Sign up for our daily Newsletter and stay up to date with all the latest news!

Subscribe I am already a subscriber

You are using software which is blocking our advertisements (adblocker).

As we provide the news for free, we are relying on revenues from our banners. So please disable your adblocker and reload the page to continue using this site.

Click here for a guide on disabling your adblocker.

Sign up for our daily Newsletter and stay up to date with all the latest news!

Subscribe I am already a subscriber

Predicting rose yield with a drone

Aligning rose production and demand is a daily challenge for rose growers delivering directly to retailers. Manually counting bud- and flower stages costs time, and manual counts are not objective. A mismatch in production and demand is very costly and has a negative OPEX effect.

Corvus Drones is launching the rose yield prediction application. "The drone flies fully automatically in the greenhouse and takes pictures of the crop, which are analyzed by AI-powered computer vision software. Reporting is sent via email, or growers can use or an ERP integration link. It's easy to implement and operate. There is no greenhouse infrastructure necessary besides WIFI at the main aisle. The drone can be operated from the growers' office, and flights can be daily scheduled. Everyone can operate the drone from anywhere", Frans-Peter Dechering of Corvus Drones explains.

Five bud and flower stages are being detected by the drone, he continues. "The accuracy meets the manual counting. The big difference is that the drone operates 24/7 and has, for instance, no Monday morning illness. The rose yield prediction is being validated by Berg Roses, Porta Nova, and Meewisse Roses in the Netherlands. The varieties Red Naomi, Avalanche, and several others are part of this validation. The results are presented via an interactive reporting tool. The bud and flower classification can be seen per detailed greenhouse location."

These Dutch companies are also testing the powdery mildew detection. "Powdery mildew is one of the most harmful diseases in roses worldwide and costs growers lots of money. The expectation is that this mildew detection application will be available in the summer of 2024. In African and Central American countries, the rollout of the rose yield prediction is currently ahead."

The development of this rose application is a result of international collaboration between agtech companies and rose growers. Corvus Drones are flying and do the data collection. Quantum Mobile from Ukraine runs the AI-powered computer vision analysis, and the growers are daily testing the solutions.

The rose yield prediction application will be introduced at the IFTF exhibition, November 8-10 in the Netherlands. The drone will fly in the Corvus Drones booth (C2.31).

For more information:
Corvus Drones

Publication date: