title: “NOAA Storm Database Analysis”

author: “Katie Scoones”

date: “November 2026”

output: html_document


Synopsis

This project analyzes the National Oceanic and Atmospheric Administration (NOAA) Storm Events Database for 2024. The purpose of the analysis is to identify which types of storms have the greatest effects on public safety, occur most frequently across different states and months, and cause the most economic damage. The dataset contains 69,801 storm events across 50 different event types. The results show that tornadoes caused the most injuries, with 658 reported injuries. Excessive heat caused the most deaths, with 253 reported fatalities. Thunderstorm winds were the most frequently reported storm event overall. Winter weather was most common during the winter months, while thunderstorm winds were especially common during the warmer months. Hurricanes caused the greatest economic damage, totaling approximately $6.81 billion in property and crop damage. These findings can help government and emergency management officials better understand storm-related risks and prepare for future events.

Data Processing

The analysis used three CSV files from the NOAA Storm Events Database for 2024: the storm details, the fatalities, and the locations files. The files were downloaded and stored in a folder named Data within the project folder.

The read.csv() function was used to import the three files into R. The datasets were combined using the EVENT_ID variable, which identifies individual storm events. A left join was used to retain all records from the details dataset while adding matching location and fatality information.

The combined dataset contained 86,556 rows and 70 columns. There were 69,801 unique event IDs in both the original details dataset and the combined dataset. Some storm events had multiple location or fatality records, which resulted in additional rows after joining.

For the main analysis, the original details dataset was used to calculate injuries, deaths, event frequencies, and economic damage. This was to avoid duplicating storm events because of the additional records created by the join functions.

The dataset contained 50 different event types. Checks to the main variables were also used in the analysis, including event type, state, month, injuries, and deaths, to see if there were any missing values. No missing values were found in these variables.

Loading the Data

# Load required packages
library(dplyr)
library(readr)
library(ggplot2)

# Load the CSV files
details <- read.csv("Data/StormEvents_details-ftp_v1.0_d2024_c20260728.csv")
fatalities <- read.csv("Data/StormEvents_fatalities-ftp_v1.0_d2024_c20260728.csv")
locations <- read.csv("Data/StormEvents_locations-ftp_v1.0_d2024_c20260728.csv")

