{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T21:13:00Z","timestamp":1778101980748,"version":"3.51.4"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72331007"],"award-info":[{"award-number":["72331007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72201021"],"award-info":[{"award-number":["72201021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.engappai.2026.114746","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:16:31Z","timestamp":1775816191000},"page":"114746","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P2","title":["Natural gas demand forecasting via latent pattern retrieval and expert specialization"],"prefix":"10.1016","volume":"176","author":[{"given":"Sichong","family":"Lu","sequence":"first","affiliation":[]},{"given":"Hairun","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jiahui","family":"Chai","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Su","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8035-4938","authenticated-orcid":false,"given":"Lean","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Yang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.engappai.2026.114746_b1","doi-asserted-by":"crossref","first-page":"1230","DOI":"10.1109\/TKDE.2010.227","article-title":"Energy time series forecasting based on pattern sequence similarity","volume":"23","author":"Alvarez","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"2","key":"10.1016\/j.engappai.2026.114746_b2","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1007\/s10115-016-0987-z","article-title":"A survey of methods for time series change point detection","volume":"51","author":"Aminikhanghahi","year":"2017","journal-title":"Knowl. Inf. Syst."},{"key":"10.1016\/j.engappai.2026.114746_b3","series-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"issue":"6","key":"10.1016\/j.engappai.2026.114746_b4","doi-asserted-by":"crossref","first-page":"2388","DOI":"10.3390\/su16062388","article-title":"Fueling the future: A comprehensive analysis and forecast of fuel consumption trends in US electricity generation","volume":"16","author":"Bhuiyan","year":"2024","journal-title":"Sustainability"},{"issue":"3","key":"10.1016\/j.engappai.2026.114746_b5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3719207","article-title":"LLM4TS: Aligning pre-trained LLMs as data-efficient time-series forecasters","volume":"16","author":"Chang","year":"2025","journal-title":"ACM Trans. Intell. Syst. Technol."},{"issue":"10","key":"10.1016\/j.engappai.2026.114746_b6","doi-asserted-by":"crossref","first-page":"10748","DOI":"10.1109\/TKDE.2023.3268199","article-title":"Multi-scale adaptive graph neural network for multivariate time series forecasting","volume":"35","author":"Chen","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.engappai.2026.114746_b7","article-title":"TSMixer: An all-MLP architecture for time series forecasting","author":"Chen","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2026.114746_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2019.114486","article-title":"Day-ahead high-resolution forecasting of natural gas demand and supply in Germany with a hybrid model","volume":"262","author":"Chen","year":"2020","journal-title":"Appl. Energy"},{"key":"10.1016\/j.engappai.2026.114746_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2023.120911","article-title":"Forecasting natural gas consumption with multiple seasonal patterns","volume":"337","author":"Ding","year":"2023","journal-title":"Appl. Energy"},{"key":"10.1016\/j.engappai.2026.114746_b10","doi-asserted-by":"crossref","unstructured":"Du, Y., Wang, J., Feng, W., Pan, S., Qin, T., Xu, R., Wang, C., 2021. Adarnn: Adaptive learning and forecasting of time series. In: Proceedings of the 30th ACM International Conference on Information & Knowledge Management. pp. 402\u2013411.","DOI":"10.1145\/3459637.3482315"},{"key":"10.1016\/j.engappai.2026.114746_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127436","article-title":"Prompting large language model for multi-location multi-step zero-shot wind power forecasting","volume":"280","author":"Duan","year":"2025","journal-title":"Expert Syst. Appl."},{"issue":"3","key":"10.1016\/j.engappai.2026.114746_b12","doi-asserted-by":"crossref","first-page":"1701","DOI":"10.1016\/j.enpol.2006.05.009","article-title":"ARIMA forecasting of primary energy demand by fuel in Turkey","volume":"35","author":"Ediger","year":"2007","journal-title":"Energy Policy"},{"issue":"18","key":"10.1016\/j.engappai.2026.114746_b13","doi-asserted-by":"crossref","first-page":"3836","DOI":"10.1016\/j.enpol.2005.08.023","article-title":"Forecasting production of fossil fuel sources in Turkey using a comparative regression and ARIMA model","volume":"34","author":"Ediger","year":"2006","journal-title":"Energy Policy"},{"key":"10.1016\/j.engappai.2026.114746_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2025.125372","article-title":"Implementing a provincial-level universal daily industrial carbon emissions prediction