Impacts of Severe Weather Events in the United States

Introduction

Storms and other severe weather events can cause both public health and economic problems for communities and municipalities. Many severe events can result in fatalities, injuries, and property damage, and preventing such outcomes to the extent possible is a key concern.

This project explored the U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database, which tracks characteristics of major storms and weather events in the United States, including estimates of any fatalities, injuries, and property damage over the period during the years 1950 - 2011. Exploration of the database sought to answer the following two questions about severe weather events across the United States of America:

• Across the United States, which types of events are most harmful with respect to population health?
• Across the United States, which types of events have the greatest economic consequences?

Synopsis

The CSV file containing the raw data was downloaded from the internet and loaded in R where:

• columns EVTYPE, FATALITIES, INJURIES, PROPDMG, PROPDMGEXP, CROPDMG, and CROPDMGEXP, deemed necessary to the assessment were retained and the other columns discarded;
• the EVTYPE variable, which indicates the types of events that are most harmful with respect to population health and economic consequences was converted to a factor variable to facilitate analysis and graphing;
• The PROPDMG and CROPDMG were converted to numeric vectors by substituting “K”, “M”, and “B” with 1,000, 1,000,000, 1,000,000,000 respectively since according to the documentation these were the approved categories; all other levels were of these variables were set to zero; and
• finally, plots of the top 10 weather events with total fatalities and injuries (Health Impacts) and total property and crop damage (Economic Costs) were made to answer the aforementioned questions.

Data Processing

library(dplyr)
library(ggplot2)
library(forcats)

# download data, if necessary
data_url <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
file_name <- "storm_data_csv.bz2"

if(!file.exists(file_name)){
        download.file(data_url, destfile = file_name, method = "curl")
}

# load data from disk
raw_data <- read.csv(file_name, header = TRUE)

# process data for analysis
cleaned_data <- raw_data %>%
        select(EVTYPE, FATALITIES, INJURIES, #
               PROPDMG, PROPDMGEXP, CROPDMG,
               CROPDMGEXP) %>%
        mutate(EVTYPE = as.factor(EVTYPE),
               PROPDMGEXP = case_when(PROPDMGEXP == "K" ~ 1e3,
                                      PROPDMGEXP == "M" ~ 1e6,
                                      PROPDMGEXP == "B" ~ 1e9,
                                      TRUE ~ 0
                                      ),
               CROPDMGEXP = case_when(CROPDMGEXP == "K" ~ 1e3,
                                      CROPDMGEXP == "M" ~ 1e6,
                                      CROPDMGEXP == "B" ~ 1e9,
                                      TRUE ~ 0
                                      )
               )

Results

# plot total causalities for top 10 weather event
cleaned_data %>%
        group_by(EVTYPE) %>%
        summarise(casualities = sum(FATALITIES + INJURIES, na.rm = TRUE)) %>%
        ungroup() %>%
        top_n(10) %>%
        ggplot(aes(x=casualities, y=fct_reorder(EVTYPE, casualities))) +
        geom_col() +
        labs(y = "Severe Weather Event",
             x = "Total Number of Direct or Indirect Casualities",
             title = "Top 10 Severe Weather Events with the Most Casualities in the United States from 1950 - 2011"
             ) +
        theme_classic() +
        theme(axis.title.x = element_text(size=11, face="bold", color = "black"),
              axis.title.y = element_text(size=11, face="bold", color = "black"),
              plot.title = element_text(size=12, face="bold", color = "black")
              )

Findings/Conclusion #1

Tornadoes were the severe weather events that resulted in the most causalities in the United States.

# plot economic damages for top 10 weather events
cleaned_data %>%
        group_by(EVTYPE) %>%
        summarise(econ_damage = sum((PROPDMG *PROPDMGEXP) + (CROPDMG * CROPDMGEXP), 
                                    na.rm = TRUE)) %>%
        ungroup() %>%
        top_n(10) %>%
        ggplot(aes(x=econ_damage, y=fct_reorder(EVTYPE, econ_damage))) +
        geom_col() +
        labs(y = "Severe Weather Event",
             x = "Total Economic Damage",
             title = "Top 10 Severe Weather Events with the Most Economic Damage from 1950 - 2011"
             ) +
        theme_classic() +
        theme(axis.title.x = element_text(size=11, face="bold", color = "black"),
              axis.title.y = element_text(size=11, face="bold", color = "black"),
              plot.title = element_text(size=12, face="bold", color = "black")
              )

Findings/Conclusion #2

Floods were the severe weather events that resulted in the most economic damage in the United States.