In 2024, there were a total of 64,897 wildland fires recorded in the United States. This represents an increase of roughly 14 percent from the previous year. That year, California was the state with the highest number of wildfires in the United States.

First, we would like to thank the wildland fire advisory group. Their wisdom and guidance helped us build the dataset as it currently exists. Currently, there are multiple, freely available fire datasets that identify wildfire and prescribed fire burned areas across the United States. However, these datasets are all limited in some way. Their time periods could cover only a couple of decades or they may have stopped collecting data many years ago. Their spatial footprints may be limited to a specific geographic area or agency. Their attribute data may be limited to nothing more than a polygon and a year. None of the existing datasets provides a comprehensive picture of fires that have burned throughout the last few centuries. Our dataset uses these existing layers and utilizes a series of both manual processes and ArcGIS Python (arcpy) scripts to merge these existing datasets into a single dataset that encompasses the known wildfires and prescribed fires within the United States and certain territories. Forty different fire layers were utilized in this dataset. First, these datasets were ranked by order of observed quality (Tiers). The datasets were given a common set of attribute fields and as many of these fields were populated as possible within each dataset. All fire layers were then merged together (the merged dataset) by their common attributes to created a merged dataset containing all fire polygons. Polygons were then processed in order of Tier (1-8) so that overlapping polygons in the same year and Tier were dissolved together. Overlapping polygons in subsequent Tiers were removed from the dataset. Attributes from the original datasets of all intersecting polygons in the same year across all Tiers were also merged so that all attributes from all Tiers were included, but only the polygons from the highest ranking Tier were dissolved to form the fire polygon. The resulting product (the combined dataset) has only one fire per year in a given area with one set of attributes. While it combines wildfire data from 40 wildfire layers and therefore has more complete information on wildfires than the datasets that went into it, this dataset has also has its own set of limitations. Please see the Data Quality attributes within the metadata record for additional information on this dataset's limitations. Overall, we believe this dataset is designed be to a comprehensive collection of fire boundaries within the United States and provides a more thorough and complete picture of fires across the United States when compared to the datasets that went into it.

Globally, ************ hectares of tree cover were lost to wildfires in 2023. During the same year, the total area of tree cover loss caused by fires in general (wildfires and other fire events like clearing for agriculture) amounted to ************ hectares.

Description:

The dataset reflects the damage sustained by structures across various fire incidents, categorized by damage percentage—ranging from minor damage (1-10%) to complete destruction (50-100%) and collected by field inspectors who evaluate structures impacted by wildland fires.

This dataset is invaluable for fire prevention, emergency response, and disaster management efforts.

Attribute Statement:

This dataset is provided by the California Department of Forestry and Fire Protection (CAL FIRE) in collaboration with the National Interagency Fire Center (NIFC) and the Fire Integrated Real-Time Intelligence System (FIRIS).

No Endorsement Statement:

The publication of this dataset does not imply endorsement by CAL FIRE, NIFC, or any associated entities. The data is provided "as-is" without any guarantees regarding accuracy or completeness.

Citation:

CAL FIRE, "California Wildfire Perimeter Data: Real-Time Insights from FIRIS & NIFC," California Open Data Portal. Available at: https://gis.data.cnra.ca.gov/datasets/CALFIRE-Forestry::ca-perimeters-nifc-firis-public-view

License:

This dataset is shared under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.

Provenance:

This dataset is sourced from the California Open Data Portal and is maintained by CAL FIRE and associated agencies.
- Original Source: California Open Data Portal - FIRIS Dataset
- Data Collection Methods:
- Data transmitted from satellites and aerial infrared platforms.
- Near-real-time processing for fire perimeter modeling by WIFIRE.
- Decision support integration through Intterra's software.

DISCLAIMER: Please independently verify the data and it's derivation(s) before applying it to research or decision-making.

Get data on forest fires, compiled annually for the National Forestry Database The National Forestry Database includes national forest data and forest management statistics to seve as a credible, accurate and reliable source of information on forest management and its impact on the forest resource. Forest fire data is grouped into eight categories, which are further broken down by geographic location. These include: * number of fires by cause class and response category * area burned by cause class and response category * number of fires by month and response category * area burned by month and response category * number of fires by fire size class and response category * area burned by fire size class and response category * area burned by productivity class, stocking class, maturity class and response category * other fire statistics, such as property losses

This dataset provides an extensive overview of wildfire activity worldwide, capturing both the frequency and intensity of fires over a range of years. It is derived from the Global Wildfire Information System (GWIS) and integrates satellite imagery from MODIS and VIIRS. The dataset is adapted and processed by Our World in Data, including standardizations for global comparisons.

