Analysis of Consequences from natural disasters from the NOAA database.

Author: Marcos de Aguiar

Synopsis

This study aims to make a data analysis to check the consequences of natural disasters, especially storm related. The study will use storm data from 1950 up to 2011 provided by NOAA (U.S. National Oceanic and Atmospheric Administration). This study will make 2 analyses. One is which kind of event has the biggest consequence in public health. The second is which kind has the biggest economic consequences.

Data processing

Packages to be used for the analysis.

library(dplyr)

First download and unzip the file from the following link:

Then uncompress an load the data into R.

stormDS <- read.csv("repdata-data-StormData.csv")

Analysis 1: Which type of events are more harmful to population health.

We will assume that the harm to the population health is the sum of fatalities and injuries.

Creates a dataset with the sum of fatalities, then another with the sum of injuries.

fatalitiesDS <- aggregate(stormDS$FATALITIES, by=list(EVTYPE=stormDS$EVTYPE), FUN=sum,  na.rm=TRUE)
injuriesDS <- aggregate(stormDS$INJURIES, by=list(EVTYPE=stormDS$EVTYPE), FUN=sum,  na.rm=TRUE)

Merges the 2 together, and create a column with the sum.

harmDS <- merge(fatalitiesDS, injuriesDS, by = "EVTYPE")
harmDS$total <- (harmDS$x.x + harmDS$x.y)

Gets the top 10 most harmfull events.

head(arrange(harmDS,desc(total)), 10)

##               EVTYPE  x.x   x.y total
## 1            TORNADO 5633 91346 96979
## 2     EXCESSIVE HEAT 1903  6525  8428
## 3          TSTM WIND  504  6957  7461
## 4              FLOOD  470  6789  7259
## 5          LIGHTNING  816  5230  6046
## 6               HEAT  937  2100  3037
## 7        FLASH FLOOD  978  1777  2755
## 8          ICE STORM   89  1975  2064
## 9  THUNDERSTORM WIND  133  1488  1621
## 10      WINTER STORM  206  1321  1527

Bar graph showing the worst events.

top4DS <- head(arrange(harmDS,desc(total)), 4)
barplot(top4DS$total, names.arg = top4DS$EVTYPE, xlab = "Event type", ylab = "Health consequences", main = "Total health consequences by event.")

Result:

As we can observe, tornados and excessive heats are the most harmfull events for the general population health.

Analysis 2: Which type of events causes more economical consequences.

We will assume that economical consequences are the sum of property damages and crop damages.

Creates a dataset with the sum of property damage, then another with the sum of crop damages.

propertydamDS <- aggregate(stormDS$PROPDMG, by=list(EVTYPE=stormDS$EVTYPE), FUN=sum,  na.rm=TRUE)
cropdamDS <- aggregate(stormDS$CROPDMG, by=list(EVTYPE=stormDS$EVTYPE), FUN=sum,  na.rm=TRUE)

Merges the 2 together, and create a column with the sum.

damageDS <- merge(propertydamDS, cropdamDS, by = "EVTYPE")
damageDS$total <- (damageDS$x.x + damageDS$x.y)

Gets the top 10 most economically damaging events.

head(arrange(damageDS,desc(total)), 10)

##                EVTYPE       x.x       x.y     total
## 1             TORNADO 3212258.2 100018.52 3312276.7
## 2         FLASH FLOOD 1420124.6 179200.46 1599325.1
## 3           TSTM WIND 1335965.6 109202.60 1445168.2
## 4                HAIL  688693.4 579596.28 1268289.7
## 5               FLOOD  899938.5 168037.88 1067976.4
## 6   THUNDERSTORM WIND  876844.2  66791.45  943635.6
## 7           LIGHTNING  603351.8   3580.61  606932.4
## 8  THUNDERSTORM WINDS  446293.2  18684.93  464978.1
## 9           HIGH WIND  324731.6  17283.21  342014.8
## 10       WINTER STORM  132720.6   1978.99  134699.6

Bar graph showing the worst events.

top4DS <- head(arrange(damageDS,desc(total)), 4)
barplot(top4DS$total, names.arg = top4DS$EVTYPE, xlab = "Event type", ylab = "Economical damage", main = "Total economic damage by event.")

## Result:

As we can observe, tornados and flash floods are the most damaging events for the economy.