Modeling projections for COVID-19 pandemic by combining epidemiological, statistical, and neural network approaches
Uhlig, S.; Nichani, K.; Uhlig, C.; Simon, K.
Show abstract
As the number of people affected by COVID-19 disease caused by the novel coronavirus SARS-CoV-2 ebbs and flows in different national and sub-national regions across the world, it is evident that our lifestyle and socio-economic trajectories will have to be adapted and adjusted to the changing scenarios. Novel forecasting tools and frameworks provide an arguable advantage to facilitate this adapting and adjusting process, by promoting efficient resource management at individual and institutional levels. Based on deterministic compartment models we propose an empirical top-down modeling approach to provide epidemic forecasts and risk calculations for (local) outbreaks. We use neural networks to develop leading indicators based on available data for different regions. These indicators are not only used to assess the risk of a (new) outbreak or to determine the effectiveness of a measure at an early stage, but also in parametric models to determine an effective forecast, along with the associated uncertainty. Based on initial results, we show the performance of such an approach and its robustness against inherent disturbances in epidemiological surveillance data. We foresee such a statistical framework to drive web-based automatic platforms to democratize the dissemination of prognosis results.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- On the use of growth models for forecasting epidemic outbreaks with application to COVID-19 data 96%
- Data Driven High Resolution Modeling and Spatial Analyses of the COVID-19 Pandemic in Germany 96%
- Tracking the Dynamics and Allocating Tests for COVID-19 in Real-Time: an Acceleration Index with an Application to French Age Groups and Départements * 95%
Similar papers in this journal
- Covid-19 Belgium: Extended SEIR-QD model with nursing homes and long-term scenarios-based forecasts 95%
- Foundation time series models for forecasting and policy evaluation in infectious disease epidemics 95%
- A prospective real-time transfer learning approach to estimate Influenza hospitalizations with limited data 94%
Similar papers in this journal
- Real-time Estimation of Disease Activity in Emerging Outbreaks using Internet Search Information 95%
- A mechanistic and data-driven reconstruction of the time-varying reproduction number: Application to the COVID-19 epidemic 95%
- An integrated framework for building trustworthy data-driven epidemiological models: Application to the COVID-19 outbreak in New York City 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.