{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T12:25:47Z","timestamp":1793967947581,"version":"4.8.0"},"reference-count":44,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T00:00:00Z","timestamp":1793923200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T00:00:00Z","timestamp":1793923200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Energy Storage"],"published-print":{"date-parts":[[2026,12]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Accurate prediction of lithium\u2010ion battery (LIB) remaining useful life (RUL) is important for assessing battery degradation and supporting reliable operation of energy systems. However, prediction across different operating conditions remains challenging because of complex spatial\u2013temporal dependencies, limited degradation observations, and difficulties in incorporating degradation\u2010related physical knowledge. To overcome these challenges, this study presents a physics\u2010informed meta\u2010graph attention network (PIMGAN) that integrates degradation feature learning, dynamical regularization, and few\u2010shot adaptation. Firstly, a multi\u2010scale graph attention mechanism is combined with adaptive bidirectional temporal convolution to characterize correlations among heterogeneous battery measurements and their temporal evolution. Then, a physics\u2010guided regulator (PGR) learns a nonlinear differential operator in the latent feature space, whose residual serves as an additional regularization term during model training. Finally, a first\u2010order meta\u2010learning strategy is integrated to learn transferable model initialization parameters across multiple degradation tasks, enabling rapid adaptation to unseen battery conditions with limited target\u2010domain observations while avoiding explicit second\u2010order meta\u2010gradient computations. The proposed PIMGAN is evaluated on two publicly available LIB datasets under cross\u2010cycle and cross\u2010condition prediction settings. Under cross\u2010condition evaluation, PIMGAN achieves mean absolute percentage errors of 0.267% and 0.336% on the MIT and XJTU datasets, respectively, demonstrating its effectiveness in battery RUL prediction with limited target\u2010domain data.<\/jats:p>","DOI":"10.1002\/est2.70561","type":"journal-article","created":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T11:38:41Z","timestamp":1793965121000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Physics\u2010Informed Meta\u2010Learning With Graph Attention for Lithium\u2010Ion Battery Remaining Useful Life Prediction"],"prefix":"10.1002","volume":"8","author":[{"given":"Yehua","family":"Ling","sequence":"first","affiliation":[{"name":"Guangxi Transportation Science and Technology Group Co. Ltd.  Nanning China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9616-7789","authenticated-orcid":false,"given":"Zexian","family":"Wei","sequence":"additional","affiliation":[{"name":"Guangxi Transportation Science and Technology Group Co. Ltd.  Nanning China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuangsong","family":"Wu","sequence":"additional","affiliation":[{"name":"Guangxi Transportation Science and Technology Group Co. Ltd.  Nanning China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feiyan","family":"Pan","sequence":"additional","affiliation":[{"name":"Guangxi Transportation Science and Technology Group Co. Ltd.  Nanning China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Guangxi Transportation Science and Technology Group Co. Ltd.  Nanning China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuqiong","family":"Li","sequence":"additional","affiliation":[{"name":"Guangxi Transportation Science and Technology Group Co. Ltd.  Nanning China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7170-2643","authenticated-orcid":false,"given":"Jinxin","family":"Wu","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Manufacturing System &amp; Advanced Manufacturing Technology, School of Mechanical Engineering Guangxi University  Nanning China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,11,6]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2021.3055811"},{"key":"e_1_2_9_3_1","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1016\/j.ensm.2022.05.026","article-title":"Prediction of Li\u2010Ion Battery Capacity Degradation Considering Polarization Recovery With a Hybrid Ensemble Learning Model","volume":"50","author":"Tong Z.","year":"2022","journal-title":"Energy Storage Materials"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.01.011"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.geits.2022.100001"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2024.132598"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2022.104026"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2017.08.096"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2925468"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2024.132395"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2024.110678"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2024.113176"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2024.114826"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2026.3658709"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2025.135719"},{"key":"e_1_2_9_16_1","article-title":"Remaining Useful Life Prediction of High\u2010Voltage DC Contactors Based on Acoustic\u2010Electrical