Wildfires are a natural occurrence, but when one breaks out close to civilization, the results can be devastating. Seniors at Monta Vista High School in Cupertino, California, Sanjana Shah and Aditya Shah have created a device that is designed to predict and prevent wildfires. Both students have been personally affected by the wildfires in California, and want to be part of the solution to reduce the devastation, and created Smart Wildfire Sensor.
Smart Wildfire Sensor works by being affixed to trees every square mile or so in a forest. The device will then capture images of nearby trees, fallen branches, and leaves. Those photos are then classified into thirteen different categories of varying threats. The students utilized an open-source machine-learning tool by Google called TensorFlow to process and categorize the photos into those thirteen different categories. When implemented, alerts will be sent to nearby fire crews when the forest fuel density and dryness reach a certain threat level.
While Smart Wildfire Sensor is still in the beta phase, progress continues to be made and the students are optimistic on the progress. The technology testing phase has been put on hold due to the recent wildfires in California, but the students should resume testing with Cal Fire once the all clear has been received. The cost for this technology is not yet readily available as the device itself needs to been tested for accuracy before widespread use can be discussed and utilized.