School testing for SARS-CoV-2 infection has been an important policy and planning issue during the COVID-19 pandemic. Decisions to test or not to test and, if testing, how many tests, how often and for how long, are complex decisions that need to be taken under uncertainty and conflicting pressures from various stakeholders. To better understand the effectiveness of testing in the school settings we developed an agent-based model incorporating a modified SEIR model with testing and spatial-temporal location of students. The simulation tool that can be used to analyze the outcomes and effectiveness of different testing strategies and scenarios with various numbers of classrooms and class sizes. Subsequently we used the agent-based simulation to develop an artificial intelligence model by running it for approximately 125,000 times. The AI tool/application can be used to evaluate various school testing strategies under different input values much faster and independent of the simulation tool. This presentation describes the simulation and AI tools and some of its sample results based on parameters setting for Ontario.

Bio: Ali Asgary is an associate professor of Disaster & Emergency MAnagement in the School of Administrative Studies at York University. He is also the associate director of the Advanced Disaster, Emergency and Rapid-response Simulation (ADERSIM). He is currently involved in a number of research projects related to the COVID-19 modelling using agent-based, artificial intelligence and virtual and augmented reality simulations.

Additional Information: School Testing Public Cloud Version (https://cloud.anylogic.com/model/a7c4411e-064e-4283-a93c-b0b27e0430ee?mo...) Preprint: Simulating Preventative Testing of SARS-CoV-2 in Schools: Policy Implications https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3699573

ADERSIM (adersim.info.yorku.ca)