Key Features:

Entity: Represents countries, regions, or territories where the wildfire data is collected.

Code: ISO or custom country/region codes.

Year: The year of recorded wildfire data.

Annual Number of Fires: The total number of wildfires recorded in a given year for a specific entity.

Annual Area Burnt per Wildfire (in hectares): The average area burned by each wildfire during the year.

Dataset Highlights: Covers various regions, including individual countries (e.g., Afghanistan, Albania) and larger areas like Africa. Includes granular data for entities like Akrotiri and Dhekelia, and zero-incident regions like the Aland Islands and American Samoa. Captures annual trends from 2012 to 2025, demonstrating variability in both the number of wildfires and the average area burnt.

Modifications Made to the Dataset: One column's name was changed to "Annual area burnt per wildfire in hectares" to improve clarity and relevance.

Note: Recent California Los Angeles fires are not included in this dataset. Data for 2025 is incomplete as the year has just begun.

An unwanted column was removed to streamline the dataset and ensure only relevant data is included.

Data Source and Processing:

Original Source: Global Wildfire Information System (GWIS), providing weekly updates on fire activity and its environmental impact.

Processing: Adaptations by Our World in Data include standardizing names, converting units, and calculating derived indicators.

Citations:

Primary data retrieved from GWIS Seasonal Trends (https://gwis.jrc.ec.europa.eu/apps/gwis.statistics/seasonaltrend). Minor processing by Our World in Data.

Usage and Licensing: This dataset is open access under the Creative Commons BY license. Users may reproduce, distribute, and adapt the data with appropriate credit to the source.

Suggested Citation for Dataset: Global Wildfire Information System (2025); Global Wildfire Information System (2024) – with minor processing by Our World in Data. “Annual number of wildfires” [dataset]. Retrieved January 26, 2025, from https://ourworldindata.org/grapher/annual-number-of-fires?time=2025#explore-the-data.

This dataset provides valuable insights into global wildfire patterns, supporting analysis for environmental studies, policy-making, and disaster management planning.

Spatial wildfire occurrence data for the United States, 1992-2020 FPA_FOD_20221014

Author: Short, Karen C. Publication Year: 2022 How to Cite: - These data were collected using funding from the U.S. Government and can be used without additional permissions or fees. If you use these data in a publication, presentation, or other research product please use the following citation: Short, Karen C. 2022. Spatial wildfire occurrence data for the United States, 1992-2020 [FPA_FOD_20221014]. 6th Edition. Fort Collins, CO: Forest Service Research Data Archive. https://doi.org/10.2737/RDS-2013-0009.6

Abstract: - This data publication contains a spatial database of wildfires that occurred in the United States from 1992 to 2020. It is the fifth update of a publication originally generated to support the national Fire Program Analysis (FPA) system. The wildfire records were acquired from the reporting systems of federal, state, and local fire organizations. The following core data elements were required for records to be included in this data publication: discovery date, final fire size, and a point location at least as precise as a Public Land Survey System (PLSS) section (1-square mile grid). The data were transformed to conform, when possible, to the data standards of the National Wildfire Coordinating Group (NWCG), including an updated wildfire-cause standard (approved August 2020). Basic error-checking was performed and redundant records were identified and removed, to the degree possible. The resulting product, referred to as the Fire Program Analysis fire-occurrence database (FPA FOD), includes 2.3 million geo-referenced wildfire records, representing a total of 180 million acres burned during the 29-year period. Identifiers necessary to link the point-based, final-fire-reporting information to published large-fire-perimeter and operational-situation-reporting datasets are included.

