The use of machine learning (ML) to refine low-level theoretical calculations to achieve higher accuracy is a promising and actively evolving approach known as Δ-ML. The density matrix renormalization group (DMRG) is a powerful variational approach widely used for studying strongly correlated quantum systems. High computational efficiency can be achieved without compromising accuracy. Here, we demonstrate the potential of a simple ML model to significantly enhance the performance of the quantum chemical DMRG method.

Applied Mathematics and Computational Research Division Lawerence Berkeley National Laboratory Berkeley 94720 United States

Department of Chemistry and Biochemistry University of California Santa Barbara Santa Barbara 93117 United States

Department of Materials University of California Santa Barbara Santa Barbara 93117 United States

J Heyrovsky Institute of Physical Chemistry v v i Czech Academy of Sciences Prague 18223 Czech Republic

J Heyrovský Institute of Physical Chemistry v v i Czech Academy of Sciences Prague 18223 Czech Republic

Zobrazit více v PubMed

Ramakrishnan R.; Dral P. O.; Rupp M.; von Lilienfeld O. A. Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach. J. Chem. Theory Comput. 2015, 11, 2087–2096. 10.1021/acs.jctc.5b00099. PubMed DOI

Smith J. S.; Nebgen B. T.; Zubatyuk R.; Lubbers N.; Devereux C.; Barros K.; Tretiak S.; Isayev O.; Roitberg A. E. Approaching Coupled Cluster Accuracy with a General-Purpose Neural Network Potential through Transfer Learning. Nat. Commun. 2019, 10, 2903.10.1038/s41467-019-10827-4. PubMed DOI PMC

Nandi A.; Qu C.; Houston P. L.; Conte R.; Bowman J. M. Δ-Machine Learning for Potential Energy Surfaces: A PIP Approach to Bring a DFT-based PES to CCSD(T) Level of Theory. J. Chem. Phys. 2021, 154, 051102.10.1063/5.0038301. PubMed DOI

Bowman J. M.; Qu C.; Conte R.; Nandi A.; Houston P. L.; Yu Q. Δ-Machine Learned Potential Energy Surfaces and Force Fields. J. Chem. Theory Comput. 2023, 19, 1–17. 10.1021/acs.jctc.2c01034. PubMed DOI

Ruth M.; Gerbig D.; Schreiner P. R. Machine Learning for Bridging the Gap between Density Functional Theory and Coupled Cluster Energies. J. Chem. Theory Comput. 2023, 19, 4912–4920. 10.1021/acs.jctc.3c00274. PubMed DOI

Maier S.; Collins E. M.; Raghavachari K. Quantitative Prediction of Vertical Ionization Potentials from DFT via a Graph-Network-Based Delta Machine Learning Model Incorporating Electronic Descriptors. J. Phys. Chem. A 2023, 127, 3472–3483. 10.1021/acs.jpca.2c08821. PubMed DOI

Collins E. M.; Raghavachari K. Interpretable Graph-Network-Based Machine Learning Models via Molecular Fragmentation. J. Chem. Theory Comput. 2023, 19, 2804–2810. 10.1021/acs.jctc.2c01308. PubMed DOI

Cheng L.; Welborn M.; Christensen A. S.; Miller T. F. III A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability Across Organic Molecules. J. Chem. Phys. 2019, 150, 131103.10.1063/1.5088393. PubMed DOI

Townsend J.; Vogiatzis K. D. Transferable MP2-Based Machine Learning for Accurate Coupled-Cluster Energies. J. Chem. Theory Comput. 2020, 16, 7453–7461. 10.1021/acs.jctc.0c00927. PubMed DOI

Käser S.; Boittier E. D.; Upadhyay M.; Meuwly M. Transfer Learning to CCSD(T): Accurate Anharmonic Frequencies from Machine Learning Models. J. Chem. Theory Comput. 2021, 17, 3687–3699. 10.1021/acs.jctc.1c00249. PubMed DOI

Ruth M.; Gerbig D.; Schreiner P. R. Machine Learning of Coupled Cluster (T)-Energy Corrections via Delta (Δ)-Learning. J. Chem. Theory Comput. 2022, 18, 4846–4855. 10.1021/acs.jctc.2c00501. PubMed DOI

Jones G. M.; Li R. R.; DePrince A. E. III; Vogiatzis K. D. Data-Driven Refinement of Electronic Energies from Two-Electron Reduced-Density-Matrix Theory. J. Phys. Chem. Lett. 2023, 14, 6377–6385. 10.1021/acs.jpclett.3c01382. PubMed DOI

White S. R. Density Matrix Formulation for Quantum Renormalization Groups. Phys. Rev. Lett. 1992, 69, 2863–2866. 10.1103/PhysRevLett.69.2863. PubMed DOI

White S. R. Density-Matrix Algorithms for Quantum Renormalization Groups. Phys. Rev. B 1993, 48, 10345–10356. 10.1103/PhysRevB.48.10345. PubMed DOI

Schollwöck U. Rev. Mod. Phys. 2005, 77, 259–315. 10.1103/RevModPhys.77.259. DOI

White S. R.; Martin R. L. Ab Initio Quantum Chemistry using the Density Matrix Renormalization Group. J. Chem. Phys. 1999, 110, 4127–4130. 10.1063/1.478295. DOI

Chan G. K.-L.; Sharma S. The Density Matrix Renormalization Group in Quantum Chemistry. Annu. Rev. Phys. Chem. 2011, 62, 465–481. 10.1146/annurev-physchem-032210-103338. PubMed DOI

Wouters S.; Van Neck D. The Density Matrix Renormalization Group for Ab Initio Quantum Chemistry. Eur. Phys. J. D 2014, 68, 272.10.1140/epjd/e2014-50500-1. DOI

