{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T12:19:50Z","timestamp":1774873190196,"version":"3.50.1"},"reference-count":41,"publisher":"IWA Publishing","issue":"3","license":[{"start":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T00:00:00Z","timestamp":1772150400000},"content-version":"vor","delay-in-days":37,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Changzhou Science and Technology Project","award":["CJ20245051"],"award-info":[{"award-number":["CJ20245051"]}]},{"name":"Open Research Fund Program of Changzhou Institute for Advanced Study of Public Health, Nanjing Medical University","award":["CPHN202302"],"award-info":[{"award-number":["CPHN202302"]}]}],"content-domain":{"domain":["iwaponline.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p\/>\n                  <jats:p>Background: Wastewater offers earlier, population-level signals, yet few models integrate environmental drivers for reliable routine COVID-19 alerts. We hypothesized that combining wastewater and environmental covariates in a dual-branch deep model leveraging FFT would improve forecasting and alerting. Methods: Using weekly wastewater, meteorological, and case data from Changzhou, China (Jan 29\u2013Dec 10, 2024), we developed a framework that forecasts case trajectories and triggers tiered yellow\/red alerts at predefined thresholds. Results: On 2-week-ahead internal tests, performance was: RMSE 1.40 (1.13\u20131.67), MAE 1.23 (0.99\u20131.48), MAPE 10.44% (5.20\u201316.40), and R2 0.99 (0.99\u20130.99). On an external test, both yellow and red alerts were correctly predicted 3 weeks ahead. Versus a naive baseline and the COVID-19 Forecast Hub model, our approach reduced missed alerts, whereas the Forecast Hub model reduced false declarations. Ablation showed necessity of the dual-branch architecture and covariates. Conclusions: The novel framework delivers accurate, timely forecasts and reliable early warnings from multi-source data, supporting proactive public health response to COVID-19. It may also be a promising approach for the prediction of other infectious diseases. However, validating and adapting the approach across locations, and epidemic patterns is a key next step to establish robustness, generalizability, and operational value.<\/jats:p>","DOI":"10.2166\/wh.2026.150","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T10:11:08Z","timestamp":1772187068000},"page":"349-366","update-policy":"https:\/\/doi.org\/10.2166\/iwapcrossmarkpolicypage","source":"Crossref","is-referenced-by-count":0,"title":["A dual-branch deep learning framework for tiered early warning of COVID-19 utilizing wastewater data"],"prefix":"10.2166","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6845-2896","authenticated-orcid":false,"given":"Xiaoqiang","family":"Li","sequence":"first","affiliation":[{"name":"a Changzhou Center for Disease Control and Prevention, Changzhou, Jiangsu 213022, China"},{"name":"b School of Public Health, Fudan University, Shanghai 200032, China"},{"name":"c Changzhou Institute for Advanced Study of Public Health, Nanjing Medical University, Changzhou, Jiangsu 213022, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changqian","family":"Wu","sequence":"additional","affiliation":[{"name":"a Changzhou Center for Disease Control and Prevention, Changzhou, Jiangsu 213022, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyi","family":"Jiang","sequence":"additional","affiliation":[{"name":"a Changzhou Center for Disease Control and Prevention, Changzhou, Jiangsu 213022, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shufan","family":"Wu","sequence":"additional","affiliation":[{"name":"a Changzhou Center for Disease Control and Prevention, Changzhou, Jiangsu 213022, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"d Changzhou Sewage Treatment Co., Ltd, Changzhou, Jiangsu 213031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minhui","family":"Yang","sequence":"additional","affiliation":[{"name":"d Changzhou Sewage Treatment Co., Ltd, Changzhou, Jiangsu 213031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Chen","sequence":"additional","affiliation":[{"name":"a Changzhou Center for Disease Control and Prevention, Changzhou, Jiangsu 213022, China"},{"name":"c Changzhou Institute for Advanced Study of Public Health, Nanjing Medical University, Changzhou, Jiangsu 213022, China"},{"name":"e School of Public Health, Nanjing Medical University, Nanjing, Jiangsu 211166, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyue","family":"Chen","sequence":"additional","affiliation":[{"name":"a Changzhou Center for Disease Control and Prevention, Changzhou, Jiangsu 213022, China"},{"name":"e School of Public Health, Nanjing Medical University, Nanjing, Jiangsu 211166, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lifeng","family":"Tan","sequence":"additional","affiliation":[{"name":"a Changzhou Center for Disease Control and Prevention, Changzhou, Jiangsu 213022, China"},{"name":"c Changzhou Institute for Advanced Study of Public Health, Nanjing Medical University, Changzhou, Jiangsu 213022, China"},{"name":"e School of Public Health, Nanjing Medical University, Nanjing, Jiangsu 