arXiv subjects

Ken-ichi Nomura

Publications and source records attributed to Ken-ichi Nomura.

18 recordsLinked to original sources

arXiv2026

Diagnosing Latent Energy Decomposition in Machine-Learning Interatomic Potentials via Interacting Quantum Atoms

Machine-learning interatomic potentials (MLIPs) can reproduce potential energies and forces accurately, but their internal energy allocation is often difficult to interpret. E3D-IQA is introduced as a diagnostic framework connecting the latent edge-energy representation of an Allegro-type MLIP with Interacting Quantum Atoms (IQA) energy decomposition. The Allegro edge-energy path is retained as a latent pair contribution, while a node-energy path is trained against the IQA intra-atomic energy. IQA interatomic energies are not direct training targets; instead, the learned edge energies are evaluated after training against the IQA pair terms. Tests on H/C/N/O organic reaction structures show that intra-atomic supervision is essential: energy and force training alone does not recover an IQA-like one-body/two-body allocation. With intra-atomic supervision, node energies reproduce IQA intra-atomic terms, and latent edge energies show meaningful correspondence with IQA interatomic terms. Residual errors are concentrated in positive or weak pair interactions, exposing internal allocation failures that remain hidden in total-energy and force metrics. Adding structures labeled only with energies and forces improves transfer to larger molecules and reduces decomposition errors. E3D-IQA therefore provides a route for diagnosing and guiding latent scientific representations using partially labeled quantum-chemical datasets.

physics.chem-ph↗

arXiv2026

Benchmarking Universal Machine Learning Force Fields for Molecular Dynamics of Lunar Regolith Minerals

Universal machine-learning interatomic potentials provide a promising route for accelerating molecular dynamics simulations of materials, but their transferability to lunar regolith-relevant silicates, oxides, and hydrogen-bearing surface species remains elucidated. Here, we benchmark six foundation models, MACE-MH, MatterSim, SevenNet-0, UPET, UMA, and NequIP-OAM-L, using NVT molecular dynamics simulations of four representative lunar minerals: forsterite, fayalite, ilmenite, and anorthite. Structural fidelity is evaluated using temperature stability, bond-distance statistics, bond-angle distributions, and partial radial distribution functions, with comparison to crystallographic reference data. The models reproduce Si--O, Mg--O, Al--O, and Ca--O local environments reasonably well, while Fe--O and Ti--O coordination environments show broader distributions and larger short-timescale fluctuations, highlighting the need for further validation and fine tuning with additional ground truth data for Fe- and Ti-bearing lunar phases. Hydroxylated surface tests show consistent O--H bond-distance distributions across models and minerals, suggesting that these foundation models may provide useful starting points for screening surface hydroxyl stability and volatile-related processes. Performance benchmarks on a single NVIDIA RTX 4090 show that SevenNet-0, MatterSim, and UPET provide the highest throughput among the six tested models, MACE-MH remains practical at intermediate cost, and UMA and NequIP-OAM-L extend the comparison to newer foundation potentials at higher runtime cost and memory demand. These results provide an initial benchmark for applying universal foundation models to lunar mineral simulations and identify key directions for future ab initio validation, model fine-tuning, and applications to lunar volatile evolution, space weathering, ISRU, and polar sample return studies.

physics.geo-ph↗

arXiv2026

EquiFiLM: Charge-Conditioned Equivariant Force Fields via Feature-wise Linear Modulation

