Severe Weather Events and Analysis
Nisha Rajan
2026-09-29
library(dplyr)
library(ggplot2)
library(tidyr)##This project encompasses severe Weather events and analysis from 1950 through November 2011.
##Data Processing The data are loaded directly into R using
read.csv, which can read the .csv.bz2 file
without manually extracting it. The variables used for this analysis are
event type, fatalities, injuries, property damage, property damage
exponent, crop damage and crop damage exponent.
storm <- read.csv("repdata_data_StormData.csv.bz2",
stringsAsFactors = FALSE)
dim(storm)## [1] 902297 37head(storm)## 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 6storm_analysis <- storm %>%
select(EVTYPE, FATALITIES, INJURIES,
PROPDMG, PROPDMGEXP,
CROPDMG, CROPDMGEXP)
head(storm_analysis)## EVTYPE FATALITIES INJURIES PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP
## 1 TORNADO 0 15 25.0 K 0
## 2 TORNADO 0 0 2.5 K 0
## 3 TORNADO 0 2 25.0 K 0
## 4 TORNADO 0 2 2.5 K 0
## 5 TORNADO 0 2 2.5 K 0
## 6 TORNADO 0 6 2.5 K 0length(unique(storm_analysis$EVTYPE))## [1] 985head(sort(unique(storm_analysis$EVTYPE)), 20)## [1] " HIGH SURF ADVISORY" " COASTAL FLOOD" " FLASH FLOOD"
## [4] " LIGHTNING" " TSTM WIND" " TSTM WIND (G45)"
## [7] " WATERSPOUT" " WIND" "?"
## [10] "ABNORMAL WARMTH" "ABNORMALLY DRY" "ABNORMALLY WET"
## [13] "ACCUMULATED SNOWFALL" "AGRICULTURAL FREEZE" "APACHE COUNTY"
## [16] "ASTRONOMICAL HIGH TIDE" "ASTRONOMICAL LOW TIDE" "AVALANCE"
## [19] "AVALANCHE" "BEACH EROSIN"health_summary <- storm_analysis %>%
group_by(EVTYPE) %>%
summarise(
fatalities = sum(FATALITIES, na.rm = TRUE),
injuries = sum(INJURIES, na.rm = TRUE),
total_health_impact = fatalities + injuries,
.groups = "drop"
) %>%
arrange(desc(total_health_impact))
head(health_summary, 10)## # A tibble: 10 × 4
## EVTYPE fatalities injuries total_health_impact
## <chr> <dbl> <dbl> <dbl>
## 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 1527top_health <- health_summary %>%
slice_max(order_by = total_health_impact, n = 10)
top_health## # A tibble: 10 × 4
## EVTYPE fatalities injuries total_health_impact
## <chr> <dbl> <dbl> <dbl>
## 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 1527fig.cap="Figure 1. The ten weather event types with the largest combined number of reported fatalities and injuries in the NOAA Storm Database."
ggplot(top_health,
aes(x = reorder(EVTYPE, total_health_impact),
y = total_health_impact)) +
geom_col(fill = "steelblue") +
coord_flip() +
labs(
title = "Top 10 Weather Events by Population Health Impact",
x = "Event Type",
y = "Fatalities + Injuries"
) +
theme_minimal()
##Economic Conseequences It refers to both property damage and crop damage.
storm_analysis <- storm_analysis %>%
mutate(
PROP_MULT = case_when(
PROPDMGEXP %in% c("K", "k") ~ 1000,
PROPDMGEXP %in% c("M", "m") ~ 1000000,
PROPDMGEXP %in% c("B", "b") ~ 1000000000,
TRUE ~ 1
),
CROP_MULT = case_when(
CROPDMGEXP %in% c("K", "k") ~ 1000,
CROPDMGEXP %in% c("M", "m") ~ 1000000,
CROPDMGEXP %in% c("B", "b") ~ 1000000000,
TRUE ~ 1
),
PROPERTY_DAMAGE = PROPDMG * PROP_MULT,
CROP_DAMAGE = CROPDMG * CROP_MULT
)economic_summary <- storm_analysis %>%
group_by(EVTYPE) %>%
summarise(
property_damage = sum(PROPERTY_DAMAGE, na.rm = TRUE),
crop_damage = sum(CROP_DAMAGE, na.rm = TRUE),
total_damage = property_damage + crop_damage,
.groups = "drop"
) %>%
arrange(desc(total_damage))
head(economic_summary, 10)## # A tibble: 10 × 4
## EVTYPE property_damage crop_damage total_damage
## <chr> <dbl> <dbl> <dbl>
## 1 FLOOD 144657709807 5661968450 150319678257
## 2 HURRICANE/TYPHOON 69305840000 2607872800 71913712800
## 3 TORNADO 56937160779. 414953270 57352114049.
## 4 STORM SURGE 43323536000 5000 43323541000
## 5 HAIL 15732267048. 3025954473 18758221521.
## 6 FLASH FLOOD 16140812067. 1421317100 17562129167.
## 7 DROUGHT 1046106000 13972566000 15018672000
## 8 HURRICANE 11868319010 2741910000 14610229010
## 9 RIVER FLOOD 5118945500 5029459000 10148404500
## 10 ICE STORM 3944927860 5022113500 8967041360top_economic <- economic_summary %>%
slice_max(order_by = total_damage, n = 10)
ggplot(top_economic,
aes(x = reorder(EVTYPE, total_damage),
y = total_damage / 1000000000)) +
geom_col(fill = "darkorange") +
coord_flip() +
labs(
title = "Top 10 Weather Events by Economic Damage",
x = "Event Type",
y = "Total Damage (Billions of Dollars)"
) +
theme_minimal()
head(health_summary, 10)
EVTYPE fatalities injuries total_health_impact
head(economic_summary, 10) # A tibble: 10 × 4 EVTYPE property_damage crop_damage total_damage
1 FLOOD 144657709807 5661968450 150319678257 2 HURRICANE/TYPHOON 69305840000 2607872800 71913712800 3 TORNADO 56937160779. 414953270 57352114049. 4 STORM SURGE 43323536000 5000 43323541000 5 HAIL 15732267048. 3025954473 18758221521. 6 FLASH FLOOD 16140812067. 1421317100 17562129167. 7 DROUGHT 1046106000 13972566000 15018672000 8 HURRICANE 11868319010 2741910000 14610229010 9 RIVER FLOOD 5118945500 5029459000 10148404500 10 ICE STORM 3944927860 5022113500 8967041360
#####Results
#Population Health
Fatalities and injuries are taken as measures of impact. In the anaysis it was found that Tornado was the highest natural calamity that had highest impact on human population followed by Excessive heat.
##Economic Consequences Measured by using both property and crop damage
Floods have the largest estimated economic impact in this analysis as it contributed to property damage and crop damage ##Conclusion This analysis was done to ascertain if weather events have their imapcts on Human population health and economy.