211166, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"945","published-online":{"date-parts":[[2026,1,21]]},"reference":[{"key":"key-10.2166\/wh.2026.150-1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109367"},{"key":"key-10.2166\/wh.2026.150-2","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2021.149757"},{"key":"key-10.2166\/wh.2026.150-3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0277154"},{"key":"key-10.2166\/wh.2026.150-4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jiph.2024.01.019"},{"key":"key-10.2166\/wh.2026.150-5","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2021.05.003"},{"key":"key-10.2166\/wh.2026.150-6","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2022.153290"},{"key":"key-10.2166\/wh.2026.150-7","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2025.179592"},{"key":"key-10.2166\/wh.2026.150-8","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2113561119"},{"key":"key-10.2166\/wh.2026.150-9","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2020.139631"},{"key":"key-10.2166\/wh.2026.150-10","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/978-3-031-30085-1_10","article-title":"Incorporating external factors into time series forecasts","volume-title":"Judgment in Predictive Analytics","author":"De Baets","year":"2023"},{"key":"key-10.2166\/wh.2026.150-11","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2023.168782"},{"key":"key-10.2166\/wh.2026.150-12","doi-asserted-by":"publisher","DOI":"10.1289\/EHP9966"},{"key":"key-10.2166\/wh.2026.150-13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3454271"},{"key":"key-10.2166\/wh.2026.150-14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2023.104482"},{"key":"key-10.2166\/wh.2026.150-15","doi-asserted-by":"publisher","DOI":"10.2166\/wh.2023.091"},{"key":"key-10.2166\/wh.2026.150-16","doi-asserted-by":"publisher","DOI":"10.1111\/1751-7915.70020"},{"key":"key-10.2166\/wh.2026.150-17","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-5122(03)00039-2"},{"key":"key-10.2166\/wh.2026.150-18","unstructured":"Johnson K., Morris D., Abbott S., Zelaya C. B., Yon G. V. & Bayer D. (2024) wwinference: Jointly Infers Infection Dynamics From Wastewater Data and Epidemiological Indicators. GitHub. Available at: https:\/\/github.com\/cdcgov\/ww-inference-model\/."},{"key":"key-10.2166\/wh.2026.150-19","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2023.119617"},{"key":"key-10.2166\/wh.2026.150-20","doi-asserted-by":"publisher","DOI":"10.5194\/hess-22-6005-2018"},{"key":"key-10.2166\/wh.2026.150-21","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40305-x"},{"key":"key-10.2166\/wh.2026.150-22","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2024.175235"},{"key":"key-10.2166\/wh.2026.150-23","doi-asserted-by":"publisher","DOI":"10.3201\/eid3009.240640"},{"key":"#cr-split#-key-10.2166\/wh.2026.150-24.1","unstructured":"Loshchilov I. & Hutter F. (2019) Decoupled Weight Decay Regularization [Internet]. arXiv"},{"key":"#cr-split#-key-10.2166\/wh.2026.150-24.2","unstructured":"2019 [cited 2025 May 29]. (ICLR 2019). Available at: http:\/\/arxiv.org\/abs\/1711.05101."},{"key":"key-10.2166\/wh.2026.150-25","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-023-17327-7"},{"key":"key-10.2166\/wh.2026.150-26","doi-asserted-by":"publisher","DOI":"10.1016\/j.coesh.2020.09.006"},{"key":"key-10.2166\/wh.2026.150-27","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(22)00167-4"},{"key":"key-10.2166\/wh.2026.150-28","doi-asserted-by":"publisher","DOI":"10.1016\/S2666-5247(24)00126-5"},{"key":"key-10.2166\/wh.2026.150-29","doi-asserted-by":"publisher","DOI":"10.1039\/D1EW00539A"},{"key":"key-10.2166\/wh.2026.150-30","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-11187-8"},{"key":"key-10.2166\/wh.2026.150-31","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2022.159326"},{"key":"key-10.2166\/wh.2026.150-32","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2023.120098"},{"key":"key-10.2166\/wh.2026.150-33","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2023.167709"},{"key":"key-10.2166\/wh.2026.150-34","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01606-1"},{"key":"#cr-split#-key-10.2166\/wh.2026.150-35.1","doi-asserted-by":"crossref","unstructured":"Wang H., Pan L., Chen Z., Yang D., Zhang S., Yang Y., Liu, X., Li, H. & Tao, D. (2025) FreDF: Learning to Forecast in the Frequency Domain [Internet]. arXiv","DOI":"10.1201\/9781003612742-3"},{"key":"#cr-split#-key-10.2166\/wh.2026.150-35.2","unstructured":"2025 [cited 2025 Jun 1]. Available at: http:\/\/arxiv.org\/abs\/2402.02399."},{"key":"key-10.2166\/wh.2026.150-36","unstructured":"World Health Organization (2022) Public Health Surveillance for COVID-19: Interim Guidance. Geneva: World Health Organization. 2022 Jul [cited 2025 May 19]. Report No.: WHO\/2019-nCoV\/SurveillanceGuidance\/2022.2. Available at: https:\/\/www.who.int\/publications\/i\/item\/WHO-2019-nCoV-SurveillanceGuidance-2022.2."},{"key":"key-10.2166\/wh.2026.150-37","doi-asserted-by":"publisher","DOI":"10.46234\/ccdcw2024.069"},{"key":"key-10.2166\/wh.2026.150-38","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-024-20968-x"},{"key":"key-10.2166\/wh.2026.150-39","doi-asserted-by":"publisher","DOI":"10.3390\/s25030652"}],"container-title":["Journal of Water and Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/iwaponline.com\/jwh\/article-pdf\/24\/3\/349\/1608703\/jwh2026150.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iwaponline.com\/jwh\/article-pdf\/24\/3\/349\/1608703\/jwh2026150.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T11:10:15Z","timestamp":1774869015000},"score":1,"resource":{"primary":{"URL":"https:\/\/iwaponline.com\/jwh\/article\/24\/3\/349\/110945\/A-dual-branch-deep-learning-framework-for-tiered"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,21]]},"references-count":41,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,1,21]]},"published-print":{"date-parts":[[2026,3,1]]}},"URL":"https:\/\/doi.org\/10.2166\/wh.2026.150","relation":{},"ISSN":["1477-8920","1996-7829"],"issn-type":[{"value":"1477-8920","type":"print"},{"value":"1996-7829","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,21]]}}}