# Interpretable Sequence Learning for COVID-19 Forecasting

arXiv: https://arxiv.org/abs/2008.00646 · HTML: https://mlsanity.com/paper/2008.00646/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2020.

## Built on by (most cited first, 22 of 22)

- [Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling](https://mlsanity.com/paper/2102.13156/) (2021)
- [EINNs: Epidemiologically-informed Neural Networks](https://mlsanity.com/paper/2202.10446/) (2022)
- [Differentiable Agent-based Epidemiology](https://mlsanity.com/paper/2207.09714/) (2022)
- [Robust Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2202.11910/) (2022)
- [Breiman's two cultures: You don't have to choose sides](https://mlsanity.com/paper/2104.12219/) (2021)
- [Data-Centric Epidemic Forecasting: A Survey](https://mlsanity.com/paper/2207.09370/) (2022)
- [Deep Bayesian Active Learning for Accelerating Stochastic Simulation](https://mlsanity.com/paper/2106.02770/) (2021)
- [Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future](https://mlsanity.com/paper/2106.04420/) (2021)
- [A spatiotemporal machine learning approach to forecasting COVID-19 incidence at the county level in the USA](https://mlsanity.com/paper/2109.12094/) (2021)
- [Deep Grey-Box Modeling With Adaptive Data-Driven Models Toward Trustworthy Estimation of Theory-Driven Models](https://mlsanity.com/paper/2210.13103/) (2022)
- [MSGNN: Multi-scale Spatio-temporal Graph Neural Network for Epidemic Forecasting](https://mlsanity.com/paper/2308.15840/) (2023)
- [SIMLR: Machine Learning inside the SIR model for COVID-19 Forecasting](https://mlsanity.com/paper/2106.01590/) (2021)
- [Scalable Continuous-time Diffusion Framework for Network Inference and Influence Estimation](https://mlsanity.com/paper/2403.02867/) (2024)
- [COUnty aggRegation mixup AuGmEntation (COURAGE) COVID-19 Prediction](https://mlsanity.com/paper/2105.00620/) (2021)
- [MAGI-X: Manifold-Constrained Gaussian Process Inference for Unknown System Dynamics](https://mlsanity.com/paper/2105.12894/) (2021)
- [Global and Local Interpretation of black-box Machine Learning models to determine prognostic factors from early COVID-19 data](https://mlsanity.com/paper/2109.05087/) (2021)
- [Predicting infections in the Covid-19 pandemic -- lessons learned](https://mlsanity.com/paper/2112.11187/) (2021)
- [Indirect Active Learning](https://mlsanity.com/paper/2206.01454/) (2022)
- [Deep COVID-19 Forecasting for Multiple States with Data Augmentation](https://mlsanity.com/paper/2302.01155/) (2023)
- [Machine Learning for Infectious Disease Risk Prediction: A Survey](https://mlsanity.com/paper/2308.03037/) (2023)
- [DemOpts: Fairness corrections in COVID-19 case prediction models](https://mlsanity.com/paper/2405.09483/) (2024)
- [Sharpness-Aware Hybrid Model Learning for Architecture-Agnostic Parameter Estimation](https://mlsanity.com/paper/2602.06837/) (2026)

## Abstract (arXiv)

We propose a novel approach that integrates machine learning into compartmental disease modeling to predict the progression of COVID-19. Our model is explainable by design as it explicitly shows how different compartments evolve and it uses interpretable encoders to incorporate covariates and improve performance. Explainability is valuable to ensure that the model's forecasts are credible to epidemiologists and to instill confidence in end-users such as policy makers and healthcare institutions. Our model can be applied at different geographic resolutions, and here we demonstrate it for states and counties in the United States. We show that our model provides more accurate forecasts, in metrics averaged across the entire US, than state-of-the-art alternatives, and that it provides qualitatively meaningful explanatory insights. Lastly, we analyze the performance of our model for different subgroups based on the subgroup distributions within the counties.