TORNADO Most Harmful to Population Health and FLOOD Causing Greatest Economic Consequences

Synopsis

Storms and other severe weather events can influence both population health and economic problems for communities and municipalities,resulting in fatalities,injuries and property damage.This project explores the U.S. NOAA storm database.The events recorded in this database start in the year 1950 and end in 2011.Analysis of the dataset tells that TORNADO is the most harmful severe weather event to population health and FLOOD causes greatest economic consequences.

Data Processing

Raw data were loaded into R.

setwd("C:\\Users\\lenovo\\Desktop")
stormdata <- read.csv(bzfile("repdata-data-StormData.csv.bz2"))

Population health includes two parts:fatalities and injuries. Calculating total population (sum of fatalities and injuries) in each type of severe weather events can tell the most harmful one.

stormdata$Population <- stormdata$FATALITIES + stormdata$INJURIES
Population <- aggregate(stormdata$Population, by = list(stormdata$EVTYPE), sum)
colnames(Population) <- c("EVTYPE", "population")

poporder <- order(Population$population, decreasing = TRUE)[1:10]
pop <- Population[poporder, ]

barplot(pop[, 2], main = "Figure 1: Top 10 Events Harmful to Population Health", 
    ylab = "FATALITIES  and  INJURIES")
text(seq(0.7, 12, by = 1.2), y = -7000, labels = pop[, 1], srt = 45, pos = 1, 
    xpd = TRUE, cex = 0.7)

plot of chunk unnamed-chunk-2

Figure 1 shows top 10 types of severe weather events most harmful with respect to population health and TORNADO is the most harmful one far more than the rest.

Economic factets include property and crop damage. Calculating total economic loss in each type of severe weather events can tell the most harmful one.

econ <- stormdata[, c(8, 25:28)]
econ1 <- econ[econ$PROPDMG != 0 | econ$CROPDMG != 0, ]

levels(econ1$PROPDMGEXP) <- list(`0` = c("", "-", "?", "+"), `1` = "0", `10` = "1", 
    `100` = c("2", "H", "h"), `1000` = c("3", "K"), `10000` = "4", `100000` = "5", 
    `1000000` = c("6", "m", "M"), `10000000` = "7", `100000000` = "8", `1000000000` = "B")
econ1$PROPDMGEXP <- as.numeric(as.character(econ1$PROPDMGEXP))

levels(econ1$CROPDMGEXP) <- list(`0` = c("", "?"), `1` = "0", `100` = "2", `1000` = c("k", 
    "K"), `1000000` = c("m", "M"), `1000000000` = "B")
econ1$CROPDMGEXP <- as.numeric(as.character(econ1$CROPDMGEXP))

econ1$economic <- econ1$PROPDMG * econ1$PROPDMGEXP + econ1$CROPDMG * econ1$CROPDMGEXP
econdmg <- aggregate(econ1$economic, by = list(econ1$EVTYPE), sum)
colnames(econdmg) <- c("EVTYPE", "economic")

econorder <- order(econdmg$economic, decreasing = TRUE)[1:10]
edmg <- econdmg[econorder, ]

barplot(edmg$economic/(1e+09), main = "Figure 2:Top 10 Events Harmful to Economics", 
    ylab = "Economic Damage (Billion Dollar)")
text(seq(0.7, 12, by = 1.2), y = -10, labels = edmg$EVTYPE, srt = 45, pos = 1, 
    xpd = TRUE, cex = 0.7)

plot of chunk unnamed-chunk-3

Figure 2 shows top 10 types of events have the greatest economic consequences and FLOOD is the most harmful one leading to economic loss.

Results

Figure 1 shows top 10 types of severe weather events most harmful with respect to population health and TORNADO is the most harmful one far more than the rest.Figure 2 shows top 10 types of events have the greatest economic consequences and FLOOD is the most harmful one leading to economic loss.Preventing huge loss and damage is a key concern.