{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T16:04:58Z","timestamp":1770998698985,"version":"3.50.1"},"reference-count":50,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"},{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2026,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Machine learning interatomic potentials (MLIPs) enable accurate atomistic modeling, but reliable uncertainty quantification (UQ) remains elusive. In this study, we investigate two UQ strategies, ensemble learning and D-optimality, within the atomic cluster expansion framework. It is revealed that higher model accuracy strengthens the correlation between predicted uncertainties and actual errors and improves novelty detection, with D-optimality yielding more conservative estimates. Both methods deliver well calibrated uncertainties on homogeneous training sets, yet they underpredict errors and exhibit reduced novelty sensitivity on heterogeneous datasets. To address this limitation, we introduce clustering enhanced local D-optimality, which partitions configuration space into clusters during training and applies D-optimality within each cluster. This approach substantially improves the detection of novel atomic environments in heterogeneous datasets. Our findings clarify the roles of model fidelity and data heterogeneity in UQ performance and provide a practical route to robust active learning and adaptive sampling strategies for MLIP development.<\/jats:p>","DOI":"10.1088\/2632-2153\/ae3d80","type":"journal-article","created":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T22:53:32Z","timestamp":1769468012000},"page":"025002","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Model accuracy and data heterogeneity shape uncertainty quantification in machine learning interatomic potentials"],"prefix":"10.1088","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6333-9237","authenticated-orcid":true,"given":"Fei","family":"Shuang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3900-3995","authenticated-orcid":true,"given":"Zixiong","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Poulumi","family":"Dey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2026,2,13]]},"reference":[{"key":"mlstae3d80bib1","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1038\/s41563-020-0777-6","type":"journal-article","article-title":"Machine-learned potentials for next-generation matter simulations","volume":"20","author":"Friederich","year":"2021","journal-title":"Nat. Mater."},{"key":"mlstae3d80bib2","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1557\/s43577-022-00440-0","type":"journal-article","article-title":"Beyond potentials: integrated machine learning models for materials","volume":"47","author":"Ceriotti","year":"2022","journal-title":"MRS Bull."},{"key":"mlstae3d80bib3","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1021\/acs.jpca.9b08723","type":"journal-article","article-title":"Performance and cost assessment of machine learning interatomic potentials","volume":"124","author":"Zuo","year":"2020","journal-title":"J. Phys. Chem. A"},{"key":"mlstae3d80bib4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cossms.2025.101214","type":"journal-article","article-title":"A practical guide to machine learning interatomic potentials - status and future","volume":"35","author":"Jacobs","year":"2025","journal-title":"Curr. Opin. Solid State Mater. Sci."},{"key":"mlstae3d80bib5","doi-asserted-by":"publisher","first-page":"5151","DOI":"10.1021\/acs.jctc.2c01149","type":"journal-article","article-title":"Atomic cluster expansion for quantum-accurate large-scale simulations of carbon","volume":"19","author":"Qamar","year":"2023","journal-title":"J. Chem. Theory Comput."},{"key":"mlstae3d80bib6","doi-asserted-by":"publisher","first-page":"5125","DOI":"10.1557\/s43578-023-01123-5","type":"journal-article","article-title":"Atomic cluster expansion for Pt-Rh catalysts: from ab initio to the simulation of nanoclusters in few steps","volume":"38","author":"Liang","year":"2023","journal-title":"J. Mater. Res."},{"key":"mlstae3d80bib7","doi-asserted-by":"publisher","first-page":"1927","DOI":"10.1038\/s41467-024-45840-9","type":"journal-article","article-title":"Modelling atomic and nanoscale structure in the silicon-oxygen system through active machine learning","volume":"15","author":"Erhard","year":"2024","journal-title":"Nat. Commun."},{"key":"mlstae3d80bib8","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1137\/15M1054183","type":"journal-article","article-title":"Moment tensor potentials: a class of systematically improvable interatomic potentials","volume":"14","author":"Shapeev","year":"2016","journal-title":"Multiscale Model. Simul."