File Index: File Index for Data Publication

Included in the zip file is 'variable_descriptions.csv' that contains the following information:

| Table | Variable | Description | --- | --- | Fires |FOD_ID| Unique numeric record identifier. Fires|FPA_ID|Unique identifier that contains information necessary to track back to the original record in the source dataset. Fires|SOURCE_SYSTEM_TYPE|Type of source database or system that the record was drawn from (FED = federal, NONFED = nonfederal, or INTERAGCY = interagency). Fires|SOURCE_SYSTEM|Name of or other identifier for source database or system that the record was drawn from. See \Supplements\FPA_FOD_source_list.pdf for a list of sources and their identifier and Short (2014) for additional source information. Fires|NWCG_REPORTING_AGENCY|Active National Wildlife Coordinating Group (NWCG) Unit Identifier for the agency preparing the fire report (BIA = Bureau of Indian Affairs, BLM = Bureau of Land Management, BOR = Bureau of Reclamation, DOD = Department of Defense, DOE = Department of Energy, FS = Forest Service, FWS = Fish and Wildlife Service, IA = Interagency Organization, NPS = National Park Service, ST/C&L = State, County, or Local Organization, and TRIBE = Tribal Organization). Fires|NWCG_REPORTING_UNIT_ID|Active NWCG Unit Identifier for the unit preparing the fire report. Fires|NWCG_REPORTING_UNIT_NAME|Active NWCG Unit Name for the unit preparing the fire report. Fires|SOURCE_REPORTING_UNIT|Code for the agency unit preparing the fire report, based on code/name in the source dataset. Fires|SOURCE_REPORTING_UNIT_NAME|Name of reporting agency unit preparing the fire report, based on code/name in the source dataset. Fires|LOCAL_FIRE_REPORT_ID|Number or code that uniquely identifies an incident report for a particular reporting unit and a particular calendar year. Fires|LOCAL_INCIDENT_ID|Number or code that uniquely identifies an incident for a particular local fire management organization within a particular calendar year. Fires|FIRE_CODE|Code used within the interagency wildland fire community to track and compile cost information for emergency fire suppression (https://www.firecode.gov/). Fires|FIRE_NAME|Name of the incident, from the fire report (primary) or ICS-209 report (secondary). Fires|ICS_209_PLUS_INCIDENT_JOIN_ID|Primary identifier needed to join into operational situation reporting data for the incident in the ICS-209-PLUS dataset. Fires|ICS_209_PLUS_COMPLEX_JOIN_ID|If part of a complex, secondary identifier potentially needed to join to operational situation reporting data for the incident in the ICS-209-PLUS dataset. Fires|MTBS_ID|Incident identifier, from the MTBS perimeter dataset. Fires|MTBS_FIRE_NAME|Name of the incident, from the MTBS perimeter dataset. Fires|COMPLEX_NAME|N...

