Autonomous Greenhouses 2nd Edition


Autonomous Greenhouses 2nd Edition

Computer scientists and horticultural experts form multidisciplinary teams to challenge themselves as well as the state of the art in human operated greenhouse production in order to make a large step towards the Autonomous Greenhouse. If the capabilities of an AI driven greenhouse can be demonstrated, it will imply a significant opportunity to drive horticultural productivity while reducing resource use and management complexity. AI might help us live healthier lives and make it possible to produce more vitamin rich food in greenhouses for growing human populations.

Join our Challenge!

We would like to invite computer scientists and horticultural experts to form multidisciplinary teams and join the second edition of the autonomous greenhouse challenge. The teams are asked to combine their expertise in artificial intelligence, machine learning, sensor technology with knowledge in greenhouse crop production, crop management and plant physiology to compete against each other as well as measured themselves against a group of experienced traditional growers.

Future proof food production

In the future even more greenhouses might be needed to produce our food. Nowadays skilled growers manage greenhouse climate and crop based on their long-term experience and the so-called "green thumb". However, it is hard to find enough skilled personnel in many countries worldwide.

Currently, significant advances are being made in automation, information technology and artificial intelligence (AI). Automated information and AI can help the grower to oversee all the information needed and to make better complex decisions.

Text continues under the video

- Unfortunately, your cookie settings do not allow videos to be displayed. - check your settings

Could AI be able to outperform the human-operated greenhouse production in the future?

In 2018, five international teams took part in the first edition of Autonomous Greenhouses. They were challenged to remotely control a greenhouse cucumber production during a 4-month period, while competing with each other and with a group of experienced manual growers. As far as we know, such a worldwide experiment had never been conducted before. The first edition resulted in a successful benchmark experiment demonstrating that state-of-the-art algorithms can control greenhouse climate and irrigation at a distance, compete with experienced growers and even outperform them in one case.


However, there is still some way to go in this combined field of AI and greenhouse horticulture: ongoing data acquisition for AI training purposes, evaluation of sensors' utility, automated data gathering on crop growing parameters, development of more robust and scalable algorithms able to generate decisions for both climate and crop. This and much more is needed for the development of an autonomous AI control system able to get closer and closer to an optimal greenhouse production. 

This challenge is sponsored by Tencent

Autonomous Greenhouses