{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:44:27Z","timestamp":1776116667176,"version":"3.50.1"},"reference-count":160,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Intell. Mag."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/mci.2025.3631772","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:39:48Z","timestamp":1768423188000},"page":"37-56","source":"Crossref","is-referenced-by-count":1,"title":["Long-Term Time Series Forecasting: The Good, the Bad, and the Ugly"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0375-4631","authenticated-orcid":false,"given":"Lorenzo","family":"Epifani","sequence":"first","affiliation":[{"name":"Politecnico di Milano, Milan, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0460-1690","authenticated-orcid":false,"given":"Alessandro","family":"Falcetta","sequence":"additional","affiliation":[{"name":"Politecnico di Milano, Milan, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7828-7687","authenticated-orcid":false,"given":"Manuel","family":"Roveri","sequence":"additional","affiliation":[{"name":"Politecnico di Milano, Milan, Italy"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1140\/epjds\/s13688-023-00383-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.11.032"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106116"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.69"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2981819"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3703412.3704452"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1922"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/01605682.2021.1892464"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-2070(00)00057-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-007-0064-z"},{"key":"ref12","article-title":"Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Li"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.08.018"},{"key":"ref14","article-title":"Revisiting long-term time series forecasting: An investigation on affine mapping","author":"Li","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cageo.2016.03.002"},{"key":"ref16","article-title":"Beyond trend and periodicity: Guide time series forecasting with textual cues","author":"Xu","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2019.104964"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPEC.2018.8312088"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.113082"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2020.117197"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.envres.2015.02.002"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.enconman.2020.113644"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411975"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10100-018-0531-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2020.117948"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2020.125187"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.043"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2022.118040"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijar.2016.10.010"},{"key":"ref30","article-title":"Timesnet: Temporal 2D-variation modeling for general time series analysis","author":"Wu","year":"2023"},{"key":"ref31","first-page":"4672","article-title":"Mixture-of-linear-experts for long-term time series forecasting","volume-title":"Proc. 27th Int. Conf. Artif. Intell. Statist.","author":"Ni","year":"2024"},{"key":"ref32","article-title":"A time series is worth 64 words: long-term forecasting with transformers","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Nie"},{"key":"ref33","first-page":"27268","article-title":"Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou","year":"2022"},{"key":"ref34","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2003.08.037"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106181"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhydrol.2009.06.019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3333824"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1111\/joes.12429"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117798"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065721300011"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1089\/big.2020.0159"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2020.0209"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CSCI58124.2022.00021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2006.01.001"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1080\/07474938.2010.481556"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/su12093612"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1049\/iet-gtd.2016.0340"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/0142-0615(87)90019-6"},{"key":"ref50","first-page":"249","article-title":"Different methods of long-term electric load demand forecasting a comprehensive review","volume":"7","author":"Ghods","year":"2011","journal-title":"Iranian J. Elect. Electron. Eng."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-70438-8"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)IR.1943-4774.0001471"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2007.07.002"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10989-8"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-025-02560-w"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.14778\/3665844.3665863"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210006"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2019.108395"},{"key":"ref59","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2021.103894","article-title":"Long-term prediction for temporal propagation of seasonal influenza using transformer-based model","volume":"122","author":"Li","year":"2021","journal-title":"J. Biomed. Informat."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.chemosphere.2004.10.032"},{"key":"ref61","first-page":"1","article-title":"Long term forecasting of ambient air quality using deep learning approach","volume-title":"Proc. IEEE 17th India Council Int. Conf.","author":"Samal","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3390\/make6030079"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.56093\/ijas.v88i8.82573"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-23618-1_5"},{"key":"ref65","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2020.117200","article-title":"A hybrid approach based on autoregressive integrated moving average and least-square support vector machine for long-term forecasting of net electricity consumption","volume":"197","author":"Kaytez","year":"2020","journal-title":"Energy"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1002\/ese3.1178"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2025.125445"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3677052.3698654"},{"key":"ref69","doi-asserted-by":"crossref","first-page":"46241","DOI":"10.1109\/ACCESS.2024.3381500","article-title":"Long-term interbank bond rate prediction based on ICEEMDAN and machine learning","volume":"12","author":"Yu","year":"2024","journal-title":"IEEE Access"},{"key":"ref70","first-page":"117","article-title":"Advanced stock price prediction with xLSTM-Based models: Improving long-term forecasting","volume-title":"Proc. 11th Int. Conf. Soft Comput. & Mach. Intell.","author":"Fan","year":"2024"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115490"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.03.002"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/505"},{"key":"ref74","article-title":"Test-time compensated representation learning for extreme traffic forecasting","author":"Zhang","year":"2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111637"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0104663"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhydrol.2020.125205"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110172"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.915109"},{"key":"ref80","article-title":"High level expert forum: How to feed the world in 2050","year":"2009","journal-title":"Rome"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.3389\/fenvs.2022.945628"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1063\/5.0045753"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/j.atmosenv.2006.10.073"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s40726-020-00159-z"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.3906\/elk-1907-218"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.3390\/rs16111891"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.3390\/en12163095"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2012.02.042"},{"key":"ref89","article-title":"Multi-plant photovoltaic energy forecasting challenge: Second place solution","volume-title":"Proc. Discov. Challenges Co-Located Eur. Conf. Mach. Learn.