# Check the datasets
head(details)
##   BEGIN_YEARMONTH BEGIN_DAY BEGIN_TIME END_YEARMONTH END_DAY END_TIME
## 1          202404        30       2033        202404      30     2033
## 2          202407         1          0        202407       5      900
## 3          202411        16        230        202411      18     1421
## 4          202405        22       1230        202405      22     1615
## 5          202405        21       1200        202405      21     1530
## 6          202405        24       1405        202405      24     1410
##   EPISODE_ID EVENT_ID       STATE STATE_FIPS YEAR MONTH_NAME        EVENT_TYPE
## 1     189851  1174463    OKLAHOMA         40 2024      April Thunderstorm Wind
## 2     193486  1195301   LOUISIANA         22 2024       July    Excessive Heat
## 3     197838  1223377      OREGON         41 2024   November        Heavy Snow
## 4     191723  1184135       TEXAS         48 2024        May              Heat
## 5     191723  1184133       TEXAS         48 2024        May              Heat
## 6     191916  1182348 MISSISSIPPI         28 2024        May Thunderstorm Wind
##   CZ_TYPE CZ_FIPS                            CZ_NAME WFO    BEGIN_DATE_TIME
## 1       C     141                            TILLMAN OUN 30-APR-24 20:33:00
## 2       Z      18                       NATCHITOCHES SHV 01-JUL-24 00:00:00
## 3       Z     509 EAST SLOPES OF THE OREGON CASCADES PDT 16-NOV-24 02:30:00
## 4       Z     254                            WILLACY BRO 22-MAY-24 12:30:00
## 5       Z     254                            WILLACY BRO 21-MAY-24 12:00:00
## 6       C     115                           PONTOTOC MEG 24-MAY-24 14:05:00
##   CZ_TIMEZONE      END_DATE_TIME INJURIES_DIRECT INJURIES_INDIRECT
## 1       CST-6 30-APR-24 20:33:00               0                 0
## 2       CST-6 05-JUL-24 09:00:00               0                 0
## 3       PST-8 18-NOV-24 14:21:00               0                 0
## 4       CST-6 22-MAY-24 16:15:00               0                 0
## 5       CST-6 21-MAY-24 15:30:00               0                 0
## 6       CST-6 24-MAY-24 14:10:00               0                 0
##   DEATHS_DIRECT DEATHS_INDIRECT DAMAGE_PROPERTY DAMAGE_CROPS SOURCE MAGNITUDE
## 1             0               0                                ASOS        55
## 2             0               0           0.00K        0.00K   ASOS        NA
## 3             0               0           0.00K        0.00K SNOTEL        NA
## 4             0               0           0.00K        0.00K   ASOS        NA
## 5             0               0           0.00K        0.00K   ASOS        NA
## 6             0               0           1.00K        0.00K Public        52
##   MAGNITUDE_TYPE FLOOD_CAUSE CATEGORY TOR_F_SCALE TOR_LENGTH TOR_WIDTH
## 1             MG                   NA                     NA        NA
## 2                                  NA                     NA        NA
## 3                                  NA                     NA        NA
## 4                                  NA                     NA        NA
## 5                                  NA                     NA        NA
## 6             EG                   NA                     NA        NA
##   TOR_OTHER_WFO TOR_OTHER_CZ_STATE TOR_OTHER_CZ_FIPS TOR_OTHER_CZ_NAME
## 1                                                 NA                  
## 2                                                 NA                  
## 3                                                 NA                  
## 4                                                 NA                  
## 5                                                 NA                  
## 6                                                 NA                  
##   BEGIN_RANGE BEGIN_AZIMUTH BEGIN_LOCATION END_RANGE END_AZIMUTH   END_LOCATION
## 1        0.42           SSW FREDERICK ARPT      0.42         SSW FREDERICK ARPT
## 2          NA                                     NA                           
## 3          NA                                     NA                           
## 4          NA                                     NA                           
## 5          NA                                     NA                           
## 6        0.00             N         ALGOMA      0.00           N         ALGOMA
##   BEGIN_LAT BEGIN_LON END_LAT END_LON
## 1   34.3444   -98.983 34.3444 -98.983
## 2        NA        NA      NA      NA
## 3        NA        NA      NA      NA
## 4        NA        NA      NA      NA
## 5        NA        NA      NA      NA
## 6   34.1800   -89.030 34.1800 -89.030
##                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      EPISODE_NARRATIVE
## 1                                                                                                                                                                                                                                                                                                                                                                              A rather nebulous upper air pattern existed across the Southern Plains on the 30th, with 30-40 knots of quasi-zonal flow at 500 mb. However, plentiful solar insolation/surface heating in the vicinity of a dryline fostered widely scattered thunderstorm development by the late afternoon. Strong instability and sufficient organizing wind shear lead to a few of these storms displaying supercellular characteristics and producing reports of large hail initially, owing to steep lapse rates and weak low-level shear (among other factors already mentioned). By the mid-evening, as low-level shear and storm-scale interactions began to increase, a few tornadoes occurred across portions of south-central into southwest Oklahoma. The most significant of these was an EF-1 tornado near the community of Hollister (Tillman County).
## 2                                                                                                                                                                                                                                                                                                                                                                                                                                                 An upper ridge of high pressure built in across the Southern Plains during the first several days of July, before eventually sliding off to the east into the Mid-South and Lower Mississippi Valley. Meanwhile, a stationary front lingered from Southeast Oklahoma into extreme Southwest Arkansas and portions of North Louisiana, which aided in compressional heating and low level moisture pooling, with temperatures climbing into the upper 90s to in excess of 100 degrees. The moisture pooling resulted in minimal mixing of dewpoints, with attendant heat indices ranging from 110-115 degrees each afternoon on July 1st through the 4th. However, slightly cooler and drier air were able to mix into the area on the 5th, resulting in slightly lower heat indices.
## 3                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               A series of cold fronts the weekend of Nov. 16th lowered snow levels across the region, which brought moderate to heavy snow accumulations across some mountain zones.
## 4 A strong upper-level subtropical ridge/heat dome centered over central and southern Mexico strengthened and shifted northward towards the Rio Grande Valley and Deep South Texas ranchlands the week prior to Memorial Day. The strong ridge aided lower level temperatures at around five thousand feet to soar to between 78 and 86F, which translated to surface temperatures rising into the upper 90s to mid 100s on most days between May 21-25. With dewpoint temperatures well into the 70s to around 80, apparent temperatures (feels like temperatures) ranged anywhere between 111-116F across parts of Deep South Texas and the Rio Grande Valley with a few locales reaching higher than this. The hottest apparent temperatures were located along and east of IH-69C from Hidalgo and Brooks County to Cameron, Willacy, and Kenedy County - but all of Deep South Texas observed at least dangerous heat levels by local definition (111F or higher for at least two hours) on most days.||Actual temperatures during the period were even hotter than the peak of the summer heat (late July through mid August) for most areas.  The month would shatter all-time temperature records by 1 to more than 3 degrees.
## 5 A strong upper-level subtropical ridge/heat dome centered over central and southern Mexico strengthened and shifted northward towards the Rio Grande Valley and Deep South Texas ranchlands the week prior to Memorial Day. The strong ridge aided lower level temperatures at around five thousand feet to soar to between 78 and 86F, which translated to surface temperatures rising into the upper 90s to mid 100s on most days between May 21-25. With dewpoint temperatures well into the 70s to around 80, apparent temperatures (feels like temperatures) ranged anywhere between 111-116F across parts of Deep South Texas and the Rio Grande Valley with a few locales reaching higher than this. The hottest apparent temperatures were located along and east of IH-69C from Hidalgo and Brooks County to Cameron, Willacy, and Kenedy County - but all of Deep South Texas observed at least dangerous heat levels by local definition (111F or higher for at least two hours) on most days.||Actual temperatures during the period were even hotter than the peak of the summer heat (late July through mid August) for most areas.  The month would shatter all-time temperature records by 1 to more than 3 degrees.
## 6                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  An active storm pattern as several mid-level shortwaves crossed the region. An MCV lifted east northeast out of the Ozarks across southern Arkansas. The MCV fired up morning convection across the Mid-South with isolated storm coverage in the afternoon. A weak capped environment was broken and steep mid-level lapse rates, roughly 30 knots of shear, and plentiful instability allowed storms to flourish.
##                                                                                                                                                                                                                                                                                                                                                  EVENT_NARRATIVE
## 1                                                                                                                                                                                                                                                                                                                Frederick Municipal Airport (KFDR) observation.
## 2                                                                                                                                                                                                                                                                                                                                                               
## 3                                                                                                                                                                                                                                  The Hog Pass SNOTEL reported an estimated 12 inches of new snow fell in a 24 hour period ending at 0800 PST on November 18th.
## 4 Harlingen Valley International Airport (KHRL) recorded max heat indices between 111-114F for nearly four hours from 130 to 515 PM CDT on May 22, 2024. By proxy, and data from northern Kenedy (1 hour of 111 to 112 heat index during this window), it can be inferred that inland Willacy County had similar heat index values for a similar period of time.
## 5                                                                                                                                                                     By proxy, between locations in northern Kenedy and in northern Cameron County, Willacy County is assumed to have observed heat index values between 111 and 114F between 1 and 430 PM CDT.
## 6                                                                                                                                                                                                                                                                                                                               Reports of trees down in Algoma.
##   DATA_SOURCE
## 1         CSV
## 2         CSV
## 3         CSV
## 4         CSV
## 5         CSV
## 6         CSV
head(fatalities)
##   FAT_YEARMONTH FAT_DAY FAT_TIME FATALITY_ID EVENT_ID FATALITY_TYPE
## 1        202408      11        0       53724  1207220             D
## 2        202408       5        0       53725  1207865             I
## 3        202408       6        0       53726  1207865             I
## 4        202406      30        0       53169  1194107             D
## 5        202406       6        0       53180  1194997             D
## 6        202406      17        0       53181  1195001             D
##         FATALITY_DATE FATALITY_AGE FATALITY_SEX            FATALITY_LOCATION
## 1 08/11/2024 00:00:00           83            M                     In Water
## 2 08/05/2024 00:00:00           93            M                      Unknown
## 3 08/06/2024 00:00:00           63            F                      Unknown
## 4 06/30/2024 00:00:00           41            M                     In Water
## 5 06/06/2024 00:00:00           27            M Heavy Equipment/Construction
## 6 06/17/2024 00:00:00           16            M                     In Water
head(locations)
##   YEARMONTH EPISODE_ID EVENT_ID LOCATION_INDEX RANGE AZIMUTH          LOCATION
## 1    202407     194961  1205741              3  2.82       W TWENTY NINE PALMS
## 2    202407     194961  1205741              4  2.80       W TWENTY NINE PALMS
## 3    202407     194961  1205744              1  1.68     WNW TWENTY NINE PALMS
## 4    202407     194961  1205745              1  2.84     NNE           LENWOOD
## 5    202407     194961  1205745              2  2.92     NNE           LENWOOD
## 6    202407     194961  1205745              3  3.02     NNE           LENWOOD
##   LATITUDE LONGITUDE    LAT2    LON2
## 1  34.1359 -116.0988  348154 1165928
## 2  34.1338 -116.0987  348028 1165922
## 3  34.1429 -116.0749  348574 1164494
## 4  34.9059 -117.0957 3454354 1175742
## 5  34.9059 -117.0929 3454354 1175574
## 6  34.9078 -117.0932 3454468 1175592
# Join datasets using EVENT_ID
joined_data <- details %>%
  left_join(locations, by = "EVENT_ID") %>%
  left_join(fatalities,
            by = "EVENT_ID",
            relationship = "many-to-many")

