Analysis of Severe Weather Events Impact on Population Health and Economic Consequences
This analysis explores the NOAA Storm Database to identify the types of severe weather events in the United States that are most harmful to population health and those with the greatest economic consequences. The analysis involves loading and processing the raw data, summarizing key statistics, and presenting the results through tables and visualizations. Key findings indicate that tornadoes are the most harmful to population health, while floods have the greatest economic impact.
Data Loading and Preprocessing
In this section, we load the dataset containing storm data. We use
the read.csv function to read the CSV file into R and
preprocess the data for analysis.
# Load the required libraries
suppressPackageStartupMessages({
library(dplyr)
library(ggplot2)
library(knitr)
})
# Read the data
storm_data <- read.csv("repdata_data_StormData.csv")
str(storm_data)## 'data.frame': 902297 obs. of 37 variables:
## $ STATE__ : num 1 1 1 1 1 1 1 1 1 1 ...
## $ BGN_DATE : chr "4/18/1950 0:00:00" "4/18/1950 0:00:00" "2/20/1951 0:00:00" "6/8/1951 0:00:00" ...
## $ BGN_TIME : chr "0130" "0145" "1600" "0900" ...
## $ TIME_ZONE : chr "CST" "CST" "CST" "CST" ...
## $ COUNTY : num 97 3 57 89 43 77 9 123 125 57 ...
## $ COUNTYNAME: chr "MOBILE" "BALDWIN" "FAYETTE" "MADISON" ...
## $ STATE : chr "AL" "AL" "AL" "AL" ...
## $ EVTYPE : chr "TORNADO" "TORNADO" "TORNADO" "TORNADO" ...
## $ BGN_RANGE : num 0 0 0 0 0 0 0 0 0 0 ...
## $ BGN_AZI : chr "" "" "" "" ...
## $ BGN_LOCATI: chr "" "" "" "" ...
## $ END_DATE : chr "" "" "" "" ...
## $ END_TIME : chr "" "" "" "" ...
## $ COUNTY_END: num 0 0 0 0 0 0 0 0 0 0 ...
## $ COUNTYENDN: logi NA NA NA NA NA NA ...
## $ END_RANGE : num 0 0 0 0 0 0 0 0 0 0 ...
## $ END_AZI : chr "" "" "" "" ...
## $ END_LOCATI: chr "" "" "" "" ...
## $ LENGTH : num 14 2 0.1 0 0 1.5 1.5 0 3.3 2.3 ...
## $ WIDTH : num 100 150 123 100 150 177 33 33 100 100 ...
## $ F : int 3 2 2 2 2 2 2 1 3 3 ...
## $ MAG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ FATALITIES: num 0 0 0 0 0 0 0 0 1 0 ...
## $ INJURIES : num 15 0 2 2 2 6 1 0 14 0 ...
## $ PROPDMG : num 25 2.5 25 2.5 2.5 2.5 2.5 2.5 25 25 ...
## $ PROPDMGEXP: chr "K" "K" "K" "K" ...
## $ CROPDMG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ CROPDMGEXP: chr "" "" "" "" ...
## $ WFO : chr "" "" "" "" ...
## $ STATEOFFIC: chr "" "" "" "" ...
## $ ZONENAMES : chr "" "" "" "" ...
## $ LATITUDE : num 3040 3042 3340 3458 3412 ...
## $ LONGITUDE : num 8812 8755 8742 8626 8642 ...
## $ LATITUDE_E: num 3051 0 0 0 0 ...
## $ LONGITUDE_: num 8806 0 0 0 0 ...
## $ REMARKS : chr "" "" "" "" ...
## $ REFNUM : num 1 2 3 4 5 6 7 8 9 10 ...head(storm_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 6# Subset the data
subset_data <- storm_data %>%
dplyr::select(`EVTYPE`, `FATALITIES`, `INJURIES`, `PROPDMG`, `PROPDMGEXP`, `CROPDMG`, `CROPDMGEXP`)
# Convert PROPDMGEXP and CROPDMGEXP to numeric
convert_exp <- function(exp) {
exp <- as.character(exp)
exp[exp == "H" | exp == "h"] <- 100
exp[exp == "K" | exp == "k"] <- 1000
exp[exp == "M" | exp == "m"] <- 1e6
exp[exp == "B" | exp == "b"] <- 1e9
exp[exp %in% c("", "-", "?", "+")] <- 1
return(as.numeric(exp))
}
subset_data$PROPDMGEXP <- convert_exp(subset_data$PROPDMGEXP)
subset_data$CROPDMGEXP <- convert_exp(subset_data$CROPDMGEXP)
# Calculate total damage
subset_data <- subset_data %>%
mutate(PROPDMGTOTAL = PROPDMG * PROPDMGEXP,
CROPDMGTOTAL = CROPDMG * CROPDMGEXP)Results
Most Harmful Events to Population Health
This section identifies the weather events that have caused the most fatalities and injuries.