Szalay S.; Pfeffer M.; Murg V.; Barcza G.; Verstraete F.; Schneider R.; Legeza Ö. Tensor Product Methods and Entanglement Optimization for Ab Initio Quantum Chemistry. Int. J. Quantum Chem. 2015, 115, 1342–1391. 10.1002/qua.24898. DOI

Baiardi A.; Reiher M. The Density Matrix Renormalization Group in Chemistry and Molecular Physics: Recent Developments and new Challenges. J. Chem. Phys. 2020, 152, 040903.10.1063/1.5129672. PubMed DOI

Schollwöck U. The density-matrix renormalization group in the age of matrix product states. Ann. Phys. 2011, 326, 96–192. 10.1016/j.aop.2010.09.012. DOI

Legeza O.; Sólyom J. Optimizing the Density-Matrix Renormalization Group Method Using Quantum Information Entropy. Phys. Rev. B 2003, 68, 195116.10.1103/PhysRevB.68.195116. DOI

Legeza O.; Sólyom J. Quantum Data Compression, Quantum Information Generation, and the Density-Matrix Renormalization-Group Method. Phys. Rev. B 2004, 70, 205118.10.1103/PhysRevB.70.205118. DOI

Rissler J.; Noack R. M.; White S. R. Measuring Orbital Interaction Using Quantum Information Theory. Chem. Phys. 2006, 323, 519–531. 10.1016/j.chemphys.2005.10.018. DOI

Legeza O.; Fath G. Accuracy of the Density-Matrix Renormalization-Group Method. Phys. Rev. B 1996, 53, 14349–14358. 10.1103/PhysRevB.53.14349. PubMed DOI

Chan G. K.-L.; Head-Gordon M. Highly Correlated Calculations with a Polynomial Cost Algorithm: A Study of the Density Matrix Renormalization Group. J. Chem. Phys. 2002, 116, 4462–4476. 10.1063/1.1449459. DOI

Olivares-Amaya R.; Hu W.; Nakatani N.; Sharma S.; Yang J.; Chan G. K.-L. The Ab-Initio Density Matrix Renormalization Group in Practice. J. Chem. Phys. 2015, 142, 034102.10.1063/1.4905329. PubMed DOI

Scarselli F.; Gori M.; Tsoi A. C.; Hagenbuchner M.; Monfardini G. The Graph Neural Network Model. IEEE Transactions on Neural Networks 2009, 20, 61–80. 10.1109/TNN.2008.2005605. PubMed DOI

Sanchez-Lengeling B.; Reif E.; Pearce A.; Wiltschko A.. A Gentle Introduction to Graph Neural Networks. Distill 2021, 6.10.23915/distill.00033 DOI

Wahab A.; Pfuderer L.; Paenurk E.; Gershoni-Poranne R. The COMPAS Project: A Computational Database of Polycyclic Aromatic Systems. Phase 1: cata-Condensed Polybenzenoid Hydrocarbons. J. Chem. Inf. Model. 2022, 62, 3704–3713. 10.1021/acs.jcim.2c00503. PubMed DOI

Ortiz R.; Boto R. A.; García-Martínez N.; Sancho-García J. C.; Melle-Franco M.; Fernández-Rossier J. Exchange Rules for Diradical π-Conjugated Hydrocarbons. Nano Lett. 2019, 19, 5991–5997. 10.1021/acs.nanolett.9b01773. PubMed DOI

Song S.; Pinar Solé A.; Matěj A.; Li G.; Stetsovych O.; Soler D.; Yang H.; Telychko M.; Li J.; Kumar M.; Chen Q.; Edalatmanesh S.; Brabec J.; Veis L.; Wu J.; Jelinek P.; Lu J. Highly entangled polyradical nanographene with coexisting strong correlation and topological frustration. Nat. Chem. 2024, 16, 938–944. 10.1038/s41557-024-01453-9. PubMed DOI

Sánchez-Grande A.; Urgel J. I.; Veis L.; Edalatmanesh S.; Santos J.; Lauwaet K.; Mutombo P.; Gallego J. M.; Brabec J.; Beran P.; Nachtigallová D.; Miranda R.; Martín N.; Jelínek P.; Écija D. Unravelling the Open-Shell Character of Peripentacene on Au(111). J. Phys. Chem. Lett. 2021, 12, 330–336. 10.1021/acs.jpclett.0c02518. PubMed DOI

Lee C.; Yang W.; Parr R. G. Development of the Colle-Salvetti Correlation-Energy Formula into a Functional of the Electron Density. Phys. Rev. B 1988, 37, 785–789. 10.1103/PhysRevB.37.785. PubMed DOI

Becke A. D. Density-Functional Exchange-Energy Approximation with Correct Asymptotic Behavior. Phys. Rev. A 1988, 38, 3098–3100. 10.1103/PhysRevA.38.3098. PubMed DOI

Dunning T. H. Gaussian Basis Sets for use in Correlated Molecular Calculations. I. The Atoms Boron Through Neon and Hydrogen. J. Chem. Phys. 1989, 90, 1007–1023. 10.1063/1.456153. DOI

Pipek J.; Mezey P. G. A fast intrinsic localization procedure applicable for ab initio and semiempirical linear combination of atomic orbital wave functions. J. Chem. Phys. 1989, 90, 4916–4926. 10.1063/1.456588. DOI

https://github.com/golubp/QC_DMRG_pred, accessed 2024-12-06.

Roemelt M.; Pantazis D. A. Multireference Approaches to Spin-State Energetics of Transition Metal Complexes Utilizing the Density Matrix Renormalization Group. Adv. Theory Simul. 2019, 2, 1800201.10.1002/adts.201800201. DOI