# Check the combined dataset
head(joined_data)
##   BEGIN_YEARMONTH BEGIN_DAY BEGIN_TIME END_YEARMONTH END_DAY END_TIME
## 1          202404        30       2033        202404      30     2033
## 2          202407         1          0        202407       5      900
## 3          202411        16        230        202411      18     1421
## 4          202405        22       1230        202405      22     1615
## 5          202405        21       1200        202405      21     1530
## 6          202405        24       1405        202405      24     1410
##   EPISODE_ID.x EVENT_ID       STATE STATE_FIPS YEAR MONTH_NAME
## 1       189851  1174463    OKLAHOMA         40 2024      April
## 2       193486  1195301   LOUISIANA         22 2024       July
## 3       197838  1223377      OREGON         41 2024   November
## 4       191723  1184135       TEXAS         48 2024        May
## 5       191723  1184133       TEXAS         48 2024        May
## 6       191916  1182348 MISSISSIPPI         28 2024        May
##          EVENT_TYPE CZ_TYPE CZ_FIPS                            CZ_NAME WFO
## 1 Thunderstorm Wind       C     141                            TILLMAN OUN
## 2    Excessive Heat       Z      18                       NATCHITOCHES SHV
## 3        Heavy Snow       Z     509 EAST SLOPES OF THE OREGON CASCADES PDT
## 4              Heat       Z     254                            WILLACY BRO
## 5              Heat       Z     254                            WILLACY BRO
## 6 Thunderstorm Wind       C     115                           PONTOTOC MEG
##      BEGIN_DATE_TIME CZ_TIMEZONE      END_DATE_TIME INJURIES_DIRECT
## 1 30-APR-24 20:33:00       CST-6 30-APR-24 20:33:00               0
## 2 01-JUL-24 00:00:00       CST-6 05-JUL-24 09:00:00               0
## 3 16-NOV-24 02:30:00       PST-8 18-NOV-24 14:21:00               0
## 4 22-MAY-24 12:30:00       CST-6 22-MAY-24 16:15:00               0
## 5 21-MAY-24 12:00:00       CST-6 21-MAY-24 15:30:00               0
## 6 24-MAY-24 14:05:00       CST-6 24-MAY-24 14:10:00               0
##   INJURIES_INDIRECT DEATHS_DIRECT DEATHS_INDIRECT DAMAGE_PROPERTY DAMAGE_CROPS
## 1                 0             0               0                             
## 2                 0             0               0           0.00K        0.00K
## 3                 0             0               0           0.00K        0.00K
## 4                 0             0               0           0.00K        0.00K
## 5                 0             0               0           0.00K        0.00K
## 6                 0             0               0           1.00K        0.00K
##   SOURCE MAGNITUDE MAGNITUDE_TYPE FLOOD_CAUSE CATEGORY TOR_F_SCALE TOR_LENGTH
## 1   ASOS        55             MG                   NA                     NA
## 2   ASOS        NA                                  NA                     NA
## 3 SNOTEL        NA                                  NA                     NA
## 4   ASOS        NA                                  NA                     NA
## 5   ASOS        NA                                  NA                     NA
## 6 Public        52             EG                   NA                     NA
##   TOR_WIDTH TOR_OTHER_WFO TOR_OTHER_CZ_STATE TOR_OTHER_CZ_FIPS
## 1        NA                                                 NA
## 2        NA                                                 NA
## 3        NA                                                 NA
## 4        NA                                                 NA
## 5        NA                                                 NA
## 6        NA                                                 NA
##   TOR_OTHER_CZ_NAME BEGIN_RANGE BEGIN_AZIMUTH BEGIN_LOCATION END_RANGE
## 1                          0.42           SSW FREDERICK ARPT      0.42
## 2                            NA                                     NA
## 3                            NA                                     NA
## 4                            NA                                     NA
## 5                            NA                                     NA
## 6                          0.00             N         ALGOMA      0.00
##   END_AZIMUTH   END_LOCATION BEGIN_LAT BEGIN_LON END_LAT END_LON
## 1         SSW FREDERICK ARPT   34.3444   -98.983 34.3444 -98.983
## 2                                   NA        NA      NA      NA
## 3                                   NA        NA      NA      NA
## 4                                   NA        NA      NA      NA
## 5                                   NA        NA      NA      NA
## 6           N         ALGOMA   34.1800   -89.030 34.1800 -89.030
##                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      EPISODE_NARRATIVE
## 1                                                                                                                                                                                                                                                                                                                                                                              A rather nebulous upper air pattern existed across the Southern Plains on the 30th, with 30-40 knots of quasi-zonal flow at 500 mb. However, plentiful solar insolation/surface heating in the vicinity of a dryline fostered widely scattered thunderstorm development by the late afternoon. Strong instability and sufficient organizing wind shear lead to a few of these storms displaying supercellular characteristics and producing reports of large hail initially, owing to steep lapse rates and weak low-level shear (among other factors already mentioned). By the mid-evening, as low-level shear and storm-scale interactions began to increase, a few tornadoes occurred across portions of south-central into southwest Oklahoma. The most significant of these was an EF-1 tornado near the community of Hollister (Tillman County).
## 2                                                                                                                                                                                                                                                                                                                                                                                                                                                 An upper ridge of high pressure built in across the Southern Plains during the first several days of July, before eventually sliding off to the east into the Mid-South and Lower Mississippi Valley. Meanwhile, a stationary front lingered from Southeast Oklahoma into extreme Southwest Arkansas and portions of North Louisiana, which aided in compressional heating and low level moisture pooling, with temperatures climbing into the upper 90s to in excess of 100 degrees. The moisture pooling resulted in minimal mixing of dewpoints, with attendant heat indices ranging from 110-115 degrees each afternoon on July 1st through the 4th. However, slightly cooler and drier air were able to mix into the area on the 5th, resulting in slightly lower heat indices.
## 3                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               A series of cold fronts the weekend of Nov. 16th lowered snow levels across the region, which brought moderate to heavy snow accumulations across some mountain zones.
## 4 A strong upper-level subtropical ridge/heat dome centered over central and southern Mexico strengthened and shifted northward towards the Rio Grande Valley and Deep South Texas ranchlands the week prior to Memorial Day. The strong ridge aided lower level temperatures at around five thousand feet to soar to between 78 and 86F, which translated to surface temperatures rising into the upper 90s to mid 100s on most days between May 21-25. With dewpoint temperatures well into the 70s to around 80, apparent temperatures (feels like temperatures) ranged anywhere between 111-116F across parts of Deep South Texas and the Rio Grande Valley with a few locales reaching higher than this. The hottest apparent temperatures were located along and east of IH-69C from Hidalgo and Brooks County to Cameron, Willacy, and Kenedy County - but all of Deep South Texas observed at least dangerous heat levels by local definition (111F or higher for at least two hours) on most days.||Actual temperatures during the period were even hotter than the peak of the summer heat (late July through mid August) for most areas.  The month would shatter all-time temperature records by 1 to more than 3 degrees.