The data included in this publication depict components of wildfire risk specifically for populated areas in the United States. These datasets represent where people live in the United States and the in situ risk from wildfire, i.e., the risk at the location where the adverse effects take place.National wildfire hazard datasets of annual burn probability and fire intensity, generated by the USDA Forest Service, Rocky Mountain Research Station and Pyrologix LLC, form the foundation of the Wildfire Risk to Communities data. Vegetation and wildland fuels data from LANDFIRE 2020 (version 2.2.0) were used as input to two different but related geospatial fire simulation systems. Annual burn probability was produced with the USFS geospatial fire simulator (FSim) at a relatively coarse cell size of 270 meters (m). To bring the burn probability raster data down to a finer resolution more useful for assessing hazard and risk to communities, we upsampled them to the native 30 m resolution of the LANDFIRE fuel and vegetation data. In this upsampling process, we also spread values of modeled burn probability into developed areas represented in LANDFIRE fuels data as non-burnable. Burn probability rasters represent landscape conditions as of the end of 2020. Fire intensity characteristics were modeled at 30 m resolution using a process that performs a comprehensive set of FlamMap runs spanning the full range of weather-related characteristics that occur during a fire season and then integrates those runs into a variety of results based on the likelihood of those weather types occurring. Before the fire intensity modeling, the LANDFIRE 2020 data were updated to reflect fuels disturbances occurring in 2021 and 2022. As such, the fire intensity datasets represent landscape conditions as of the end of 2022. The data products in this publication that represent where people live, reflect 2021 estimates of housing unit and population counts from the U.S. Census Bureau, combined with building footprint data from Onegeo and USA Structures, both reflecting 2022 conditions.The specific raster datasets included in this publication include:Building Count: Building Count is a 30-m raster representing the count of buildings in the building footprint dataset located within each 30-m pixel.Building Density: Building Density is a 30-m raster representing the density of buildings in the building footprint dataset (buildings per square kilometer [km²]).Building Coverage: Building Coverage is a 30-m raster depicting the percentage of habitable land area covered by building footprints.Population Count (PopCount): PopCount is a 30-m raster with pixel values representing residential population count (persons) in each pixel.Population Density (PopDen): PopDen is a 30-m raster of residential population density (people/km²).Housing Unit Count (HUCount): HUCount is a 30-m raster representing the number of housing units in each pixel.Housing Unit Density (HUDen): HUDen is a 30-m raster of housing-unit density (housing units/km²).Housing Unit Exposure (HUExposure): HUExposure is a 30-m raster that represents the expected number of housing units within a pixel potentially exposed to wildfire in a year. This is a long-term annual average and not intended to represent the actual number of housing units exposed in any specific year.Housing Unit Impact (HUImpact): HUImpact is a 30-m raster that represents the relative potential impact of fire to housing units at any pixel, if a fire were to occur. It is an index that incorporates the general consequences of fire on a home as a function of fire intensity and uses flame length probabilities from wildfire modeling to capture likely intensity of fire.Housing Unit Risk (HURisk): HURisk is a 30-m raster that integrates all four primary elements of wildfire risk - likelihood, intensity, susceptibility, and exposure - on pixels where housing unit density is greater than zero.Additional methodology documentation is provided with the data publication download. Metadata and Downloads: (https://www.fs.usda.gov/rds/archive/catalog/RDS-2020-0060-2).Note: Pixel values in this image service have been altered from the original raster dataset due to data requirements in web services. The service is intended primarily for data visualization. Relative values and spatial patterns have been largely preserved in the service, but users are encouraged to download the source data for quantitative analysis.

Field Description:

A wildfire is an uncontrolled burn of vegetation, which includes the burning of forests, shrublands and grasslands, savannas, and croplands.

Wildfires can be caused by human activity — such as arson, unattended fires, or the loss of control of planned burns — and natural causes, such as lightning.

The spread of wildfires, once ignited, is determined by a range of factors, such as the amount and types of dry vegetation in the surrounding area, wind direction and speed, moisture levels, and heat. The amount of area burned by wildfires — and the impacts on ecosystems — is driven by a combination of weather patterns, human activity, the management of vegetation and landscapes, and responses to suppress their spread.

Data Description:

There are 5 csv files in this dataset.

1- cumulative area burnt by wildfires by week:

Weekly burned area

A useful way of tracking the evolution of wildfires across the year is to look at their week-by-week progression. This allows us to compare the extent of wildfires at a given time this year to the same period in a previous year.

It lets us see whether wildfires have started earlier or later than in previous years and whether they’re tracking above or below what we might expect from historical records.

2- annual area burnt by wildfires

Burned area by year

How much area is burned by wildfires each year? The data for the current year is also included to allow you to put this year’s current burn figures into context.

3- share of the total land area burnt by wildfires each year

Share of land area burned by wildfires

It’s useful to put the total extent of wildfires in the context of total land area: what share of land is burned each year?

Africa tends to be the region with the largest share of area burned — typically ranging from 6% to 8% each year. Figures tend to be lower in other regions but can vary a lot from year to year.

It’s important to note that the same land area can burn multiple times over successive years. So, a rate of 5% burn per year doesn’t mean that 50% of a country is burned over a decade. Some areas will burn multiple times over that period, while others will never be exposed.

4- annual area burnt per wildfire

Land area burned per wildfire

The spread of a wildfire, once ignited, will be influenced by many factors. Natural phenomena such as the type of vegetation, weather conditions, and the intensity of heat will influence how well the fire will be contained. Certain types of vegetation, for example, burn more easily than others. The effectiveness of the local fire containment management strategies will also play a role. This means some wildfires end up being significantly larger than others, and the impact can vary across different regions and countries.

5- annual burned area by landcover

Burned area by land type

When “wildfires” are mentioned, people often picture forest fires. But lots of other ecosystem types can burn. Much larger areas of grasslands and savannas are burned each year than forests.