Signal Feature Fusion and TCN\u2010Transformer","volume":"75","author":"Sun S.","year":"2026","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_2_9_17_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.renene.2025.123641","article-title":"Remaining Useful Life Prediction of Lithium\u2010Ion Battery Based on Real\u2010Time Decomposition and Tightly Coupled Convolutional Informer","volume":"253","author":"Wu J.","year":"2025","journal-title":"Renewable Energy"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2022.108947"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/tte.2025.3640141"},{"key":"e_1_2_9_20_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.measurement.2025.119005","article-title":"Aging\u2010Aware Capacity Prediction for Lithium\u2010Ion Batteries: A Dynamic Graph Networks Framework With Spatial\u2010Temporal Feature Fusion","volume":"258","author":"Zheng X.","year":"2026","journal-title":"Measurement"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2025.111003"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2022.106437"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.geits.2025.100301"},{"key":"e_1_2_9_24_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2025.138045","article-title":"A Novel Spatio\u2010Temporal Feature Fusion Attention Model for Lithium\u2010Ion Battery Capacity Estimation Using Graph Convolutional Network","author":"Zhang C.","year":"2025","journal-title":"Energy"},{"key":"e_1_2_9_25_1","first-page":"11","article-title":"Statistical Models for Condition Monitoring and State of Health Estimation of Lithium\u2010Ion Batteries for Ships","volume":"3","author":"Vanem E.","year":"2024","journal-title":"Journal of Dynamics, Monitoring and Diagnostics"},{"issue":"2","key":"e_1_2_9_26_1","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1038\/s42256-024-00972-x","article-title":"Battery Lifetime Prediction Across Diverse Ageing Conditions With Inter\u2010Cell Deep Learning","volume":"7","author":"Zhang H.","year":"2025","journal-title":"Nature Machine Intelligence"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/tim.2022.3142757"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyai.2024.100405"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010023\u201038458\u2010w"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124161"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/tte.2025.3563217"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/taes.2025.3540806"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2025.138078"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2026.127927"},{"key":"e_1_2_9_35_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2026.140288","article-title":"A Physics\u2010Informed Deep Learning Framework for Remaining Useful Life Prediction of Lithium\u2010Ion Batteries With Feature Subset Construction","author":"Cheng H.","year":"2026","journal-title":"Energy"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2026.127785"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/tie.2026.3654816"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/tte.2026.3667124"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/tte.2023.3247614"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2025.05.009"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2024.111120"},{"key":"e_1_2_9_42_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2025.111152","article-title":"An Adaptive Multi\u2010Scale Spatial\u2010Temporal Graph Attention Ensemble Network With Physical Guidance for Remaining Useful Life Prediction of Multi\u2010Sensor Equipment","volume":"262","author":"Zhou L.","year":"2025","journal-title":"Reliability Engineering & System Safety"},{"key":"e_1_2_9_43_1","unstructured":"A.Nichol J.Achiam andJ.Schulman \u201cOn First\u2010Order Meta\u2010Learning Algorithms \u201darXiv Preprint(2018): arXiv:1803.02999."},{"issue":"5","key":"e_1_2_9_44_1","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1038\/s41560-019-0356-8","article-title":"Data\u2010Driven Prediction of Battery Cycle Life Before Capacity Degradation","volume":"4","author":"Severson K. A.","year":"2019","journal-title":"Nature Energy"},{"issue":"1","key":"e_1_2_9_45_1","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-024-48779-z","article-title":"Physics\u2010Informed Neural Network for Lithium\u2010Ion Battery Degradation Stable Modeling and Prognosis","volume":"15","author":"Wang F.","year":"2024","journal-title":"Nature Communications"}],"container-title":["Energy Storage"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/est2.70561","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/est2.70561","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/est2.70561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T11:38:44Z","timestamp":1793965124000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/est2.70561"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11,6]]},"references-count":44,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["10.1002\/est2.70561"],"URL":"https:\/\/doi.org\/10.1002\/est2.70561","archive":["Portico"],"relation":{},"ISSN":["2578-4862","2578-4862"],"issn-type":[{"value":"2578-4862","type":"print"},{"value":"2578-4862","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,11,6]]},"assertion":[{"value":"2026-09-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-11-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70561"}}