COVID-19 Forecasting from U.S. Wastewater Surveillance Data: A Retrospective Multi-Model Study (2022-2024)

2025-11-30

AI Summary

This study addresses the problem of forecasting COVID-19 trends in the United States using wastewater surveillance data. We develop a comprehensive time-series forecasting framework comprising ARIMA, generalized additive models (GAM), Prophet, simple linear regression (SLR), and an n-subepidemic model, and systematically evaluate both weighted and unweighted ensemble strategies across 1–4-week forecast horizons. Our key contribution is the proposal and empirical validation of an unweighted n-subepidemic ensemble model, which significantly outperforms all baselines for medium- to long-term forecasts (3–4 weeks), particularly at the national level and in the Midwest and Western regions. For short-term forecasts (1–2 weeks), ARIMA and GAM yield superior accuracy. Results underscore the critical importance of region-specific modeling for improving forecast precision, establishing an interpretable, robust, and spatially adaptive prediction paradigm for wastewater-informed public health response.

Technology Category

• Machine Learning: Ensemble Methods
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web search models and ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurate and reliable forecasting models are critical for guiding public health responses and policy decisions during pandemics such as COVID-19. Retrospective evaluation of model performance is essential for improving epidemic forecasting capabilities. In this study, we used COVID-19 wastewater data from CDC's National Wastewater Surveillance System to generate sequential weekly retrospective forecasts for the United States from March 2022 through September 2024, both at the national level and for four major regions (Northeast, Midwest, South, and West). We produced 133 weekly forecasts using 11 models, including ARIMA, generalized additive models (GAM), simple linear regression (SLR), Prophet, and the n-sub-epidemic framework (top-ranked, weighted-ensemble, and unweighted-ensemble variants). Forecast performance was assessed using mean absolute error (MAE), mean squared error (MSE), weighted interval score (WIS), and 95% prediction interval coverage. The n-sub-epidemic unweighted ensembles outperformed all other models at 3-4-week horizons, particularly at the national level and in the Midwest and West. ARIMA and GAM performed best at 1-2-week horizons in most regions, whereas Prophet and SLR consistently underperformed across regions and horizons. These findings highlight the value of region-specific modeling strategies and demonstrate the utility of the n-sub-epidemic framework for real-time outbreak forecasting using wastewater surveillance data.

Problem

• Evaluating COVID-19 forecasting models using wastewater surveillance data
• Comparing performance of multiple models across different U.S. regions
• Identifying optimal modeling strategies for outbreak prediction horizons

Innovation

• Used wastewater data for COVID-19 forecasting
• Applied multiple models including n-sub-epidemic ensembles
• Evaluated performance with region-specific strategies