Date/time/location
- Date: Wednesday 01 December 2021
- Time: 09.00-13.00 Eastern Time, 14.00-18.00 (London)
- Location: Virtual/Zoom
Register for free
You need to register to receive the Zoom link and attend the workshop by Friday 26 November 2021.
Instructors
School of Computational Science and Engineering, College of Computing, Georgia Institute of Technology
Who is the training for?
Anyone who is interested in epidemic forecasting research and practice, from recent machine learning innovations to real-time forecasting challenges;
A decision maker who wants to learn how forecasts are used in decision making and the tradeoffs of modeling approaches;
An academic or graduate student that wants to expand their understanding of the state of the art;
An epidemiologist who wants to complement their knowledge with a data-driven perspective;
What participants will learn in the training?
Participants will be able to:
Identify modeling approaches and their use in practice. Distinguish a diverse set of challenges in real-time forecasting;
Recognize research directions;
Leverage software for modeling, data acquisition and processing, and evaluation;
Prerequisites
Basic knowledge of R or a high-level programming language.
Basic knowledge of statistics and statistical modeling
Outline (4hrs):
Epidemic forecasting (0.5 hr)
- Targets of interest
- Datasets
- Evaluation
Mechanistic models (1 hrs)
- Introduce basic concepts
- Mass-action models (Coding example with R)
- Metapopulation
- Agent-based models
Statistical models (1.5 hrs)
- Google Flu Trends
- ARIMA (Code example with R)
- Density estimation
- Deep learning (Coding example with R, compare with ARIMA)
- State of the art research
- Demos
Hybrid models (0.5 hrs)
- Discrepancy modeling
- Ensembles (COVID Forecast ensemble)
Epidemic forecasting on the ground (0.5 hrs)
- Real time experiences
- CDC initiatives
- Decision making
Join Forecasting for Social Good email list to stay informed about upcoming events