SMLQC seminar by Fang Liu, May 18, 2023

The 7th SMLQC seminar will be given by Fang Liu on May 18, 2023 (15:00 Paris | 21:00 Beijing | 09:00 New York).

Title

Machine learning aided fast and accurate quantum chemistry for solvated molecules

Abstract

The fast and accurate description of the solvent environment is crucial for quantum chemical (QC) discovery in the solution phase. We combine high-performance computing hardware and machine learning (ML) techniques to improve the efficiency and accuracy of QC discovery of solvated molecules.   To improve the efficiency, we developed strategies to accelerate both the implicit and explicit solvent models. For the implicit solvent models such as the conductor-like polarization model (C-PCM), we exploited graphical processing units (GPUs) to accelerate the calculation and achieved hundreds of speedups for ground- and excited- state calculations. For the explicit solvent model, we developed AutoSolvate, an open-source toolkit to streamline the QC calculation workflow of explicitly solvated molecules.  To improve the accuracy, we develop ML models to reduce the discrepancy between experimental measurements and computationally predicted molecular properties in both implicit and explicit solvent models. For ground-state redox potential calculations, our ML models can reduce both the systematic bias and the number of outliers, and the ML corrected results demonstrate less sensitivity to density functional theory (DFT) functional choice. This ML correction technique is transferrable to predicting other molecular properties in the solution phase, including the excited state redox potential and absorption/fluorescence wavelength.

Introduction to the speaker

Dr. Fang Liu is an assistant professor at the Department of Chemistry, Emory University. Her research focuses on developing algorithms to accelerate quantum chemistry calculations on GPUs and using machine learning to accelerate chemistry discovery. Dr. Liu obtained her B.S. in Chemical Physics at the University of Science and Technology of China in 2011, and Ph.D. in Chemistry at Stanford University in 2017. She did postdoctoral research in MIT from 2017 to 2020 and joined Emory University in 2020.

How to join

Join Zoom Meeting 
https://zoom.us/j/86004422973?pwd=WjNKQlEydmdFL3hJbUx4NjByYjVJZz09

Meeting ID: 860 0442 2973 

Passcode: 703098

SMLQC seminar by Johannes Margraf, May 4, 2023

The 6th SMLQC seminar will be given by Johannes Margraf on May 4, 2023 (22:00 Beijing | 16:00 Paris | 10:00 New York).

Title

Physical Description of Long-Range Interactions in Atomistic Machine Learning Models

Abstract

The dominating paradigm of state-of-the-art machine learning (ML) interatomic potentials is the use of local representations of atomic environments. While this locality has many computational and practical advantages, it ultimately also limits the achievable accuracy of a potentials, since information beyond the cutoff radius is not taken into account. Indeed, long-range interactions can be substantial in bulk systems, most prominently due to the Coulomb interaction, which decays slowly (~ 1/r) with the interatomic distance. These electrostatic interactions are often screened in practice, so that local potentials can still effectively describe polar solids and liquids with surprising accuracy. Unfortunately, this cannot always be relied upon. The inclusion of long-range interactions in ML potentials has therefore been an active field of study in recent years with many different approaches.
 In this seminar, I will focus on approaches that tackle the problem of long-range electrostatics by describing charge distributions via partial charges within the ML model itself. In particular, our recently reported Kernel Charge Equilibration (kQEq) method uses sparse Gaussian Processes to learn atomic electronegativities as a function of the chemical environment. This allows predicting partial charges with a charge equilibration model, including full long-range interactions and non-local charge transfer. Applications of kQEq in predicting molecular dipole moments and developing long-ranged interatomic potentials will be discussed.

Introduction to the speaker

Johannes T. Margraf studied chemistry at the University of Erlangen, where he also obtained his Ph.D. Subsequently he joined the Quantum Theory Project at the University of Florida as a PostDoc, funded by a Feodor-Lynen fellowship. This was followed by another postdoctoral fellowship at the Technical University of Munich. Since 2021, he is a group leader at the Theory Department of the Fritz-Haber-Institute in Berlin. His group focuses on using and developing machine-learning and electronic structure methods to study chemical reactions and discover new functional materials.

How to join

Join Zoom Meeting
https://zoom.us/j/86004422973?pwd=WjNKQlEydmdFL3hJbUx4NjByYjVJZz09

Meeting ID: 860 0442 2973

Passcode: 703098