by fine-tuning the large language model","volume":"383","author":"Feng","year":"2025","journal-title":"Appl. Energy"},{"key":"10.1016\/j.engappai.2026.114746_b15","series-title":"Proceedings of the 42nd International Conference on Machine Learning","first-page":"21774","article-title":"Retrieval augmented time series forecasting","volume":"Vol. 267","author":"Han","year":"2025"},{"issue":"124","key":"10.1016\/j.engappai.2026.114746_b16","first-page":"1","article-title":"Darts: User-friendly modern machine learning for time series","volume":"23","author":"Herzen","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2026.114746_b17","doi-asserted-by":"crossref","unstructured":"Hundman, K., Constantinou, V., Laporte, C., Colwell, I., Soderstrom, T., 2018. Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. pp. 387\u2013395.","DOI":"10.1145\/3219819.3219845"},{"issue":"4","key":"10.1016\/j.engappai.2026.114746_b18","first-page":"49","article-title":"Forecasting natural gas consumption using PSO optimized least squares support vector machines","volume":"2","author":"Iranmanesh","year":"2011","journal-title":"Int. J. Artif. Intell. Appl."},{"key":"10.1016\/j.engappai.2026.114746_b19","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"23343","article-title":"GPT4MTS: Prompt-based large language model for multimodal time-series forecasting","volume":"Vol. 38","author":"Jia","year":"2024"},{"key":"10.1016\/j.engappai.2026.114746_b20","series-title":"International Conference on Learning Representations","article-title":"Time-LLM: Time series forecasting by reprogramming large language models","author":"Jin","year":"2024"},{"key":"10.1016\/j.engappai.2026.114746_b21","article-title":"Forecasts of China mainland new energy index prices through Gaussian process regressions","volume":"1","author":"Jin","year":"2024","journal-title":"J. Clean Energy Storage"},{"key":"10.1016\/j.engappai.2026.114746_b22","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1016\/j.energy.2019.04.075","article-title":"Toward efficient energy systems based on natural gas consumption prediction with LSTM recurrent neural networks","volume":"177","author":"Laib","year":"2019","journal-title":"Energy"},{"key":"10.1016\/j.engappai.2026.114746_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.jngse.2021.103930","article-title":"Natural gas consumption forecasting: A discussion on forecasting history and future challenges","volume":"90","author":"Liu","year":"2021","journal-title":"J. Nat. Gas Sci. Eng."},{"key":"10.1016\/j.engappai.2026.114746_b24","series-title":"Advances in Neural Information Processing Systems","first-page":"2766","article-title":"Retrieval-augmented diffusion models for time series forecasting","volume":"Vol. 37","author":"Liu","year":"2024"},{"key":"10.1016\/j.engappai.2026.114746_b25","series-title":"The Fourteenth International Conference on Learning Representations","article-title":"Semantic-enhanced time-series forecasting via large language models","author":"Liu","year":"2026"},{"issue":"4","key":"10.1016\/j.engappai.2026.114746_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104091","article-title":"LLM-infused bi-level semantic enhancement for corporate credit risk prediction","volume":"62","author":"Lu","year":"2025","journal-title":"Inf. Process. Manag."},{"issue":"4","key":"10.1016\/j.engappai.2026.114746_b27","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1016\/j.ijforecast.2018.06.001","article-title":"The M4 competition: Results, findings, conclusion and way forward","volume":"34","author":"Makridakis","year":"2018","journal-title":"Int. J. Forecast."},{"issue":"1","key":"10.1016\/j.engappai.2026.114746_b28","doi-asserted-by":"crossref","first-page":"94","DOI":"10.3390\/en12010094","article-title":"A novel hybrid algorithm to forecast functional time series based on pattern sequence similarity with application to electricity demand","volume":"12","author":"Mart\u00ednez-\u00c1lvarez","year":"2018","journal-title":"Energies"},{"key":"10.1016\/j.engappai.2026.114746_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2025.136559","article-title":"P-KTFNet: A prior knowledge enhanced time-frequency forecasting model for natural gas consumption","volume":"328","author":"Niu","year":"2025","journal-title":"Energy"},{"key":"10.1016\/j.engappai.2026.114746_b30","series-title":"Int. Conf. Learn. Represent.","article-title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","author":"Oreshkin","year":"2020"},{"key":"10.1016\/j.engappai.2026.114746_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2019.103323","article-title":"Short-term natural gas consumption prediction based on Volterra adaptive filter and improved whale optimization algorithm","volume":"87","author":"Qiao","year":"2020","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"8","key":"10.1016\/j.engappai.2026.114746_b32","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"10.1016\/j.engappai.2026.114746_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2022.104998","article-title":"Energy