These electronic ‘noses’ can smell wildfires using AI and alert fire officials

solo
Tech news
solo21 July 2023Last Update : 2 months ago
These electronic ‘noses’ can smell wildfires using AI and alert fire officials

Sensors can detect gases emitted during the early stages of a fire, allowing for more efficient and faster intervention.

Around 400 early-detection sensors have been installed in the Eberswalde forest in Brandenburg, the German region most affected by wildfires.

Solar-powered sensors are attached to the trees and also monitor temperature, humidity and air pressure.

The company behind the technology, Droid Networks, says they essentially act like “an electronic nose” and can detect gases emitted during the early stages of a fire, allowing for more efficient and quicker intervention.

As soon as a fire is detected, the data is sent to a cloud-based monitoring system and fire officials are alerted.

The Dryad network uses artificial intelligence to train sensors that can, for example, tell the difference between a forest fire or smoke from a passing diesel truck.

Jürgen Müller, co-founder of Dryad Networks, said, “Here in our lab, we are teaching artificial intelligence to use sensors for different forest fires: this sensor is the electronic nose. They now smell the smell of smoke coming from a pine or beech forest and the artificial intelligence maps this pattern, this ecosystem.”

Müller also teaches to differentiate between different types of wildfires by exposing the equipment to smoke from different types of wood shavings.

By doing so, the sensor learns “what the smoke smells like from a pine or beech forest,” he said.

Mueller says Droid Networks’ technology is faster than traditional surveillance systems.

“An important advantage is ultra-early detection. This means we can detect an emerging fire only a few minutes, 10 or 15 minutes before it starts to open fire. This means we can fight it quickly and thus reduce the damage significantly compared to optical systems,” he said.

Brandenburg is currently testing the reliability of the sensor in a pilot project in addition to the visual recognition method used in the state.

360-degree rotating cameras scan the surrounding landscape from the top of 105 towers.

The images are sent to the Forest Fire Center in Wuensdorf, south of Berlin, for close monitoring.

Brandenburg’s Forest Fire Protection Officer, Raimund Engel, says early intervention is key to preventing wildfires from spiraling out of control.

“The faster we detect a fire, the faster firefighters can get to the scene,” Engel said.

“In recent years, we have been able to reduce the size of the average fire area substantially, because wildfire early detection systems mean we can detect many fires earlier, preventing major damage,” he said.

According to Droid Networks, about ten countries are already experimenting with the device, including the United States, Greece and Spain.

The company sold around 10,000 devices last year and aims to install 120 million devices worldwide by 2030.

Scientists have warned that increased drought and hotter weather due to climate change will increase the risk of wildfires.

According to the European Forest Fire Information System (EFFIS), as of 18 June more than 119,000 hectares of land had already been burnt across the EU, far higher than the average of 80,000 hectares recorded up to that time in the period 2003–2022.

Short Link

Sorry Comments are closed