Conference proceeding
DeepCOVID: An Operational Deep Learning -driven Framework for Explainable Real-time COVID-19 Forecasting
THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, Vol.35(17), pp.15393-15400
AAAI Conference on Artificial Intelligence
05/18/2021
DOI: 10.1609/aaai.v35i17.17808
Abstract
How do we forecast an emerging pandemic in real time in a purely data-driven manner? How to leverage rich heterogeneous data based on various signals such as mobility, testing, and/or disease exposure for forecasting? How to handle noisy data and generate uncertainties in the forecast? In this paper, we present DEEPCOVID, an operational deep learning framework designed for real-time COVID-19 forecasting. DEEPCOVID works well with sparse data and can handle noisy heterogeneous data signals by propagating the uncertainty from the data in a principled manner resulting in meaningful uncertainties in the forecast. The deployed framework also consists of modules for both real-time and retrospective exploratory analysis to enable interpretation of the forecasts. Results from real-time predictions (featured on the CDC website and FiveThirtyEight.com) since April 2020 indicates that our approach is competitive among the methods in the COVID-19 Forecast Hub, especially for short-term predictions.
Details
- Title: Subtitle
- DeepCOVID: An Operational Deep Learning -driven Framework for Explainable Real-time COVID-19 Forecasting
- Creators
- Alexander Rodriguez - Georgia Institute of TechnologyAnika Tabassum - Virginia TechJiaming Cui - Georgia Institute of TechnologyJiajia Xie - Georgia Institute of TechnologyJaven Ho - Georgia Institute of TechnologyPulak Agarwal - Georgia Institute of TechnologyBijaya Adhikari - University of IowaB. Aditya Prakash - Georgia Institute of Technology
- Resource Type
- Conference proceeding
- Publication Details
- THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, Vol.35(17), pp.15393-15400
- Publisher
- Assoc Advancement Artificial Intelligence
- Series
- AAAI Conference on Artificial Intelligence
- DOI
- 10.1609/aaai.v35i17.17808
- ISSN
- 2159-5399
- eISSN
- 2374-3468
- Number of pages
- 8
- Grant note
- U01CK000531 / CDC MInD-Healthcare; United States Department of Health & Human Services; Centers for Disease Control & Prevention - USA Georgia Tech CCF-1918770; CAREER IIS-2028586; RAPID IIS-2027862; IIS-1955883; NRT DGE-1545362 / NSF; National Science Foundation (NSF) GTRI ORNL CDC MInD program
- Language
- English
- Date published
- 05/18/2021
- Academic Unit
- Computer Science
- Record Identifier
- 9984411060702771
Metrics
1 Record Views