},{"key":"mlstae3d80bib9","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abc9fe","type":"journal-article","article-title":"The MLIP package: moment tensor potentials with MPI and active learning","volume":"2","author":"Novikov","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstae3d80bib10","doi-asserted-by":"publisher","DOI":"10.1063\/5.0155887","type":"journal-article","article-title":"MLIP-3: active learning on atomic environments with moment tensor potentials","volume":"159","author":"Podryabinkin","year":"2023","journal-title":"J. Chem. Phys."},{"key":"mlstae3d80bib11","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.99.014104","type":"journal-article","article-title":"Atomic cluster expansion for accurate and transferable interatomic potentials","volume":"99","author":"Drautz","year":"2019","journal-title":"Phys. Rev. B"},{"key":"mlstae3d80bib12","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1038\/s41524-021-00559-9","type":"journal-article","article-title":"Performant implementation of the atomic cluster expansion (PACE) and application to copper and silicon","volume":"7","author":"Lysogorskiy","year":"2021","journal-title":"npj Comput. Mater."},{"key":"mlstae3d80bib13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevMaterials.6.013804","type":"journal-article","article-title":"Efficient parametrization of the atomic cluster expansion","volume":"6","author":"Bochkarev","year":"2022","journal-title":"Phys. Rev. Mater."},{"key":"mlstae3d80bib14","doi-asserted-by":"publisher","DOI":"10.1002\/mgea.70028","type":"journal-article","article-title":"GPUMD 4.0: a high performance molecular dynamics package for versatile materials simulations with machine learned potentials","volume":"3","author":"Xu","year":"2025","journal-title":"Mater. Genome Eng. Adv."},{"key":"mlstae3d80bib15","doi-asserted-by":"publisher","DOI":"10.1016\/j.matchemphys.2023.128053","type":"journal-article","article-title":"Stability of binary precipitates in Cu-Ni-Si-Cr alloys investigated through active learning","volume":"306","author":"Carral","year":"2023","journal-title":"Mater. Chem. Phys."},{"key":"mlstae3d80bib16","doi-asserted-by":"publisher","DOI":"10.1016\/j.actamat.2024.120423","type":"journal-article","article-title":"Origin of the yield stress anomaly in L12 intermetallics unveiled with physically informed machine-learning potentials","volume":"281","author":"Xu","year":"2024","journal-title":"Acta Mater."},{"key":"mlstae3d80bib17","doi-asserted-by":"publisher","first-page":"5141","DOI":"10.1039\/D4CP04578E","type":"journal-article","article-title":"Accelerating structure prediction of molecular crystals using actively trained moment tensor potential","volume":"27","author":"Rybin","year":"2025","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstae3d80bib18","doi-asserted-by":"publisher","first-page":"9201","DOI":"10.1039\/D5CP00532A","type":"journal-article","article-title":"Accelerating the global search of adsorbate molecule positions using machine-learning interatomic potentials with active learning","volume":"27","author":"Klimanova","year":"2025","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstae3d80bib19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.111.094438","type":"journal-article","article-title":"Actively trained magnetic moment tensor potentials for mechanical, dynamical and thermal properties of paramagnetic CrN","volume":"111","author":"Kotykhov","year":"2025","journal-title":"Phys. Rev. B"},{"key":"mlstae3d80bib20","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1038\/s41524-023-01104-6","type":"journal-article","article-title":"Hyperactive learning for data-driven interatomic potentials","volume":"9","author":"van der Oord","year":"2023","journal-title":"npj Comput. Mater."},{"key":"mlstae3d80bib21","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1038\/s41524-025-01758-4","type":"journal-article","article-title":"Uncertainty quantification for misspecified machine learned interatomic potentials","volume":"11","author":"Perez","year":"2025","journal-title":"npj Comput. Mater."},{"key":"mlstae3d80bib22","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1038\/s41524-025-01572-y","type":"journal-article","article-title":"Uncertainty quantification for neural network potential foundation models","volume":"11","author":"Bilbrey","year":"2025","journal-title":"npj Comput. Mater."},{"key":"mlstae3d80bib23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevMaterials.7.043801","type":"journal-article","article-title":"Active learning strategies for atomic cluster expansion models","volume":"7","author":"Lysogorskiy","year":"2023","journal-title":"Phys. Rev. Mater."