arXiv subjects

Ondrej Krejci

Publications and source records attributed to Ondrej Krejci.

6 recordsLinked to original sources

arXiv2026

Benchmarking machine-learned interatomic potentials for molecular infrared spectroscopy

Machine learning has transformed the field of atomistic simulations by enabling the development of interatomic potentials that are computationally efficient and highly accurate. These advances have opened the door to modeling molecular vibrations and predicting infrared spectra with near ab-initio accuracy at a fraction of the computational cost. Among these approaches, message-passing neural networks (MPNNs) have emerged as a particularly powerful class of models for representing complex atomic interactions. In this study, we benchmark five MPNN architectures, SchNet, FieldSchNet, SO3Net, PaiNN, and MACE, for predicting infrared spectra of small organic molecules. SchNet and FieldSchNet are invariant models, while SO3Net, PaiNN, and MACE are equivariant, explicitly accounting for rotational symmetries in molecular representations. We evaluate their performance in terms of computational efficiency, accuracy, and robustness. All models accurately predict properties, such as energies, forces, and dipole moments, required for infrared spectra calculations. They also capture harmonic frequencies and infrared spectra derived from molecular dynamics with high fidelity for molecules in the training set. However, SchNet and FieldSchNet show limited transferability to unseen systems, while SO3Net, PaiNN, and MACE generalize more effectively. In terms of computational efficiency, SchNet is the most efficient and FieldSchNet enables field-dependent response modeling but with higher cost. PaiNN achieves the best balance between accuracy and efficiency, MACE provides the highest spectral accuracy and transferability, and SO3Net performs between PaiNN and MACE.

physics.chem-ph↗

arXiv2026

MACE4IRmol: An uncertainty-aware foundation model for molecular infrared spectroscopy

Machine-learned interatomic potentials (MLIPs) have shown significant promise in predicting infrared spectra with high fidelity. However, the absence of general-purpose MLIPs that simultaneously span broad chemical diversity and provide reliable uncertainty estimates has limited their wider applicability. In this work, we introduce MACE4IRmol, an uncertainty-aware foundation model ensemble built on the MACE architecture. MACE4IRmol is trained on ~16 million molecular geometries and the corresponding density-functional theory (DFT) energies, forces, and dipole moments from the QCML dataset. The training data encompasses approximately 80 elements and a diverse set of molecules, including organic and inorganic compounds, and metal complexes. Importantly, MACE4IRmol is formulated as an ensemble of models to enable uncertainty quantification, which helps improve robustness in chemically diverse systems. Within this ensemble, separate models are trained with and without explicit dispersion corrections, allowing systematic assessment of van der Waals effects. In addition, MACE4IRmol delivers accurate predictions of energies, forces, dipole moments, and infrared spectra at a fraction of the computational cost of DFT, while enabling the explicit inclusion of nuclear quantum effects in infrared spectrum simulations. By combining generality, accuracy, efficiency, and uncertainty estimation, MACE4IRmol opens the door to rapid and reliable infrared spectra prediction for complex and diverse molecular systems.

physics.chem-ph↗

arXiv2025

Machine Learning Accelerated Descriptor Design for Catalyst Discovery in CO$_2$ to Methanol Conversion

Transforming CO$_2$ into methanol represents a crucial step towards closing the carbon cycle, with thermoreduction technology nearing industrial application. However, obtaining high methanol yields and ensuring the stability of heterocatalysts remain significant challenges. Herein, we present a sophisticated computational framework to accelerate the discovery of thermal heterogeneous catalysts, using machine-learned force fields. We propose a new catalytic descriptor, termed adsorption energy distribution, that aggregates the binding energies for different catalyst facets, binding sites, and adsorbates. The descriptor is versatile and can be adjusted to a specific reaction through careful choice of the key-step reactants and reaction intermediates. By applying unsupervised machine learning and statistical analysis to a dataset comprising nearly 160 metallic alloys, we offer a powerful tool for catalyst discovery. We propose new promising candidates such as ZnRh and ZnPt$_3$, which to our knowledge, have not yet been tested, and discuss their possible advantage in terms of stability.

physics.chem-ph↗

arXiv2025

Leveraging active learning-enhanced machine-learned interatomic potential for efficient infrared spectra prediction

Infrared (IR) spectroscopy is a pivotal analytical tool as it provides real-time molecular insight into material structures and enables the observation of reaction intermediates in situ. However, interpreting IR spectra often requires high-fidelity simulations, such as density functional theory based ab-initio molecular dynamics, which are computationally expensive and therefore limited in the tractable system size and complexity. In this work, we present a novel active learning-based framework, implemented in the open-source software package PALIRS, for efficiently predicting the IR spectra of small catalytically relevant organic molecules. PALIRS leverages active learning to train a machine-learned interatomic potential, which is then used for machine learning-assisted molecular dynamics simulations to calculate IR spectra. PALIRS reproduces IR spectra computed with ab-initio molecular dynamics accurately at a fraction of the computational cost. PALIRS further agrees well with available experimental data not only for IR peak positions but also for their amplitudes. This advancement with PALIRS enables high-throughput prediction of IR spectra, facilitating the exploration of larger and more intricate catalytic systems and aiding the identification of novel reaction pathways.

physics.chem-ph↗

arXiv2024

Advancing Scanning Probe Microscopy Simulations: A Decade of Development in Probe-Particle Models

The Probe-Particle Model combine theories designed for the simulation of scanning probe microscopy experiments, employing non-reactive, flexible tip apices to achieve sub-molecular resolution. In the article we present the latest version of the Probe-Particle Model implemented in the open-source ppafm package, highlighting substantial advancements in accuracy, computational performance, and userfriendliness. To demonstrate this we provide a comprehensive review of approaches for simulating non-contact Atomic Force Microscopy. They vary in complexity from simple Lennard-Jones potential to the latest full density-based model. We compared those approaches with ab initio calculated references, showcasing their respective merits. All parts of the ppafm package have undergone acceleration by 1-2 orders of magnitude using OpenMP and OpenCL technologies. The updated package includes n interactive graphical user interface and seamless integration into the Python ecosystem via pip, facilitating advanced scripting and interoperability with other software. This adaptability positions ppafm as an ideal tool for high-throughput applications, including the training of machine learning models for the automatic recovery of atomic structures from nc-AFM measurements. We envision significant potential for this application in future single-molecule analysis, synthesis, and advancements in on-surface science in general. Additionally, we discuss simulations of other sub-molecular scanning-probe imaging techniques, such as bond-resolved scanning tunnelling microscopy and kelvin probe force microscopy, all built on the robust foundation of the Probe-Particle Model. Altogether this demonstrates the broad impact of the model across diverse domains of surface science and molecular chemistry.

cond-mat.mes-hall↗

arXiv2019

Automated Structure Discovery in Atomic Force Microscopy

Atomic force microscopy (AFM) with molecule-functionalized tips has emerged as the primary experimental technique for probing the atomic structure of organic molecules on surfaces. Most experiments have been limited to nearly planar aromatic molecules, due to difficulties with interpretation of highly distorted AFM images originating from non-planar molecules. Here we develop a deep learning infrastructure that matches a set of AFM images with a unique descriptor characterizing the molecular configuration, allowing us to predict the molecular structure directly. We apply this methodology to resolve several distinct adsorption configurations of 1S-camphor on Cu(111) based on low-temperature AFM measurements. This approach will open the door to apply high-resolution AFM to a large variety of systems for which routine atomic and chemical structural resolution on the level of individual objects/molecules would be a major breakthrough.

physics.comp-ph↗