Predicting the spread of COVID-19 in Delhi, India using Deep Residual Recurrent Neural Networks
This work addresses the need for real-time decision-making in pandemic management, though it appears incremental as it builds on existing SEIRD models with neural network enhancements.
The paper tackled the problem of slow and inaccurate COVID-19 spread prediction in Delhi, India by using Deep Residual Recurrent Neural Networks (DRRNNs) with Partial Differential Equations, resulting in accurate predictions as measured by Mean Squared Error.
Detecting the spread of coronavirus will go a long way toward reducing human and economic loss. Unfortunately, existing Epidemiological models used for COVID 19 prediction models are too slow and fail to capture the COVID-19 development in detail. This research uses Partial Differential Equations to improve the processing speed and accuracy of forecasting of COVID 19 governed by SEIRD model equations. The dynamics of COVID 19 were extracted using Convolutional Neural Networks and Deep Residual Recurrent Neural Networks from data simulated using PDEs. The DRRNNs accuracy is measured using Mean Squared Error. The DRRNNs COVID-19 prediction model has been shown to have accurate COVID-19 predictions. In addition, we concluded that DR-RNNs can significantly advance the ability to support decision-making in real time COVID-19 prediction.