A Neural SIR Model for Global Forecasting

Philip Nadler, Rossella Arcucci, Yike Guo
Proceedings of the Machine Learning for Health NeurIPS Workshop, PMLR 136:254-266, 2020.

Abstract

Being able to understand and forecast epidemic developments is crucial for policymakers. We develop a predictive model combining epidemiological dynamics of compartmental models with highly non-linear interactions learned by a LSTM Network. A novel dynamic SIR model is fit to variables related to the population transmission of Covid-19. This is embedded in a Bayesian recursive updating framework which is then coupled with a LSTM network to forecast cases of Covid-19. The model significantly improves forecasts over simple univariate LSTM or SIR models. We apply the model to developed and developing countries and forecast confirmed infections and analyze future trajectories.

Cite this Paper


BibTeX
@InProceedings{pmlr-v136-nadler20a, title = {A Neural SIR Model for Global Forecasting}, author = {Nadler, Philip and Arcucci, Rossella and Guo, Yike}, booktitle = {Proceedings of the Machine Learning for Health NeurIPS Workshop}, pages = {254--266}, year = {2020}, editor = {Emily Alsentzer and Matthew B. A. McDermott and Fabian Falck and Suproteem K. Sarkar and Subhrajit Roy and Stephanie L. Hyland}, volume = {136}, series = {Proceedings of Machine Learning Research}, month = {11 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v136/nadler20a/nadler20a.pdf}, url = {http://proceedings.mlr.press/v136/nadler20a.html}, abstract = {Being able to understand and forecast epidemic developments is crucial for policymakers. We develop a predictive model combining epidemiological dynamics of compartmental models with highly non-linear interactions learned by a LSTM Network. A novel dynamic SIR model is fit to variables related to the population transmission of Covid-19. This is embedded in a Bayesian recursive updating framework which is then coupled with a LSTM network to forecast cases of Covid-19. The model significantly improves forecasts over simple univariate LSTM or SIR models. We apply the model to developed and developing countries and forecast confirmed infections and analyze future trajectories.} }
Endnote
%0 Conference Paper %T A Neural SIR Model for Global Forecasting %A Philip Nadler %A Rossella Arcucci %A Yike Guo %B Proceedings of the Machine Learning for Health NeurIPS Workshop %C Proceedings of Machine Learning Research %D 2020 %E Emily Alsentzer %E Matthew B. A. McDermott %E Fabian Falck %E Suproteem K. Sarkar %E Subhrajit Roy %E Stephanie L. Hyland %F pmlr-v136-nadler20a %I PMLR %P 254--266 %U http://proceedings.mlr.press/v136/nadler20a.html %V 136 %X Being able to understand and forecast epidemic developments is crucial for policymakers. We develop a predictive model combining epidemiological dynamics of compartmental models with highly non-linear interactions learned by a LSTM Network. A novel dynamic SIR model is fit to variables related to the population transmission of Covid-19. This is embedded in a Bayesian recursive updating framework which is then coupled with a LSTM network to forecast cases of Covid-19. The model significantly improves forecasts over simple univariate LSTM or SIR models. We apply the model to developed and developing countries and forecast confirmed infections and analyze future trajectories.
APA
Nadler, P., Arcucci, R. & Guo, Y.. (2020). A Neural SIR Model for Global Forecasting. Proceedings of the Machine Learning for Health NeurIPS Workshop, in Proceedings of Machine Learning Research 136:254-266 Available from http://proceedings.mlr.press/v136/nadler20a.html.

Related Material