Open Climate Tech

Open Climate Tech is a non-profit organization focused on building open source technologies that have the potential to help mitigate the adverse impacts of climate change.


Wildfire Detection and Checking

Wildfires are getting more destructive over time due to many factors including climate change. Besides the devastating impact on lives and property, wildfires also release significant amount of carbon back into the atmosphere, thus speeding up climate change even further. Depending on the location situation, sometimes it is better in the long-term to let fires burn, while at other times it's better to extinguish the fires as soon as possible. This project does not have any opinion on determining the optimal action for each fire. The goal of this project is to automatically detect wildfires in their initial phase, so the authorities responsible for wildfires can take appropriate action while the fire is still small and easy to manage.

This project uses machine learning to identify potential smoke from wildfires using real-time images from images installed on vantage points, such as mountain tops. The information about the potential wildfires are then sent to website for people to check and confirm whether they are real fires. This system has successfully detected some fires before authorities were aware of them, but the system also generates some false notificatons. Therefore, it is useful to have people review the notificatons. This system monitors more than a hundred cameras continuously, and usually generates less than 50 notifications a day. Doing the same task without such a system would require a large group of people to continuously stare at real-time images coming from a hundred cameras and maintain high vigilence throughout. That is the main impediment why these cameras are currently not used for detection, but only for verifying reports and for monitoring known fires.

Folks from multiple organizations have contributed to this project during its lifetime - listing some of them here in alphabetical order: FFLA San Diego, HPWREN, and Lawrence Berkeley National Lab.

This article describes some lessons learned while operating the system.

Wildfire Detection

The detection technique used by this project relies on machine learning based system. We trained a machine learning model for image object recognitionon (Inception V3) on cropped images of smoke from early phases of historical fires. Real-time images are collected from HPWREN cameras, divided into slightly overlapping squares of 299x299 pixels, and the machine learning system computes a value (between 0.0 and 1.0) for each square. High values are more likely to be real wildfires. The system is not perfect and regularly generates false positives, which are mostly triggered by fog or clouds. We are continuously working on improving the accuracy of the system. Below are sample images of both true and false positives.
True Positive
True Positive Smoke
False Positive
True Positive Smoke
When one of the squares scores high, the detection system applies a few other checks to discard cases that are unlikely to be smoke from real fires. A detailed description of an earlier version of the system and how it performed during a pilot period in Oct 2019 are published in this paper published in peer reviewed Remote Sensing journal. Also, the source code for the detection system is available on Github.

Wildfire Checking

The real-time potential fire notifications from the detection service are displayed on this live updating site. In case someone discovers a real fire that recently ignited, they should consider informing the wildfire dispatch center to take appropriate action. Please note that this site does not alert the authorities directly.

The site also allows users to vote on each notificaton to indicate whether it was a real fire or not. The events where the majority of the users confirm a real fire are displayed on a separate Confirmed Fires tab. The votes are also helpful for improving the system by retraining the machine learning system with new images. Users can also specify a desired geographical region to limit the notifications to those that may overlap the specified region. The source code for the wildfire checking website is available is available on Github.

Check potential wildfires


Open Climate Tech, Inc. is a non-profit organization that was formally founded in 2020. Although technology alone can't fix all the problems made worse by climate change, we believe technology can help mitigate some of the adverse effects. The projects supported by this organization are developed by volunteers, and we welcome enthusiastic contributors interested in joining existing projects or starting new projects. We believe that open sourcing the technology helps collaboration with other groups and encourages volunteers. All code should have an open source license.


Email if you have any questions, suggestions, or would like to collaborate.