Fire Event Data Suite (FEDS) Algorithm

The Fire Event Data Suite (FEDS) algorithm (Chen et al., 2022) clusters active fire detections into individual events and estimates the perimeter and properties of ongoing fire events every 12 hours, based on Visible Infrared Imaging Radiometer Suite (VIIRS) 375 m active fire detections. The estimated perimeter data are routinely produced within approximately four hours of each VIIRS overpass for the Continental United States (CONUS) and Canada. For fires that ultimately grow larger than 4 km2, these modeled perimeters and associated attributes are stored in sequence to track the growth and behavior of each large fire event.

Data and Resources

Field Value
accessRights <p>Open access and licensed under <span style="color: rgb(34, 34, 34);">Creative Commons Attribution 4.0 International License.</span></p>
appAccessMethod Web based, software download, programmatic
appSummary <p>This tool provides reproducible Python code to preprocess FEDS data, run the FEDS algorithm, and generate outputs. The open source code is available on <a href="https://github.com/Earth-Information-System/fireatlas" rel="noopener noreferrer" target="_blank">GitHub</a> and includes example notebooks to read FEDS data and set up experiments. Additional usage example notebooks can be found at <a href="https://docs.openveda.cloud/user-guide/notebooks/" rel="noopener noreferrer" target="_blank">https://docs.openveda.cloud/user-guide/notebooks/</a>.</p>
cndp NDP
creationMethod <p>The FEDs algorithm tracks fire movement and severity by ingesting observations from the VIIRS thermal sensors on the Suomi NPP and NOAA-20 satellites. This algorithm uses raw VIIRS observations to generate a polygon of the fire, locations of the active fire line, and estimates of fire mean Fire Radiative Power (FRP). The VIIRS sensors overpass at approximately 1:30 AM and PM local time, and provide estimates of fire evolution approximately every 12 hours. The data produced by this algorithm describe where fires are in space and how fires evolve through time.&nbsp;</p>
dataAuthType public
dataProvenance [{"date":"2022-05-12","name":"California FEDS data records posted to open source figshare repository."}]
dataType Cloud Optimized GeoTIFF (COG)
datasetPageUrl https://earth-information-system.github.io/fireatlas/docs/data_overview.html
docsURL https://earth-information-system.github.io/fireatlas/docs/data.html
enable_contextual_insight true
issueDate 2022-05-30
lang en
lastUpdateDate 2026-07-15
libsPkgsUsed fireatlas
license cc-by
modelAccessMethod web based, software download
ndp_creator_md5 5fbc9b6d7ef314a337c2cad359f8ea0c
pocEmail yang.chen@uci.edu
pocName Yang Chen
purpose <p>The FEDS (aka VIIRS Modeled Fire Perimeters) product is intended to provide situational awareness for ongoing fire events in the US and Canada, not as a precise estimate of the fire perimeter for emergency response. Near real time (NRT) FEDS fire tracking data can be visualized online using <a href="https://earthdata.nasa.gov/dashboard/tools/fire-event-explorer" rel="noopener noreferrer" target="_blank" style="background-color: rgb(255, 255, 255); color: rgb(39, 97, 227);"><strong>Fire Events Explorer</strong></a>, <a href="https://gis.earthdata.nasa.gov/portal/home/item.html?id=e2e14a2a640b404c903976b2fb4467f8" rel="noopener noreferrer" target="_blank" style="background-color: rgb(255, 255, 255); color: rgb(39, 97, 227);"><strong>ArcGIS Online</strong></a>, and <a href="https://firms.modaps.eosdis.nasa.gov/usfs/map/#m:experimental;d:24hrs,24hrs;l:fires_viirs_noaa20,fires_viirs_noaa21,fires_viirs_snpp,eis_fire_lf_perimeter_nrt,countries,earth;@-102.8,37.6,5.1z" rel="noopener noreferrer" target="_blank" style="background-color: rgb(255, 255, 255); color: rgb(39, 97, 227);"><strong>NASA FIRMS US/Canada</strong></a>, and is accessible via the NASA Visual Exploration and Data Analysis (VEDA) platform API.</p>
spatialCov Continental United States (CONUS), Canada
spatialCovFormat text
spatialRes 375m meter
status submitted
temporalRes hours
totalFilesSize 28 MB
uploadType application
usageInfo <p>The intended use for the FEDS Python scripts is to process satellite active fire detections to track the spread and intensity of individual wildland fires, which can support risk evaluation, fire management, and air quality forecasts. The FEDS fire tracking system can be used to analyze the response of wildfires to climate and land variabilities, evaluate and optimize of fire spread models, and compare large fires. Other potential uses include estimating high-resolution fire emissions in near-real-time, and supporting machine learning applications that improve real-time prediction of active fire evolution.</p>
Tags
  • Active Fire Perimeters
  • FIRMS
  • Fire Perimeters
  • NASA
  • arc
  • canada-ca
  • conus
  • fire-growth-models
  • fire-spread-modeling
  • raster-map
  • united-states
  • viirs
isopen False
metadata_created 2026-10-30T16:58:14.785736
metadata_modified 2026-10-30T16:58:14.785741
notes <p><span style="color: rgb(52, 58, 64);">The Fire Event Data Suite (FEDS) algorithm </span><a href="https://www.nature.com/articles/s41597-022-01343-0/" rel="noopener noreferrer" target="_blank" style="color: rgb(39, 97, 227); background-color: rgb(255, 255, 255);">(Chen et al., 2022)</a> <span style="color: rgb(52, 58, 64);">clusters active fire detections into individual events and estimates the perimeter and properties of ongoing fire events every 12 hours, based on Visible Infrared Imaging Radiometer Suite (VIIRS) 375 m active fire detections. The estimated perimeter data are routinely produced within approximately four hours of each VIIRS overpass for the Continental United States (CONUS) and Canada. For fires that ultimately grow larger than 4 km2, these modeled perimeters and associated attributes are stored in sequence to track the growth and behavior of each large fire event.</span></p>
num_resources 3
num_tags 12
title Fire Event Data Suite (FEDS) Algorithm