Evaluation of NOAA Storm Database on severe weather events
Panagiotis Paschalidis
December 2021
1: Synopsis
The goal of this assignment is to explore the NOAA Storm Database and answer some basic questions about severe weather events.
The basic questions are the following:
Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?
Across the United States, which types of events have the greatest economic consequences?
For Question 1, we preprocess and aggregate the data to find the event type which has the most severe impact in heath. This is manifested in injuries and fatalities.
For Question 2, we preprocess and aggregate the data to identify the event types which have the most severe economic impact. This is manifested in dollars.
2: Data Processing
Data loading and main preprocessing
We need to download the raw data from the webpage.
setwd("C:/GIO/PC/Rprojects/5.ReproducibleResearch/week 4")
Url_datafile <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
# download only if not downloaded again.
datafile <- str_replace_all("repdata%2Fdata%2FStormData.csv.bz2", "%2F", "_")
if (!file.exists(datafile)) {
download.file(Url_datafile, datafile, mode = "wb")
}
# We read the .csv file
raw_data <- read.csv(file = datafile, header = TRUE)We inspect our data in order to identify the relevant headers
head(raw_data)## STATE__ BGN_DATE BGN_TIME TIME_ZONE COUNTY COUNTYNAME STATE EVTYPE
## 1 1 4/18/1950 0:00:00 0130 CST 97 MOBILE AL TORNADO
## 2 1 4/18/1950 0:00:00 0145 CST 3 BALDWIN AL TORNADO
## 3 1 2/20/1951 0:00:00 1600 CST 57 FAYETTE AL TORNADO
## 4 1 6/8/1951 0:00:00 0900 CST 89 MADISON AL TORNADO
## 5 1 11/15/1951 0:00:00 1500 CST 43 CULLMAN AL TORNADO
## 6 1 11/15/1951 0:00:00 2000 CST 77 LAUDERDALE AL TORNADO
## BGN_RANGE BGN_AZI BGN_LOCATI END_DATE END_TIME COUNTY_END COUNTYENDN
## 1 0 0 NA
## 2 0 0 NA
## 3 0 0 NA
## 4 0 0 NA
## 5 0 0 NA
## 6 0 0 NA
## END_RANGE END_AZI END_LOCATI LENGTH WIDTH F MAG FATALITIES INJURIES PROPDMG
## 1 0 14.0 100 3 0 0 15 25.0
## 2 0 2.0 150 2 0 0 0 2.5
## 3 0 0.1 123 2 0 0 2 25.0
## 4 0 0.0 100 2 0 0 2 2.5
## 5 0 0.0 150 2 0 0 2 2.5
## 6 0 1.5 177 2 0 0 6 2.5
## PROPDMGEXP CROPDMG CROPDMGEXP WFO STATEOFFIC ZONENAMES LATITUDE LONGITUDE
## 1 K 0 3040 8812
## 2 K 0 3042 8755
## 3 K 0 3340 8742
## 4 K 0 3458 8626
## 5 K 0 3412 8642
## 6 K 0 3450 8748
## LATITUDE_E LONGITUDE_ REMARKS REFNUM
## 1 3051 8806 1
## 2 0 0 2
## 3 0 0 3
## 4 0 0 4
## 5 0 0 5
## 6 0 0 63: Question 1
3.1: Data Processing Q1
Towards question 1 - impact on public health, we investigate the contents of EVTYPE, INJURIES and FATALITIES. We will first process the data:
# We aggregate injuries and fatalities using event type
injuries <- aggregate(INJURIES ~ EVTYPE, data = raw_data, sum)
fatalities <- aggregate(FATALITIES ~ EVTYPE, data = raw_data, sum)
# We arrange the number of injuries or fatalities in descending order by Event Type
injuries <- arrange(injuries, desc(INJURIES), EVTYPE)[1:10, ]
fatalities <- arrange(fatalities, desc(FATALITIES), EVTYPE)[1:10, ]3.2: Results Q1
Lets investigate fatalities and injuries:
injuries## EVTYPE INJURIES
## 1 TORNADO 91346
## 2 TSTM WIND 6957
## 3 FLOOD 6789
## 4 EXCESSIVE HEAT 6525
## 5 LIGHTNING 5230
## 6 HEAT 2100
## 7 ICE STORM 1975
## 8 FLASH FLOOD 1777
## 9 THUNDERSTORM WIND 1488
## 10 HAIL 1361fatalities## EVTYPE FATALITIES
## 1 TORNADO 5633
## 2 EXCESSIVE HEAT 1903
## 3 FLASH FLOOD 978
## 4 HEAT 937
## 5 LIGHTNING 816
## 6 TSTM WIND 504
## 7 FLOOD 470
## 8 RIP CURRENT 368
## 9 HIGH WIND 248
## 10 AVALANCHE 224The events with the most severe impact in terms of injuries are TORNADO while the events with the most severe impact in terms of fatalities are TORNADO.
