{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T18:19:17Z","timestamp":1783189157356,"version":"3.54.6"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100018601","name":"Guangdong Special Support Plan","doi-asserted-by":"publisher","award":["2023TQ07L745"],"award-info":[{"award-number":["2023TQ07L745"]}],"id":[{"id":"10.13039\/501100018601","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018601","name":"Guangdong Special Support Plan","doi-asserted-by":"publisher","award":["2024TQ08L818"],"award-info":[{"award-number":["2024TQ08L818"]}],"id":[{"id":"10.13039\/501100018601","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.eswa.2026.132654","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:53:06Z","timestamp":1777571586000},"page":"132654","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["ST3-KAN2.0: A holistic neural network framework for multi-energy load forecasting in integrated energy systems"],"prefix":"10.1016","volume":"326","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6956-9815","authenticated-orcid":false,"given":"Xiangfei","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8332-9333","authenticated-orcid":false,"given":"Chun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2213-5489","authenticated-orcid":false,"given":"Yuanjun","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8580-534X","authenticated-orcid":false,"given":"Zhile","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6657-0522","authenticated-orcid":false,"given":"Kang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132654_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.rser.2024.115251","article-title":"Artificial intelligence integrated grid systems: technologies, potential frameworks, challenges, and research directions","volume":"211","author":"Alam","year":"2025","journal-title":"Renewable and Sustainable Energy Reviews"},{"key":"10.1016\/j.eswa.2026.132654_bib0002","doi-asserted-by":"crossref","DOI":"10.1038\/nenergy.2017.71","article-title":"Integrating uncertainty into public energy research and development decisions","volume":"2","author":"Anad\u00f3n","year":"2017","journal-title":"Nature Energy"},{"key":"10.1016\/j.eswa.2026.132654_bib0003","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1007\/s00365-009-9054-2","article-title":"On a constructive proof of Kolmogorov\u2019s superposition theorem","volume":"30","author":"Braun","year":"2009","journal-title":"Constructive Approximation"},{"key":"10.1016\/j.eswa.2026.132654_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2025.104454","article-title":"Federated neural nonparametric point processes","volume":"351","author":"Chen","year":"2026","journal-title":"Artificial Intelligence"},{"issue":"9","key":"10.1016\/j.eswa.2026.132654_bib0005","doi-asserted-by":"crossref","first-page":"16975","DOI":"10.1109\/TNNLS.2025.3562164","article-title":"FedSI: Federated subnetwork inference for efficient uncertainty quantification","volume":"36","author":"Chen","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.eswa.2026.132654_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2024.130930","article-title":"A novel dynamic spatio-temporal graph convolutional network for wind speed interval prediction","volume":"294","author":"Chen","year":"2024","journal-title":"Energy"},{"key":"10.1016\/j.eswa.2026.132654_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2020.115332","article-title":"A hybrid load forecasting model based on support vector machine with intelligent methods for feature selection and parameter optimization","volume":"279","author":"Dai","year":"2020","journal-title":"Applied Energy"},{"key":"10.1016\/j.eswa.2026.132654_bib0008","unstructured":"Tempe campus energy data. https:\/\/cm.asu.edu\/. Accessed: June 2023."},{"key":"10.1016\/j.eswa.2026.132654_bib0009","unstructured":"Tempe regional meteorological data. https:\/\/nsrdb.nrel.gov\/data-viewer\/. Accessed: June 2023."},{"key":"10.1016\/j.eswa.2026.132654_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2024.124580","article-title":"Building electricity load forecasting based on spatiotemporal correlation and electricity consumption behavior information","volume":"377","author":"Dong","year":"2025","journal-title":"Applied Energy"},{"issue":"12","key":"10.1016\/j.eswa.2026.132654_bib0011","doi-asserted-by":"crossref","first-page":"7743","DOI":"10.1109\/TII.2020.2970165","article-title":"Short-term forecasting of heat demand of buildings for efficient and optimal energy management based on integrated machine learning models","volume":"16","author":"Eseye","year":"2020","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.eswa.2026.132654_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.116561","article-title":"Exploratory spatial analysis for interval data: A new autocorrelation index with COVID-19 and rent price applications","volume":"195","author":"Freitas","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132654_bib0013","doi-asserted-by":"crossref","first-page":"98887","DOI":"10.1109\/ACCESS.2020.2996708","article-title":"Reliability modeling and evaluation of urban multi-energy systems: A review of the state of the art and future challenges","volume":"8","author":"He","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.132654_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128269","article-title":"Multi-task learning and single-task learning joint multi-energy load forecasting of integrated energy systems considering meteorological variations","volume":"288","author":"Huang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132654_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123169","article-title":"Chaos-based support vector regression for load power forecasting of excavators","volume":"246","author":"Huo","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132654_bib0016","article-title":"Artificial intelligence-based forecasting models for integrated energy system