Weather-inspired ensemble-based probabilistic prediction of COVID-19

Abstract

The objective of this work is to predict the spread of COVID-19 starting from observed data, using a forecast method inspired by probabilistic weather prediction systems operational today. Results show that this method works well for China: on day 25 we could have predicted well the outcome for the next 35 days. The same method has been applied to Italy and South Korea, and forecasts for the forthcoming weeks are included in this work. For Italy, forecasts based on data collected up to today (24 March) indicate that number of observed cases could grow from the current value of 69,176, to between 101k-180k, with a 50% probability of being between 110k-135k. For South Korea, it suggests that the number of observed cases could grow from the current value of 9,018 (as of the 23rd of March), to values between 8,500 and 9,300, with a 50% probability of being between 8,700 and 8,900. We conclude by suggesting that probabilistic disease prediction systems are possible and could be developed following key ideas and methods from weather forecasting. Having access to skilful daily updated forecasts could help taking better informed decisions on how to manage the spread of diseases such as COVID-19.