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

Automation of Active Space Selection for Multireference Methods via Machine Learning on Chemical Bond Dissociation

Journal Article · · Journal of Chemical Theory and Computation
 [1];  [2];  [2];  [2];  [2];  [3];  [2]
  1. Univ. of Minnesota, Minneapolis, MN (United States); University of Minnesota
  2. Univ. of Minnesota, Minneapolis, MN (United States)
  3. Uppsala Univ. (Sweden)
+ Show Author Affiliations
Predicting and understanding the chemical bond is one of the major challenges of computational quantum chemistry. Kohn–Sham density functional theory (KS-DFT) is the most common method, but approximate density functionals may not be able to describe systems where multiple electronic configurations are equally important. Multiconfigurational wave functions, on the other hand, can provide a detailed understanding of the electronic structures and chemical bonds of such systems. In the complete active space self-consistent field (CASSCF) method, one performs a full configuration interaction calculation in an active space consisting of active electrons and active orbitals. However, CASSCF and its variants require the selection of these active spaces. This choice is not black box; it requires significant experience and testing by the user, and thus active space methods are not considered particularly user-friendly and are employed only by a minority of quantum chemists. Our goal is to popularize these methods by making it easier to make good active space choices. Here, we present a machine learning protocol that performs an automated selection of active spaces for chemical bond dissociation calculations of main group diatomic molecules. The protocol shows high prediction performance for a given target system as long as a properly correlated system is chosen for training. Good active spaces are correctly predicted with a considerably better success rate than random guess (larger than 80% precision for most systems studied). Our automated machine learning protocol shows that a “black-box” mode is possible for facilitating and accelerating the large-scale calculations on multireference systems where single-reference methods such as KS-DFT cannot be applied.
Research Organization:
Univ. of Minnesota, Minneapolis, MN (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Basic Energy Sciences (BES). Chemical Sciences, Geosciences & Biosciences Division
Grant/Contract Number:
SC0008688
OSTI ID:
1712738
Journal Information:
Journal of Chemical Theory and Computation, Journal Name: Journal of Chemical Theory and Computation Journal Issue: 4 Vol. 16; ISSN 1549-9618
Publisher:
American Chemical SocietyCopyright Statement
Country of Publication:
United States
Language:
English

References (80)