},{"key":"mlstae3d80bib24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.102.024104","type":"journal-article","article-title":"Atomic cluster expansion of scalar, vectorial and tensorial properties including magnetism and charge transfer","volume":"102","author":"Drautz","year":"2020","journal-title":"Phys. Rev. B"},{"key":"mlstae3d80bib25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2022.110946","type":"journal-article","article-title":"Atomic cluster expansion: completeness, efficiency and stability","volume":"454","author":"Dusson","year":"2022","journal-title":"J. Comput. Phys."},{"key":"mlstae3d80bib26","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1016\/j.jcp.2014.12.018","type":"journal-article","article-title":"Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials","volume":"285","author":"Thompson","year":"2015","journal-title":"J. Comput. Phys."},{"key":"mlstae3d80bib27","doi-asserted-by":"publisher","DOI":"10.1088\/1361-648X\/aa680e","type":"journal-article","article-title":"The atomic simulation environment-a python library for working with atoms","volume":"29","author":"Larsen","year":"2017","journal-title":"J. Phys.: Condens. Matter"},{"key":"mlstae3d80bib28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2021.108171","type":"journal-article","article-title":"LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso and continuum scales","volume":"271","author":"Thompson","year":"2022","journal-title":"Comput. Phys. Commun."},{"key":"mlstae3d80bib29","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.commatsci.2017.08.031","type":"journal-article","article-title":"Active learning of linearly parametrized interatomic potentials","volume":"140","author":"Podryabinkin","year":"2017","journal-title":"Comput. Mater. Sci."},{"key":"mlstae3d80bib30","doi-asserted-by":"publisher","first-page":"11169","DOI":"10.1103\/PhysRevB.54.11169","type":"journal-article","article-title":"Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set","volume":"54","author":"Kresse","year":"1996","journal-title":"Phys. Rev. B"},{"key":"mlstae3d80bib31","doi-asserted-by":"publisher","first-page":"3865","DOI":"10.1103\/PhysRevLett.77.3865","type":"journal-article","article-title":"Generalized gradient approximation made simple","volume":"77","author":"Perdew","year":"1996","journal-title":"Phys. Rev. Lett."},{"key":"mlstae3d80bib32","doi-asserted-by":"publisher","first-page":"17953","DOI":"10.1103\/PhysRevB.50.17953","type":"journal-article","article-title":"Projector augmented-wave method","volume":"50","author":"Bl\u00f6chl","year":"1994","journal-title":"Phys. Rev. B"},{"key":"mlstae3d80bib33","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2021.108033","type":"journal-article","article-title":"VASPKIT: a user-friendly interface facilitating high-throughput computing and analysis using VASP code","volume":"267","author":"Wang","year":"2021","journal-title":"Comput. Phys. Commun."},{"key":"mlstae3d80bib34","doi-asserted-by":"publisher","first-page":"5188","DOI":"10.1103\/PhysRevB.13.5188","type":"journal-article","article-title":"Special points for brillouin-zone integrations","volume":"13","author":"Monkhorst","year":"1976","journal-title":"Phys. Rev. B"},{"key":"mlstae3d80bib35","doi-asserted-by":"publisher","DOI":"10.1088\/0965-0393\/18\/1\/015012","type":"journal-article","article-title":"Visualization and analysis of atomistic simulation data with OVITO-the open visualization tool","volume":"18","author":"Stukowski","year":"2010","journal-title":"Modelling Simul. Mater. Sci. Eng."},{"key":"mlstae3d80bib36","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1038\/s41524-025-01599-1","type":"journal-article","article-title":"Modeling extensive defects in metals through classical potential-guided sampling and automated configuration reconstruction","volume":"11","author":"Shuang","year":"2025","journal-title":"npj Comput. Mater."},{"key":"mlstae3d80bib37","article-title":"MACE: higher order equivariant message passing neural networks for fast and accurate force fields","author":"Batatia","year":"2022","type":"conference-proceedings"},{"key":"mlstae3d80bib38","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1038\/s41524-023-01174-6","type":"journal-article","article-title":"Atomistic fracture in bcc iron revealed by active learning of Gaussian approximation potential","volume":"9","author":"Zhang","year":"2023","journal-title":"npj Comput. Mater."},{"key":"mlstae3d80bib39","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevMaterials.4.093802","type":"journal-article","article-title":"Gaussian approximation potentials for body-centered-cubic transition metals","volume":"4 093802","author":"Byggm\u00e4star","year":"2020","journal-title":"Phys. Rev. Mater."