# Deep diffusion-based forecasting of COVID-19 by incorporating network-level mobility information

arXiv: https://arxiv.org/abs/2111.05199 · HTML: https://mlsanity.com/paper/2111.05199/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 9 Nov 2021.

## Builds on (most cited first, 8 of 8)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks](https://mlsanity.com/paper/2007.03113/) (2020)
- [Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting](https://mlsanity.com/paper/1707.01926/) (2017)
- [Mobility Based SIR Model For Pandemics -- With Case Study Of COVID-19](https://mlsanity.com/paper/2004.13015/) (2020)
- [Better call Surrogates: A hybrid Evolutionary Algorithm for Hyperparameter optimization](https://mlsanity.com/paper/2012.06453/) (2020)
- [Forecasting Across Time Series Databases using Recurrent Neural Networks on Groups of Similar Series: A Clustering Approach](https://mlsanity.com/paper/1710.03222/) (2017)
- [Prediction of COVID-19 Disease Progression in India : Under the Effect of National Lockdown](https://mlsanity.com/paper/2004.03147/) (2020)

## Built on by (most cited first, 2 of 2)

- [EINNs: Epidemiologically-informed Neural Networks](https://mlsanity.com/paper/2202.10446/) (2022)
- [Data-Centric Epidemic Forecasting: A Survey](https://mlsanity.com/paper/2207.09370/) (2022)

## Abstract (arXiv)

Modeling the spatiotemporal nature of the spread of infectious diseases can provide useful intuition in understanding the time-varying aspect of the disease spread and the underlying complex spatial dependency observed in people's mobility patterns. Besides, the county level multiple related time series information can be leveraged to make a forecast on an individual time series. Adding to this challenge is the fact that real-time data often deviates from the unimodal Gaussian distribution assumption and may show some complex mixed patterns. Motivated by this, we develop a deep learning-based time-series model for probabilistic forecasting called Auto-regressive Mixed Density Dynamic Diffusion Network(ARM3Dnet), which considers both people's mobility and disease spread as a diffusion process on a dynamic directed graph. The Gaussian Mixture Model layer is implemented to consider the multimodal nature of the real-time data while learning from multiple related time series. We show that our model, when trained with the best combination of dynamic covariate features and mixture components, can outperform both traditional statistical and deep learning models in forecasting the number of Covid-19 deaths and cases at the county level in the United States.