Foundation machine learning force fields (MLFFs) such as MACE-MP-0 and UMA cover broad chemical space at near density functional theory (DFT) accuracy. However, they assume equilibrium ground-state physics and do not natively handle externally induced changes to the electronic state, such as charging, applied fields, or electronic excitation, which limits their use for driven processes such as photoexcitation and charge injection. We propose EquiFiLM, a lightweight extension that adds continuous external conditioning to any equivariant foundation MLFF via a per-layer Feature-wise Linear Modulation (FiLM) block, learning externally driven changes to the potential energy surface from minimal training data. The block modulates only scalar channels and preserves E(3)-equivariance exactly. We demonstrate the recipe on charged liquid water with the foundation model MACE-MatPES as the backbone, yielding E-MACE. On the four training charges, E-MACE delivers a $3.1\times$ reduction in force RMSE ($21.3$ to $6.96$ meV/$\mathring{A}$) and a $61\times$ reduction in per-atom energy RMSE ($6.1$ to $0.1$ meV/atom) over a baseline without EquiFiLM trained on the same data, at indistinguishable inference cost. Across seven held-out interpolation and extrapolation charges, force RMSE stays within $18-61$ meV/$\mathring{A}$ and energy RMSE within $0.7-5.4$ meV/atom. The model runs stable molecular dynamics across the full range tested and predicts the charge-dependent first-shell response of the reduced pair distribution function probed by ultrafast electron diffraction. Adding this conditioning axis to the foundation requires only a few thousand DFT-labeled frames, against the $\approx 10^8$ structures of a charge-aware foundation trained from scratch. The recipe is backbone- and conditioning-agnostic: it applies without architectural change to any equivariant MLFF with scalar interaction-layer channels.

cs.LG↗

arXiv2026

Toward Exascale AI for Science: A Scalable AI Skill for Autonomous Microkinetics Discovery

We present a scalable AI-driven framework that advances autonomous scientific discovery by combining agentic workflow automation, high-performance computing, and scientific surrogate models. Using microkinetics discovery as a testbed, the work demonstrates how AI can reduce expert intervention, recover from failed simulations, and systematically evaluate surrogate model reliability. This study shows how AI skills can transform complex domain workflows into robust, scalable capabilities for next-generation materials research.

cs.CE↗

arXiv2025

Multiscale light-matter dynamics in quantum materials: from electrons to topological superlattices

Light-matter dynamics in topological quantum materials enables ultralow-power, ultrafast devices. A challenge is simulating multiple field and particle equations for light, electrons, and atoms over vast spatiotemporal scales on Exaflop/s computers with increased heterogeneity and low-precision focus. We present a paradigm shift that solves the multiscale/multiphysics/heterogeneity challenge harnessing hardware heterogeneity and low-precision arithmetic. Divide-conquer-recombine algorithms divide the problem into not only spatial but also physical subproblems of small dynamic ranges and minimal mutual information, which are mapped onto best-characteristics-matching hardware units, while metamodel-space algebra minimizes communication and precision requirements. Using 60,000 GPUs of Aurora, DC-MESH (divide-and-conquer Maxwell-Ehrenfest-surface hopping) and XS-NNQMD (excited-state neural-network quantum molecular dynamics) modules of MLMD (multiscale light-matter dynamics) software were 152- and 3,780-times faster than the state-of-the-art for 15.4 million-electron and 1.23 trillion-atom PbTiO3 material, achieving 1.87 EFLOP/s for the former. This enabled the first study of light-induced switching of topological superlattices for future ferroelectric 'topotronics'.

physics.comp-ph↗

arXiv2025

Beyond Scaling: Chemical Intuition as Emergent Ability of Universal Machine Learning Interatomic Potentials

Machine Learning Interatomic Potentials (MLIPs) have successfully demonstrated scaling behavior, i.e. the power-law improvement in training performance, however the emergence of novel capabilities at scale remains unexplored. We have developed Edge-wise Emergent Decomposition (E3D) framework to investigate how an MLIP develops the ability to derive physically meaningful local representations of chemical bonds without explicit supervision. Employing an E(3)-equivariant network (Allegro) trained on molecular data (SPICE~2), we found that the trained MLIP spontaneously learned representations of bond dissociation energy (BDE) by decomposing the global potential energy landscape. The learned BDE values quantitatively agree with literature and its scalability are found to be robust across diverse training datasets, suggesting the presence of underlying representation that captures chemical reactions faithfully beyond given training information. Our E3D analysis utilizing Shannon's entropy reveals a close interplay between the decomposability of potential energy learning, scalability of learning, and emergent chemical reactivity, thus providing novel insights of scaling limitations and pathways toward more physically interpretable and predictive simulations.

cond-mat.mtrl-sci↗

arXiv2025

Allegro-FM: Towards Equivariant Foundation Model for Exascale Molecular Dynamics Simulations