management planning: An exploration of the prospects for south africa","volume":"24","author":"Krishnamurthy","year":"2024","journal-title":"Energy Conversion and Management: X"},{"key":"10.1016\/j.eswa.2026.132654_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.compenvurbsys.2023.101980","article-title":"A novel spatio-temporal principal component analysis based on geary\u2019s contiguity ratio","volume":"103","author":"Krzy\u015bko","year":"2023","journal-title":"Computers, Environment and Urban Systems"},{"key":"10.1016\/j.eswa.2026.132654_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2022.124967","article-title":"A multi-energy load forecasting method based on parallel architecture CNN-GRU and transfer learning for data deficient integrated energy systems","volume":"259","author":"Li","year":"2022","journal-title":"Energy"},{"key":"10.1016\/j.eswa.2026.132654_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103665","article-title":"SearchExpert: A genAI-driven framework for reasoning-intensive multimedia information fusion through fine-tuning and reinforcement learning","volume":"126","author":"Li","year":"2026","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132654_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2023.121823","article-title":"A novel short-term multi-energy load forecasting method for integrated energy system based on feature separation-fusion technology and improved CNN","volume":"351","author":"Li","year":"2023","journal-title":"Applied Energy"},{"key":"10.1016\/j.eswa.2026.132654_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2024.122821","article-title":"Joint forecasting of source-load-price for integrated energy system based on multi-task learning and hybrid attention mechanism","volume":"360","author":"Li","year":"2024","journal-title":"Applied Energy"},{"key":"10.1016\/j.eswa.2026.132654_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.129232","article-title":"Low-carbon economic optimization of park integrated energy system under hybrid market regulation: A multi-scenario dispatch system integrating ladder-type carbon trading and green certificate trading","volume":"297","author":"Li","year":"2026","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"10.1016\/j.eswa.2026.132654_bib0023","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/TSTE.2022.3198816","article-title":"A spatiotemporal directed graph convolution network for ultra-short-term wind power prediction","volume":"14","author":"Li","year":"2023","journal-title":"IEEE Transactions on Sustainable Energy"},{"key":"10.1016\/j.eswa.2026.132654_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2022.123417","article-title":"Forecasting the occurrence of extreme electricity prices using a multivariate logistic regression model","volume":"247","author":"Liu","year":"2022","journal-title":"Energy"},{"issue":"3","key":"10.1016\/j.eswa.2026.132654_bib0025","doi-asserted-by":"crossref","first-page":"1820","DOI":"10.1109\/TSTE.2021.3067436","article-title":"Short-term multi-step ahead wind power predictions based on a novel deep convolutional recurrent network method","volume":"12","author":"Liu","year":"2021","journal-title":"IEEE Transactions on Sustainable Energy"},{"key":"10.1016\/j.eswa.2026.132654_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.enconman.2024.119388","article-title":"A novel correlation feature self-assigned Kolmogorov-Arnold networks for multi-energy load forecasting in integrated energy systems","volume":"325","author":"Liu","year":"2025","journal-title":"Energy Conversion and Management"},{"key":"10.1016\/j.eswa.2026.132654_bib0027","unstructured":"Liu, Z., Ma, P., Wang, Y., Matusik, W., & Tegmark, M. (2024a). Kan 2.0: Kolmogorov-Arnold networks meet science.arXiv: 2408.10205\">arXiv preprint arXiv: 2408.10205."},{"key":"10.1016\/j.eswa.2026.132654_bib0028","unstructured":"Liu, Z., Wang, Y., Vaidya, S., Ruehle, F., Halverson, J., Solja\u010di\u0107, M., Hou, T.Y., & Tegmark, M. (2024b). Kan: Kolmogorov-Arnold networks. arXiv: 2404.19756\">arXiv preprint arXiv: 2404.19756,."},{"key":"10.1016\/j.eswa.2026.132654_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2024.123896","article-title":"A novel real-time dynamic performance evaluation and capacity configuration optimization method of generation-storage-load for integrated energy system","volume":"374","author":"Ma","year":"2024","journal-title":"Applied Energy"},{"key":"10.1016\/j.eswa.2026.132654_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2024.132796","article-title":"Multi-energy load forecasting for integrated energy system based on sequence decomposition fusion and factors correlation analysis","volume":"308","author":"Peng","year":"2024","journal-title":"Energy"},{"key":"10.1016\/j.eswa.2026.132654_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121737","article-title":"MSGCN-ISTL: A multi-scaled self-attention-enhanced graph convolutional network with improved stl decomposition for probabilistic load forecasting","volume":"238","author":"Qiu","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132654_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.enconman.2024.118397","article-title":"A structural depth network embedding stacking model based on moran\u2019s index and seasonal trend for short-term solar irradiance prediction","volume":"308","author":"Qu","year":"2024","journal-title":"Energy Conversion and Management"},{"key":"10.1016\/j.eswa.2026.132654_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126446","article-title":"Integrated energy short-term multivariate load forecasting based on patchTST secondary decoupling reconstruction for progressive layered extraction multi-task learning network","volume":"269","author":"Qu","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132654_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2024.130975","article-title":"A novel probabilistic gradient boosting model with multi-approach