Forecasting of COVID-19 epidemic size in four high hitting nations (USA, Brazil, India and Russia) by Fb-Prophet machine learning model
Problem
Forecasting the 60-day trajectory of total COVID-19 infections in the USA, Brazil, India and Russia to support pandemic planning.
Why it matters
Epidemic size projections guide government preparedness and resource allocation during a deadly pandemic with no vaccine at the time.
What the AI did
Applied the Fb-Prophet machine learning model to daily national infection data to produce 60-day forecasts of total confirmed cases.
Results
Projected 7.56, 4.65, 3.01 and 1.22 million cases (USA, Brazil, India, Russia) by late September 2020
Impact
Provided short-term case projections for four heavily affected countries; forecast accuracy is not stated in source.
Record
| Venue | Applied Computing and Informatics |
|---|---|
| Published | 2020 |
| Work type | article |
| Authors | Gopi Battineni, Nalini Chintalapudi, Francesco Amenta |
| Citations | 57 (OpenAlex, at import time) |
| References | 18 |
| Model or method | Fb-Prophet (Prophet logistic growth model) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1108/aci-09-2020-0059 |
| Open access | diamond |
| Keywords | COVID-19, forecasting, Fb-Prophet, time series, epidemic modeling |
Importance rating
existential / global scale
Abstract cites a global pandemic with 17M+ cases and 671,500 deaths, no medicine or vaccine at the time; forecasting supports national preparedness in four heavily affected countries.