Health and Economic Impact of Storms and Severe Weather Events

Synopsis

The basic goal of this report is to explore the NOAA Storm Database (including events starting in the year 1950 and ending in November 2011) and answer some basic questions about the impact of severe weather events on public health and economy. Based on this data, we draw the conclusion that on average across the U.S., the most harmful on people's health (as measured by fatalities and injuries) event type is tornado. The most harmful on economy (as measured by property damage and crop damage) event type is also tornado.

Loading and Processing the Raw Data

The data come from NOAA Storm Database in the form of a comma-separated-value file compressed via the bzip2 algorithm: Storm Data [47Mb] The documentation of the database is located at

National Weather Service Storm Data Documentation
National Climatic Data Center Storm Events FAQ The events in the database start in the year 1950 and end in November 2011. In the earlier years of the database there are generally fewer events recorded, most likely due to a lack of good records. More recent years should be considered more complete.

Download, unzip and read raw data

library(bitops)
library(RCurl)
url <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
bin <- getBinaryURL(url, ssl.verifypeer = FALSE)
## download.file(url, 'repdata-data-StormData.csv.bz2', method='curl', mode =
## 'wb')
con <- file("repdata-data-StormData.csv.bz2", open = "wb")
writeBin(bin, con)
close(con)
library(R.utils)

## Loading required package: R.oo
## Loading required package: R.methodsS3
## R.methodsS3 v1.6.1 (2014-01-04) successfully loaded. See ?R.methodsS3 for help.
## R.oo v1.18.0 (2014-02-22) successfully loaded. See ?R.oo for help.
## 
## Attaching package: 'R.oo'
## 
## The following object is masked from 'package:RCurl':
## 
##     clone
## 
## The following objects are masked from 'package:methods':
## 
##     getClasses, getMethods
## 
## The following objects are masked from 'package:base':
## 
##     attach, detach, gc, load, save
## 
## R.utils v1.32.4 (2014-05-14) successfully loaded. See ?R.utils for help.
## 
## Attaching package: 'R.utils'
## 
## The following object is masked from 'package:RCurl':
## 
##     reset
## 
## The following object is masked from 'package:utils':
## 
##     timestamp
## 
## The following objects are masked from 'package:base':
## 
##     cat, commandArgs, getOption, inherits, isOpen, parse, warnings

bunzip2("repdata-data-StormData.csv.bz2", destname = "repdata-data-StormData.csv", 
    overwrite = FALSE, remove = TRUE, BFR.SIZE = 1e+07)
StormData <- read.csv("repdata-data-StormData.csv")

Data Aggregation (Health Impact per Event Type)

In order to answer the question which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health, we aggregate the sum of fatalities and injuries per event type, produce a summary and sort them in descending order.

library(data.table)
storm <- data.table(StormData)
HealthImpactPerEvent <- storm[, sum(FATALITIES) + sum(INJURIES), by = EVTYPE]
# names(HealthImpactPerEvent) <- c('event_type','health_impact')
setnames(HealthImpactPerEvent, "EVTYPE", "event_type")
setnames(HealthImpactPerEvent, "V1", "health_impact")
summary(HealthImpactPerEvent)

##                  event_type  health_impact  
##     HIGH SURF ADVISORY:  1   Min.   :    0  
##   COASTAL FLOOD       :  1   1st Qu.:    0  
##   FLASH FLOOD         :  1   Median :    0  
##   LIGHTNING           :  1   Mean   :  158  
##   TSTM WIND           :  1   3rd Qu.:    0  
##   TSTM WIND (G45)     :  1   Max.   :96979  
##  (Other)              :979

library(plyr)
TopHealthImpactPerEvent <- arrange(HealthImpactPerEvent, desc(health_impact))

Data Aggregation (Economy Impact per Event Type)

In order to answer the question which types of events have the greatest economic consequences (in dollar amount), we aggregate the sum of property and crop damage per event type, produce a summary and sort them in descending order.

EconomyImpactPerEvent <- storm[, sum(PROPDMG) + sum(CROPDMG), by = EVTYPE]
setnames(EconomyImpactPerEvent, "EVTYPE", "event_type")
setnames(EconomyImpactPerEvent, "V1", "economy_impact")
summary(EconomyImpactPerEvent)

##                  event_type  economy_impact   
##     HIGH SURF ADVISORY:  1   Min.   :      0  
##   COASTAL FLOOD       :  1   1st Qu.:      0  
##   FLASH FLOOD         :  1   Median :      0  
##   LIGHTNING           :  1   Mean   :  12449  
##   TSTM WIND           :  1   3rd Qu.:     50  
##   TSTM WIND (G45)     :  1   Max.   :3312277  
##  (Other)              :979

TopEconomyImpactPerEvent <- arrange(EconomyImpactPerEvent, desc(economy_impact))

Results

The top 10 event types per impact category are:

Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health? Top 10 of most harmful storm events with respect to population health are listed below:

head(TopHealthImpactPerEvent, 10)

##            event_type health_impact
##  1:           TORNADO         96979
##  2:    EXCESSIVE HEAT          8428
##  3:         TSTM WIND          7461
##  4:             FLOOD          7259
##  5:         LIGHTNING          6046
##  6:              HEAT          3037
##  7:       FLASH FLOOD          2755
##  8:         ICE STORM          2064
##  9: THUNDERSTORM WIND          1621
## 10:      WINTER STORM          1527

Across the United States, which types of events have the greatest economic consequences? Top 10 of most harmful storm events with respect to their economic consequences are listed below:

head(TopEconomyImpactPerEvent, 10)

##             event_type economy_impact
##  1:            TORNADO        3312277
##  2:        FLASH FLOOD        1599325
##  3:          TSTM WIND        1445168
##  4:               HAIL        1268290
##  5:              FLOOD        1067976
##  6:  THUNDERSTORM WIND         943636
##  7:          LIGHTNING         606932
##  8: THUNDERSTORM WINDS         464978
##  9:          HIGH WIND         342015
## 10:       WINTER STORM         134700

The figures below display an overview of the impact on health and economy of storm event types:

TopHealthEconomy <- merge(TopHealthImpactPerEvent[1:10, ], TopEconomyImpactPerEvent[1:10, 
    ], by = "event_type")
TopHealthEconomy

##           event_type health_impact economy_impact
## 1:       FLASH FLOOD          2755        1599325
## 2:             FLOOD          7259        1067976
## 3:         LIGHTNING          6046         606932
## 4: THUNDERSTORM WIND          1621         943636
## 5:           TORNADO         96979        3312277
## 6:         TSTM WIND          7461        1445168
## 7:      WINTER STORM          1527         134700

library(lattice)
par(mfrow = c(1, 2))
barchart(event_type ~ health_impact, data = TopHealthEconomy, ylab = "Event Types", 
    xlab = "Number of Incidents")

plot of chunk unnamed-chunk-6

barchart(event_type ~ (economy_impact)/1000, data = TopHealthEconomy, ylab = "Event Types", 
    xlab = "Damages (in thousand $)")

plot of chunk unnamed-chunk-6