922 citations · 1.4k across the 25 of their papers we have counts for
21 papers · 1 filter
Can Machine Learning Potentials Be More Accurate Than the Methods They Are Trained On?
Pavlo O. Dral, Yi-Fan Hou, Yuxinxin Chen +4
Although machine learning potentials (MLPs) generalize across configurational and chemical compound spaces, their accuracy is commonly believed to be limited by their training meth…
Science Done on a Machine by a Machine: AI Agents in Computational Chemistry
Pavlo O. Dral, Hassan Nawaz, Arif Ullah
We are witnessing an explosion of agentic systems for computational chemistry: from four in 2024 to seventeen in 2025 and over sixty now, surveyed here. What is delegated to these…
Toward Machine Learning Enhancement of Accelerated Surface Hopping with Scaled Spin--Orbit Couplings
Jakub Martinka, Mahesh Kumar Sit, Pavlo O. Dral +1
Surface hopping (SH) methods are typically employed to simulate ultrafast nonadiabatic processes, but long timescales often remain beyond their reach. To address this, accelerated…
Flexible Framework for Surface Hopping: From Hybrid Schemes for Machine Learning to Benchmarkable Nonadiabatic Dynamics
Jakub Martinka, Mikołaj Martyka, Biman Medhi +2
Nonadiabatic molecular dynamics is a key technique for investigating a broad range of photochemical and photophysical processes. Among the established approaches, surface hopping s…
Artificial Intelligence for Direct Prediction of Molecular Dynamics Across Chemical Space
Fuchun Ge, Yuxinxin Chen, Pavlo O. Dral
Molecular dynamics (MD) is a powerful tool for exploring the behavior of atomistic systems, but its reliance on sequential numerical integration limits simulation efficiency. We pr…
All-in-one foundational models learning across quantum chemical levels
Yuxinxin Chen, Pavlo O. Dral
Machine learning (ML) potentials typically target a single quantum chemical (QC) level while the ML models developed for multi-fidelity learning have not been shown to provide scal…
Molecular Quantum Chemical Data Sets and Databases for Machine Learning Potentials
Arif Ullah, Yuxinxin Chen, Pavlo O. Dral
The field of computational chemistry is increasingly leveraging machine learning (ML) potentials to predict molecular properties with high accuracy and efficiency, providing a viab…
A simple approach to rotationally invariant machine learning of avector quantity
Jakub Martinka, Marek Pederzoli, Mario Barbatti +2
Unlike with the energy, which is a scalar property, machine learning (ML) predictions of vector or tensor properties poses the additional challenge of achieving proper invariance (…
MLatom software ecosystem for surface hopping dynamics in Python with quantum mechanical and machine learning methods
Lina Zhang, Sebastian V. Pios, Mikołaj Martyka +7
We present an open-source MLatom@XACS software ecosystem for on-the-fly surface hopping nonadiabatic dynamics based on the Landau-Zener-Belyaev-Lebedev (LZBL) algorithm. The dynami…
Tell machine learning potentials what they are needed for: Simulation-oriented training exemplified for glycine
Fuchun Ge, Ran Wang, Chen Qu +6
Machine learning potentials (MLPs) are widely applied as an efficient alternative way to represent potential energy surfaces (PES) in many chemical simulations. The MLPs are often…
Physics-Informed Neural Networks and Beyond: Enforcing Physical Constraints in Quantum Dissipative Dynamics
Arif Ullah, Yu Huang, Ming Yang +1
Neural networks (NNs) accelerate simulations of quantum dissipative dynamics. Ensuring that these simulations adhere to fundamental physical laws is crucial, but has been largely i…
Physics-informed active learning for accelerating quantum chemical simulations
Yi-Fan Hou, Lina Zhang, Quanhao Zhang +2
Quantum chemical simulations can be greatly accelerated by constructing machine learning potentials, which is often done using active learning (AL). The usefulness of the construct…
AI-enhanced on-the-fly simulation of nonlinear time-resolved spectra
Sebastian V. Pios, Maxim F. Gelin, Arif Ullah +2
Time-resolved spectroscopy is an important tool for unraveling the minute details of structural changes of molecules of biological and technological significance. The nonlinear fem…
MLatom 3: Platform for machine learning-enhanced computational chemistry simulations and workflows
Pavlo O. Dral, Fuchun Ge, Yi-Fan Hou +15
Machine learning (ML) is increasingly becoming a common tool in computational chemistry. At the same time, the rapid development of ML methods requires a flexible software framewor…
Four-Dimensional-Spacetime Atomistic Artificial Intelligence Models
Fuchun Ge, Lina Zhang, Yi-Fan Hou +3
We demonstrate that AI can learn atomistic systems in the four-dimensional (4D) spacetime. For this, we introduce the 4D-spacetime GICnet model which for the given initial conditio…
Energy-conserving molecular dynamics is not energy conserving
Lina Zhang, Yi-Fan Hou, Fuchun Ge +1
Molecular dynamics (MD) is a widely-used tool for simulating the molecular and materials properties. It is a common wisdom that molecular dynamics simulations should obey physical…
MLQD: A package for machine learning-based quantum dissipative dynamics
Arif Ullah, Pavlo O. Dral
Machine learning has emerged as a promising paradigm to study the quantum dissipative dynamics of open quantum systems. To facilitate the use of our recently published ML-based app…
QD3SET-1: A Database with Quantum Dissipative Dynamics Data Sets
Arif Ullah, Luis E. Herrera Rodriguez, Pavlo O. Dral +1
Simulations of the dynamics of dissipative quantum systems utilize many methods such as physics-based quantum, semiclassical, and quantum-classical as well as machine learning-base…
Ultra-Fast Semi-Empirical Quantum Chemistry for High-Throughput Computational Campaigns with Sparrow
Francesco Bosia, Peikun Zheng, Alain Vaucher +3
Semi-empirical quantum chemical approaches are known to compromise accuracy for feasibility of calculations on huge molecules. However, the need for ultrafast calculations in inter…
Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
Pavlo O. Dral, Alec Owens, Sergei N. Yurchenko +1
We present an efficient approach for generating highly accurate molecular potential energy surfaces (PESs) using self-correcting, kernel ridge regression (KRR) based machine learni…
Big Data meets Quantum Chemistry Approximations: The -Machine Learning Approach
Raghunathan Ramakrishnan, Pavlo O. Dral, Matthias Rupp +1
Chemically accurate and comprehensive studies of the virtual space of all possible molecules are severely limited by the computational cost of quantum chemistry. We introduce a com…