Kieron Burke

About

Kieron Burke is a distinguished professor in both the chemistry and physics departments at UC Irvine, with a research focus on developing a theory of quantum mechanics known as density functional theory (DFT). His work involves developing all aspects of DFT, including formalism, extensions to new areas, new approximations, and simplifications. DFT is a widely used tool in science, especially in chemistry and materials science, for solving the equations of quantum mechanics for electrons in various substances. Burke's research has practical applications in materials science, chemistry, matter under extreme conditions, magnetic materials, and molecular electronics. He has pioneered new applications of machine learning to electronic structure problems, collaborating with Google Accelerated Science and Google DeepMind. Burke is also known for his educational and outreach activities, and his graduate course in machine learning for scientists is among the most popular in the school of physical sciences.

Research topics

• Computer Science
• Artificial Intelligence
• Machine Learning
• Mathematics
• Physics
• Statistical physics
• Data science
• Management science
• Chemistry
• Cognitive science

Selected publications

• Quantum chemical accuracy from density functional approximations via machine learning

  Nature Communications · 2020 · 357 citations

  Senior authorCorresponding

  ) to obtain MD trajectories with coupled-cluster accuracy. We conclude, therefore, that Δ-DFT facilitates running gas-phase MD simulations with quantum chemical accuracy, even for strained geometries and conformer changes where standard DFT fails.

  DOI

• Retrospective on a decade of machine learning for chemical discovery

  Nature Communications · 2020 · 187 citations

  Senior authorCorresponding

  Over the last decade, we have witnessed the emergence of ever more machine learning applications in all aspects of the chemical sciences. Here, we highlight specific achievements of machine learning models in the field of computational chemistry by considering selected studies of electronic structure, interatomic potentials, and chemical compound space in chronological order.

  DOI

• Roadmap on Machine learning in electronic structure

  Electronic Structure · 2022 · 184 citations

  Abstract In recent years, we have been witnessing a paradigm shift in computational materials science. In fact, traditional methods, mostly developed in the second half of the XXth century, are being complemented, extended, and sometimes even completely replaced by faster, simpler, and often more accurate approaches. The new approaches, that we collectively label by machine learning, have their origins in the fields of informatics and artificial intelligence, but are making rapid inroads in all…

  PublisherOA PDFDOI

• Kohn-Sham Equations as Regularizer: Building Prior Knowledge into Machine-Learned Physics

  Physical Review Letters · 2021 · 179 citations

  Senior authorCorresponding

  Including prior knowledge is important for effective machine learning models in physics and is usually achieved by explicitly adding loss terms or constraints on model architectures. Prior knowledge embedded in the physics computation itself rarely draws attention. We show that solving the Kohn-Sham equations when training neural networks for the exchange-correlation functional provides an implicit regularization that greatly improves generalization. Two separations suffice for learning the enti…

  DOI

• Generalized Gradient Approximation Made Thermal

  arXiv (Cornell University) · 2023-08-07 · 15 citations

  preprintOpen accessSenior author

  Using the methodology of conditional-probability density functional theory, and several mild assumptions, we calculate the temperature-dependence of the Perdew-Burke-Ernzerhof (PBE) generalized gradient approximation (GGA). This numerically-defined thermal GGA reduces to the local approximation in the uniform limit and PBE at zero temperature, and can be fit reasonably accurately (within 8%) assuming the temperature-dependent enhancement is independent of the gradient. This locally thermal PBE s…

  PublisherOA PDFDOI

Recent grants

• EAGER: Density functionals from Machine Learning

  NSF · $300k · 2012–2015

• Electron-molecule Collisions From Time-dependent Density Functional Theory

  NSF · $345k · 2004–2007

• Aiming for Chemical Accuracy in Ground-state Density Functional Theory

  NSF · $510k · 2022–2025

Frequent coauthors

• John P. Perdew

  Temple University

  71 shared

• Adam Wasserman

  Purdue University West Lafayette

  49 shared

• Eunji Sim

  Yonsei University

  42 shared

• Peter Elliott

  Max-Born-Institute for Nonlinear Optics and Short Pulse Spectroscopy

  41 shared

• Morrel H. Cohen

  Princeton University

  39 shared

• Neepa T. Maitra

  31 shared

• Suhwan Song

  Yonsei University

  28 shared

• Aurora Pribram‐Jones

  University of California, Merced

  28 shared

Awards & honors

• Fellow of the American Physical Society
• Fellow of the Royal Society of Chemistry
• Fellow of the American Association for the Advancement of Sc…
• Member of the International Academy of Quantum Molecular Sci…

Similar researchers at University of California, Irvine

• Donald R. Blakeh-144
• Shaul Mukamelh-112
• Barbara J. Finlayson-Pittsh-73