Source of data:

Ourworldindata.org

By Veronika Samborska and Hannah Ritchie

These data were used to examine how post-fire sedimentation might change in western USA watersheds with future fire from the decade of 2001-10 through 2041-50. The data include previously published projections (Hawbaker and Zhu, 2012a, b) of areas burned by future wildfires for several climate change scenarios and general circulation models (GCMs) that we summarized for 471 watersheds of the western USA. The data also include previously published predictions (Miller et al., 2011) of first year post-fire hillslope soil erosion from GeoWEPP that we summarized for 471 watersheds of the western USA. We synthesized these summarized data in order to project sediment yield from future fires for 471 watersheds through the year 2050 at the hydrologic unit 8 (HUC8) scale. The detailed methods, results, and original data sources (i.e.: Hawbaker and Zhu, 2012a, b; Miller et al., 2011) were reported in the manuscript.

Get data on forest fires, compiled annually for the National Forestry Database

The National Forestry Database includes national forest data and forest management statistics to seve as a credible, accurate and reliable source of information on forest management and its impact on the forest resource.

Forest fire data is grouped into eight categories, which are further broken down by geographic location. These include:

• number of fires by cause class and response category
• area burned by cause class and response category
• number of fires by month and response category
• area burned by month and response category
• number of fires by fire size class and response category
• area burned by fire size class and response category
• area burned by productivity class, stocking class, maturity class and response category
• other fire statistics, such as property losses

Q: Where is the chance for wildfires enhanced at this time of year? A: Shading on each map reflects how often fires with an area of 100 acres or larger were reported within 25 miles during a 24-year base period. The darker the shading, the higher the number of fires reported close in time to the displayed date. Q: How were these maps produced? A: Using daily fire records from the beginning of 1992 through the end of 2015, meteorologists who specialize in predicting fire weather plotted all fires of 100 acres or larger on a map. Grid lines on the map divide the entire area into rectangles—called grid cells—approximately 50 miles on a side. For every day of the year, scientists counted the number of years each grid cell contained at least one qualifying fire, and then divided by the total number of years. To reveal the long-term pattern of fires, scientists applied mathematical filters to smooth the raw counts, both across the land (spatially) and through the year (temporally). Fire locations and sizes were originally obtained from the U.S Forest Service Fire Program Analysis Fire-Occurrence Database. Q: What do the colors mean? A: Shaded areas show the historical probability of a wildfire that covers 100 acres or more occurring within 25 miles. Q: Why do these data matter? A: Knowing when and where large wildfires occur through the year can promote preparedness. Residents who are alert to the possibility of wildfires are better able to respond in ways that can keep them safe. These maps can also help firefighting agencies plan for when and where their services and equipment may be needed. Q: How did you produce these snapshots? A: Data Snapshots are derivatives of existing data products: to meet the needs of a broad audience, we present the source data in a simplified visual style. NOAA's National Weather Service Storm Prediction Center produced the original Probability of a Wildfire ≥ 100 acres files. To produce our images, we obtained the map data, and ran a set of scripts to display the mapped areas on our base maps with a custom color bar. See box at right for a link to the original data source. References Short, Karen C. 2017. Spatial wildfire occurrence data for the United States, 1992-2015 [FPA_FOD_20170508]. 4th Edition. Fort Collins, CO: Forest Service Research Data Archive. https://doi.org/10.2737/RDS-2013-0009.4 Source: https://www.climate.gov/maps-data/data-snapshots/data-source/historic-probability-large-wildfire This upload includes two additional files:* Historic Probability of Large Wildfire _NOAA Climate.gov.pdf is a screenshot of the main Climate.gov site for these snapshots (https://www.climate.gov/maps-data/data-snapshots/data-source/historic-probability-large-wildfire)* Cimate_gov_ Data Snapshots.pdf is a screenshot of the data download page for the full-resolution files.

Wildfires resulted in *** deaths in the United States in 2023. This has been the highest figure since 1990, mostly related to the Maui wildfires in Hawaii. There have been more than *** wildfire-related deaths in the U.S. since 1990.

Historic Fire Perimeter Dataset Feedback

Current criteria for data collection are as follows:

CAL FIRE (including contract counties) submit perimeters ≥10 acres in timber, ≥50 acres in brush, or ≥300 acres in grass, and/or ≥3 impacted residential or commercial structures, and/or caused ≥1 fatality.

