AI ‘Sniffs Out’ First Signs of Forest Fires in Germany

New technology produces ‘noises’ that help prevent natural disasters and could transform fire management.

Thu 20 Jul 23


Forestry is amongst the industries most impacted by the push towards Artificial Intelligence (AI) and automation.

Wood Central has reported that AI is increasingly used to assist with planting, carbon monitoring and real-time biodiversity reporting.

Now, AI sensors that can sniff out a wildfire in minutes are being trialled in Brandenburg, the German region most hit by forest fires.

In the heart of Eberswalde forest, northeast of Berlin, Jürgen Müller coaxed flames out of a fire pit using highly flammable pine branches as kindling.

It didn’t take long before the first wisps of smoke started curling into the air.

The 69-year-old retired forestry expert was testing a green-and-black device powered by solar energy that can detect the gases emitted during the earliest smouldering phase of a fire.

The devices were created two years ago by the Berlin startup Dryad Networks, which Müller co-founded, and come equipped with ultra-sensitive gas sensors developed by German engineering firm Bosch.

These devices come fitted with ultra-sensitive sensors powered with AI learning, which can differentiate between smoke of various types and alert authorities accordingly.

“In 10 to 15 minutes, we can detect an incipient fire before it becomes an open fire,” Müller said, adding that it was way faster than traditional systems involving monitoring through cameras.

Fire detection devices come fitted with ultra-sensitive sensors and are powered with AI learning.

He says that when a wildfire is detected, the data is immediately relayed to a cloud-based monitoring system and local authorities are alerted.

As more and more nations experience a surge in deadly wildfire incidents, the makers of the device believe their sales will shoot up. Dryad Networks says ten countries, including the US, Greece and Spain, are already experimenting with the device.

The startup sold 10,000 devices last year and hopes to install at least 120 million devices by the end of 2030.

Raimund Engel, Brandenburg’s forest fire protection officer, has hailed the devices as a useful addition to the current visual detection method.

“Weather conditions in the forest-rich area of Eberswalde are very similar to some Mediterranean regions”, Engel said, “with periods of drought and temperatures that sometimes reach up to 40 degrees celsius.”

He added: “The faster we detect fires, the quicker firefighters can be on the scene, so the intervention can greatly help authorities to prevent disasters before they rage out of control.”


  • Wood Central

    Wood Central is Australia’s first and only dedicated platform covering wood-based media across all digital platforms. Our vision is to develop an integrated platform for media, events, education, and products that connect, inform, and inspire the people and organisations who work in and promote forestry, timber, and fibre.


Related Articles