## 5 A strong upper-level subtropical ridge/heat dome centered over central and southern Mexico strengthened and shifted northward towards the Rio Grande Valley and Deep South Texas ranchlands the week prior to Memorial Day. The strong ridge aided lower level temperatures at around five thousand feet to soar to between 78 and 86F, which translated to surface temperatures rising into the upper 90s to mid 100s on most days between May 21-25. With dewpoint temperatures well into the 70s to around 80, apparent temperatures (feels like temperatures) ranged anywhere between 111-116F across parts of Deep South Texas and the Rio Grande Valley with a few locales reaching higher than this. The hottest apparent temperatures were located along and east of IH-69C from Hidalgo and Brooks County to Cameron, Willacy, and Kenedy County - but all of Deep South Texas observed at least dangerous heat levels by local definition (111F or higher for at least two hours) on most days.||Actual temperatures during the period were even hotter than the peak of the summer heat (late July through mid August) for most areas.  The month would shatter all-time temperature records by 1 to more than 3 degrees.
## 6                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  An active storm pattern as several mid-level shortwaves crossed the region. An MCV lifted east northeast out of the Ozarks across southern Arkansas. The MCV fired up morning convection across the Mid-South with isolated storm coverage in the afternoon. A weak capped environment was broken and steep mid-level lapse rates, roughly 30 knots of shear, and plentiful instability allowed storms to flourish.
##                                                                                                                                                                                                                                                                                                                                                  EVENT_NARRATIVE
## 1                                                                                                                                                                                                                                                                                                                Frederick Municipal Airport (KFDR) observation.
## 2                                                                                                                                                                                                                                                                                                                                                               
## 3                                                                                                                                                                                                                                  The Hog Pass SNOTEL reported an estimated 12 inches of new snow fell in a 24 hour period ending at 0800 PST on November 18th.
## 4 Harlingen Valley International Airport (KHRL) recorded max heat indices between 111-114F for nearly four hours from 130 to 515 PM CDT on May 22, 2024. By proxy, and data from northern Kenedy (1 hour of 111 to 112 heat index during this window), it can be inferred that inland Willacy County had similar heat index values for a similar period of time.
## 5                                                                                                                                                                     By proxy, between locations in northern Kenedy and in northern Cameron County, Willacy County is assumed to have observed heat index values between 111 and 114F between 1 and 430 PM CDT.
## 6                                                                                                                                                                                                                                                                                                                               Reports of trees down in Algoma.
##   DATA_SOURCE YEARMONTH EPISODE_ID.y LOCATION_INDEX RANGE AZIMUTH LOCATION
## 1         CSV        NA           NA             NA    NA    <NA>     <NA>
## 2         CSV        NA           NA             NA    NA    <NA>     <NA>
## 3         CSV        NA           NA             NA    NA    <NA>     <NA>
## 4         CSV        NA           NA             NA    NA    <NA>     <NA>
## 5         CSV        NA           NA             NA    NA    <NA>     <NA>
## 6         CSV        NA           NA             NA    NA    <NA>     <NA>
##   LATITUDE LONGITUDE LAT2 LON2 FAT_YEARMONTH FAT_DAY FAT_TIME FATALITY_ID
## 1       NA        NA   NA   NA            NA      NA       NA          NA
## 2       NA        NA   NA   NA            NA      NA       NA          NA
## 3       NA        NA   NA   NA            NA      NA       NA          NA
## 4       NA        NA   NA   NA            NA      NA       NA          NA
## 5       NA        NA   NA   NA            NA      NA       NA          NA
## 6       NA        NA   NA   NA            NA      NA       NA          NA
##   FATALITY_TYPE FATALITY_DATE FATALITY_AGE FATALITY_SEX FATALITY_LOCATION
## 1          <NA>          <NA>           NA         <NA>              <NA>
## 2          <NA>          <NA>           NA         <NA>              <NA>
## 3          <NA>          <NA>           NA         <NA>              <NA>
## 4          <NA>          <NA>           NA         <NA>              <NA>
## 5          <NA>          <NA>           NA         <NA>              <NA>
## 6          <NA>          <NA>           NA         <NA>              <NA>
# Check the dimensions of the combined dataset
dim(joined_data)
## [1] 86556    70
# Display the number of rows and columns
print(dim(joined_data))
## [1] 86556    70
# Count unique storm events in original details file
print(n_distinct(details$EVENT_ID))
## [1] 69801
# Count unique storm events in the combined dataset
print(n_distinct(joined_data$EVENT_ID))
## [1] 69801
# Display the column names
print(names(joined_data))
##  [1] "BEGIN_YEARMONTH"    "BEGIN_DAY"          "BEGIN_TIME"        
##  [4] "END_YEARMONTH"      "END_DAY"            "END_TIME"          
##  [7] "EPISODE_ID.x"       "EVENT_ID"           "STATE"             
## [10] "STATE_FIPS"         "YEAR"               "MONTH_NAME"        
## [13] "EVENT_TYPE"         "CZ_TYPE"            "CZ_FIPS"           
## [16] "CZ_NAME"            "WFO"                "BEGIN_DATE_TIME"   
## [19] "CZ_TIMEZONE"        "END_DATE_TIME"      "INJURIES_DIRECT"   
## [22] "INJURIES_INDIRECT"  "DEATHS_DIRECT"      "DEATHS_INDIRECT"   
## [25] "DAMAGE_PROPERTY"    "DAMAGE_CROPS"       "SOURCE"            
## [28] "MAGNITUDE"          "MAGNITUDE_TYPE"     "FLOOD_CAUSE"       
## [31] "CATEGORY"           "TOR_F_SCALE"        "TOR_LENGTH"        
## [34] "TOR_WIDTH"          "TOR_OTHER_WFO"      "TOR_OTHER_CZ_STATE"
## [37] "TOR_OTHER_CZ_FIPS"  "TOR_OTHER_CZ_NAME"  "BEGIN_RANGE"       
## [40] "BEGIN_AZIMUTH"      "BEGIN_LOCATION"     "END_RANGE"         
## [43] "END_AZIMUTH"        "END_LOCATION"       "BEGIN_LAT"         
## [46] "BEGIN_LON"          "END_LAT"            "END_LON"           
## [49] "EPISODE_NARRATIVE"  "EVENT_NARRATIVE"    "DATA_SOURCE"       
## [52] "YEARMONTH"          "EPISODE_ID.y"       "LOCATION_INDEX"    
## [55] "RANGE"              "AZIMUTH"            "LOCATION"          
## [58] "LATITUDE"           "LONGITUDE"          "LAT2"              
## [61] "LON2"               "FAT_YEARMONTH"      "FAT_DAY"           
## [64] "FAT_TIME"           "FATALITY_ID"        "FATALITY_TYPE"     
## [67] "FATALITY_DATE"      "FATALITY_AGE"       "FATALITY_SEX"      
## [70] "FATALITY_LOCATION"
# Count the number of different event types in the combined dataset
length(unique(details$EVENT_TYPE))
## [1] 50
# Display the 15 most common event types of the combined dataset
sort(table(details$EVENT_TYPE), decreasing = TRUE)[1:15]
## 
##        Thunderstorm Wind                     Hail              Flash Flood 
##                    19940                     8941                     4661 
##                High Wind           Winter Weather                  Drought 
##                     3994                     3557                     3473 
##                     Heat           Excessive Heat                    Flood 
##                     3171                     2660                     2472 
##               Heavy Snow Marine Thunderstorm Wind                  Tornado 
##                     2210                     2192                     2137 
##             Winter Storm              Strong Wind               Heavy Rain 
##                     2112                     1311                      918
# Check for missing values in important columns
colSums(is.na(details[, c("EVENT_TYPE", "STATE", "MONTH_NAME",
                          "INJURIES_DIRECT", "INJURIES_INDIRECT",
                          "DEATHS_DIRECT", "DEATHS_INDIRECT")]))
##        EVENT_TYPE             STATE        MONTH_NAME   INJURIES_DIRECT 
##                 0                 0                 0                 0 
## INJURIES_INDIRECT     DEATHS_DIRECT   DEATHS_INDIRECT 
##                 0                 0                 0

