Using the U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database, we identify the weather events with the highest adverse impacts on population health and economic wellbeing. Tornadoes have the worst impact on population health: 91346 injuries and 5633 fatalities. Hurricanes and typhoons have the worst economic consequences, at $72T. From a policy perspective, it is highly important to focus on mitigating the effects of these weather event types.
In the following, I load in the data, process it, and investigate the events with the highest impacts.
if(!file.exists("StormData.csv.bz2")){
download.file("https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2","StormData.csv.bz2")
}
storms <- read.csv("StormData.csv.bz2")
head(storms)
## 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 6
The variables of interest are the following:
EVTYPE : type of event
FATALITIES and INJURIES : count of damage to individuals
PROPDMG & PROPDMGEXP : property damage, given as a combination of number and magnitude designation (K for thousands, M for millions, B for billions)
CROPDMG & CROPDMGEXP : damage to crops plus magnitude as above
The database records fatalities and injuries per event. It is intuitive to count fatalities as worse than injuries, but hard to quantify just how much worse: is a fatality worth 100 injuries? 1000 injuries? And are we talking about bumped knees injuries or shattered limbs and severed spinal cords? That said, if fatalities strongly correlate with injuries, we may not need to answer that question at all.
par(mfrow = c(2,2))
plot(storms$FATALITIES, storms$INJURIES)
abline(lm(storms$INJURIES ~ storms$FATALITIES))
plot(storms$FATALITIES, storms$INJURIES, xlim = c(0,200))
plot(storms$FATALITIES, storms$INJURIES, xlim = c(0,50))
plot(log(storms$FATALITIES), log(storms$INJURIES))
We clearly see a positive correlation, but it is an ambiguous one. It is significantly skewed by the outlier of a 1995 heatwave in Northern Illinois with 583 fatalities and 0 injuries reported. Even aside from that one, as we limit the x-axis, we see a very crowded region near the base of the chart: most of the damaging events have 0-15 fatalities, but for each of those, there’s a high variation between 0-200 injuries. Using a log scale to uncrowd the plot makes the pattern of high injury variation even clearer. Though this is an entirely arbitrary decision, I will make the calculation based on a 1:100 fatality-injury conversion.
storms$health_impact <- 100* storms$FATALITIES + storms$INJURIES
library(dplyr)
##
## Attaching package: 'dplyr'
## The following object is masked _by_ '.GlobalEnv':
##
## storms
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
population_impact <- storms %>%
group_by(EVTYPE) %>%
summarize(total_impact = sum(health_impact),
avg_impact = mean(health_impact))
population_impact %>% arrange(desc(avg_impact)) %>% head()
## # A tibble: 6 x 3
## EVTYPE total_impact avg_impact
## <chr> <dbl> <dbl>
## 1 TORNADOES, TSTM WIND, HAIL 2500 2500
## 2 COLD AND SNOW 1400 1400
## 3 TROPICAL STORM GORDON 843 843
## 4 RECORD/EXCESSIVE HEAT 1700 567.
## 5 EXTREME HEAT 9755 443.
## 6 HEAT WAVE DROUGHT 415 415
population_impact %>% arrange(desc(total_impact)) %>% head()
## # A tibble: 6 x 3
## EVTYPE total_impact avg_impact
## <chr> <dbl> <dbl>
## 1 TORNADO 654646 10.8
## 2 EXCESSIVE HEAT 196825 117.
## 3 FLASH FLOOD 99577 1.83
## 4 HEAT 95800 125.
## 5 LIGHTNING 86830 5.51
## 6 TSTM WIND 57357 0.261
Ostensibly, “TORNADOES, TSTM WIND, HAIL” has the largest average impact, at 70, but a closer look reveals that we’re dealing with a recording fluke. A single event with an impact of 70 was labeled with a unique title, yielding an erroneous average of 2500. Most of the top average entries are such single-entry events.
Total impact counts are far less sensitive to such input errors, and tornadoes clearly take the lead with a total impact of 654,646. Disaggregating that total figures yields the following figures:
tornado_focus <- storms %>%
filter(EVTYPE == "TORNADO") %>%
select(EVTYPE, FATALITIES, INJURIES) %>%
summarise(num = n(),
tot_fatalities = sum(FATALITIES),
avg_fatalities = mean(FATALITIES),
tot_injuries = sum(INJURIES),
avg_injuries = mean(INJURIES))
tornado_focus
## num tot_fatalities avg_fatalities tot_injuries avg_injuries
## 1 60652 5633 0.0928741 91346 1.506067
The dataset reports property and crop damage, both relevant to the question. The only caveat is that each is reported as a combination of number and order of magnitude, but that is easily corrected.
storms$economic_impact <- case_when(
storms$PROPDMGEXP == "" ~ 0,
storms$PROPDMGEXP == "K" ~ storms$PROPDMG * 1000,
storms$PROPDMGEXP == "M" ~ storms$PROPDMG * 1000000,
storms$PROPDMGEXP == "B" ~ storms$PROPDMG * 1000000000
) + case_when(
storms$CROPDMGEXP == "" ~ 0,
storms$CROPDMGEXP == "K" ~ storms$CROPDMG * 1000,
storms$CROPDMGEXP == "M" ~ storms$CROPDMG * 1000000,
storms$CROPDMGEXP == "B" ~ storms$CROPDMG * 1000000000)
economic_impact <- storms %>%
group_by(EVTYPE) %>%
summarize(total_impact = sum(economic_impact),
avg_impact = mean(economic_impact))
economic_impact %>% arrange(desc(avg_impact)) %>% head()
## # A tibble: 6 x 3
## EVTYPE total_impact avg_impact
## <chr> <dbl> <dbl>
## 1 TORNADOES, TSTM WIND, HAIL 1602500000 1602500000
## 2 HEAVY RAIN/SEVERE WEATHER 2500000000 1250000000
## 3 HURRICANE/TYPHOON 71913712800 817201282.
## 4 STORM SURGE 43323541000 165990579.
## 5 WILD FIRES 624100000 156025000
## 6 EXCESSIVE WETNESS 142000000 142000000
economic_impact %>% arrange(desc(total_impact)) %>% head()
## # A tibble: 6 x 3
## EVTYPE total_impact avg_impact
## <chr> <dbl> <dbl>
## 1 HURRICANE/TYPHOON 71913712800 817201282.
## 2 STORM SURGE 43323541000 165990579.
## 3 HURRICANE 14610229010 83966833.
## 4 RIVER FLOOD 10148404500 58661298.
## 5 TROPICAL STORM 8382236550 12148169.
## 6 WILDFIRE 5060586800 1832882.
Average damage values, again, show noise from single-occurrence events. Total impact figures are more robust, and show hurricanes & typhoons clearly in the lead with $71,913,712,800--that’s nearly 72 trillion dollars. Hurricane as a separate category comes in third at $14.7T, but since I am not manually totaling other duplicate categories, I will let this one be, too.