We present a foundation model for exascale molecular dynamics simulations by leveraging an E(3) equivariant network architecture (Allegro) and a set of large-scale organic and inorganic materials datasets merged by Total Energy Alignment (TEA) framework. Thanks to the large-scale training sets, the obtained model (Allegro-FM) is versatile for various materials simulations for diverse downstream tasks covering 89 elements in the periodic table. Allegro-FM exhibits excellent agreements with high-level quantum chemistry theories in describing structural, mechanical, and thermodynamic properties, while exhibiting emergent capabilities for structural correlations, reaction kinetics, mechanical strengths, fracture, and solid/liquid dissolution, for which the model has not been trained. Furthermore, we demonstrate the robust predictability and generalizability of Allegro-FM for chemical reactions using the Transition1x that consists of 10k organic reactions and 9.6 million configurations including transition state data, as well as calcium silicate hydrates as a testbed. With its computationally efficient, strictly-local network architecture, Allegro-FM scales up to multi-billion-atom systems with a parallel efficiency of 0.964 on the exaflop/s Aurora supercomputer at Argonne Leadership Computing Facility. The approach presented in this work demonstrates the potential of the foundation model for a novel materials design and discovery based on large-scale atomistic simulations.

cond-mat.mtrl-sci↗

arXiv2024

Generative AI-driven forecasting of oil production

Forecasting oil production from oilfields with multiple wells is an important problem in petroleum and geothermal energy extraction, as well as energy storage technologies. The accuracy of oil forecasts is a critical determinant of economic projections, hydrocarbon reserves estimation, construction of fluid processing facilities, and energy price fluctuations. Leveraging generative AI techniques, we model time series forecasting of oil and water productions across four multi-well sites spanning four decades. Our goal is to effectively model uncertainties and make precise forecasts to inform decision-making processes at the field scale. We utilize an autoregressive model known as TimeGrad and a variant of a transformer architecture named Informer, tailored specifically for forecasting long sequence time series data. Predictions from both TimeGrad and Informer closely align with the ground truth data. The overall performance of the Informer stands out, demonstrating greater efficiency compared to TimeGrad in forecasting oil production rates across all sites.

cs.LG↗

arXiv2024

Catalysis in Extreme Field Environments: The Case of Strongly Ionized $SiO_{2}$ Nanoparticle Surfaces

High electric fields can significantly alter catalytic environments and the resultant chemical processes. Such fields arise naturally in biological systems but can also be artificially induced through localized excitations at nanoscale. Recently, strong field excitation of dielectric nanoparticles has emerged as an avenue for studying catalysis in highly ionized environments producing extreme electric fields. While the dynamics of surface ion emission driven by ultrafast laser ionization has been heavily explored, understanding the molecular dynamics leading to fragmentation has remained elusive. To address this, we employed a multiscale approach utilizing non-adiabatic quantum molecular dynamics (NAQMD) simulations on hydrogenated silica surfaces in both bare and wetted environments under field conditions mimicking those of an ionized nanoparticle. Our findings indicate that hole localization drives fragmentation dynamics, leading to surface silanol dissociation within 50 fs and charge transfer-induced water splitting in wetted environments within 150 fs. Further insight into such ultrafast mechanisms is critical for advancement of catalysis on the surface of charged nanosystems.

physics.chem-ph↗

arXiv2024

Thermal Conductivity Calculation using Homogeneous Non-equilibrium Molecular Dynamics Simulation with Allegro

In this study, we derive the heat flux formula for the Allegro model, one of machine-learning interatomic potentials using the equivariant deep neural network, to calculate lattice thermal conductivity using the homogeneous non-equilibrium molecular dynamics (HNEMD) method based on the Green-Kubo formula. Allegro can construct more advanced atomic descriptors than conventional ones, and can be applied to multicomponent and large-scale systems, providing a significant advantage in estimating the thermal conductivity of anharmonic materials, such as thermoelectric materials. In addition, the spectral heat current (SHC) method, recently developed for the HNEMD framework (HNEMD-SHC), allows the calculation of not only the total thermal conductivity but also its frequency components. The verification of the heat flux and the demonstration of HNEMD-SHC method are performed for the extremely anharmonic low-temperature phase of Ag$_2$Se.