Results

Research Question 1: Which storm events are most harmful to population health?

To examine the effects of storms on population health, total injuries and deaths were calculated for each event type, including both direct and indirect injuries and fatalities.

In 2024, tornadoes caused the greatest number of injuries with 658 reported. Heat and thunderstorm wind followed, with 173 and 161 injuries.

With 253 fatalities, excessive heat caused the most deaths followed by heat with 219 deaths. Another significant cause of fatalities were flash floods with 117 deaths.

The results suggest that different types of storms create different risks. Tornadoes were particularly harmful in terms of injuries, while excessive heat and heat-related events were leading the causes of fatalities.

# Calculate total injuries and deaths for each event type
health_impact <- details %>%
  group_by(EVENT_TYPE) %>%
  summarize(
    Total_Injuries = sum(INJURIES_DIRECT + INJURIES_INDIRECT),
    Total_Deaths = sum(DEATHS_DIRECT + DEATHS_INDIRECT)
  )

# Display the top 10 event types by injuries
health_impact %>%
  arrange(desc(Total_Injuries)) %>%
  slice_head(n = 10)
## # A tibble: 10 × 3
##    EVENT_TYPE          Total_Injuries Total_Deaths
##    <chr>                        <int>        <int>
##  1 Tornado                        658           53
##  2 Heat                           173          219
##  3 Thunderstorm Wind              161           53
##  4 Excessive Heat                 100          253
##  5 Winter Weather                  87           25
##  6 Hurricane (Typhoon)             85           17
##  7 Dust Storm                      74            1
##  8 Dense Fog                       65           18
##  9 Ice Storm                       58            7
## 10 Wildfire                        57           10
# Display the top 10 event types by deaths
health_impact %>%
  arrange(desc(Total_Deaths)) %>%
  slice_head(n = 10)
## # A tibble: 10 × 3
##    EVENT_TYPE        Total_Injuries Total_Deaths
##    <chr>                      <int>        <int>
##  1 Excessive Heat               100          253
##  2 Heat                         173          219
##  3 Flash Flood                   19          117
##  4 Tropical Storm                12           78
##  5 Rip Current                   42           65
##  6 Thunderstorm Wind            161           53
##  7 Tornado                      658           53
##  8 Cold/Wind Chill                0           39
##  9 Flood                          0           35
## 10 Winter Weather                87           25

Figure 1: Top 10 Storm Events Causing Injuries

injury_plot <- health_impact %>%
  arrange(desc(Total_Injuries)) %>%
  slice_head(n = 10) %>%
  ggplot(aes(x = reorder(EVENT_TYPE, Total_Injuries),
             y = Total_Injuries)) +
  geom_col(fill = "steelblue") +
  geom_text(aes(label = Total_Injuries), hjust = -0.3) +
  coord_flip(clip = "off") +
  scale_y_continuous(expand = expansion(mult = c(0, 0.12))) +
  labs(
    title = "Top 10 Storm Events Causing Injuries",
    x = "Storm Event Type",
    y = "Total Injuries",
    caption = "Source: NOAA Storm Events Database, 2024"
  ) +
  theme_minimal()

print(injury_plot)
Figure 1. The ten storm event types with the highest total number of reported injuries in 2024.

Figure 1. The ten storm event types with the highest total number of reported injuries in 2024.

Figure 2: Top 10 Storm Events Causing Deaths

death_plot <- health_impact %>%
  arrange(desc(Total_Deaths)) %>%
  slice_head(n = 10) %>%
  ggplot(aes(x = reorder(EVENT_TYPE, Total_Deaths),
             y = Total_Deaths)) +
  geom_col(fill = "firebrick") +
  geom_text(aes(label = Total_Deaths), hjust = -0.3) +
  coord_flip(clip = "off") +
  scale_y_continuous(expand = expansion(mult = c(0, 0.12))) +
  labs(
    title = "Top 10 Storm Events Causing Deaths",
    x = "Storm Event Type",
    y = "Total Deaths",
    caption = "Source: NOAA Storm Events Database, 2024"
  ) +
  theme_minimal()

print(death_plot)
Figure 2. The ten storm event types with the highest total number of reported deaths in 2024.

Figure 2. The ten storm event types with the highest total number of reported deaths in 2024.

Research Question 2: Which storm event types happen most often in which states?

To examine storm events geographically, the number of reported events was calculated for each combination of state and event type. The most frequently reported event type was then identified for each state.

Thunderstorm wind was a leader in total events and exhibited the most in New York, Kansas, Georgia, Texas, and Pennsylvania. Hail was another leader of total events, and Texas, Kansas, Oklahoma, Nebraska, and Missouri exhibited the most. And for leading total events in Winter Weather, the most were reported in New York, Colorado, West Virginia, South Dakota, and Wisconsin.

These results demonstrate that storm patterns vary geographically. Some states experience more frequent thunderstorms, while others are more affected by winter weather, hail, or other regional hazards.

# Count storm events by state and event type
state_events <- details %>%
  group_by(STATE, EVENT_TYPE) %>%
  summarize(
    Total_Events = n(),
    .groups = "drop"
  )

# Find the most common event type in each state
state_events %>%
  group_by(STATE) %>%
  slice_max(Total_Events, n = 1) %>%
  arrange(STATE)
## # A tibble: 70 × 3
## # Groups:   STATE [68]
##    STATE          EVENT_TYPE               Total_Events
##    <chr>          <chr>                           <int>
##  1 ALABAMA        Thunderstorm Wind                 569
##  2 ALASKA         Blizzard                           85
##  3 AMERICAN SAMOA Flash Flood                         6
##  4 AMERICAN SAMOA Heavy Rain                          6
##  5 AMERICAN SAMOA Thunderstorm Wind                   6
##  6 ARIZONA        Thunderstorm Wind                 174
##  7 ARKANSAS       Thunderstorm Wind                 329
##  8 ATLANTIC NORTH Marine Thunderstorm Wind          652
##  9 ATLANTIC SOUTH Marine Thunderstorm Wind          486
## 10 CALIFORNIA     High Wind                         583
## # ℹ 60 more rows
top_state_events <- state_events %>%
  group_by(STATE) %>%
  slice_max(Total_Events, n = 1) %>%
  arrange(STATE)

# Find the top 20 states by total number of events
top_20_states <- state_events %>%
  group_by(STATE) %>%
  summarize(Total_State_Events = sum(Total_Events), .groups = "drop") %>%
  arrange(desc(Total_State_Events)) %>%
  slice_head(n = 20)

# Find the most common event type for each of the top 20 states
top_state_events <- state_events %>%
  filter(STATE %in% top_20_states$STATE) %>%
  group_by(STATE) %>%
  slice_max(Total_Events, n = 1) %>%
  arrange(desc(Total_Events))

# View the results
print(top_state_events, n = 20)
## # A tibble: 20 × 3
## # Groups:   STATE [20]
##    STATE          EVENT_TYPE        Total_Events
##    <chr>          <chr>                    <int>
##  1 TEXAS          Hail                      1588
##  2 KANSAS         Thunderstorm Wind         1043
##  3 NEW YORK       Thunderstorm Wind         1021
##  4 GEORGIA        Thunderstorm Wind         1002
##  5 PENNSYLVANIA   Thunderstorm Wind          971
##  6 ILLINOIS       Thunderstorm Wind          959
##  7 OKLAHOMA       Heat                       912
##  8 KENTUCKY       Thunderstorm Wind          818
##  9 VIRGINIA       Thunderstorm Wind          732
## 10 MISSOURI       Thunderstorm Wind          723
## 11 NORTH CAROLINA Thunderstorm Wind          696
## 12 IOWA           Thunderstorm Wind          659
## 13 OHIO           Thunderstorm Wind          639
## 14 NEBRASKA       Thunderstorm Wind          599
## 15 CALIFORNIA     High Wind                  583
## 16 TENNESSEE      Thunderstorm Wind          504
## 17 SOUTH DAKOTA   Thunderstorm Wind          501
## 18 WEST VIRGINIA  Thunderstorm Wind          481
## 19 COLORADO       Heavy Snow                 439
## 20 MINNESOTA      Thunderstorm Wind          363
# Find the top 5 states for each event type
top_5_states_by_event <- state_events %>%
  group_by(EVENT_TYPE) %>%
  slice_max(Total_Events, n = 5) %>%
  arrange(EVENT_TYPE, desc(Total_Events))