All cooperating agencies submit perimeters ≥10 acres.

Version update:

Firep24_1 was released in April 2025. Five hundred forty-eight fires from the 2024 fire season were added to the database (2 from BIA, 56 from BLM, 197 from CAL FIRE, 193 from Contract Counties, 27 from LRA, 8 from NPS, 55 from USFS and 8 from USFW). Six perimeters were added from the 2025 fire season (as a special case due to an unusual January fire siege). Five duplicate fires were removed, and the 2023 Sage was replaced with a more accurate perimeter. There were 900 perimeters that received updated attribution (705 removed “FIRE” from the end of Fire Name field and 148 replaced Complex IRWIN ID with Complex local incident number for COMPLEX_ID field). The following fires were identified as meeting our collection criteria but are not included in this version and will hopefully be added in a future update: Addie (2024-CACND-002119), Alpaugh (2024-CACND-001715), South (2024-CATIA-001375). One perimeter is missing containment date that will be updated in the next release.

Cross checking CALFIRS reporting for new CAL FIRE submissions to ensure accuracy with cause class was added to the compilation process. The cause class domain description for “Powerline” was updated to “Electrical Power” to be more inclusive of cause reports.

Includes separate layers filtered by criteria as follows:

California Fire Perimeters (All): Unfiltered. The entire collection of wildfire perimeters in the database. It is scale dependent and starts displaying at the country level scale.

Recent Large Fire Perimeters (≥5000 acres): Filtered for wildfires greater or equal to 5,000 acres for the last 5 years of fires (2020-January 2025), symbolized with color by year and is scale dependent and starts displaying at the country level scale. Year-only labels for recent large fires.

California Fire Perimeters (1950+): Filtered for wildfires that started in 1950-January 2025. Symbolized by decade, and display starting at country level scale.

Detailed metadata is included in the following documents:

Wildland Fire Perimeters (Firep24_1) Metadata

See more information on our Living Atlas data release here:

CAL FIRE Historical Fire Perimeters Available in ArcGIS Living Atlas

For any questions, please contact the data steward:

Kim Wallin, GIS Specialist

CAL FIRE, Fire & Resource Assessment Program (FRAP)

kimberly.wallin@fire.ca.gov

Wildfire activity in the United States saw a significant increase in 2024, with approximately *** million acres burned. This marks a more than ********* increase from the previous year. Such development boosts the concerning upward trend in wildfire damage across the country that has developed in the past half a century. Humans or lightning? A wildfire can start by natural causes. In 2024, Oregon and Arizona were the states most affected, each with more than *** cases recorded. Nevertheless, human-caused wildfires continue to play a significant role in the overall landscape. In 2024, over ****** wildfires in the U.S. were attributed to human activity, resulting in more than *** million acres burned. Wildfire suppression The financial burden of wildfire suppression remains substantial. The estimated costs of wildfire suppression in the U.S. stood at almost *** million U.S. dollars in 2023, a 13-fold increase in comparison to 1985. As climate change continues to alter weather patterns and create more favorable conditions for wildfires, the need for effective prevention, management, and suppression strategies is becoming increasingly critical.

Context:

This data publication contains a spatial database of wildfires that occurred in the United States from 1992 to 2015. It is the third update of a publication originally generated to support the national Fire Program Analysis (FPA) system. The wildfire records were acquired from the reporting systems of federal, state, and local fire organizations. The following core data elements were required for records to be included in this data publication: discovery date, final fire size, and a point location at least as precise as Public Land Survey System (PLSS) section (1-square mile grid). The data were transformed to conform, when possible, to the data standards of the National Wildfire Coordinating Group (NWCG). Basic error-checking was performed and redundant records were identified and removed, to the degree possible. The resulting product, referred to as the Fire Program Analysis fire-occurrence database (FPA FOD), includes 1.88 million geo-referenced wildfire records, representing a total of 140 million acres burned during the 24-year period.

