{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T11:39:56Z","timestamp":1762861196987,"version":"build-2065373602"},"reference-count":27,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100006151","name":"Basic Energy Sciences","doi-asserted-by":"crossref","award":["DE-AC02-76SF00515"],"award-info":[{"award-number":["DE-AC02-76SF00515"]}],"id":[{"id":"10.13039\/100006151","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100017223","name":"National Energy Research Scientific Computing Center","doi-asserted-by":"crossref","award":["BES-ERCAP0026843"],"award-info":[{"award-number":["BES-ERCAP0026843"]}],"id":[{"id":"10.13039\/100017223","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,12,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Significant challenges exist in efficient data analysis of most advanced experimental and observational techniques because the collected signals often include unwanted contributions, such as background and signal distortions, that can obscure the physically relevant information of interest. To address this, we have developed a self-supervised machine-learning approach for source separation using a dual implicit neural representation framework that jointly trains two neural networks: one for approximating distortions of the physical signal of interest and the other for learning the\n                    <jats:italic>effective<\/jats:italic>\n                    background contribution. Our method learns directly from the raw data by minimizing a reconstruction-based loss function without requiring labeled data or pre-defined dictionaries. We demonstrate the effectiveness of our framework by considering a challenging case study involving large-scale simulated, as well as experimental, momentum-energy-dependent inelastic neutron scattering data in a four-dimensional parameter space, characterized by heterogeneous background contributions and unknown distortions to the target signal. The method is found to successfully separate physically meaningful signals from a complex or structured background even when the signal characteristics vary across all four dimensions of the parameter space. An analytical approach that informs the choice of the regularization parameter is presented. Our method offers a versatile framework for addressing source separation problems across diverse domains, ranging from superimposed signals in astronomical measurements to structural features in biomedical image reconstructions.\n                  <\/jats:p>","DOI":"10.1088\/2632-2153\/ae14ac","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T22:51:13Z","timestamp":1760741473000},"page":"045042","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Physics-guided dual implicit neural representations for source separation"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5797-5234","authenticated-orcid":false,"given":"Yuan","family":"Ni","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1954-3868","authenticated-orcid":true,"given":"Zhantao","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7597-9626","authenticated-orcid":false,"given":"Alexander N","family":"Petsch","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8261-6899","authenticated-orcid":true,"given":"Edmund","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9267-1789","authenticated-orcid":true,"given":"Cheng","family":"Peng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1940-4649","authenticated-orcid":true,"given":"Alexander I","family":"Kolesnikov","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5480-6075","authenticated-orcid":false,"given":"Sugata","family":"Chowdhury","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3864-3461","authenticated-orcid":false,"given":"Arun","family":"Bansil","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9051-1677","authenticated-orcid":false,"given":"Jana B","family":"Thayer","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2106-7955","authenticated-orcid":false,"given":"Joshua J","family":"Turner","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"mlstae14acbib1","doi-asserted-by":"publisher","first-page":"5185","DOI":"10.1093\/mnras\/stac2072","type":"journal-article","article-title":"A probabilistic method of background removal for high energy astrophysics data","volume":"515","author":"Ehlert","year":"2022","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstae14acbib2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.5.033113","type":"journal-article","article-title":"High-energy spin waves in the spin-1 square-lattice antiferromagnet La2NiO4","volume":"5","author":"Petsch","year":"2023","journal-title":"Phys. Rev. Res."},{"key":"mlstae14acbib3","doi-asserted-by":"publisher","first-page":"3099","DOI":"10.1109\/ICSMC.2004.1400815","type":"conference-proceedings","article-title":"Background subtraction techniques: a review","volume":"vol 4","author":"Piccardi","year":"2004"},{"key":"mlstae14acbib4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2012\/292695","type":"journal-article","article-title":"Three-dimensional acoustic source mapping with different beamforming steering vector formulations","volume":"2012","author":"Sarradj","year":"2012","journal-title":"Adv. Acoust. Vib."},{"key":"mlstae14acbib5","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrp.2024.102333","type":"journal-article","article-title":"Implicit neural representations for experimental steering of advanced experiments","volume":"6","author":"Chen","year":"2025","journal-title":"Cell Rep. Phys. Sci."},{"key":"mlstae14acbib6","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.jsv.2018.10.050","type":"journal-article","article-title":"Extension of sound field separation technique based on the equivalent source method in a sparsity framework","volume":"442","author":"Bi","year":"2019","journal-title":"J. Sound Vib."},{"key":"mlstae14acbib7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cosrev.2016.11.001","type":"journal-article","article-title":"Decomposition into Low-rank plus additive matrices for background\/foreground separation: a review for a comparative evaluation with a large-scale dataset","volume":"23","author":"Bouwmans","year":"2017","journal-title":"Comput. Sci. Rev."