-Princ. Pract. Know. Discov. Databases","author":"Gautrais"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.69"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2005.06.024"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2019.07.001"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106435"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.gsf.2022.101349"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1002\/env.2833"},{"key":"ref96","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-60339-6","volume-title":"Statistical Learning Tools for Electricity Load Forecasting","author":"Antoniadis","year":"2024"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.21314\/JEM.2020.216"},{"key":"ref98","article-title":"What does past correlation structure tell us about the future? An answer from network filtering","author":"Musmeci","year":"2016"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.32996\/jmss.2023.4.4.4"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482441"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103200"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pntd.0008056"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.58175\/gjrst.2024.2.2.0074"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/s12199-012-0294-6"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2023.1248254"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-020-09747-z"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(01)00702-0"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2013.04.036"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/476"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2849820"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3192342"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219822"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/932"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.09.082"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2019.07.367"},{"key":"ref116","article-title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Oreshkin"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2021.03.012"},{"key":"ref119","first-page":"5816","article-title":"SCINet: Time series modeling and forecasting with sample convolution and interaction","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Liu","year":"2022"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25854"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.06.014"},{"key":"ref122","first-page":"28341","article-title":"Predict, refine, synthesize: Self-guiding diffusion models for probabilistic time series forecasting","volume":"36","author":"Kollovieh","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref123","first-page":"10148","article-title":"A decoder-only foundation model for time-series forecasting","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Das","year":"2024"},{"key":"ref124","article-title":"From tables to time: How tabpfn-v2 outperforms specialized time series forecasting models","author":"Hoo","year":"2025"},{"key":"ref125","article-title":"TiRex: Zero-shot forecasting across long and short horizons","volume-title":"Proc. 1st ICML Workshop Found. Models Structured Data","author":"Auer"},{"key":"ref126","article-title":"Mamba4Cast: Efficient zero-shot time series forecasting with state space models","volume-title":"Proc. NeurIPS Workshop Time Series Age Large Models","author":"Bhethanabhotla"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.04.167"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.2017.1380080"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065704001899"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-0872-7_15"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhydrol.2020.124789"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2019.04.014"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref137","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1145\/3742784"},{"key":"ref139","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Representations Conf. Track","author":"Simonyan"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298594"},{"key":"ref142","first-page":"2766","article-title":"Retrieval-augmented diffusion models for time series forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Liu","year":"2024"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671451"},{"key":"ref144","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"Proc. 1st Conf. Lang. Model","author":"Gu"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2021.11.013"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33904-3_36"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2023.07.001"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.21236\/ADA459827"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.2307\/2280095"},{"key":"ref150","article-title":"Copula conformal prediction for multi-step time series prediction","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Sun","year":"2023"},{"key":"ref151","first-page":"55076","article-title":"Conformal prediction for multi-dimensional time series by ellipsoidal sets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2024"},{"key":"ref152","first-page":"48045","article-title":"Probts: Benchmarking point and distributional forecasting across diverse prediction horizons","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Zhang"},{"key":"ref153","volume-title":"Introducing MLOps","author":"Treveil","year":"2020"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1002\/for.3980010202"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2010.04.009"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2019.03.015"},{"key":"ref157","article-title":"Shifts 2.0: Extending the dataset of real distributional shifts","author":"Malinin","year":"2023"},{"key":"ref158","first-page":"5637","article-title":"WILDS: A Benchmark of in-the-wild distribution shifts","volume-title":"Proc. 38th Int. Conf. Mach. Learn., 2021","volume":"139","author":"Koh"},{"key":"ref159","article-title":"ProbTS: Benchmarking point and distributional forecasting across diverse prediction horizons","author":"Zhang","year":"2024","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref160","first-page":"23958","article-title":"Regions of reliability in the evaluation of multivariate probabilistic forecasts","volume":"202","author":"Marcotte","year":"2023","journal-title":"Proc. Int. Conf. Mach. Learn"}],"container-title":["IEEE Computational Intelligence Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10207\/11353090\/11353101.pdf?arnumber=11353101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:49:04Z","timestamp":1768510144000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11353101\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":160,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/mci.2025.3631772","relation":{},"ISSN":["1556-603X","1556-6048"],"issn-type":[{"value":"1556-603X","type":"print"},{"value":"1556-6048","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}