Fine-Grained Forecasting of COVID-19 Trends at the County Level in the United States

Tzu‐Hsi Song, Leonardo Clemente, Xiang Pan, Junbong Jang, Mauricio Santillana, Kwonmoo Lee

Abstract

The novel coronavirus (COVID-19) pandemic, first identified in Wuhan China in December 2019, has profoundly impacted various aspects of daily life, society, healthcare systems, and global health policies. There have been more than half a billion human infections and more than 6 million deaths globally attributable to COVID-19. Although treatments and vaccines to protect against COVID-19 are now available, people continue being hospitalized and dying due to COVID-19 infections. Real-time surveillance of population-level infections, hospitalizations, and deaths has helped public health officials better allocate healthcare resources and deploy mitigation strategies. However, producing reliable, real-time, short-term disease activity forecasts (one or two weeks into the future) remains a practical challenge. The recent emergence of robust time-series forecasting methodologies based on deep learning approaches has led to clear improvements in multiple research fields. We propose a recurrent neural network model named Fine-Grained Infection Forecast Network (FIGI-Net), which utilizes a stacked bidirectional LSTM structure designed to leverage fine-grained county-level data, to produce daily forecasts of COVID-19 infection trends up to two weeks in advance. We show that FIGI-Net improves existing COVID-19 forecasting approaches and delivers accurate county-level COVID-19 disease estimates. Specifically, FIGI-Net is capable of anticipating upcoming sudden changes in disease trends such as the onset of a new outbreak or the peak of an ongoing outbreak, a skill that multiple existing state-of-the-art models fail to achieve. This improved performance is observed across locations and periods. Our enhanced forecasting methodologies may help protect human populations against future disease outbreaks.

Introduction: The Challenge of Local Heterogeneity

Forecasting an infectious disease like COVID-19 is notoriously difficult because "the pandemic" isn't one single event—it’s thousands of local events happening simultaneously. Traditional epidemiological models (like SIR) often struggle to incorporate local variables like socioeconomic factors, varying vaccination rates, and specific mitigation policies.

On the other hand, many existing machine learning models focus on national or state-level data. While this makes the math easier, it "averages out" the local heterogeneity. If a specific county sees a sudden spike due to a local event, a state-level model might miss it entirely until it's too late. The challenge addressed by FIGI-Net is creating a "fine-grained" system that is sensitive enough to catch local shifts but robust enough to learn from global patterns.

Methodology: The FIGI-Net Framework

The researchers introduced the Fine-Grained Infection Forecast Network (FIGI-Net), which rests on three main architectural pillars:

  1. Stacked Bidirectional LSTMs (biLSTM): Unlike standard LSTMs that only process data chronologically, biLSTMs look at the sequence in both forward and backward directions. This allows the model to better capture complex temporal dependencies and "state changes," such as the sudden onset of a wave.
  2. Spatio-Temporal Clustering: The model uses UMAP for dimensionality reduction and DBScan for clustering to group counties based on their actual infection and fatality patterns. This means a rural county in one state might be clustered with a similar rural county elsewhere if their outbreak "signatures" look alike.
  3. Transfer Learning: The model is first trained on data from all counties to learn universal infection features, then fine-tuned into eight specific "sub-models" based on the clusters. This allows the model to benefit from a massive dataset while specializing in local dynamics.
Overview of the FIGI-Net architecture, including the clustering pipeline (a) and the stacked bidirectional LSTM structure (b).

Datasets

The study utilized daily COVID-19 confirmed cases and deaths from 3,143 U.S. counties, sourced from the Johns Hopkins Center for Systems Science and Engineering (CSSE). The data spans from February 2020 to April 2022, covering major waves including Alpha, Delta, and Omicron. FIGI-Net was benchmarked against the COVIDhub-ensemble (the "CDC model") and several baseline neural networks.

Key Insights and Results

A critical finding was determining the optimal training window. The authors found that a 75-day moving window provided the best balance—long enough to capture meaningful trends, but short enough to remain "agile" and responsive to new variants like Omicron that change transmission dynamics.

RRMSE and R^2 scores for 1-week and 2-week ahead forecasts, demonstrating the performance of the proposed 75-day training window.

Performance Evaluation

FIGI-Net demonstrated significant performance gains across several metrics:

  • Superior Accuracy: At the county level, FIGI-Net achieved an approximate 58.5% reduction in RMSE (Root Mean Square Error) compared to the CDC’s ensemble model for 1- and 2-week forecasts.
  • National Impact: When county-level forecasts were aggregated to the national level, the model showed an 86.5% error reduction at the 1-day horizon and a 53.8% reduction at the 14-day horizon compared to baseline models.
  • Anticipating the "Pivot": During "critical time periods" of rapid growth, FIGI-Net maintained a much higher "slope similarity" to ground truth data, correctly predicting the direction and intensity of new waves while other models lagged.

Conclusion

While FIGI-Net is powerful, it is computationally resource-intensive due to the need for multiple sub-models and complex clustering. Furthermore, the model is sensitive to data quality; when reporting shifted from daily to weekly, error rates increased. Future work may involve applying this "cluster-then-transfer" architecture to other infectious diseases like influenza or RSV, where local social dynamics play a similarly outsized role.

Summary updated

Abstract

The novel coronavirus (COVID-19) pandemic, first identified in Wuhan China in December 2019, has profoundly impacted various aspects of daily life, society, healthcare systems, and global health policies. There have been more than half a billion human infections and more than 6 million deaths globally attributable to COVID-19. Although treatments and vaccines to protect against COVID-19 are now available, people continue being hospitalized and dying due to COVID-19 infections. Real-time surveillance of population-level infections, hospitalizations, and deaths has helped public health officials better allocate healthcare resources and deploy mitigation strategies. However, producing reliable, real-time, short-term disease activity forecasts (one or two weeks into the future) remains a practical challenge. The recent emergence of robust time-series forecasting methodologies based on deep learning approaches has led to clear improvements in multiple research fields. We propose a recurrent neural network model named Fine-Grained Infection Forecast Network (FIGI-Net), which utilizes a stacked bidirectional LSTM structure designed to leverage fine-grained county-level data, to produce daily forecasts of COVID-19 infection trends up to two weeks in advance. We show that FIGI-Net improves existing COVID-19 forecasting approaches and delivers accurate county-level COVID-19 disease estimates. Specifically, FIGI-Net is capable of anticipating upcoming sudden changes in disease trends such as the onset of a new outbreak or the peak of an ongoing outbreak, a skill that multiple existing state-of-the-art models fail to achieve. This improved performance is observed across locations and periods. Our enhanced forecasting methodologies may help protect human populations against future disease outbreaks.
BibTeX
@article{song2025fine,
  author = {Tzu‐Hsi Song and Leonardo Clemente and Xiang Pan and Junbong Jang and Mauricio Santillana and Kwonmoo Lee},
  title = {{Fine-Grained Forecasting of COVID-19 Trends at the County Level in the United States}},
  journal = {Npj Digit. Medicine},
  year = {2025},
  doi = {10.1038/s41746-025-01606-1},
}
Figure