Congratulations to Amii alum Roberto Vega, research supervisor Russ Greiner (Amii Fellow and Canada CIFAR AI Chair), and collaborator Leonardo Flores who were recently awarded the Forecasting 2022 Best Paper Award for their paper, “SIMLR: Machine Learning inside the SIR Model for Covid-19 forecasting”. The award was announced on December 31, 2023.

As demonstrated throughout the COVID-19 pandemic, accurate forecasting of newly infected people during an epidemic is critical for making effective, timely decisions. Their paper explores using a SIMLR model to help make more accurate forecasts by incorporating machine learning into the epidemiological SIR model.

For each region, SIMLR tracks the changes in the policies implemented at the government level, which it uses to estimate the time-varying parameters of a SIR model to forecast the number of new infections one to four weeks in advance. It also forecasts the probability of changes in those government policies at each of these future times, which is essential for longer-range forecasts.

The team applied SIMLR to data from Canada and the United States. It showed that its mean average percentage error is as good as state-of-the-art forecasting models, with the added advantage of being an interpretable model. They expect that this approach will be useful for forecasting COVID-19 infections and predicting the evolution of other infectious diseases.

The paper was a part of Vega’s PhD dissertation while he was studying under Greiner. He has since completed his PhD in November 2022. Vega is currently based in Edmonton and works at Exo at the intersection of machine learning and ultrasound imaging.

Forecasting (ISSN 2571-9394) is an international peer-reviewed, open-access journal, which provides theoretical, practical, computational, and methodological studies related to forecasting. All papers published in Forecasting from January 1 2022 to December 2022 were considered for the award.