What are the most recent successes from Dryad?
Dryad recently closed €10.5m in Series A Funding to bring ‘Ultra-Early’ Wildfire Detection to the global market.
The funding will enable us to scale its team, accelerate its go-to-market strategy, and deliver on its mission to fight climate change and protect forests around the world.
How are you testing and applying the fire detection technology?
Also, we are currently running 10 Proof of Concept trials in southern Europe, the US, and Asia and our first medium-scale rollouts are planned for later this year. Our partner Prüfrex will manufacture a batch of 10,000 sensors in October and we are planning for 230,000 units in 2023.
For months now, we’ve been organizing a series of prescribed burnings over Europe to continue developing our sensors and machine learning algorithms. After conducting a recent prescribed burning in Nuremburg, Germany we decided to leave our sensors in the burnt field to continue monitoring.
Then, while setting up our stand at INTERFORST in Munich with Bosch Security and Safety Systems, we unexpectedly received an alert from one of our sensors.
Despite thinking it could be a false alarm, we decided to err on the side of caution and alert the fire services anyway. It turns out it was real! A zombie fire had continued after extinguishing the prescribed burning and the next day’s wind had reignited it.
This is the first unplanned wildfire detected by our Silvanet sensor system and it was detected ultra-fast. Since we caught it in its smoldering phase, it was an easy task for the fire services to put it out and stop it from spreading.
How did working with Omdena Top Talent AI teams provide better results?
By hosting an Omdena AI Innovation Challenge, we got access to a selected team of 50 AI engineers in a short time frame.
The project’s goal was to build an intelligent model that will detect fire in different types of wood through analysis of the existing sensor data. During the period of eight weeks, the team designed and implemented several data-based pipelines, leveraging the dataset provided by the Dryad team.
The results of this project lie in the state of art machine learning models and correctly classify the sensor data into two categories, “in-smoke” and “clean-air”. The model developed in this project is scalable and replicable.
In addition, we are working with Omdena top talent teams to improve our current gas detection model performance by optimizing the training pipeline.