We propose a novel approach that integrates machine learning into compartmental disease modeling (e.g., SEIR) 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 we demonstrate it for states and counties in the United States. We show that our model provides more accurate forecasts compared to the alternatives, and that it provides qualitatively meaningful explanatory insights.

Table 1: Covariates selected for model.

In the related work section, the authors summarize some related models for infectious diseases and address their weaknesses. However, it seems none of them are used as baseline models for comparison in the experiment section. Instead, the authors present the results of five top-performing models designed for COVID-19. It would be better if the authors can give a summary of these COVID-19 models to address their weakness and point out the major improvement of their method compared with these ones. The author claims the extra compartment has significant benefits for the prediction. However, Table 4 does not directly show this benefit.

Three knowledgeable reviewers support acceptance, particularly due to the proposed model novelty, performance, interpretability, and relatively good reproducibility. I agree with these strengths and overall paper contribution and must accept. For the final version, please strongly consider enhancing the paper with (1) Code: making the code available will help with further research and reproducibility (2) Related work: it would be a great addition to the paper if the five top-performing models in the experiment section were explained in better detail in the related work section (see R2). (3) Limitations: address R3 feedback regarding acknowledging limitations.

We propose a novel approach that integrates machine learning into compartmental disease modeling (e.g., SEIR) 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 we demonstrate it for states and counties in the United States. We show that our model provides more accurate forecasts compared to the alternatives, and that it provides qualitatively meaningful explanatory insights.