corrections and machine learning journal June 2021
Machine learning and genetic algorithm prediction of energy differences between electronic calculations of graphene nanoflakes journal August 2017
Interatomic Forces in Condensed Matter book October 2003
Density functional tight binding
  • Elstner, Marcus; Seifert, Gotthard
  • Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 372, Issue 2011 https://doi.org/10.1098/rsta.2012.0483
journal March 2014
Self-Consistent Equations Including Exchange and Correlation Effects journal November 1965
Simplified LCAO Method for the Periodic Potential Problem journal June 1954
Locality meets machine learning: Excited and ground-state energy surfaces of large systems at the cost of small ones journal March 2020
Construction of tight-binding-like potentials on the basis of density-functional theory: Application to carbon journal May 1995
Self-consistent-charge density-functional tight-binding method for simulations of complex materials properties journal September 1998
Relative energetics and structural properties of zirconia using a self-consistent tight-binding model journal March 2000
Automatic generation of matrix element derivatives for tight binding models journal October 2005
Generalized Gradient Approximation Made Simple journal October 1996
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces journal April 2007
Parametrization protocol and refinement strategies for accurate and transferable analytic bond-order potentials: Application to Re journal January 2024
Artificial neural network correction for density-functional tight-binding molecular dynamics simulations journal June 2019

Similar Records

A Density Functional Tight Binding Model with an Extended Basis Set and Three-Body Repulsion for Hydrogen under Extreme Thermodynamic Conditions
Journal Article · Mon Jun 23 20:00:00 EDT 2014 · Journal of Physical Chemistry. A, Molecules, Spectroscopy, Kinetics, Environment, and General Theory · OSTI ID:1466917

Self-Consistent Charge Density-Functional Tight-Binding Parametrization for Pt–Ru Alloys
Journal Article · Mon Mar 06 19:00:00 EST 2017 · Journal of Physical Chemistry. A, Molecules, Spectroscopy, Kinetics, Environment, and General Theory · OSTI ID:1480252