},{"key":"mlstae3d80bib40","article-title":"NEP89: universal neuroevolution potential for inorganic and organic materials across 89 elements","author":"Liang","year":"2025","type":"preprint"},{"key":"mlstae3d80bib41","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1038\/s41524-025-01669-4","type":"journal-article","article-title":"Automated generation of structure datasets for machine learning potentials and alloys","volume":"11","author":"Poul","year":"2025","journal-title":"npj Comput. Mater."},{"key":"mlstae3d80bib42","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.107.104103","type":"journal-article","article-title":"Systematic atomic structure datasets for machine learning potentials: application to defects in magnesium","volume":"107","author":"Poul","year":"2023","journal-title":"Phys. Rev. B"},{"key":"mlstae3d80bib43","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/aba373","type":"journal-article","article-title":"In operando active learning of interatomic interaction during large-scale simulations","volume":"1","author":"Hodapp","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstae3d80bib44","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.109.094120","type":"journal-article","article-title":"Automated atomistic simulations of dissociated dislocations with ab initio accuracy","volume":"109","author":"Mismetti","year":"2024","journal-title":"Phys. Rev. B"},{"key":"mlstae3d80bib45","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1038\/s41524-024-01227-4","type":"journal-article","article-title":"Robust training of machine learning interatomic potentials with dimensionality reduction and stratified sampling","volume":"10","author":"Qi","year":"2024","journal-title":"npj Comput. Mater."},{"key":"mlstae3d80bib46","doi-asserted-by":"publisher","first-page":"4014","DOI":"10.1038\/s41467-025-59232-0","type":"journal-article","article-title":"Model-free estimation of completeness, uncertainties and outliers in atomistic machine learning using information theory","volume":"16","author":"Schwalbe-Koda","year":"2025","journal-title":"Nat. Commun."},{"key":"mlstae3d80bib47","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.87.184115","type":"journal-article","article-title":"On representing chemical environments","volume":"87 184115","author":"Bart\u00f3k","year":"2013","journal-title":"Phys. Rev. B"},{"key":"mlstae3d80bib48","doi-asserted-by":"publisher","DOI":"10.1063\/5.0297006","type":"journal-article","article-title":"A foundation model for atomistic materials chemistry","volume":"163","author":"Batatia","year":"2025","journal-title":"J. Chem. Phys."},{"key":"mlstae3d80bib49","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-024-00956-x","type":"journal-article","article-title":"The design space of E(3)-equivariant atom-centred interatomic potentials","volume":"7","author":"Batatia","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"mlstae3d80bib50","type":"dataset","article-title":"Data for: Model accuracy and data heterogeneity shape uncertainty quantification in machine learning interatomic potentials","author":"Fei","year":"2025","unstructured":"Fei S 2025 Data for: Model accuracy and data heterogeneity shape uncertainty quantification in machine learning interatomic potentials GitHub (available at: https:\/\/github.com\/ufsf\/UQ-ACE )"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae3d80","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae3d80\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae3d80","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae3d80\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae3d80\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae3d80\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae3d80\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae3d80\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T15:05:18Z","timestamp":1770995118000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae3d80"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,13]]},"references-count":50,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2,13]]},"published-print":{"date-parts":[[2026,4,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ae3d80","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,13]]},"assertion":[{"value":"Model accuracy and data heterogeneity shape uncertainty quantification in machine learning interatomic potentials","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-09-12","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-01-26","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-02-13","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}