Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.23643

Scalable long-range machine learning interatomic potentials with electrical response for atomistic material modeling

Yicheng Chen·Xiaoyun Yu·Hyejeong Song·Xintian Wang·Zihui Li·Zixi Xia·Junmin Chen·Peichen Zhong
View original source ↗Read source document ↗Export metadata ↓

Abstract

Accurate atomistic simulations of materials under electric fields require long-range electrostatics and electrical-response modeling at length scales beyond the reach of conventional first-principles methods. Yet these capabilities remain difficult to reconcile with the scalability of machine-learning interatomic potentials (MLIPs). Strictly local models enable efficient spatial parallelization but neglect long-range interactions, whereas existing electrostatic extensions introduce global dependencies that hinder distributed computation. Here, we overcome this limitation by analytically separating the long-range electrostatic forces and Born effective charges (BECs) into a global electrostatics calculation and strictly local derivatives of learned latent charges. This formulation preserves the spatial decomposability of equivariant MLIPs while enabling distributed evaluation of energies, forces, stresses, and BECs across different boundary conditions. Implemented as DPA4C-LR on the \texttt{nvalchemi} platform, the framework scales to 5.2 million atoms on four GPUs at approximately twice the computational cost of its short-range backbone. Trained on energies and forces, DPA4C-LR accurately infers BECs and reproduces the field-dependent infrared spectra of water. We further demonstrate its capabilities by recovering the characteristic slim polarization hysteresis of relaxor \ce{Pb(Mg_{1/3}Nb_{2/3})O3}, which is obscured by finite-size effects in smaller simulations; predicting a room-temperature field-driven ionic conductivity of $6.8 \pm 0.7$~mS/cm in amorphous \ce{Li_{0.9}NbO_{0.9}Cl_{4.1}}; and modeling interfacial thermal transport across Si/diamond interfaces with slab-corrected electrostatics. By combining long-range physics, electrical-response inference, and distributed computation, this framework extends predictive atomistic modeling toward device-relevant length scales.

Explore related subjects

cond-mat.mtrl-scics.LG

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Yicheng Chen, Xiaoyun Yu, Hyejeong Song, Xintian Wang, Zihui Li, Zixi Xia, Junmin Chen, Peichen Zhong. 2026-10-16. Scalable long-range machine learning interatomic potentials with electrical response for atomistic material modeling. https://arxiv.org/abs/2610.23643

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Resolving the energy alignment between methylammonium lead iodide and C60: an in-situ photoelectron spectroscopy study

Understanding and controlling the energy level alignment at interfaces between lead halide perovskites and electron transport layers is crucial for optimizing perovskite-based devices such as solar cells. In this work, we investigated the energy level alignment of C60 on in-situ cleaved MAPbI3 single crystals in multiple repeat experiments using photoelectron spectroscopy aiming to resolve inconsistencies reported in earlier studies. Our results show that both materials remain chemically stable upon interface formation, in contrast to the strong reactions typically seen when metals are evaporated on perovskite surfaces. By analyzing the Pb 4f and C 1s binding energies in detail, we determined that C60 consistently exhibits a downward energy shift toward MAPbI3, which works against efficient charge extraction. The magnitude of this shift, however, varies between different sample positions, highlighting that small variations in sample surfaces can lead to significant differences in energetic alignment. These findings underscore the decisive role of surface chemistry on interfacial energetics, explain performance variability in perovskite devices, and demonstrate the need to control and accurately measure surface properties. Furthermore, the observed energetic alignment can explain why further interface modification by charge blocking layers or surface passivation is needed for optimized device efficiencies.

cond-mat.mtrl-sci↗
arXiv2026

Data-Efficient Indentation Size Effect Mitigation in Steels Using Machine Learning and a Physics-Constrained Neural Network

Shallow nanoindentation, needed for thin layers, individual phases and small volumes, gives hardness inflated by the indentation size effect (ISE). The Nix-Gao correction reduces this inflation but requires deep indentations of the same material, often impossible in such samples. We present a data-efficient workflow, trained on a few reference materials, that predicts a high-load reference hardness from a single shallow indentation. Seven models were trained on 703 indentations (5-350 mN) on three steels (2.0-6.5 GPa): Ridge regression, Random Forest, XGBoost, two feed-forward networks, and two physics-constrained neural networks (PCNNs) that apply a bounded learned correction q as H_app/sqrt(1+q). Over five seeds, models were tested on an external steel not used for training and indented at different loads, in leave-one-steel-out folds, and on fused silica, an out-of-domain material where all models failed. Random Forest and XGBoost, the best on the development set, transferred worst over all loads (MAPE 10.2 and 8.5%), whereas Ridge regression, the PCNNs and one feed-forward network reached 3.7-4.8%; with three training steels, development-set accuracy thus did not indicate accuracy on an unseen steel. From only the external steel's 3-15 mN indentations, the smooth (non-tree) models estimated the reference within 0.03-0.19 GPa on average. The PCNNs matched the linear baseline within the training hardness range and were the most accurate for a held-out steel softer than the training steels, but failed for a harder one. The workflow uses no steel-specific inputs and can be retrained for other material classes.

cond-mat.mtrl-sci↗
arXiv2026

Theoretical study of nitrogen-vacancy spin coherence enhanced by vacancy aggregation in diamond using cluster-correlation expansion

Annealing a semiconductor makes its vacancies mobile; they aggregate into multi-vacancy complexes that often carry spin. Such centres are a magnetic-noise source for any spin qubit among them, in silicon and silicon carbide as well as in diamond, and they are accordingly blamed for NV- decoherence in irradiated and implanted diamond, with two coherence records credited to removing them. Cluster-correlation-expansion simulations driven by published electron-paramagnetic-resonance parameters invert that attribution. At a fixed paramagnetic spin density a multi-vacancy bath gives a Hahn-echo coherence time 3.1-7.1 times longer than a bath of isolated negative vacancies, over three decades of concentration. A bath dephases the qubit because its spins exchange spin projections with one another, and two can exchange only if their transition frequencies match. A fine-structure splitting shifts those frequencies. Were every defect on the same crystallographic site, all would shift alike and still match: worth only a factor 1.15. Real defects occupy symmetry-equivalent sites pointing in different directions, so neighbours land at different frequencies and stop exchanging: a further 2.7. What governs the coherence time is therefore the fraction of bath pairs sharing a transition frequency, not the zero-field splitting. Vacancy aggregation extends NV- spin coherence rather than shortening it.

cond-mat.mtrl-sci↗