The following plot provides a graphical display of the top 10 events with the maximum impact on public health in terms of injuries and fatalities.
# We create the plots for the events.
ggplotInjuriesOverEvents <- ggplot(injuries, aes(x = EVTYPE, y = INJURIES)) +
geom_line(aes(group=1), colour= "red") +
geom_point(size=3, colour = "red") +
xlab("Event Type") + ylab("Injuries") +
theme(axis.text.x = element_text(angle = 90))
ggplotFatalitiesOverEvents <- ggplot(fatalities, aes(x = EVTYPE, y = FATALITIES)) +
geom_line(aes(group=1), colour= "blue") +
geom_point(size=3, colour = "blue") +
xlab("Event Type") + ylab("Fatalities") +
theme(axis.text.x = element_text(angle = 90))
# we create/display a panel plot (2 columns)
grid.arrange(ggplotInjuriesOverEvents, ggplotFatalitiesOverEvents, ncol = 2, nrow = 1,
top = textGrob("Events with maximum impact on public health in terms of injuries and fatalities",
gp = gpar(fontsize = 14)))
The peak in the graphic plot indicates the events (TORNADO causing most injuries and TORNADO causing most fatalities) from the most severe impact in public health.
4: Question 2
4.1: Data Processing Q2
Towards question 2 - greatest economic impact, we investigate the content of CROPDMG (Crop damage) and CROPDMGEXP (corresponding exponent) as well as PROPDMG (Property damage) and PROPDMGEXP (corresponding exponent).
We will need to fuse the information of both variables in order to have a single value for the damage. This is performed by factoring the exponent value into the magnitude value. We will create a further variable TOTALDMG_VAL with the total damage as the sum of both types of damage.
# We factor the exponent value into the magintude value
raw_data$CROPDMG_VAL[raw_data$CROPDMG==0] <- 0
raw_data$PROPDMG_VAL[raw_data$PROPDMG==0] <- 0
raw_data$CROPDMG_VAL[raw_data$CROPDMGEXP=="H"| raw_data$CROPDMGEXP=="h"] <- raw_data$CROPDMG[raw_data$CROPDMGEXP=="H"|raw_data$CROPDMGEXP=="h"]*1e2
raw_data$PROPDMG_VAL[raw_data$PROPDMGEXP=="H"| raw_data$PROPDMGEXP=="h"] <- raw_data$PROPDMG[raw_data$PROPDMGEXP=="H"|raw_data$PROPDMGEXP=="h"]*1e2
raw_data$CROPDMG_VAL[raw_data$CROPDMGEXP=="K"| raw_data$CROPDMGEXP=="k"] <- raw_data$CROPDMG[raw_data$CROPDMGEXP=="K"|raw_data$CROPDMGEXP=="k"]*1e3
raw_data$PROPDMG_VAL[raw_data$PROPDMGEXP=="K"| raw_data$PROPDMGEXP=="k"] <- raw_data$PROPDMG[raw_data$PROPDMGEXP=="K"|raw_data$PROPDMGEXP=="k"]*1e3
raw_data$CROPDMG_VAL[raw_data$CROPDMGEXP=="M"| raw_data$CROPDMGEXP=="m"] <- raw_data$CROPDMG[raw_data$CROPDMGEXP=="M"|raw_data$CROPDMGEXP=="m"]*1e6
raw_data$PROPDMG_VAL[raw_data$PROPDMGEXP=="M"| raw_data$PROPDMGEXP=="m"] <- raw_data$PROPDMG[raw_data$PROPDMGEXP=="M"|raw_data$PROPDMGEXP=="m"]*1e6
raw_data$CROPDMG_VAL[raw_data$CROPDMGEXP=="B"| raw_data$CROPDMGEXP=="b"] <- raw_data$CROPDMG[raw_data$CROPDMGEXP=="B"|raw_data$CROPDMGEXP=="b"]*1e9
raw_data$PROPDMG_VAL[raw_data$PROPDMGEXP=="B"| raw_data$PROPDMGEXP=="b"] <- raw_data$PROPDMG[raw_data$PROPDMGEXP=="B"|raw_data$PROPDMGEXP=="b"]*1e9
# We create a total damage variable
raw_data$TOTALDMG_VAL <- raw_data$CROPDMG_VAL + raw_data$PROPDMG_VALNow we will aggregate the new variables CROPDMG_VAL, PROPDMG_VAL and TOTALDMG_VAL with the full range values along the events.