# Print the results
print(top_5_states_by_event, n = Inf)
## # A tibble: 222 × 3
## # Groups:   EVENT_TYPE [50]
##     STATE          EVENT_TYPE                 Total_Events
##     <chr>          <chr>                             <int>
##   1 LOUISIANA      Astronomical Low Tide                 8
##   2 DELAWARE       Astronomical Low Tide                 2
##   3 TEXAS          Astronomical Low Tide                 2
##   4 ALABAMA        Astronomical Low Tide                 1
##   5 CONNECTICUT    Astronomical Low Tide                 1
##   6 NEW JERSEY     Astronomical Low Tide                 1
##   7 NEW YORK       Astronomical Low Tide                 1
##   8 TENNESSEE      Astronomical Low Tide                 1
##   9 UTAH           Avalanche                            10
##  10 IDAHO          Avalanche                             6
##  11 COLORADO       Avalanche                             4
##  12 WYOMING        Avalanche                             2
##  13 ALASKA         Avalanche                             1
##  14 NEVADA         Avalanche                             1
##  15 VIRGINIA       Avalanche                             1
##  16 WASHINGTON     Avalanche                             1
##  17 ALASKA         Blizzard                             85
##  18 IOWA           Blizzard                             64
##  19 NEBRASKA       Blizzard                             38
##  20 KANSAS         Blizzard                             29
##  21 NORTH DAKOTA   Blizzard                             25
##  22 NEW JERSEY     Coastal Flood                        77
##  23 MARYLAND       Coastal Flood                        51
##  24 VIRGINIA       Coastal Flood                        30
##  25 NEW YORK       Coastal Flood                        24
##  26 MAINE          Coastal Flood                        22
##  27 TEXAS          Cold/Wind Chill                     122
##  28 ILLINOIS       Cold/Wind Chill                      78
##  29 OKLAHOMA       Cold/Wind Chill                      78
##  30 MISSOURI       Cold/Wind Chill                      46
##  31 WISCONSIN      Cold/Wind Chill                      46
##  32 PUERTO RICO    Debris Flow                          78
##  33 CALIFORNIA     Debris Flow                          37
##  34 COLORADO       Debris Flow                          33
##  35 NEW MEXICO     Debris Flow                           6
##  36 IDAHO          Debris Flow                           4
##  37 CALIFORNIA     Dense Fog                           226
##  38 KENTUCKY       Dense Fog                           135
##  39 ILLINOIS       Dense Fog                           132
##  40 MISSOURI       Dense Fog                            96
##  41 NEW JERSEY     Dense Fog                            68
##  42 TEXAS          Drought                             449
##  43 NEW MEXICO     Drought                             375
##  44 IOWA           Drought                             299
##  45 TENNESSEE      Drought                             244
##  46 WEST VIRGINIA  Drought                             210
##  47 NEVADA         Dust Devil                            3
##  48 ARIZONA        Dust Devil                            1
##  49 CALIFORNIA     Dust Devil                            1
##  50 GUAM           Dust Devil                            1
##  51 OREGON         Dust Devil                            1
##  52 ARIZONA        Dust Storm                           28
##  53 NEW MEXICO     Dust Storm                           15
##  54 KANSAS         Dust Storm                           13
##  55 ILLINOIS       Dust Storm                            8
##  56 CALIFORNIA     Dust Storm                            7
##  57 OKLAHOMA       Excessive Heat                      567
##  58 TEXAS          Excessive Heat                      336
##  59 CALIFORNIA     Excessive Heat                      186
##  60 MISSISSIPPI    Excessive Heat                      163
##  61 PUERTO RICO    Excessive Heat                      158
##  62 NEBRASKA       Extreme Cold/Wind Chill             101
##  63 IOWA           Extreme Cold/Wind Chill              81
##  64 SOUTH DAKOTA   Extreme Cold/Wind Chill              78
##  65 INDIANA        Extreme Cold/Wind Chill              58
##  66 WYOMING        Extreme Cold/Wind Chill              53
##  67 TEXAS          Flash Flood                         539
##  68 NORTH CAROLINA Flash Flood                         367
##  69 VIRGINIA       Flash Flood                         281
##  70 LOUISIANA      Flash Flood                         244
##  71 GEORGIA        Flash Flood                         231
##  72 CALIFORNIA     Flood                               414
##  73 PUERTO RICO    Flood                               207
##  74 IOWA           Flood                               185
##  75 VIRGINIA       Flood                               169
##  76 MISSOURI       Flood                               130
##  77 ARKANSAS       Freezing Fog                          1
##  78 CALIFORNIA     Freezing Fog                          1
##  79 IDAHO          Freezing Fog                          1
##  80 MINNESOTA      Freezing Fog                          1
##  81 WASHINGTON     Freezing Fog                          1
##  82 CALIFORNIA     Frost/Freeze                         70
##  83 OREGON         Frost/Freeze                         61
##  84 TEXAS          Frost/Freeze                         47
##  85 KENTUCKY       Frost/Freeze                         46
##  86 ILLINOIS       Frost/Freeze                         43
##  87 IOWA           Funnel Cloud                         52
##  88 FLORIDA        Funnel Cloud                         34
##  89 NEBRASKA       Funnel Cloud                         26
##  90 NORTH DAKOTA   Funnel Cloud                         20
##  91 TEXAS          Funnel Cloud                         17
##  92 TEXAS          Hail                               1588
##  93 KANSAS         Hail                                767
##  94 OKLAHOMA       Hail                                765
##  95 NEBRASKA       Hail                                510
##  96 MISSOURI       Hail                                496
##  97 OKLAHOMA       Heat                                912
##  98 TEXAS          Heat                                828
##  99 MISSISSIPPI    Heat                                195
## 100 TENNESSEE      Heat                                146
## 101 NEW YORK       Heat                                132
## 102 VIRGINIA       Heavy Rain                          150
## 103 MISSOURI       Heavy Rain                          106
## 104 CALIFORNIA     Heavy Rain                          104
## 105 IOWA           Heavy Rain                          104
## 106 FLORIDA        Heavy Rain                           94
## 107 COLORADO       Heavy Snow                          439
## 108 CALIFORNIA     Heavy Snow                          275
## 109 NEVADA         Heavy Snow                          103
## 110 NEW MEXICO     Heavy Snow                           95
## 111 WASHINGTON     Heavy Snow                           90
## 112 HAWAII         High Surf                            77
## 113 CALIFORNIA     High Surf                            13
## 114 OREGON         High Surf                            11
## 115 PUERTO RICO    High Surf                             4
## 116 AMERICAN SAMOA High Surf                             3
## 117 CALIFORNIA     High Wind                           583
## 118 MONTANA        High Wind                           435
## 119 TEXAS          High Wind                           318
## 120 WYOMING        High Wind                           271
## 121 NEVADA         High Wind                           245
## 122 FLORIDA        Hurricane (Typhoon)                  40
## 123 GEORGIA        Hurricane (Typhoon)                  29
## 124 LOUISIANA      Hurricane (Typhoon)                   7
## 125 IOWA           Ice Storm                            30
## 126 OREGON         Ice Storm                            20
## 127 WASHINGTON     Ice Storm                            20
## 128 ILLINOIS       Ice Storm                            11
## 129 TEXAS          Ice Storm                            11
## 130 NEW YORK       Lake-Effect Snow                     57
## 131 PENNSYLVANIA   Lake-Effect Snow                     32
## 132 OHIO           Lake-Effect Snow                     20
## 133 INDIANA        Lake-Effect Snow                      9
## 134 MICHIGAN       Lake-Effect Snow                      6
## 135 NEW YORK       Lakeshore Flood                       1
## 136 FLORIDA        Lightning                            23
## 137 TEXAS          Lightning                            18
## 138 TENNESSEE      Lightning                            14
## 139 GEORGIA        Lightning                             9
## 140 MISSISSIPPI    Lightning                             9
## 141 SOUTH CAROLINA Lightning                             9
## 142 LAKE ERIE      Marine Dense Fog                      2
## 143 ATLANTIC SOUTH Marine Hail                           9
## 144 LAKE ERIE      Marine Hail                           4
## 145 LAKE MICHIGAN  Marine Hail                           4
## 146 LAKE SUPERIOR  Marine Hail                           4
## 147 ATLANTIC NORTH Marine Hail                           1
## 148 LAKE SUPERIOR  Marine High Wind                     32
## 149 ATLANTIC NORTH Marine High Wind                     16
## 150 LAKE MICHIGAN  Marine High Wind                     14
## 151 ATLANTIC SOUTH Marine High Wind                      1
## 152 LAKE ERIE      Marine High Wind                      1
## 153 GULF OF MEXICO Marine Hurricane/Typhoon             10
## 154 ATLANTIC SOUTH Marine Hurricane/Typhoon              1
## 155 GUAM WATERS    Marine Strong Wind                    1
## 156 GULF OF MEXICO Marine Strong Wind                    1
## 157 LAKE ERIE      Marine Strong Wind                    1
## 158 GULF OF MEXICO Marine Thunderstorm Wind            728
## 159 ATLANTIC NORTH Marine Thunderstorm Wind            652
## 160 ATLANTIC SOUTH Marine Thunderstorm Wind            486
## 161 LAKE MICHIGAN  Marine Thunderstorm Wind            117
## 162 LAKE ERIE      Marine Thunderstorm Wind             92
## 163 ATLANTIC SOUTH Marine Tropical Depression            1
## 164 GULF OF MEXICO Marine Tropical Storm                45
## 165 ATLANTIC SOUTH Marine Tropical Storm                29
## 166 FLORIDA        Rip Current                          18
## 167 PUERTO RICO    Rip Current                          16
## 168 GUAM           Rip Current                           8
## 169 SOUTH CAROLINA Rip Current                           7
## 170 NORTH CAROLINA Rip Current                           6
## 171 ILLINOIS       Seiche                                2
## 172 INDIANA        Seiche                                1
## 173 ALABAMA        Sleet                                 6
## 174 OREGON         Sneakerwave                          12
## 175 CALIFORNIA     Sneakerwave                           3
## 176 LOUISIANA      Storm Surge/Tide                     32
## 177 FLORIDA        Storm Surge/Tide                     28
## 178 MISSISSIPPI    Storm Surge/Tide                      6
## 179 TEXAS          Storm Surge/Tide                      5
## 180 WEST VIRGINIA  Strong Wind                         187
## 181 SOUTH CAROLINA Strong Wind                         112
## 182 SOUTH DAKOTA   Strong Wind                         105
## 183 KENTUCKY       Strong Wind                          96
## 184 NEW YORK       Strong Wind                          87
## 185 KANSAS         Thunderstorm Wind                  1043
## 186 NEW YORK       Thunderstorm Wind                  1021
## 187 GEORGIA        Thunderstorm Wind                  1002
## 188 TEXAS          Thunderstorm Wind                   988
## 189 PENNSYLVANIA   Thunderstorm Wind                   971
## 190 OKLAHOMA       Tornado                             178
## 191 ILLINOIS       Tornado                             174
## 192 IOWA           Tornado                             155
## 193 TEXAS          Tornado                             149
## 194 FLORIDA        Tornado                             132
## 195 FLORIDA        Tropical Depression                  29
## 196 ALABAMA        Tropical Depression                   4
## 197 GUAM           Tropical Depression                   3
## 198 FLORIDA        Tropical Storm                      187
## 199 GEORGIA        Tropical Storm                      169
## 200 SOUTH CAROLINA Tropical Storm                       59
## 201 NORTH CAROLINA Tropical Storm                       35
## 202 LOUISIANA      Tropical Storm                       32
## 203 GULF OF MEXICO Waterspout                           93
## 204 ATLANTIC SOUTH Waterspout                           55
## 205 LAKE MICHIGAN  Waterspout                           19
## 206 LAKE ERIE      Waterspout                           11
## 207 E PACIFIC      Waterspout                            5
## 208 CALIFORNIA     Wildfire                             56
## 209 OKLAHOMA       Wildfire                             41
## 210 TEXAS          Wildfire                             37
## 211 OREGON         Wildfire                             28
## 212 COLORADO       Wildfire                             27
## 213 IOWA           Winter Storm                        175
## 214 MICHIGAN       Winter Storm                        156
## 215 WISCONSIN      Winter Storm                        144
## 216 NEBRASKA       Winter Storm                        138
## 217 WYOMING        Winter Storm                        103
## 218 NEW YORK       Winter Weather                      283
## 219 COLORADO       Winter Weather                      273
## 220 WEST VIRGINIA  Winter Weather                      194
## 221 SOUTH DAKOTA   Winter Weather                      185
## 222 WISCONSIN      Winter Weather                      176
# Find the top 5 most common event types overall
top_5_events <- state_events %>%
  group_by(EVENT_TYPE) %>%
  summarize(Total_Events = sum(Total_Events), .groups = "drop") %>%
  arrange(desc(Total_Events)) %>%
  slice_head(n = 5)