Content:

This dataset is an SQLite database that contains the following information:

• Fires: Table including wildfire data for the period of 1992-2015 compiled from US federal, state, and local reporting systems.
• FOD_ID = Global unique identifier.
• FPA_ID = Unique identifier that contains information necessary to track back to the original record in the source dataset.
• SOURCE_SYSTEM_TYPE = Type of source database or system that the record was drawn from (federal, nonfederal, or interagency).
• SOURCE_SYSTEM = Name of or other identifier for source database or system that the record was drawn from. See Table 1 in Short (2014), or \Supplements\FPA_FOD_source_list.pdf, for a list of sources and their identifier.
• NWCG_REPORTING_AGENCY = Active National Wildlife Coordinating Group (NWCG) Unit Identifier for the agency preparing the fire report (BIA = Bureau of Indian Affairs, BLM = Bureau of Land Management, BOR = Bureau of Reclamation, DOD = Department of Defense, DOE = Department of Energy, FS = Forest Service, FWS = Fish and Wildlife Service, IA = Interagency Organization, NPS = National Park Service, ST/C&L = State, County, or Local Organization, and TRIBE = Tribal Organization).
• NWCG_REPORTING_UNIT_ID = Active NWCG Unit Identifier for the unit preparing the fire report.
• NWCG_REPORTING_UNIT_NAME = Active NWCG Unit Name for the unit preparing the fire report.
• SOURCE_REPORTING_UNIT = Code for the agency unit preparing the fire report, based on code/name in the source dataset.
• SOURCE_REPORTING_UNIT_NAME = Name of reporting agency unit preparing the fire report, based on code/name in the source dataset.
• LOCAL_FIRE_REPORT_ID = Number or code that uniquely identifies an incident report for a particular reporting unit and a particular calendar year.
• LOCAL_INCIDENT_ID = Number or code that uniquely identifies an incident for a particular local fire management organization within a particular calendar year.
• FIRE_CODE = Code used within the interagency wildland fire community to track and compile cost information for emergency fire suppression (https://www.firecode.gov/).
• FIRE_NAME = Name of the incident, from the fire report (primary) or ICS-209 report (secondary).
• ICS_209_INCIDENT_NUMBER = Incident (event) identifier, from the ICS-209 report.
• ICS_209_NAME = Name of the incident, from the ICS-209 report.
• MTBS_ID = Incident identifier, from the MTBS perimeter dataset.
• MTBS_FIRE_NAME = Name of the incident, from the MTBS perimeter dataset.
• COMPLEX_NAME = Name of the complex under which the fire was ultimately managed, when discernible.
• FIRE_YEAR = Calendar year in which the fire was discovered or confirmed to exist.
• DISCOVERY_DATE = Date on which the fire was discovered or confirmed to exist.
• DISCOVERY_DOY = Day of year on which the fire was discovered or confirmed to exist.
• DISCOVERY_TIME = Time of day that the fire was discovered or confirmed to exist.
• STAT_CAUSE_CODE = Code for the (statistical) cause of the fire.
• STAT_CAUSE_DESCR = Description of the (statistical) cause of the fire.
• CONT_DATE = Date on which the fire was declared contained or otherwise controlled (mm/dd/yyyy where mm=month, dd=day, and yyyy=year).
• CONT_DOY = Day of year on which the fire was declared contained or otherwise controlled.
• CONT_TIME = Time of day that the fire was declared contained or otherwise controlled (hhmm where hh=hour, mm=minutes).
• FIRE_SIZE = Estimate of acres within the final perimeter of the fire.
• FIRE_SIZE_CLASS = Code for fire size based on the number of acres within the final fire perimeter expenditures (A=greater than 0 but less than or equal to 0.25 acres, B=0.26-9.9 acres, C=10.0-99.9 acres, D=100-299 acres, E=300 to 999 acres, F=1000 to 4999 acres, and G=5000+ acres).
• LATITUDE = Latitude (NAD83) for p...

This dataset is used to track wildfire information, assess wildfire risks, and to plan wildfire prevention activities.

It includes information about wildfires that have occurred on lands protected by the Washington State Department of Natural Resources, 2008 to present.This dataset is used to track wildfire information, assess wildfire risks, and to plan wildfire prevention activities.