physics.comp-ph↗

arXiv2023

Molecular Autonomous Pathfinder using Deep Reinforcement Learning

Diffusion in solids is a slow process that dictates rate-limiting processes in key chemical reactions. Unlike crystalline solids that offer well-defined diffusion pathways, the lack of similar structural motifs in amorphous or glassy materials poses a great scientific challenge in estimating slow diffusion time. To tackle this problem, we have developed an AI-guided long-time atomistic simulation approach: Molecular Autonomous Pathfinder (MAP) framework based on Deep Reinforcement Learning (RL), where RL agent is trained to uncover energy efficient diffusion pathways. We employ Deep Q-Network architecture with distributed prioritized replay buffer enabling fully online agent training with accelerated experience sampling by an ensemble of asynchronous agents. After training, the agents provide atomistic configurations of diffusion pathways with their energy profile. We use a piecewise Nudged Elastic Band to refine the energy profile of the obtained pathway and corresponding diffusion time on the basis of transition state theory. With MAP, we have successfully identified atomistic mechanisms along molecular diffusion pathways in amorphous silica, with time scales comparable to experiments.

cond-mat.mtrl-sci↗

arXiv2023

Allegro-Legato: Scalable, Fast, and Robust Neural-Network Quantum Molecular Dynamics via Sharpness-Aware Minimization

Neural-network quantum molecular dynamics (NNQMD) simulations based on machine learning are revolutionizing atomistic simulations of materials by providing quantum-mechanical accuracy but orders-of-magnitude faster, illustrated by ACM Gordon Bell prize (2020) and finalist (2021). State-of-the-art (SOTA) NNQMD model founded on group theory featuring rotational equivariance and local descriptors has provided much higher accuracy and speed than those models, thus named Allegro (meaning fast). On massively parallel supercomputers, however, it suffers a fidelity-scaling problem, where growing number of unphysical predictions of interatomic forces prohibits simulations involving larger numbers of atoms for longer times. Here, we solve this problem by combining the Allegro model with sharpness aware minimization (SAM) for enhancing the robustness of model through improved smoothness of the loss landscape. The resulting Allegro-Legato (meaning fast and "smooth") model was shown to elongate the time-to-failure $t_\textrm{failure}$, without sacrificing computational speed or accuracy. Specifically, Allegro-Legato exhibits much weaker dependence of timei-to-failure on the problem size, $t_{\textrm{failure}} \propto N^{-0.14}$ ($N$ is the number of atoms) compared to the SOTA Allegro model $\left(t_{\textrm{failure}} \propto N^{-0.29}\right)$, i.e., systematically delayed time-to-failure, thus allowing much larger and longer NNQMD simulations without failure. The model also exhibits excellent computational scalability and GPU acceleration on the Polaris supercomputer at Argonne Leadership Computing Facility. Such scalable, accurate, fast and robust NNQMD models will likely find broad applications in NNQMD simulations on emerging exaflop/s computers, with a specific example of accounting for nuclear quantum effects in the dynamics of ammonia.

cs.DC↗

arXiv2022

Multiscale Graph Neural Networks for Protein Residue Contact Map Prediction

Machine learning (ML) is revolutionizing protein structural analysis, including an important subproblem of predicting protein residue contact maps, i.e., which amino-acid residues are in close spatial proximity given the amino-acid sequence of a protein. Despite recent progresses in ML-based protein contact prediction, predicting contacts with a wide range of distances (commonly classified into short-, medium- and long-range contacts) remains a challenge. Here, we propose a multiscale graph neural network (GNN) based approach taking a cue from multiscale physics simulations, in which a standard pipeline involving a recurrent neural network (RNN) is augmented with three GNNs to refine predictive capability for short-, medium- and long-range residue contacts, respectively. Test results on the ProteinNet dataset show improved accuracy for contacts of all ranges using the proposed multiscale RNN+GNN approach over the conventional approach, including the most challenging case of long-range contact prediction.

q-bio.QM↗

arXiv2021

MISTIQS: An open-source software for performing quantum dynamics simulations on quantum computers

We present MISTIQS, a Multiplatform Software for Time-dependent Quantum Simulations. MISTIQS delivers end-to-end functionality for simulating the quantum many-body dynamics of systems governed by time-dependent Heisenberg Hamiltonians across multiple quantum computing platforms. It provides high-level programming functionality for generating intermediate representations of quantum circuits which can be translated into a variety of industry-standard representations. Furthermore, it offers a selection of circuit compilation and optimization methods and facilitates execution of the quantum circuits on currently available cloud-based quantum computing backends. MISTIQS serves as an accessible and highly flexible research and education platform, allowing a broader community of scientists and students to perform quantum many-body dynamics simulations on current quantum computers.

