Git Product home page Git Product logo

covid19-natural-disasters's Introduction

COVID19-Natural-Disasters


Executive Summary

Fires can occur for many reasons. Some are caused naturally (think lighting striking a tree) and others are man-made (accidental or intentional). The year of 2020 has been unprecedented in the amount of destruction caused by fires across the country, all spurred by heat waves in some place, tropical storms in others, and even debris burning (Source 1; Source 2). It is important to note that not all fires are bad, some ecosystems depend on them and people use it in agriculture. Although not all fires that occur are detrimental, there are really important reasons why we should be actively tracking them. It helps us locate volcanoes, gas flares and the sources of air pollution caused by smoke (Source).

The Coronavirus pandemic has plagued the world in the year 2020, and has been particularly deadly in the United States where, at the time this project was completed, total confirmed cases have just passed 9 Million, while deaths are at about 230,000. We began our exploratory data analysis by graphing cumulative confirmed for each state and comparing them to eachother, we then chose the top three states with the most total confirmed cases and mapped the top 10 counties in each state to observe the severity of infection rates at more granular level.

We then combined the information we had on the spread of the virus with the information we had about fires and heat anomalies to create an interactive map. The heatmap layer shows precise geographical locations of fires and heat anomalies in the United States from February to October 2020, and an additional chloropleth layer illustrates daily confirmed cases in each State for the same range of dates.


Problem Statement

Can we create a web-based application that maps fires/heat anomalies as well as COVID-19 infection rates in the US? Is it possible to showcase a relationship between fire occurrences and COVID-19 infection rates?


Hypothesis

We hypothesized that people would be more likely to stay at home/indoors in areas with fires, thereby decreasing the likelihood of contracting COVID-19.


Contents:

Data

The heat anomaly data set was provided by LANCE FIRMS operated by NASA ESDIS with funding provided by NASA Headquarters and can be found here

  • Covered the dates of 1/1/2020 โ€“ 10/23/2020
  • 41,709 fire occurrences for the continental US (including the District of Columbia), Alaska and Hawaii

COVID-19 statewide incidence numbers inputted into folium can be found here

COVID-19 data used in EDA graphs can be found here

Data Dictionaries


NASA FIRMS MODIS (Fire) Data Dictionary

Feature Type Description
latitude numeric latitude
longitude numeric longitude
brightness numeric channel 21/22 brightness temperature of the fire pixel ( in Kelvin)
scan numeric along scan pixel size
track numeric along scan pixel size
acq_date date date of MODIS acquisition
acq_time numeric time of /overpass of the satellite (in UTC)
satellite categorical Aqua vs. Terra satellite
instrument categorical Imaging instrument
confidence numeric score representing how confident the software is that a fire is present in the location
version categorical collection and source
bright_t31 numeric channel 31 brightness temp of the fire pixel (in Kelvin)
frp numeric fire radiative power (in megawatts)
daynight categorical D = daytime fire, N = nighttime fire
type categorical inferred hot spot type

COVIDcast Statewide Incidence Data Dictionary

Feature Type Description
geo_value string state
signal string name of signal derived from upstream data
time_value string month, day, year
issue list of time values time unit when the signal data were published
lag integer time between when the underlying events happened and when the data were published
geo_type string spacial resolution of the signal(e.g. state
data_source string name of upstream data source

Conclusions/ Recommendations

After looking at our map of COVID-19 data on top of the fire data, we can see that there is a relationship. If we had more time on this project, we would look further into specific counties and look at exact correlations. If we had more time on this project, we would also try to automate the map to ensure the data is current to the date that the person is looking at it. Because of the spike in COVID cases in California on June 28 after the large amount of fires in California on June 14, we believe there is some sort of relationship. Originally, we hypothesized that there would be no relationship because people would be staying inside because of the fires. However, we were wrong. We think this might be because of poorly executed evacuation plans in regards to the wildfires. Our recommendation for the future is that next time there is a pandemic, there should be more strict regulations, especially in counties that are prone to experiencing natural disasters.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.