Multi-scale CyberGIS Analytics for Detecting Spatiotemporal Patterns of COVID-19

  • Fangzheng Lyu (Creator)
  • Jeon Young Kang (Creator)
  • Shaohua Wang (Creator)
  • Su Han (Creator)
  • Zhiyu Li (Creator)
  • Shaowen Wang (Creator)
  • Anand Padmanabhan (Creator)

Dataset

Description

This dataset contains all the code, notebooks, datasets used in the study conducted for the research publication titled "Multi-scale CyberGIS Analytics for Detecting Spatiotemporal Patterns of COVID-19 Data". Specifically, this package include the artifacts used to conduct spatial-temporal analysis with space time kernel density estimation (STKDE) using COVID-19 data, which should help readers to reproduce some of the analysis and learn about the methods that were conducted in the associated book chapter.

## What’s inside - A quick explanation of the components of the zip file
* Multi-scale CyberGIS Analytics for Detecting Spatiotemporal Patterns of COVID-19.ipynb is a jupyter notebook for this project. It contains codes for preprocessing, space time kernel density estimation, postprocessing, and visualization.
* data is a folder containing all data needed for the notebook
* data/county.txt: US counties information and fip code from Natural Resources Conservation Service.
* data/us-counties.txt: County-level COVID-19 data collected from New York Times COVID-19 github repository on August 9th, 2020.
* data/covid_death.txt: COVID-19 death information derived after preprocessing step, preparing the input data for STKDE. Each record is if the following format (fips, spatial_x, spatial_y, date, number of death ).
* data/stkdefinal.txt: result obtained by conducting STKDE.
* wolfram_mathmatica is a folder for 3D visulization code.
* wolfram_mathmatica/Visualization.nb: code for visulization of STKDE result via weolfram mathmatica.
* img is a folder for figures.
* img/above.png: result of 3-D visulization result, above view.
* img/side.png: result of 3-D visulization, side view.
Date made availableApr 18 2021
PublisherUniversity of Illinois at Urbana-Champaign

Keywords

  • COVID-19
  • Spatiotemporal patterns
  • Space-time kernel density estimation
  • CyberGIS

Cite this