quant-ph↗

arXiv2020

Physics-informed Neural-Network Software for Molecular Dynamics Applications

We have developed a novel differential equation solver software called PND based on the physics-informed neural network for molecular dynamics simulators. Based on automatic differentiation technique provided by Pytorch, our software allows users to flexibly implement equation of atom motions, initial and boundary conditions, and conservation laws as loss function to train the network. PND comes with a parallel molecular dynamics (MD) engine in order for users to examine and optimize loss function design, and different conservation laws and boundary conditions, and hyperparameters, thereby accelerate the PINN-based development for molecular applications.

physics.chem-ph↗

arXiv2020

Computational framework for polymer synthesis to study dielectric properties using polarizable reactive molecular dynamics

The increased energy and power density required in modern electronics poses a challenge for designing new dielectric polymer materials with high energy density while maintaining low loss at high applied electric fields. Recently, an advanced computational screening method coupled with hierarchical modelling has accelerated the identification of promising high energy density materials. It is well known that the dielectric response of polymeric materials is largely influenced by their phases and local heterogeneous structures as well as operational temperature. Such inputs are crucial to accelerate the design and discovery of potential polymer candidates. However, an efficient computational framework to probe temperature dependence of the dielectric properties of polymers, while incorporating effects controlled by their morphology is still lacking. In this paper, we propose a scalable computational framework based on reactive molecular dynamics with a valence-state aware polarizable charge model, which is capable of handling practically relevant polymer morphologies and simultaneously provide near-quantum accuracy in estimating dielectric properties of various polymer systems. We demonstrate the predictive power of our framework on high energy density polymer systems recently identified through rational experimental-theoretical co-design. Our scalable and automated framework may be used for high-throughput theoretical screenings of combinatorial large design space to identify next-generation high energy density polymer materials.

physics.chem-ph↗

arXiv2020

EZFF: Python Library for Multi-Objective Parameterization and Uncertainty Quantification of Interatomic Forcefields for Molecular Dynamics

Parameterization of interatomic forcefields is a necessary first step in performing molecular dynamics simulations. This is a non-trivial global optimization problem involving quantification of multiple empirical variables against one or more properties. We present EZFF, a lightweight Python library for parameterization of several types of interatomic forcefields implemented in several molecular dynamics engines against multiple objectives using genetic-algorithm-based global optimization methods. The EZFF scheme provides unique functionality such as the parameterization of hybrid forcefields composed of multiple forcefield interactions as well as built-in quantification of uncertainty in forcefield parameters and can be easily extended to other forcefield functional forms as well as MD engines.

physics.comp-ph↗

arXiv2010

DNA Sequencing via Quantum Mechanics and Machine Learning

Rapid sequencing of individual human genome is prerequisite to genomic medicine, where diseases will be prevented by preemptive cures. Quantum-mechanical tunneling through single-stranded DNA in a solid-state nanopore has been proposed for rapid DNA sequencing, but unfortunately the tunneling current alone cannot distinguish the four nucleotides due to large fluctuations in molecular conformation and solvent. Here, we propose a machine-learning approach applied to the tunneling current-voltage (I-V) characteristic for efficient discrimination between the four nucleotides. We first combine principal component analysis (PCA) and fuzzy c-means (FCM) clustering to learn the "fingerprints" of the electronic density-of-states (DOS) of the four nucleotides, which can be derived from the I-V data. We then apply the hidden Markov model and the Viterbi algorithm to sequence a time series of DOS data (i.e., to solve the sequencing problem). Numerical experiments show that the PCA-FCM approach can classify unlabeled DOS data with 91% accuracy. Furthermore, the classification is found to be robust against moderate levels of noise, i.e., 70% accuracy is retained with a signal-to-noise ratio of 26 dB. The PCA-FCM-Viterbi approach provides a 4-fold increase in accuracy for the sequencing problem compared with PCA alone. In conjunction with recent developments in nanotechnology, this machine-learning method may pave the way to the much-awaited rapid, low-cost genome sequencer.

physics.bio-ph↗