Forecasting COVID-19 spreading through an ensemble of classical and machine learning models: Spain's case study

In this work the applicability of an ensemble of population and machine learning models to predict the evolution of the COVID-19 pandemic in Spain is evaluated, relying solely on public datasets. Firstly, using only incidence data, we trained machine learning models and adjusted classical ODE-based population models, especially suited to capture long term trends. As a novel approach, we then made an ensemble of these two families of models in order to obtain a more robust and accurate prediction. We then proceed to improve machine learning models by adding more input features: vaccination, human mobility and weather conditions. However, these improvements did not translate to the overall ensemble, as the different model families had also different prediction patterns. Additionally, machine learning models degraded when new COVID variants appeared after training. We finally used Shapley Additive Explanation values to discern the relative importance of the different input features for the machine learning models' predictions. The conclusion of this work is that the ensemble of machine learning models and population models can be a promising alternative to SEIR-like compartmental models, especially given that the former do not need data from recovered patients, which are hard to collect and generally unavailable.

Automated summary

This study evaluated the use of an ensemble of population and machine learning models to predict the COVID-19 pandemic in Spain using only public datasets. Machine learning models were trained using incidence data and classical ODE-based population models were adjusted to capture long term trends. A novel approach was used by combining these models to improve robustness and accuracy. However, adding more input features did not improve the overall ensemble due to different prediction patterns among model families. Machine learning models also degraded with the emergence of new COVID variants. The study concluded that the ensemble of machine learning and population models shows promise as an alternative to SEIR-like compartmental models.