# Summarize the total fatalities and injuries by event type
health_impact <- subset_data %>%
group_by(EVTYPE) %>%
summarize(Total_Fatalities = sum(FATALITIES), Total_Injuries = sum(INJURIES)) %>%
arrange(desc(Total_Fatalities), desc(Total_Injuries))
# Display top 10 events by fatalities and injuries
kable(head(health_impact, 10))| EVTYPE | Total_Fatalities | Total_Injuries |
|---|---|---|
| TORNADO | 5633 | 91346 |
| EXCESSIVE HEAT | 1903 | 6525 |
| FLASH FLOOD | 978 | 1777 |
| HEAT | 937 | 2100 |
| LIGHTNING | 816 | 5230 |
| TSTM WIND | 504 | 6957 |
| FLOOD | 470 | 6789 |
| RIP CURRENT | 368 | 232 |
| HIGH WIND | 248 | 1137 |
| AVALANCHE | 224 | 170 |
Figure 1 & 2: Top Events by Health Impact
# Plot top 10 events by fatalities
top_health_impact <- health_impact %>% top_n(10, Total_Fatalities)
ggplot(top_health_impact, aes(x = reorder(EVTYPE, -Total_Fatalities), y = Total_Fatalities)) +
geom_bar(stat = "identity") +
labs(title = "Top 10 Weather Events by Fatalities", x = "Event Type", y = "Total Fatalities") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
# Plot top 10 events by injuries
health_impact <- health_impact %>% top_n(10, Total_Injuries)
ggplot(health_impact, aes(x = reorder(EVTYPE, -Total_Injuries), y = Total_Injuries)) +
geom_bar(stat = "identity") +
labs(title = "Top 10 Weather Events by Injuries", x = "Event Type", y = "Total Injuries") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
Events with the Greatest Economic Consequences
This section identifies the weather events that have caused the most economic damage.
# Summarize the total economic damage by event type
economic_impact <- subset_data %>%
group_by(EVTYPE) %>%
summarize(Total_Property_Damage = sum(PROPDMGTOTAL), Total_Crop_Damage = sum(CROPDMGTOTAL), Total_Economic_Damage = sum(PROPDMGTOTAL + CROPDMGTOTAL)) %>%
arrange(desc(Total_Economic_Damage))
# Display top 10 events by economic damage
kable(head(economic_impact, 10))| EVTYPE | Total_Property_Damage | Total_Crop_Damage | Total_Economic_Damage |
|---|---|---|---|
| FLOOD | 144657709807 | 5661968450 | 150319678257 |
| HURRICANE/TYPHOON | 69305840000 | 2607872800 | 71913712800 |
| TORNADO | 56937161054 | 414953110 | 57352114164 |
| STORM SURGE | 43323536000 | 5000 | 43323541000 |
| HAIL | 15732267427 | 3025954453 | 18758221880 |
| FLASH FLOOD | 16140812294 | 1421317100 | 17562129394 |
| DROUGHT | 1046106000 | 13972566000 | 15018672000 |
| HURRICANE | 11868319010 | 2741910000 | 14610229010 |
| RIVER FLOOD | 5118945500 | 5029459000 | 10148404500 |
| ICE STORM | 3944927810 | 5022113500 | 8967041310 |
Figure 3: Top Events by Economic Impact
# Plot top 10 events by economic damage
top_economic_impact <- economic_impact %>% top_n(10, Total_Economic_Damage)
ggplot(top_economic_impact, aes(x = reorder(EVTYPE, -Total_Economic_Damage), y = Total_Economic_Damage)) +
geom_bar(stat = "identity") +
labs(title = "Top 10 Weather Events by Economic Damage", x = "Event Type", y = "Total Economic Damage") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))