forecasting model based on CNN-LSTM-AE for many time series with unequal lengths","volume":"113","author":"Rick","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114746_b34","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.apenergy.2011.11.003","article-title":"Forecasting natural gas consumption","volume":"92","author":"Soldo","year":"2012","journal-title":"Appl. Energy"},{"key":"10.1016\/j.engappai.2026.114746_b35","series-title":"2013 International Conference on Computing, Management and Telecommunications","first-page":"401","article-title":"Time series prediction using pattern matching","author":"Son","year":"2013"},{"key":"10.1016\/j.engappai.2026.114746_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108431","article-title":"A novel grey prediction model with four-parameter and its application to forecast natural gas production in China","volume":"133","author":"Song","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"2","key":"10.1016\/j.engappai.2026.114746_b37","article-title":"An effective prediction system for time series data using pattern matching algorithms.","volume":"25","author":"Sridevi","year":"2018","journal-title":"Int. J. Ind. Eng."},{"key":"10.1016\/j.engappai.2026.114746_b38","series-title":"Advances in Neural Information Processing Systems","first-page":"60162","article-title":"Are language models actually useful for time series forecasting?","volume":"37","author":"Tan","year":"2024"},{"issue":"2","key":"10.1016\/j.engappai.2026.114746_b39","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1145\/3715073.3715083","article-title":"Time series forecasting with LLMs: Understanding and enhancing model capabilities","volume":"26","author":"Tang","year":"2025","journal-title":"SIGKDD Explor. Newsl."},{"key":"10.1016\/j.engappai.2026.114746_b40","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.enbuild.2012.10.023","article-title":"Forecasting of daily natural gas consumption on regional basis in Turkey using various computational methods","volume":"56","author":"Ta\u015ep\u0131nar","year":"2013","journal-title":"Energy Build."},{"key":"10.1016\/j.engappai.2026.114746_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107644","article-title":"Application of forecasting strategies and techniques to natural gas consumption: A comprehensive review and comparative study","volume":"129","author":"Tian","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114746_b42","doi-asserted-by":"crossref","DOI":"10.1016\/j.eneco.2024.107608","article-title":"Unraveling the crystal ball: Machine learning models for crude oil and natural gas volatility forecasting","volume":"134","author":"Tiwari","year":"2024","journal-title":"Energy Econ."},{"key":"10.1016\/j.engappai.2026.114746_b43","doi-asserted-by":"crossref","DOI":"10.1016\/j.nexus.2023.100210","article-title":"China mainland new energy index price forecasting with the neural network","volume":"10","author":"Xu","year":"2023","journal-title":"Energy Nexus"},{"key":"10.1016\/j.engappai.2026.114746_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.110407","article-title":"A novel structural adaptive seasonal grey Bernoulli model in natural gas production forecasting","volume":"148","author":"Yan","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"7","key":"10.1016\/j.engappai.2026.114746_b45","doi-asserted-by":"crossref","first-page":"1998","DOI":"10.1002\/ese3.1122","article-title":"A hybrid deep learning approach by integrating extreme gradient boosting-long short-term memory with generalized autoregressive conditional heteroscedasticity family models for natural gas load volatility prediction","volume":"10","author":"Zeng","year":"2022","journal-title":"Energy Sci. Eng."},{"key":"10.1016\/j.engappai.2026.114746_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2026.108687","article-title":"TF-LLM: Enhanced time series analysis with time-frequency large language models","volume":"199","author":"Zhang","year":"2026","journal-title":"Neural Netw."},{"key":"10.1016\/j.engappai.2026.114746_b47","series-title":"Advances in Neural Information Processing Systems","first-page":"43322","article-title":"One fits all: Power general time series analysis by pretrained LM","volume":"Vol. 36","author":"Zhou","year":"2023"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626010286?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626010286?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T20:28:31Z","timestamp":1778099311000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626010286"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":47,"alternative-id":["S0952197626010286"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114746","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Natural gas demand forecasting via latent pattern retrieval and expert specialization","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114746","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114746"}}