Geospatial forecasting of COVID-19 spread and risk of reaching hospital capacity

Abstract

Prompt surveillance and forecasting of COVID-19 spread are of critical importance for slowing down the pandemic and for the success of any public mitigation efforts. However, as with any infectious disease with rapid transmission and high virulence, lack of COVID-19 observations for near-real-time forecasting is still the key challenge obstructing operational disease prediction and control. In this context, we can follow the two approaches to forecasting COVID-19 dynamics: based on mechanistic models and based on machine learning. Mechanistic models are better in capturing an epidemiological curve, using a low amount of data, and describing the overall trajectory of the disease dynamics, hence, providing long-term insights into where the disease might go. Machine learning, in turn, can provide more precise data-driven forecasts especially in the short-term horizons, while suffering from limited interpretability and usually requiring backlog history on the infectious disease. We propose a unified reinforcement learning framework that combines the two approaches. That is, long-term trajectory forecasts are used in machine learning techniques to forecast local variability which is not captured by the mechanistic model.

An Integrated GIS-Based Reinforcement Learning Approach for Efficient Prediction of Disease Transmission in Aquaculture

“…The prediction of disease propagation within aquaculture systems stands as a central issue that directly affects the industry's economic and ecological viability. Historically, conventional models provided overarching insights into long-term disease patterns but operated under limited data scopes [81]. Alternatively, while machine learning techniques excel in generating detailed short-term forecasts, they require a comprehensive historical data set and often present challenges in model interpretability [82].…”

Deep learning for Covid-19 forecasting: State-of-the-art review.

“…Machine learning is also used in conjunction with other methods. The authors in [12] combine mechanistic and machine learning approaches in a unified reinforcement learning framework. The overall trajectory of the disease is estimated by the mechanistic model which in implemented in the machine learning model to forecast local variability.…”

Understanding COVID-19 Effects on Mobility: A Community-Engaged Approach

“…Beyond contact tracing applications, two popular disease dynamic transition models, namely SIR (susceptible, infectious, and recovered) and SEIR (susceptible, exposed, infected, and recovered,) have recently been adapted to benefit from spatiotemporal data to simulate the spread of COVID-19. Bobashev et al [3] proposed a unified framework to combine data-driven predictive modeling (i.e., reinforcement learning) with overall trajectories of disease dynamics from a mechanistic model (i.e., SEIR model) for forecasting COVID-19 spread. A variant of the SIR model, namely the time-dependent SIR model [7] models transmission rate as well as recovery rate at a given time t. This work also considers both how infected but asymptomatic individuals may contribute to the spread of COVID-19 disease.…”