NOAA’s US$3m experimental Next Generation Fire System (NGFS) is undergoing a second evaluation in the Fire Weather Testbed, which is managed by the Global Systems Laboratory in Boulder, Colorado. The follow-up visit is intended to evaluate how to best send NGFS fire detections directly to land management partners across the western USA.
NGFS was developed by NOAA Satellites and CIMSS, NOAA’s cooperative institute with the University of Wisconsin-Madison. During the first test in June 2024, NOAA scientists evaluated routing NGFS detections through NWS offices, which would issue hotspot notifications to partner agencies.
Technological features
The first of two key features of the experimental system are the Advanced Baseline Imager, the primary instrument on NOAA’s two GOES geostationary satellites orbiting 22,000 miles above the equator. The second is a set of NGFS algorithms that continuously comb through data generated by the imager and automatically identify heat anomalies or hot spots, even through clouds and smoke.
Any new sources of heat are overlaid on surface imagery and geolocated. Then an alert is sent instantly to an online dashboard so users can easily visualize the location. Once a fire is detected, the system tracks and records the fire’s spread and intensity. The information is simultaneously available to weather forecasters, fire dispatchers and first responders.
“NGFS can provide alerts in as little as one minute from the time the energy from the fire reaches the satellite,” said Mike Pavolonis, NOAA’s satellites wildland fire program manager, who is leading the research and development effort. “I’ve seen NGFS alerts for fires as small as a quarter acre.”
The satellites’ stationary positions enable the system to scan new imagery over an area covering multiple states every minute and generates a fresh image of the entire contiguous USA every five minutes.
“Lives can be saved or lost from what you learn in minutes or even seconds,” said Todd Lindley, science and operations officer with the Norman Weather Forecast Office in Oklahoma, which relied on the system during the spring wildfire outbreak.
Once a fire is burning, NGFS provides real-time weather and fire monitoring needed by fire incident management teams to keep firefighters safe.
Industry adoption
Less than a year after first being evaluated in NOAA’s Fire Weather Testbed, the automated satellite fire detection capability of the experimental Next Generation Fire System (NGFS) has been embraced by the firefighting community and is being increasingly integrated into operations across the country, NOAA said.
“The rapid adoption of NGFS demonstrates its significant value to meteorologists,” said Zach Tolby, the fire weather testbed manager at NOAA. “Now we want to look for ways to optimize the system for wildland fire management in the field.”
During the recent Oklahoma wildfire outbreak, state officials said GOES satellites provided initial detection on 19 separate fires. Of those, preliminary analysis of fire spread modeling found that rapid firefighter response likely saved more than US$850m worth of structures and property. In comparison, the total cost of NGFS development was under US$3m.
“The amount of damage that NGFS helped firefighters prevent during this single outbreak was 250 times greater than the cost of developing this system,” Pavolonis said.
Overall, 90% of the NWS’s 122 Weather Forecast Offices around the country have subscribed to the NGFS feed since it became available. Forecast offices in California, Oregon, New Mexico, Texas, Oklahoma, Nebraska and North Carolina have used it so far in 2025.
The California Office of Emergency Services (Cal OES) is using NGFS to improve situational awareness, and displays NGFS fire detections on its Statewide Initial Attack Viewer. In recent weeks, NGFS tracked the progress of a large fire in New Jersey’s Pine Barrens.
In related news, researchers at Bar-Ilan University in Israel recently developed an AI model that can predict where and when lightning strikes are most likely to cause wildfires, achieving over 90% accuracy. Click here to read the full story
