A High-Resolution Global-Scale Model for COVID-19 Infection Rate

This dataset contains all information to reproduce our experiment to produce a high-resolution global map (0.1°) of infection-rate risk for COVID-19, based on temperature, precipitation, and CO2.

The produced risk index map predicts most of the areas with an actual high risk (87% accuracy), which are characterized by a moderate-high level of CO2, moderate-low temperatures, and a moderate level of precipitation. With respect to our previous model (https://zenodo.org/record/3945495#.YG7UEugzaUk)  - which had a coarser 0.5° resolution - this new model is much more accurate at predicting real-world scenarios that reported both high and low infection rates in 2020 (80% accuracy). 

Explanation of data and images:

comparisonvert.png    -> Visualisation of the output produced by our model: (a) distribution of high-infection-rate areas using the MaxEnt balanced threshold (0.008), (b) probability peak areas (0.13 threshold), (c) overlap between low infection rate countries extracted from real data and our risk map, and (d) highlight of low infection rate countries not predicted by our model
countries_high_rate.csv-> high-infection-rate countries
countries_low_rate.csv-> low-infection-rate countries
countries_low_rate_mispredicted.csv-> low-infection-rate countries mispredicted by our model
covid_derivatives.csv->    extracted average derivatives of world countries

covid_risk.csv->Risk Map dataset
gp.asc-> MaxEnt distribution raster
LowDerivativeRegions.png->low-infection-rate countries - image
MaxEnt distribution.png->distribution of high-infection-rate areas using the MaxEnt balanced threshold (0.008) - image
MaxEnt peaks.png-> MaxEnt probability peak areas (0.13 threshold)
Precipitation.png->Average precipitation 2000-2005
RiskMap.png-> New high-infection-rate risk map based on a 0.1° resolution MaxEnt model
RiskMap05.png->our previous risk map based on a 0.5° resolution MaxEnt model
riskmapcomparison.png->    Visual comparison between (a) our new high-infection-rate risk map based on a 0.1° resolution MaxEnt model and (b) our previous risk map based on a 0.5° resolution MaxEnt model.
RiskMapOverlap_mispredicted.png->highlight of low infection rate countries not predicted by our model
Temperature.png->Average Surface Air Temperature 2000-2005
time_series_covid19_confirmed_global.csv->World COVID-19 reports up to April 2021