{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T18:20:59Z","timestamp":1782930059660,"version":"3.54.5"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3619552","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:54:48Z","timestamp":1760032488000},"page":"176813-176829","source":"Crossref","is-referenced-by-count":11,"title":["Causal-Aware Multimodal Transformer for Supply Chain Demand Forecasting: Integrating Text, Time Series, and Satellite Imagery"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5474-3503","authenticated-orcid":false,"given":"Ying","family":"Wang","sequence":"first","affiliation":[{"name":"Pepperdine University, Malibu, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanyu","family":"Ding","sequence":"additional","affiliation":[{"name":"New York University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0330-4411","authenticated-orcid":false,"given":"Ziyang","family":"Zeng","sequence":"additional","affiliation":[{"name":"New York University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8173-5120","authenticated-orcid":false,"given":"Shiyu","family":"Yang","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/asi7050093"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-020-00329-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/13675567.2020.1803246"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2022.05.119"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1108\/IJLM-02-2024-0120"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref8","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-021-01621-0"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s43017-023-00431-y"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1186\/s40854-024-00681-9"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-37929-w"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref14","first-page":"27268","article-title":"FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou"},{"key":"ref15","article-title":"A time series is worth 64 words: Long-term forecasting with transformers","author":"Nie","year":"2022","journal-title":"arXiv:2211.14730"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2022.0130581"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2025.2458121"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3243725"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3498443"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc8020014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2021.07.007"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15864\/ajamc.124"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71918-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCMC51019.2021.9418033"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref28","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv:1409.0473"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref30","article-title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","author":"Oreshkin","year":"2019","journal-title":"arXiv:1905.10437"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11197533.pdf?arnumber=11197533","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:42:22Z","timestamp":1760722942000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11197533\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3619552","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}