Abstract
Prompt surveillance and forecasting of COVID-19 spread are of critical importance for slowing down the pandemic and for the success of any public mitigation efforts. However, as with any infectious disease with rapid transmission and high virulence, lack of COVID-19 observations for near-real-time forecasting is still the key challenge obstructing operational disease prediction and control. In this context, we can follow the two approaches to forecasting COVID-19 dynamics: based on mechanistic models and based on machine learning. Mechanistic models are better in capturing an epidemiological curve, using a low amount of data, and describing the overall trajectory of the disease dynamics, hence, providing long-term insights into where the disease might go. Machine learning, in turn, can provide more precise data-driven forecasts especially in the short-term horizons, while suffering from limited interpretability and usually requiring backlog history on the infectious disease. We propose a unified reinforcement learning framework that combines the two approaches. That is, long-term trajectory forecasts are used in machine learning techniques to forecast local variability which is not captured by the mechanistic model.
- D. Bertsekas. Rollout, Policy Iteration, and Distributed Reinforcement Learning. Athena Scientific, 1 edition, 8 2020.Google Scholar
- G. Bobashev. Simulation modeling of hiv infection---from individuals to risk groups and entire populations. In C. Chan, M. G. Hudgens, and S.-C. Chow, editors, Quantitative Methods for HIV/AIDS Research, chapter 10, pages 201--229. Chapman & Hall/CRC Biostatistics Series, 1 edition, 8 2017.Google ScholarCross Ref
- J. Cajka, P. Cooley, and W. Wheaton. Attribute assignment to a synthetic population in support of agent-based disease modeling. Methods report (RTI Press), 19:1--14, 09 2010.Google ScholarCross Ref
- P. Cooley, L. Ganapathi, G. Ghneim, S. Holmberg, W. Wheaton, and C. Hollingsworth. Using influenza-like illness data to reconstruct an influenza outbreak. Mathematical and Computer Modelling, 48:929--939, 02 2008.Google ScholarDigital Library
- N. Ferguson, D. Cummings, C. Fraser, J. Cajka, P. Cooley, and S. Burke. Strategies for mitigating an influenza pandemic. Nature, 442:448--52, 08 2006.Google ScholarCross Ref
- P. Hernandez-Leal, B. Kartal, and M. Taylor. A survey and critique of multiagent deep reinforcement learning. Autonomous Agents and Multi-Agent Systems, 33, 10 2019.Google ScholarCross Ref
- S. Ivanov and A. D'yakonov. Modern deep reinforcement learning algorithms, 2019. Available at https://arxiv.org/abs/1906.10025.Google Scholar
- V. Leonenko and G. Bobashev. Analyzing influenza outbreaks in russia using an age-structured dynamic transmission model. Epidemics, 29:100358, 2019.Google ScholarCross Ref
- P. Libin, A. Moonens, T. Verstraeten, F. Perez-Sanjines, N. Hens, P. Lemey, and A. Nowé. Deep reinforcement learning for large-scale epidemic control. ALA 2020, Auckland, New Zealand, 5 2020.Google Scholar
- I. M. Longini, A. Nizam, S. Xu, K. Ungchusak, W. Hanshaoworakul, D. A. T. Cummings, and M. E. Halloran. Containing pandemic influenza at the source. Science, 309(5737):1083--1087, 2005.Google ScholarCross Ref
- J. Mathieu, M. Pfaff, G. Klein, J. Drury, M. Geodecke, J. James, P. Mahoney, and G. Bobashev. Tactical Robust Decision-Making Methodology: Effect of Disease Spread Model Fidelity on Option Awareness. Seattle, WA, 01 2010.Google Scholar
- W. Probert, S. Lakkur, C. Fonnesbeck, K. Shea, M. Runge, M. Tildesley, and M. Ferrari. Context matters: using reinforcement learning to develop human-readable, state-dependent outbreak response policies. Philosophical transactions of the Royal Society of London. Series B, Biological sciences, 374:20180277, 07 2019.Google Scholar
- W. D. Wheaton, J. Cajka, B. M. Chasteen, D. Wagener, P. Cooley, L. Ganapathi, D. J. Roberts, and J. Allpress. Synthesized population databases: A us geospatial database for agent-based models. Methods report, 2009 10:905, 2009. Available at http://www.rti.org/sites/default/files/resources/mr-0010-0905-wheaton.pdf.Google Scholar
Index Terms
- Geospatial forecasting of COVID-19 spread and risk of reaching hospital capacity
Recommendations
COVID-19 ICU demand forecasting: A two-stage Prophet-LSTM approach
AbstractRecent literature has revealed a growing interest in methods for anticipating the demand for medical items and personnel at hospital, especially during turbulent scenarios such as the COVID-19 pandemic. In times like those, new ...
Highlights- We propose a novel two-stage integration of Prophet and LSTM forecasting models.
Multiplicative Holts Winter Model for Trend Analysis and Forecasting of COVID-19 Spread in India
AbstractThe surge of the novel COVID-19 caused a tremendous effect on the health and life of the people resulting in more than 4.4 million confirmed cases in 213 countries of the world as of May 14, 2020. In India, the number of cases is constantly ...
Deep Forecasting of COVID-19: Canadian Case Study
Advances and Trends in Artificial Intelligence. Artificial Intelligence PracticesAbstractCOVID-19 is an infectious disease, which is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). In this research, we firstly present an overview of the main forecasting models to predict the new cases of COVID-19. In this ...
Comments