A dual-branch deep learning framework for tiered early warning of COVID-19 utilizing wastewater data
Journal of Water and Health · 2026
DOI: 10.2166/wh.2026.150 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Water and Health, 2026. Verfasst von Xiaoqiang Li und 8 weiteren Autor:innen. Beteiligte Einrichtung: Changzhou Center for Disease Control and Prevention, Changzhou, Jiangsu 213022, China. Hauptthemen laut MEDLINE: COVID-19, Deep Learning, Wastewater. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Changzhou Science and Technology Project, Open Research Fund Program of Changzhou Institute for Advanced Study of Public Health, Nanjing Medical University.
Abstract (Originalsprache)
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–Dec 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 (1.13–1.67), MAE 1.23 (0.99–1.48), MAPE 10.44% (5.20–16.40), and R2 0.99 (0.99–0.99). 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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Changzhou Center for Disease Control and Prevention, Changzhou, Jiangsu 213022, China.
- School of Public Health, Fudan University, Shanghai 200032, China.
- Changzhou Institute for Advanced Study of Public Health, Nanjing Medical University, Changzhou, Jiangsu 213022, China E-mail: xiaoqiangli16@fudan.edu.cn.
- Changzhou Sewage Treatment Co., Ltd, Changzhou, Jiangsu 213031, China.
- Changzhou Institute for Advanced Study of Public Health, Nanjing Medical University, Changzhou, Jiangsu 213022, China.
- School of Public Health, Nanjing Medical University, Nanjing, Jiangsu 211166, China.
ORCID-Profile: Xiaoqiang Li
Förderung
- Changzhou Science and Technology Project
- Open Research Fund Program of Changzhou Institute for Advanced Study of Public Health, Nanjing Medical University
Zitieren
APA
Li, X., Wu, C., Jiang, J., Wu, S., Zhu, C., Yang, M., Chen, Z., Chen, X., & Tan, L. (2026). A dual-branch deep learning framework for tiered early warning of COVID-19 utilizing wastewater data. Journal of Water and Health. https://doi.org/10.2166/wh.2026.150
Vancouver
Li X, Wu C, Jiang J, Wu S, Zhu C, Yang M, et al. A dual-branch deep learning framework for tiered early warning of COVID-19 utilizing wastewater data. Journal of Water and Health. 2026. doi:10.2166/wh.2026.150
BibTeX
@article{Li2026,
author = {Li, Xiaoqiang and Wu, Changqian and Jiang, Jingyi and Wu, Shufan and Zhu, Cheng and Yang, Minhui and Chen, Zhiyong and Chen, Xiaoyue and Tan, Lifeng},
title = {A dual-branch deep learning framework for tiered early warning of COVID-19 utilizing wastewater data},
journal = {Journal of Water and Health},
year = {2026},
doi = {10.2166/wh.2026.150}
}
EUVIMED