Learning from the Harvard Clean Energy Project: The Use of Neural Networks to Accelerate Materials Discovery journal September 2015
Charge‐Shift Bonding: A New and Unique Form of Bonding journal November 2019
Molcas 8: New capabilities for multiconfigurational quantum chemical calculations across the periodic table : Molcas 8 journal November 2015
Deep learning for computational chemistry journal March 2017
autoCAS : A Program for Fully Automated Multiconfigurational Calculations journal June 2019
How to select active space for multiconfigurational quantum chemistry? journal April 2011
The complete active space SCF method in a fock-matrix-based super-CI formulation journal March 1980
Deadwood in configuration spaces. II. Singles + doubles and singles + doubles + triples + quadruples spaces journal April 2002
Identification of deadwood in configuration spaces through general direct configuration interaction journal October 2001
A comparative study of analytic representations of potential energy curves for O2, N2, and SO in their ground electronic states journal June 2019
Discontinuity of valence CASSCF wave functions around weakly avoided crossing between valence configurations journal August 1990
Next-Generation Experimentation with Self-Driving Laboratories journal June 2019
Spin State Energetics and Oxyl Character of Mn-Oxo Porphyrins by Multiconfigurational ab Initio Calculations: Implications on Reactivity journal February 2016
MultiDK: A Multiple Descriptor Multiple Kernel Approach for Molecular Discovery and Its Application to Organic Flow Battery Electrolytes journal April 2017
Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach journal April 2015
Multireference Character for 4d Transition Metal-Containing Molecules journal November 2015
Automated Selection of Active Orbital Spaces journal March 2016
Automated Construction of Molecular Active Spaces from Atomic Valence Orbitals journal August 2017
Automatic Selection of an Active Space for Calculating Electronic Excitation Spectra by MS-CASPT2 or MC-PDFT journal February 2018
Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis journal July 2018
Many-Body Expanded Full Configuration Interaction. I. Weakly Correlated Regime journal August 2018
Machine Learning Configuration Interaction journal October 2018
Constructing Molecular π-Orbital Active Spaces for Multireference Calculations of Conjugated Systems journal January 2019
Active Space Selection Based on Natural Orbital Occupation Numbers from n -Electron Valence Perturbation Theory journal April 2019
Automatic Active Space Selection for Calculating Electronic Excitation Energies Based on High-Spin Unrestricted Hartree–Fock Orbitals journal August 2019
Making the Coupled Cluster Correlation Energy Machine-Learnable journal July 2018
DFT Variants for Mixed-Metal Oxides. Benchmarks Using Multi-Center Cluster Models journal August 2018
Self-Evolving Machine: A Continuously Improving Model for Molecular Thermochemistry journal February 2019
Prediction of Adsorption Energies for Chemical Species on Metal Catalyst Surfaces Using Machine Learning journal November 2018
Virtual Orbital Many-Body Expansions: A Possible Route towards the Full Configuration Interaction Limit journal September 2017
Metallic Metal–Organic Frameworks Predicted by the Combination of Machine Learning Methods and Ab Initio Calculations journal July 2018
Nonadiabatic Excited-State Dynamics with Machine Learning journal September 2018
Data-Driven Acceleration of the Coupled-Cluster Singles and Doubles Iterative Solver journal June 2019
The Matter Simulation (R)evolution journal February 2018
Automatic Differentiation in Quantum Chemistry with Applications to Fully Variational Hartree–Fock journal May 2018
Transferable Machine-Learning Model of the Electron Density journal December 2018
A Mixed Quantum Chemistry/Machine Learning Approach for the Fast and Accurate Prediction of Biochemical Redox Potentials and Its Large-Scale Application to 315 000 Redox Reactions journal June 2019
Multireference Character for 3d Transition-Metal-Containing Molecules journal January 2012
Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies journal July 2013
Machine-Learning Prediction of CO Adsorption in Thiolated, Ag-Alloyed Au Nanoclusters journal November 2018
Use machine learning to find energy materials  journal December 2017
Charge-shift bonding and its manifestations in chemistry journal August 2009
The high-throughput highway to computational materials design journal February 2013
Bypassing the Kohn-Sham equations with machine learning journal October 2017
Capturing chemical intuition in synthesis of metal-organic frameworks journal February 2019
Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning journal July 2019
Active learning for accelerated design of layered materials journal December 2018
Accelerating the discovery of materials for clean energy in the era of smart automation journal April 2018
Active learning across intermetallics to guide discovery of electrocatalysts for CO2 reduction and H2 evolution journal September 2018
Revisiting the role of exact exchange in DFT spin-state energetics of transition metal complexes journal January 2014
Machine learning exciton dynamics journal January 2016
ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost journal January 2017
Machine learning for quantum dynamics: deep learning of excitation energy transfer properties journal January 2017
High-throughput screening of bimetallic catalysts enabled by machine learning journal January 2017
Automated calculation of thermal rate coefficients using ring polymer molecular dynamics and machine-learning interatomic potentials with active learning journal January 2018
How machine learning can assist the interpretation of ab initio molecular dynamics simulations and conceptual understanding of chemistry journal January 2019
Potential Energy Functions for Diatomic Molecules journal January 1941
The unrestricted natural orbital–complete active space (UNO–CAS) method: An inexpensive alternative to the complete active space–self‐consistent‐field (CAS–SCF) method journal April 1989
Ab initio quantum chemistry using the density matrix renormalization group journal March 1999
Adaptive multiconfigurational wave functions journal March 2014
Selection of active spaces for multiconfigurational wavefunctions journal June 2015
Perspective: Kohn-Sham density functional theory descending a staircase journal October 2016
Incremental full configuration interaction journal March 2017
Improving the accuracy of Møller-Plesset perturbation theory with neural networks journal October 2017
Machine learning of molecular properties: Locality and active learning journal June 2018
SchNet – A deep learning architecture for molecules and materials journal June 2018
Less is more: Sampling chemical space with active learning journal June 2018
A universal density matrix functional from molecular orbital-based machine learning: Transferability across organic molecules journal April 2019
Machine-learned electron correlation model based on correlation energy density at complete basis set limit journal July 2019
Measuring multi-configurational character by orbital entanglement journal February 2017
The 2019 materials by design roadmap journal October 2018
Machine learning of molecular electronic properties in chemical compound space journal September 2013
Self-Consistent Equations Including Exchange and Correlation Effects journal November 1965
Density-matrix algorithms for quantum renormalization groups journal October 1993
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning journal January 2012
Molecular Dynamics with On-the-Fly Machine Learning of Quantum-Mechanical Forces journal March 2015
Density matrix formulation for quantum renormalization groups journal November 1992
What Is High-Throughput Virtual Screening? A Perspective from Organic Materials Discovery journal July 2015
The Exploration of Chemical Reaction Networks journal April 2020
Automated Identification of Relevant Frontier Orbitals for Chemical Compounds and Processes journal April 2017

Similar Records

Weighted active space protocol for multireference machine-learned potentials
Journal Article · Sun Sep 14 20:00:00 EDT 2025 · Proceedings of the National Academy of Sciences of the United States of America · OSTI ID:3005508
Modeling Oxidative Dehydrogenation of Propane with Supported Vanadia Catalysts Using Multireference Methods
Journal Article · Wed Jul 30 20:00:00 EDT 2025 · Journal of Physical Chemistry. C · OSTI ID:2587283
Distinguishing homolytic vs heterolytic bond dissociation of phenylsulfonium cations with localized active space methods
Journal Article · Sun Jun 30 20:00:00 EDT 2024 · Journal of Chemical Physics · OSTI ID:2403625

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
Chemical bonding
Chemical calculations
Kinetic parameters
Machine learning
Molecules