AI-based Intervention Recommendations
for COVID-19

This demo illustrates the non-pharmaceutical interventions (NPIs) that the AI generates for different countries and regions over time, and their predicted effect. You first select country/region from the map at right, and then select the degree to which you'd like to minimize the number of cases vs. minimize the stringency of NPIs from the slider on the left. Among the ~101240 possible NPI schedules for the next 180 days, the AI will then recommend one that implements that tradeoff with as few cases and NPIs as possible. The predicted number of cases and the recommended NPIs will be shown over time in the charts below. NEW: You can also go back in time with "counterfactuals", and edit recommendations with "Custom NPIs".

See Optimizing COVID-19 Interventions for the general context, in-depth paper for the technical details, and ESP Introduction for the Evolutionary AI technology and its other applications. See also the XPRIZE Pandemic Response Challenge (and its technical details) for a recent machine learning competition inspired by this demo.



What is going on?

Data-based Pandemic Modeling: The ESP system learned to make recommendations based on historical data, i.e. the publicly available COVID-19 data on number of cases and NPIs over time provided by Oxford University (Hale, Webster, Petherick, Phillips, Kira, 2020, Oxford COVID-19 Government Response Tracker, Blavatnik School of Government, Oxford University). As described in this detailed technical paper, ESP consists of two learning tasks: (1) learning to predict, and (2) using the predictor as a surrogate for the real world, learning to prescribe actions that lead to desirable outcomes.

Predictor was first trained with historical data. It is an LSTM recurrent neural network. Given the number of cases and NPIs in the past three weeks, its task is to predict the cases the next day. This prediction and any changes to NPIs are then fed back into the LSTM as input data to predict the next day, cascading predictions upto 180 days into the future.

Prescriptor neural networks were then created through population-based search, i.e. evolutionary optimization. Initially a population of random Prescriptor neural networks was created. During each generation, each network was evaluated in turn, based on how well their NPI recommendations fared in two dimensions: the number of cases, and the sum of NPI stringency levels, both averaged over the following 180 days and over the 20 countries with the most deaths. The Predictor model was used as a surrogate for the real world in this evaluation. As usual in evolution, those networks that performed well along one or both objectives were crossed over and mutated to form offspring networks, replacing those that performed poorly. The population thus discovered a Pareto front of tradeoffs between these two objectives (for an animation of this process, see Demo 2.2).

Running the demo: Twenty different Prescriptors from Demo 2.2 are used in this demo. The selected one is initialized with data for a selected country, and it recommends NPIs over time. The same initial sequence and the recommended NPIs are given to the Predictor, and it generates the plot of cases over time (you can zoom in with the mouse by dragging). Uncertainty in the predictions is estimated through RIO, a Gaussian process approach for estimating residuals (RIO). The gray area represents the upper and lower quartiles of the distribution for each day. It is formed by rolling out uncertainties stochastically day by day for 180 days, thus resulting in jagged boundaries.

Explore especially the intermediate prescriptors that try to balance the two objectives by combining and alternating various NPI recommendations. You can also go back in time and see what recommendations the AI would have made, and how such "counterfactual" NPIs would have affected the pandemic, compared to what actually happened. Through the "Custom NPI" interface, you can also change the NPIs manually, and thus explore alternatives to the AIs recommendations.

Tracking the changing pandemic: The data is updated almost daily, and the Predictors and Prescriptors trained with it. Note in particular that even though other data such as vaccination rates are not explicitly input to the models, the case histories in different countries reflect them implicitly, and the models thus adapt to them. Similarly, changes like the delta variant are not explicitly given to the models, but the rising case counts causes the models to take it into account. Thus the system is continuously adjusting to the changing face of the pandemic.