# Find the top 5 states for each of the top 5 event types
top_5_states_top_events <- state_events %>%
  filter(EVENT_TYPE %in% top_5_events$EVENT_TYPE) %>%
  group_by(EVENT_TYPE) %>%
  slice_max(Total_Events, n = 5) %>%
  arrange(EVENT_TYPE, desc(Total_Events))

# Print the results
print(top_5_states_top_events, n = Inf)
## # A tibble: 25 × 3
## # Groups:   EVENT_TYPE [5]
##    STATE          EVENT_TYPE        Total_Events
##    <chr>          <chr>                    <int>
##  1 TEXAS          Flash Flood                539
##  2 NORTH CAROLINA Flash Flood                367
##  3 VIRGINIA       Flash Flood                281
##  4 LOUISIANA      Flash Flood                244
##  5 GEORGIA        Flash Flood                231
##  6 TEXAS          Hail                      1588
##  7 KANSAS         Hail                       767
##  8 OKLAHOMA       Hail                       765
##  9 NEBRASKA       Hail                       510
## 10 MISSOURI       Hail                       496
## 11 CALIFORNIA     High Wind                  583
## 12 MONTANA        High Wind                  435
## 13 TEXAS          High Wind                  318
## 14 WYOMING        High Wind                  271
## 15 NEVADA         High Wind                  245
## 16 KANSAS         Thunderstorm Wind         1043
## 17 NEW YORK       Thunderstorm Wind         1021
## 18 GEORGIA        Thunderstorm Wind         1002
## 19 TEXAS          Thunderstorm Wind          988
## 20 PENNSYLVANIA   Thunderstorm Wind          971
## 21 NEW YORK       Winter Weather             283
## 22 COLORADO       Winter Weather             273
## 23 WEST VIRGINIA  Winter Weather             194
## 24 SOUTH DAKOTA   Winter Weather             185
## 25 WISCONSIN      Winter Weather             176

Research Question 3: Which storm event types characterize different months?