},{"key":"mlstae14acbib8","doi-asserted-by":"publisher","first-page":"4900","DOI":"10.1109\/TCSVT.2021.3129503","type":"journal-article","article-title":"Efficient low-rank matrix factorization based on \u21131,\u03b5-norm for online background subtraction","volume":"32","author":"Liu","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"mlstae14acbib9","doi-asserted-by":"publisher","DOI":"10.1145\/1970392.1970395","type":"journal-article","article-title":"Robust principal component analysis?","volume":"58","author":"Cand\u00e8s","year":"2011","journal-title":"J. ACM"},{"key":"mlstae14acbib10","doi-asserted-by":"publisher","first-page":"11026","DOI":"10.1109\/CVPR.2019.01128","type":"conference-proceedings","article-title":"Double-DIP: unsupervised image decomposition via coupled deep-image-priors","author":"Gandelsman","year":"2019"},{"key":"mlstae14acbib11","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/0165-1684(94)90029-9","type":"journal-article","article-title":"Independent component analysis, a new concept?","volume":"36","author":"Comon","year":"1994","journal-title":"Signal Process."},{"key":"mlstae14acbib12","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1016\/j.jvcir.2007.01.004","type":"journal-article","article-title":"A comparison of three total variation based texture extraction models","volume":"18","author":"Yin","year":"2007","journal-title":"J. Vis. Commun. Image Represent."},{"key":"mlstae14acbib13","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1117\/12.507447","type":"journal-article","article-title":"Image decomposition: separation of texture from piecewise smooth content","volume":"5207","author":"Starck","year":"2003","journal-title":"Proc. SPIE"},{"key":"mlstae14acbib14","doi-asserted-by":"publisher","first-page":"1076","DOI":"10.1109\/TMI.2010.2097275","type":"journal-article","article-title":"A Data-driven sparse GLM for fMRI analysis using sparse dictionary learning with MDL criterion","volume":"30","author":"Lee","year":"2011","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstae14acbib15","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1186\/1687-6180-2013-185","type":"journal-article","article-title":"Dependent component analysis","volume":"2013","author":"Kuruoglu","year":"2013","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"mlstae14acbib16","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1016\/0039-6028(89)90380-4","type":"journal-article","article-title":"Practical algorithm for background subtraction","volume":"216","author":"Tougaard","year":"1989","journal-title":"Surf. Sci."},{"key":"mlstae14acbib17","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.elspec.2005.12.002","type":"journal-article","article-title":"The shirley background revised","volume":"151","author":"V\u00e9gh","year":"2006","journal-title":"J. Electron Spectrosc. Relat. Phenom."},{"key":"mlstae14acbib18","doi-asserted-by":"publisher","first-page":"1138","DOI":"10.1016\/j.jvir.2018.03.030","type":"journal-article","article-title":"The history of digital subtraction angiography","volume":"29","author":"Crummy","year":"2018","journal-title":"J. Vasc. Interv. Radiol."},{"article-title":"Where do we stand with implicit neural representations? A technical and performance survey","year":"2025","author":"Essakine","key":"mlstae14acbib19","type":"preprint"},{"key":"mlstae14acbib20","doi-asserted-by":"publisher","first-page":"5852","DOI":"10.1038\/s41467-023-41378-4","type":"journal-article","article-title":"Capturing dynamical correlations using implicit neural representations","volume":"14","author":"Chitturi","year":"2023","journal-title":"Nat. Commun."},{"key":"mlstae14acbib21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmds.2021.100008","type":"journal-article","article-title":"Neural networks as smooth priors for inverse problems for PDEs","volume":"1","author":"Berg","year":"2021","journal-title":"J. Comput. Math. Data Sci."},{"article-title":"Implicit neural representations and the algebra of complex wavelets","year":"2023","author":"Roddenberry","key":"mlstae14acbib22","type":"preprint"},{"key":"mlstae14acbib23","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1557\/s43580-021-00051-y","type":"journal-article","article-title":"A snapshot review\u2013fluctuations in quantum materials: from skyrmions to superconductivity","volume":"6","author":"Shen","year":"2021","journal-title":"MRS Adv."},{"key":"mlstae14acbib24","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1039\/C4AN01061B","type":"journal-article","article-title":"Baseline correction using asymmetrically reweighted penalized least squares smoothing","volume":"140","author":"Baek","year":"2015","journal-title":"Analyst"},{"key":"mlstae14acbib25","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.16790579","type":"preprint","article-title":"pybaselines: a Python library of algorithms for the baseline correction of experimental data (v1.2.1)","author":"Erb","year":"2025"},{"year":"2024","author":"Chen","key":"mlstae14acbib26","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.14048251","type":"book"},{"article-title":"Implicit neural representations with periodic activation functions","year":"2020","author":"Sitzmann","key":"mlstae14acbib27","type":"preprint"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae14ac","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae14ac\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae14ac","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae14ac\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae14ac\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae14ac\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae14ac\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae14ac\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T11:37:04Z","timestamp":1762861024000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae14ac"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":27,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,11,11]]},"published-print":{"date-parts":[[2025,12,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ae14ac","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2025,11,11]]},"assertion":[{"value":"Physics-guided dual implicit neural representations for source separation","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 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-07-08","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-10-17","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-11-11","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}