feature selection and iterative seasonal trend decomposition for short-term load forecasting","volume":"294","author":"Saini","year":"2024","journal-title":"Energy"},{"key":"10.1016\/j.eswa.2026.132654_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2024.123788","article-title":"Multi-energy load forecasting via hierarchical multi-task learning and spatiotemporal attention","volume":"373","author":"Song","year":"2024","journal-title":"Applied Energy"},{"issue":"1","key":"10.1016\/j.eswa.2026.132654_bib0036","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1109\/TSTE.2024.3447023","article-title":"Graph-based large scale probabilistic PV power forecasting insensitive to space-time missing data","volume":"16","author":"Song","year":"2025","journal-title":"IEEE Transactions on Sustainable Energy"},{"issue":"1","key":"10.1016\/j.eswa.2026.132654_bib0037","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1109\/TSTE.2022.3212168","article-title":"Tri-level multi-energy system planning method for zero energy buildings considering long- and short-term uncertainties","volume":"14","author":"Sun","year":"2023","journal-title":"IEEE Transactions on Sustainable Energy"},{"key":"10.1016\/j.eswa.2026.132654_bib0038","series-title":"2020 IEEE power & energy society general meeting (PESGM)","first-page":"1","article-title":"Probabilistic power consumption modeling for commercial buildings using logistic regression Markov Chain","author":"Tian","year":"2020"},{"key":"10.1016\/j.eswa.2026.132654_bib0039","doi-asserted-by":"crossref","DOI":"10.1109\/TCE.2026.3667765","article-title":"FedKT: A nature-inspired bayesian federated learning framework for privacy-preserving and lightweight consumer devices","author":"Tian","year":"2026","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"10.1016\/j.eswa.2026.132654_bib0040","series-title":"On the representation of continuous functions of several variables as superpositions of continuous functions of a smaller number of variables","author":"Tikhomirov","year":"1991"},{"issue":"10","key":"10.1016\/j.eswa.2026.132654_bib0041","doi-asserted-by":"crossref","first-page":"12262","DOI":"10.1109\/TII.2024.3417297","article-title":"Multi-energy load forecasting in integrated energy systems: A spatial-temporal adaptive personalized federated learning approach","volume":"20","author":"Wu","year":"2024","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.eswa.2026.132654_bib0042","article-title":"SepDiff: Self-encoding parameter diffusion for learning latent semantics","author":"Wu","year":"2025","journal-title":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"},{"key":"10.1016\/j.eswa.2026.132654_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103462","article-title":"WAVAE: A weakly augmented variational autoencoder for time series anomaly detection","volume":"125","author":"Wu","year":"2026","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132654_bib0044","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.renene.2021.01.003","article-title":"Application of autoregressive dynamic adaptive (ARDA) model in real-time wind power forecasting","volume":"169","author":"Zhang","year":"2021","journal-title":"Renewable Energy"},{"key":"10.1016\/j.eswa.2026.132654_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126981","article-title":"Optimization study of county multi-level power grid co-dispatch based on hybrid game considering multivariate source-load interaction","volume":"275","author":"Zhang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132654_bib0046","doi-asserted-by":"crossref","DOI":"10.1016\/j.enconman.2024.119027","article-title":"Multi-energy load forecasting for small-sample integrated energy systems based on neural network gaussian process and multi-task learning","volume":"321","author":"Zhang","year":"2024","journal-title":"Energy Conversion and Management"},{"issue":"5","key":"10.1016\/j.eswa.2026.132654_bib0047","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/MIS.2025.3597120","article-title":"A generative random modality dropout framework for robust multimodal emotion recognition","volume":"40","author":"Zhang","year":"2025","journal-title":"IEEE Intelligent Systems"},{"issue":"4","key":"10.1016\/j.eswa.2026.132654_bib0048","doi-asserted-by":"crossref","first-page":"5659","DOI":"10.1109\/TPWRS.2023.3345328","article-title":"Geometric loss-enabled complex neural network for multi-energy load forecasting in integrated energy systems","volume":"39","author":"Zhao","year":"2024","journal-title":"IEEE Transactions on Power Systems"},{"key":"10.1016\/j.eswa.2026.132654_bib0049","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2022.119269","article-title":"Review and prospect of data-driven techniques for load forecasting in integrated energy systems","volume":"321","author":"Zhu","year":"2022","journal-title":"Applied Energy"},{"issue":"2","key":"10.1016\/j.eswa.2026.132654_bib0050","doi-asserted-by":"crossref","first-page":"1239","DOI":"10.1109\/TSTE.2023.3334723","article-title":"Low carbon planning of multiple integrated energy systems considering trans-regional battery logistics network","volume":"15","author":"Zhu","year":"2024","journal-title":"IEEE Transactions on Sustainable Energy"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426015678?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426015678?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T17:54:57Z","timestamp":1783187697000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426015678"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":50,"alternative-id":["S0957417426015678"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132654","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ST3-KAN2.0: A holistic neural network framework for multi-energy load forecasting in integrated energy systems","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132654","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"132654"}}