To examine seasonal patterns, the number of storm events was calculated for each month and event type. The most frequently reported event type for each month was also identified.

Winter weather was the most common event type in January, February, and December. Thunderstorm wind was the leading event type from April through September. Hail was the most common event type in March, while drought was most frequently reported in October and November.

The results show that storm activity changes throughout the year. Unsurprisingly, winter weather is more common during colder months, while thunderstorms and hail are more frequent during the warmer months. These patterns can help communities prepare for the types of severe weather they are more likely to experience during different seasons.

# Count storm events by month and event type
monthly_events <- details %>%
  group_by(MONTH_NAME, EVENT_TYPE) %>%
  summarize(Total_Events = n(), .groups = "drop")

# Find the most common event type in each month
monthly_events %>%
  group_by(MONTH_NAME) %>%
  slice_max(Total_Events, n = 1) %>%
  arrange(match(MONTH_NAME, month.name))
## # A tibble: 12 × 3
## # Groups:   MONTH_NAME [12]
##    MONTH_NAME EVENT_TYPE        Total_Events
##    <chr>      <chr>                    <int>
##  1 January    Winter Weather            1584
##  2 February   Winter Weather             625
##  3 March      Hail                       847
##  4 April      Thunderstorm Wind         1441
##  5 May        Thunderstorm Wind         4638
##  6 June       Thunderstorm Wind         3895
##  7 July       Thunderstorm Wind         4162
##  8 August     Thunderstorm Wind         3126
##  9 September  Thunderstorm Wind          666
## 10 October    Drought                    522
## 11 November   Drought                    648
## 12 December   Winter Weather             584

Figure 3: Monthly Patterns in the Five Most Common Storm Events

# Identify the five most common event types overall
top_monthly_types <- details %>%
  count(EVENT_TYPE, sort = TRUE) %>%
  slice_head(n = 5) %>%
  pull(EVENT_TYPE)

# Count monthly events for those five event types
monthly_plot_data <- details %>%
  filter(EVENT_TYPE %in% top_monthly_types) %>%
  group_by(MONTH_NAME, EVENT_TYPE) %>%
  summarize(Total_Events = n(), .groups = "drop") %>%
  mutate(Month_Number = match(MONTH_NAME, month.name))

# Create a line chart
monthly_plot <- ggplot(monthly_plot_data,
                       aes(x = Month_Number,
                           y = Total_Events,
                           color = EVENT_TYPE,
                           group = EVENT_TYPE)) +
  geom_line(linewidth = 1) +
  geom_point(size = 2) +
  scale_x_continuous(
    breaks = 1:12,
    labels = month.abb
  ) +
  labs(
    title = "Monthly Patterns in the Five Most Common Storm Events",
    x = "Month",
    y = "Number of Events",
    color = "Event Type",
    caption = "Source: NOAA Storm Events Database, 2024"
  ) +
  theme_minimal()

print(monthly_plot)
Figure 3. Monthly frequency of the five most commonly reported storm event types in 2024.

Figure 3. Monthly frequency of the five most commonly reported storm event types in 2024.

Original Research Question: Which storm events cause the greatest economic damage?

Lastly, we examined the economic effects of different events, both property and crop damage were included in this analysis.

The original damage variables were recorded as text, with suffixes representing thousands (K), millions (M), and billions (B) of dollars. These values were converted into numerical dollar amounts so that total economic damage could be calculated and properly compared.

In 2024, the results show that hurricanes caused the greatest economic damage, with approximately $6.81 billion in combined property and crop damage. Flash floods followed with about $3.24 billion, while tropical storms caused around $2.16 billion.

These findings demonstrate that certain storm events can have higher financial consequences. Hurricanes, floods, and tropical storms were especially costly, highlighting the importance of preparation and disaster planning to help reduce property and crop losses.

# Convert property and crop damage into dollar amounts
convert_damage <- function(x) {
  x[x == ""] <- "0"
  multiplier <- ifelse(grepl("K$", x), 1000,
                ifelse(grepl("M$", x), 1000000,
                ifelse(grepl("B$", x), 1000000000, 1)))
  as.numeric(gsub("[KMB]", "", x)) * multiplier
}

# Create numeric damage columns
details$Property_Damage <- convert_damage(details$DAMAGE_PROPERTY)
details$Crop_Damage <- convert_damage(details$DAMAGE_CROPS)

# Calculate total damage by event type
economic_impact <- details %>%
  group_by(EVENT_TYPE) %>%
  summarize(
    Total_Property_Damage = sum(Property_Damage),
    Total_Crop_Damage = sum(Crop_Damage),
    Total_Economic_Damage = sum(Property_Damage + Crop_Damage)
  )

# Display the top 10 event types by total economic damage
economic_impact %>%
  arrange(desc(Total_Economic_Damage)) %>%
  slice_head(n = 10)
## # A tibble: 10 × 4
##    EVENT_TYPE      Total_Property_Damage Total_Crop_Damage Total_Economic_Damage
##    <chr>                           <dbl>             <dbl>                 <dbl>
##  1 Hurricane (Typ…            5302560000        1510000000            6812560000
##  2 Flash Flood                3143421200         101576500            3244997700
##  3 Tropical Storm             1902007000         253006000            2155013000
##  4 Tornado                    1721030380           8531200            1729561580
##  5 Wildfire                   1102899870          64817000            1167716870
##  6 Storm Surge/Ti…             870042000                 0             870042000
##  7 Flood                       649031930           4905300             653937230
##  8 Thunderstorm W…             412498090          29056210             441554300
##  9 Hail                        226989630         142860000             369849630
## 10 High Wind                   127967600         112595200             240562800

Figure 4: Top 10 Storm Events Causing Economic Damage

economic_plot <- economic_impact %>%
  arrange(desc(Total_Economic_Damage)) %>%
  slice_head(n = 10) %>%
  ggplot(aes(x = reorder(EVENT_TYPE, Total_Economic_Damage),
             y = Total_Economic_Damage / 1000000000)) +
  geom_col(fill = "darkorange") +
  geom_text(
    aes(label = paste0("$", round(Total_Economic_Damage / 1000000000, 2), "B")),
    hjust = -0.2
  ) +
  coord_flip(clip = "off") +
  scale_y_continuous(expand = expansion(mult = c(0, 0.18))) +
  labs(
    title = "Top 10 Storm Events Causing Economic Damage",
    x = "Storm Event Type",
    y = "Total Economic Damage (Billions of Dollars)",
    caption = "Source: NOAA Storm Events Database, 2024"
  ) +
  theme_minimal()

print(economic_plot)
Figure 4. The ten storm event types with the greatest combined property and crop damage in 2024, measured in billions of dollars.

Figure 4. The ten storm event types with the greatest combined property and crop damage in 2024, measured in billions of dollars.

Conclusion

The analysis of the 2024 NOAA Storm Events Database shows that different types of storms create different challenges for communities across the United States. Tornadoes caused the most injuries, while excessive heat caused the most fatalities. Thunderstorm wind was the most frequently reported event type overall, although the most common storm types varied geographically and seasonally.

The economic analysis showed that hurricanes caused the greatest financial damage, followed by flash floods and tropical storms. These findings highlight the importance of preparation for different types of severe weather based on geographic location and seasonal patterns.

Overall, the results can help government officials and emergency management organizations identify important weather-related risks, prioritize preparation efforts, and better allocate financial resources to protect public safety and property.