Modeling COVID-19 Case Counts with Long Short-Term Memory Networks

Student

Brandon Voigt

Advisor

Tracy Flood

Abstract

Accurate predictions of COVID-19 case counts can help medical professionals and community leaders determine the best way to respond to the pandemic. This project uses long short-term memory (LSTM) networks, which are a type of recurrent neural network, to predict new COVID-19 cases over a 14-day interval. The results are compared to those of several other time series forecasting methods. On average, the LSTM network predictions achieve lower error rates than these other methods.

Video

Modeling COVID-19 Case Counts with Long Short-Term Memory Networks