# We aggregate the damages by event type
cropdmg <- aggregate(CROPDMG_VAL ~ EVTYPE, data = raw_data, sum, na.rm = TRUE)
propdmg <- aggregate(PROPDMG_VAL ~ EVTYPE, data = raw_data, sum, na.rm = TRUE)
totaldmg <- aggregate(TOTALDMG_VAL ~ EVTYPE, data = raw_data, sum, na.rm = TRUE)
# We arrange the damage value on crop, property and in total in descending order by Event Type
cropdmg <- arrange(cropdmg, desc(CROPDMG_VAL), EVTYPE)[1:10, ]
propdmg <- arrange(propdmg, desc(PROPDMG_VAL), EVTYPE)[1:10, ]
totaldmg <- arrange(totaldmg, desc(TOTALDMG_VAL), EVTYPE)[1:10, ]4.2: Results Q2
Now lets investigate the damages by event type.
cropdmg ## EVTYPE CROPDMG_VAL
## 1 DROUGHT 13972566000
## 2 FLOOD 5661968450
## 3 RIVER FLOOD 5029459000
## 4 ICE STORM 5022113500
## 5 HAIL 3025954450
## 6 HURRICANE 2741910000
## 7 HURRICANE/TYPHOON 2607872800
## 8 FLASH FLOOD 1421317100
## 9 EXTREME COLD 1292973000
## 10 FROST/FREEZE 1094086000propdmg ## EVTYPE PROPDMG_VAL
## 1 FLOOD 144657709800
## 2 HURRICANE/TYPHOON 69305840000
## 3 TORNADO 56937160480
## 4 STORM SURGE 43323536000
## 5 FLASH FLOOD 16140811510
## 6 HAIL 15732267220
## 7 HURRICANE 11868319010
## 8 TROPICAL STORM 7703890550
## 9 WINTER STORM 6688497250
## 10 HIGH WIND 5270046260totaldmg ## EVTYPE TOTALDMG_VAL
## 1 FLOOD 150319678250
## 2 HURRICANE/TYPHOON 71913712800
## 3 TORNADO 57301940590
## 4 STORM SURGE 43323541000
## 5 HAIL 18733211670
## 6 FLASH FLOOD 17561528610
## 7 DROUGHT 15018672000
## 8 HURRICANE 14610229010
## 9 RIVER FLOOD 10148404500
## 10 ICE STORM 8967037810The events with the most severe economic impact are DROUGHT on crop damage, FLOOD on property damage and, FLOOD in total damage.
The following plot provides a graphical display of the top 10 events with the maximum economic impact.
# We create the plots for the events.
ggplotCropDmgOverEvents <- ggplot(cropdmg, aes(x = EVTYPE, y = CROPDMG_VAL/1e9)) +
geom_line(aes(group=1), colour= "red") +
geom_point(size=3, colour = "red") +
xlab("Event Type") + ylab("Crop Damage [Billions $]") +
theme(axis.text.x = element_text(angle = 90))
ggplotPropDmgOverEvents <- ggplot(propdmg, aes(x = EVTYPE, y = PROPDMG_VAL/1e9)) +
geom_line(aes(group=1), colour= "blue") +
geom_point(size=3, colour = "blue") +
xlab("Event Type") + ylab("Property Damage [Billions $]") +
theme(axis.text.x = element_text(angle = 90))
ggplotTotalDmgOverEvents <- ggplot(totaldmg, aes(x = EVTYPE, y = TOTALDMG_VAL/1e9)) +
geom_line(aes(group=1), colour= "black") +
geom_point(size=3, colour = "black") +
xlab("Event Type") + ylab("Total Damage [Billions $]") +
theme(axis.text.x = element_text(angle = 90))
# We create/display a panel plot (3 columns)
grid.arrange(ggplotCropDmgOverEvents, ggplotPropDmgOverEvents, ggplotTotalDmgOverEvents, ncol = 3, nrow = 1,
top = textGrob("Events with maximum economic impact on crop, property and in total",
gp = gpar(fontsize = 14)))
The peaks in the graphic plots indicate the events with the most severe economic impact (DROUGHT on crop damage, FLOOD on property damage and, FLOOD in total damage).
Conclusions
Q1: The events with the most severe impact in terms of injuries are TORNADO while the events with the most severe impact in terms of fatalities are TORNADO.
Q2: The events with the most severe economic impact are DROUGHT on crop damage, FLOOD on property damage and, FLOOD in total damage.