arXiv subjects

Maksim Kulichenko

Publications and source records attributed to Maksim Kulichenko.

4 recordsLinked to original sources

arXiv2026

SEDACS: A Scalable Framework for Complex Chemistry Simulations

Graph-based linear-scaling electronic-structure theory provides a scalable framework for parallel quantum-mechanical molecular dynamics (QMD) simulations by exploiting the nearsightedness of the non-local electronic connectivity in non-metallic systems. When combined with recent shadow molecular dynamics in an extended-Lagrangian formulation, it enables stable long-time simulations of large, chemically active systems. This article introduces the Scalable Ecosystem, Driver, and Analyzer for Complex Chemistry Simulations (SEDACS), which integrates all these advances within a modular, Python-based software package for large-scale QMD simulations driven by external electronic-structure codes. SEDACS provides a tunable, adaptive graph construction in which edges encode the non-local electronic overlap between atoms. This graph is then decomposed into a set of smaller, overlapping subgraphs, where the electronic structure of each of these subgraphs is solved for independently and in parallel using an external electronic-structure code. SEDACS can be coupled to a variety of external electronic-structure solvers with minimal modifications to their software, enabling rapid adoption of the graph-based QMD approach. In this way, SEDACS can greatly extend the capability of existing electronic-structure packages by enabling stable QMD simulations of systems that were previously computationally inaccessible. We demonstrate highly efficient and stable QMD simulations for chemically active systems with tens of thousands of atoms by interfacing SEDACS with an external Fortran-based electronic-structure code based on self-consistent-charge density functional tight-binding theory.

physics.chem-ph↗

arXiv2025

Enhancing Molecular Dipole Moment Prediction with Multitask Machine Learning

We present a multitask machine learning strategy for improving the prediction of molecular dipole moments by simultaneously training on quantum dipole magnitudes and inexpensive Mulliken atomic charges. With dipole magnitudes as the primary target and assuming only scalar dipole values are available without vector components we examine whether incorporating lower quality labels that do not quantitatively reproduce the target property can still enhance model accuracy. Mulliken charges were chosen intentionally as an auxiliary task, since they lack quantitative accuracy yet encode qualitative physical information about charge distribution. Our results show that including Mulliken charges with a small weight in the loss function yields up to a 30% improvement in dipole prediction accuracy. This multitask approach enables the model to learn a more physically grounded representation of charge distributions, thereby improving both the accuracy and consistency of dipole magnitude predictions. These findings highlight that even auxiliary data of limited quantitative reliability can provide valuable qualitative physical insights, ultimately strengthening the predictive power of machine learning models for molecular properties.

physics.chem-ph↗

arXiv2025

PySEQM 2.0: Accelerated Semiempirical Excited State Calculations on Graphical Processing Units

We report the implementation of electronic excited states for semi-empirical quantum chemical methods at the configuration interaction singles (CIS) and time-dependent Hartree-Fock (TDHF) level of theory in the PySEQM software. Built on PyTorch, this implementation leverages GPU acceleration to significantly speed up molecular property calculations. Benchmark tests demonstrate that our approach can compute excited states for molecules with nearly a thousand atoms in under a minute. Additionally, the implementation also includes a machine learning interface to enable parameters re-optimization and neural network training for future machine learning applications for excited state dynamics.

physics.chem-ph↗

arXiv2023

Semi-Empirical Shadow Molecular Dynamics: A PyTorch implementation

Extended Lagrangian Born-Oppenheimer molecular dynamics (XL-BOMD) in its most recent shadow potential energy version has been implemented in the semiempirical PyTorch-based software PySeQM. The implementation includes finite electronic temperatures, canonical density matrix perturbation theory, and an adaptive Krylov Subspace Approximation for the integration of the electronic equations of motion within the XL-BOMB approach (KSA-XL-BOMD). The PyTorch implementation leverages the use of GPU and machine learning hardware accelerators for the simulations. The new XL-BOMD formulation allows studying more challenging chemical systems with charge instabilities and low electronic energy gaps. Current public release of PySeQM continues our development of modular architecture for large-scale simulations employing semiempirical quantum mechanical treatment. Applied to molecular dynamics simulation of 840 carbon atoms, one integration time step executes in 4 seconds on a single Nvidia RTX A6000 GPU.

physics.comp-ph↗