This archive contains the data and code used to produce the Western United States Large Forest-Fire Stochastic Simulator (WULFFSS), version 1.0, which is a monthly gridded forest-fire model using interpretable statistics. The WULFFSS operates at 12-km resolution and calculates monthly probabilities of forest fires ≥100 ha as well as the area burned per fire. The model is forced by variables related to vegetation, topographic, anthropogenic, and climate factors, organized into three indices representing spatial, annual-cycle, and lower frequency temporal domains. These indices can interact, so variables promoting fire in one domain amplify fire-promoting effects in another. The fire probability and size modules use multiple logistic and linear regression, respectively, and can be easily updated as new data or ideas emerge. During its training period of 1985–2024, WULFFSS captures >70% and >80% of observed interannual variability in western US forest-fire frequency and area, respect..., , # The western United States large forest-fire stochastic simulator (WULFFSS) 1.0: A monthly gridded forest-fire model using interpretable statistics

Dataset DOI: 10.5061/dryad.63xsj3vdb

Description of the data and file structure

This repository contains the data and code used to produce version 1.0 of the Western United States Large Forest-Fire Stochastic Simulator (WULFFSS), as well as the equations that comprise the model and code to run the model. The WULFFSS simulates the probabilities and sizes of forest fires at least 1 km2 in size every month across forested areas of the western US on a 12-km resolution grid. The model is forced by variables related to vegetation, topographic, anthropogenic, and climate factors, organized into three indices representing spatial, annual-cycle, and lower frequency temporal domains. These indices can interact, so variables promoting fire in one domain amplify fire-promoting effects in another. Fire probability and si...,

Context

Wildfires are one of the most economically devastating natural events that occur almost on a regular basis. During the height of summer, the west sets ablaze across the entire coast. With a large number of fires burning at the same time and limited resources, land managers and fire departments are forced to make difficult choices on which fire to focus on. The goal of this project is to leverage machine learning to help answer this question.

Content

The dataset presented here is a sub-sample of data presented here :1.88 Million US Fires [1]. I took this dataset and downselected to a random sampling of 50,000 fire samples and combined this dataset with historical weather data at a specific lat/long [2], historical vegetation data [3]. A metric is representing the measure of the remoteness of a fire using city lat/long database [4].

Sources :

[1] Short, Karen C. 2017. Spatial wildfire occurrence data for the United States, 1992-2015 [FPA_FOD_20170508]. 4th Edition. Fort Collins, CO: Forest Service Research Data Archive. https://doi.org/10.2737/RDS-2013-0009.4

[2] NOAA National Centers for Environmental Information (2001): Integrated Surface Hourly [1992-2015] - ftp://ftp.ncdc.noaa.gov/pub/data/noaa/

[3] Meiyappan, Prasanth, and Atul K. Jain. "Three distinct global estimates of historical land-cover change and land-use conversions for over 200 years." Frontiers of Earth Science 6.2 (2012): 122-139.

[4] "World Cities Database." Simplemaps, simplemaps.com/data/world-cities.

Inspiration

Build a machine learning model to predict what is the likelihood that the fire would grow to devastating proportions. This model can help policy makers and land managers triage wildfires during the summer, where multiple fires burn at the same time, and resources are limited.

description: The increase in wildfires, particularly in the western U.S., represents one of the greatest threats to multiple native ecosystems. Despite this threat, there is currently no central repository to store both past and current wildfire perimeter data. Currently, wildfire boundaries can only be found in disparate local or national datasets. These datasets are generally restricted to specific locations, fire sizes, or time periods. Our objective was to create a comprehensive national wildfire perimeter dataset by combining all freely available wildfire datasets that we could download. We combined and dissolved individual wildfire polygons from multiple datasets if they were in the same year and overlapped each other or were within 1km of the fire boundary. This combined dataset includes spatial summary statistics such as number of times burned, earliest fire of record, and most recent fire of record.; abstract: The increase in wildfires, particularly in the western U.S., represents one of the greatest threats to multiple native ecosystems. Despite this threat, there is currently no central repository to store both past and current wildfire perimeter data. Currently, wildfire boundaries can only be found in disparate local or national datasets. These datasets are generally restricted to specific locations, fire sizes, or time periods. Our objective was to create a comprehensive national wildfire perimeter dataset by combining all freely available wildfire datasets that we could download. We combined and dissolved individual wildfire polygons from multiple datasets if they were in the same year and overlapped each other or were within 1km of the fire boundary. This combined dataset includes spatial summary statistics such as number of times burned, earliest fire of record, and most recent fire of record.