Impact of Nature Events on human population in the USA between 1950-2011

Synopsis

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.Preventing such outcomes to the extent possible is a key concern. This analysis tries to provide an answer on the following questions:

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 across the United States?

Data processing

Set glopbal knitr parameters for further processing.

knitr::opts_chunk$set(echo = TRUE)

Read data

This section will load the relevant dataset if not already loaded.

url <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
projectDataBz2 <- "./stormData.bz2"
if(!file.exists(projectDataBz2)) {
    download.file(url, projectDataBz2)
}

if (!exists("projectData")) {
    projectData <- read.csv(bzfile(projectDataBz2), header = TRUE)
}

names(projectData)

##  [1] "STATE__"    "BGN_DATE"   "BGN_TIME"   "TIME_ZONE"  "COUNTY"    
##  [6] "COUNTYNAME" "STATE"      "EVTYPE"     "BGN_RANGE"  "BGN_AZI"   
## [11] "BGN_LOCATI" "END_DATE"   "END_TIME"   "COUNTY_END" "COUNTYENDN"
## [16] "END_RANGE"  "END_AZI"    "END_LOCATI" "LENGTH"     "WIDTH"     
## [21] "F"          "MAG"        "FATALITIES" "INJURIES"   "PROPDMG"   
## [26] "PROPDMGEXP" "CROPDMG"    "CROPDMGEXP" "WFO"        "STATEOFFIC"
## [31] "ZONENAMES"  "LATITUDE"   "LONGITUDE"  "LATITUDE_E" "LONGITUDE_"
## [36] "REMARKS"    "REFNUM"

rows <- nrow(projectData)
observedAttrs <- ncol(projectData)

The file contains 902297 observations and 37 observed attributes.

Process data

This are the relevant columns to process:

EVTYPE the event type to report on (e.g. tornado, flood, etc.)
FATALITIES as a measure of harm to human health
INJURIES as a measure of harm to human health
PROPDMG as a measure of property damage and hence economic damage in USD
PROPDMGEXP as a measure of magnitude of property damage (e.g. thousands, millions USD, etc.)
CROPDMG as a measure of crop damage and hence economic damage in USD
CROPDMGEXP as a measure of magnitude of crop damage (e.g. thousands, millions USD, etc.)

Calculate Human impact

Caluculate events with top 10 of Human impact for Fatalities and Injuries

agrfatalities<-aggregate(FATALITIES~EVTYPE, data = projectData, "sum")
fatalities<-agrfatalities[order(-agrfatalities$FATALITIES), ][1:10, ]
fatalities

##             EVTYPE FATALITIES
## 834        TORNADO       5633
## 130 EXCESSIVE HEAT       1903
## 153    FLASH FLOOD        978
## 275           HEAT        937
## 464      LIGHTNING        816
## 856      TSTM WIND        504
## 170          FLOOD        470
## 585    RIP CURRENT        368
## 359      HIGH WIND        248
## 19       AVALANCHE        224

agrinjuries<-aggregate(INJURIES~EVTYPE, data = projectData, "sum")
injuries<-agrinjuries[order(-agrinjuries$INJURIES), ][1:10, ]
injuries

##                EVTYPE INJURIES
## 834           TORNADO    91346
## 856         TSTM WIND     6957
## 170             FLOOD     6789
## 130    EXCESSIVE HEAT     6525
## 464         LIGHTNING     5230
## 275              HEAT     2100
## 427         ICE STORM     1975
## 153       FLASH FLOOD     1777
## 760 THUNDERSTORM WIND     1488
## 244              HAIL     1361

Calculate economic damage

PROPDMGEXP and CROPDMGEXP must be transformed to a numeric factor to multiply with PROPDMG to get the total impact value to work with.

projectData$PROPDMGEXP <- as.character(projectData$PROPDMGEXP)
projectData$PROPDMGEXP = gsub("\\-|\\+|\\?","0",projectData$PROPDMGEXP)
projectData$PROPDMGEXP = gsub("B|b", "9", projectData$PROPDMGEXP)
projectData$PROPDMGEXP = gsub("M|m", "6", projectData$PROPDMGEXP)
projectData$PROPDMGEXP = gsub("K|k", "3", projectData$PROPDMGEXP)
projectData$PROPDMGEXP = gsub("H|h", "2", projectData$PROPDMGEXP)
projectData$PROPDMGEXP <- as.numeric(projectData$PROPDMGEXP)
projectData$PROPDMGEXP[is.na(projectData$PROPDMGEXP)] = 0
projectData$ActPropDamage<- projectData$PROPDMG * 10^projectData$PROPDMGEXP
propDamage <- aggregate(ActPropDamage~EVTYPE, data=projectData, sum)
propDamage_reorder<- propDamage[order(-propDamage$ActPropDamage),]
PropDamage10<-propDamage_reorder[1:10,]
PropDamage10$ActPropDamage <- PropDamage10$ActPropDamage / 10^9
PropDamage10

