Collaborative estimation and evaluation of SARS-CoV-2 variant nowcasting in the United States

2026-06-05

AI Summary

Existing platforms struggle to collaboratively forecast the dynamic trajectories of SARS-CoV-2 variants across U.S. states. This work proposes the first state-level nowcasting Hub specifically designed for viral variants, integrating a multi-model framework grounded in genomic sequencing data to estimate the current relative abundance of designated variants and incorporating a scoring system to evaluate model performance. The Hub addresses a critical gap in real-time variant surveillance by enabling localized modeling alongside national benchmark comparisons. Results demonstrate that nationally aggregated benchmark models exhibit overall robustness, while state-specific local models generally outperform national ones—except in regions with low sequencing volumes, where prediction stability markedly declines.

Abstract

The ability to estimate and predict pathogen variant dynamics can inform public health responses, including planning for increased transmission or severity, shifts in population immunity, or changes to vaccine or therapeutic effectiveness. The COVID-19 pandemic demonstrated the importance of monitoring SARS-CoV-2 variant evolution through viral genome sequencing, enabling predictive models to estimate variant frequencies in the recent past, present, and short-term future. Collaborative forecasting Hubs provided a valuable way to centralize predictive modeling of epidemiological indicators such as cases, hospitalizations, and deaths during the pandemic; however, none existed for variant dynamics. Here, we discuss the creation of the United States SARS-CoV-2 Variant Nowcast Hub, designed to solicit estimates of the relative abundance of a specified set of SARS-CoV-2 variants at the U.S. state level. We discuss the design decisions and challenges in building the Hub and its scoring procedures. Using submissions from the Hub's first respiratory virus season (nowcast dates October 9th, 2024 to June 4th, 2025), we evaluate five individual models and a baseline model. We found that the baseline model, which pools sequences across the U.S., performs well overall, with most individual models performing similarly or slightly worse. Locations with lower sequencing volumes exhibited greater variability in model performance. Models submitted for a single location outperformed those submitted for all locations, potentially due to greater timeliness and magnitude of local data. Much remains to be investigated regarding relative model performance across different phases of variant emergence, and we conclude by proposing future directions within and beyond this Hub.

Problem

• SARS-CoV-2 variant
• nowcasting
• collaborative forecasting
• variant dynamics
• epidemiological modeling

Innovation

• variant nowcasting
• collaborative forecasting
• SARS-CoV-2 surveillance
• model evaluation
• genomic epidemiology