##                EVTYPE ActPropDamage
## 170             FLOOD    144.657710
## 411 HURRICANE/TYPHOON     69.305840
## 834           TORNADO     56.947381
## 670       STORM SURGE     43.323536
## 153       FLASH FLOOD     16.822674
## 244              HAIL     15.735268
## 402         HURRICANE     11.868319
## 848    TROPICAL STORM      7.703891
## 972      WINTER STORM      6.688497
## 359         HIGH WIND      5.270046

projectData$CROPDMGEXP <- as.character(projectData$CROPDMGEXP)
projectData$CROPDMGEXP = gsub("\\-|\\+|\\?","0",projectData$CROPDMGEXP)
projectData$CROPDMGEXP = gsub("B|b", "9", projectData$CROPDMGEXP)
projectData$CROPDMGEXP = gsub("M|m", "6", projectData$CROPDMGEXP)
projectData$CROPDMGEXP = gsub("K|k", "3", projectData$CROPDMGEXP)
projectData$CROPDMGEXP = gsub("H|h", "2", projectData$CROPDMGEXP)
projectData$CROPDMGEXP <- as.numeric(projectData$CROPDMGEXP)
projectData$CROPDMGEXP[is.na(projectData$CROPDMGEXP)] = 0
projectData$ActCropDamage<- projectData$CROPDMG * 10^projectData$CROPDMGEXP
cropDamage <- aggregate(ActCropDamage~EVTYPE, data=projectData, sum)
cropDamage_reorder<- cropDamage[order(-cropDamage$ActCropDamage),]
CropDamage10<-cropDamage_reorder[1:10,]
CropDamage10$ActCropDamage <- CropDamage10$ActCropDamage / 10^9
CropDamage10

##                EVTYPE ActCropDamage
## 95            DROUGHT     13.972566
## 170             FLOOD      5.661968
## 590       RIVER FLOOD      5.029459
## 427         ICE STORM      5.022113
## 244              HAIL      3.025954
## 402         HURRICANE      2.741910
## 411 HURRICANE/TYPHOON      2.607873
## 153       FLASH FLOOD      1.421317
## 140      EXTREME COLD      1.292973
## 212      FROST/FREEZE      1.094086

totalDamage <- aggregate(ActPropDamage + ActCropDamage~EVTYPE, data=projectData, sum)
names(totalDamage)[2] <- "total"
totalDamage_reorder<- totalDamage[order(-totalDamage$total),]
totalDamage10 <- totalDamage_reorder[1:10,]
totalDamage10$total <- totalDamage10$total/10^9 
totalDamage10

##                EVTYPE      total
## 170             FLOOD 150.319678
## 411 HURRICANE/TYPHOON  71.913713
## 834           TORNADO  57.362334
## 670       STORM SURGE  43.323541
## 244              HAIL  18.761222
## 153       FLASH FLOOD  18.243991
## 95            DROUGHT  15.018672
## 402         HURRICANE  14.610229
## 590       RIVER FLOOD  10.148404
## 427         ICE STORM   8.967041

Results

In this section we show the impact of the top 10 events on human and on econonomic damage.

require(gridExtra)

## Loading required package: gridExtra

require(ggplot2)

## Loading required package: ggplot2

Show Human Impact of events

Plot the top 10 of human impact caused by event types for fatalities and injuries.

p1 <- ggplot(injuries,aes(x=reorder(EVTYPE, -INJURIES), y = INJURIES), xlim= 10, ylim=max(INJURIES)) + geom_bar(stat="identity",fill="darkred", colour="black") + theme(axis.text.x = element_text(angle=60, hjust=1))+ ylab("Number of Injuries")+ xlab("Kind of event")

p2 <- ggplot(fatalities,aes(x=reorder(EVTYPE, -FATALITIES), y = FATALITIES), xlim= 10, ylim=max(FATALITIES)) + geom_bar(stat="identity",fill="maroon4", colour="black") + theme(axis.text.x = element_text(angle=60, hjust=1))+ ylab("Number of Fatalities")+ xlab("Kind of event")

grid.arrange(p1, p2, top = "Human impact caused by Event Types", ncol=2)

Show economic impact

Plot top 10 of economic impact for Properties, Crop and Totals in Billions of USD

p1 <- ggplot(PropDamage10,aes(x=reorder(EVTYPE, -ActPropDamage), y = ActPropDamage), xlim= 10, ylim=max(ActPropDamage)) + geom_bar(stat="identity",fill="darkred", colour="black") + theme(axis.text.x = element_text(angle=60, hjust=1))+ ylab("Economic Impact on properties")+ xlab("Event Type")

p2 <- ggplot(CropDamage10,aes(x=reorder(EVTYPE, -ActCropDamage), y = ActCropDamage), xlim= 10, ylim=max(ActCropDamage)) + geom_bar(stat="identity",fill="chartreuse4", colour="black") + theme(axis.text.x = element_text(angle=60, hjust=1))+ ylab("Economic Impact on crop")+ xlab("Event Type")

p3 <- ggplot(totalDamage10,aes(x=reorder(EVTYPE, -total), y = total), xlim= 10, ylim=max(total)) + geom_bar(stat="identity",fill="maroon4", colour="black") + theme(axis.text.x = element_text(angle=60, hjust=1))+ ylab("Sum of Economic Impact")+ xlab("Event Type")

grid.arrange(p1, p2, p3, top = "Economic impact caused by Event Types in Billion USD", ncol=3)

Summary

From these plots we can conclude, across the United States:

Tornado’s have the biggest impact on fatalities and injuries
Flood has the biggest economic impact for properties
Drought has the most economic impect for crop
Flood has the biggest economic impact for properties and crop together.

usaStormDatabase

Peter Geers

24 november 2016