Can artificial intelligence grow a lettuce crop completely autonomously?
Growing lettuce with artificial intelligence (AI) in autonomous greenhouses, by algorithms developed in different parts of the world: today the young lettuce plants of the five international teams that compete in the two final rounds of the Autonomous Greenhouse Challenge were planted in the experimental greenhouses of Wageningen University & Research in Bleiswijk. The goal is to grow these lettuces fully autonomously with an AI algorithm on a cloud platform with good quality and little resource and energy use and without any human interference. The competition and teams’ performance can be followed live on an online dashboard. Will the computer be able to complete a fully autonomous growing cycle?
What is done?
Five international teams located around the world will produce a lettuce crop using a fully autonomous algorithm during two growing cycles. With the lowest possible input of resources such as energy and CO2 and the production of many good quality heads of lettuce, they will optimize the net profit. Each team has a 96 m2 compartment at its disposal in the high-tech greenhouses of Wageningen University & Research in Bleiswijk.
The teams have created their own AI algorithms. These algorithms will fully autonomously determine the set points for temperature, amount of daylight and artificial light, heating, CO2 concentration and cultivation-related parameters such as crop density. Next to given standard sensors, the teams have access to specific sensors of Sigrow and Ridder and some of them also installed own sensors to deliver input for their algorithm.
The teams’ algorithms are mounted on a virtual machine on a protected WUR server. Data from the greenhouse is received via a digital interface from LetsGrow and Azure Cloud. At the same time, the algorithms autonomously send setpoints back to the process computer, which ultimately takes the action on climate control in the experimental greenhouse.
In a first cultivation cycle the algorithm and procedure are tested, in a second crop cycle the result counts. The team with the highest net profit will win the competition. Like in the earlier editions all collected data (not the algorithms) will be made publicly available after the competition has ended.
Who are the participants?
We expect an exciting competition of our 5 teams:
Team Crop Vision and Automation comes from Korea. The team members each have different backgrounds, from a grower to machine learning expert, robotics expert, software engineer, and full-stack programmer, but all of them have a common interest, which is to integrate agriculture and artificial intelligence. Their motto is “Anyone can grow”.
Team digital_cucumber, the team with the strange name comes from Russia. By participating in this competition they hope to not only contribute to the overall development of agriculture, exchange knowledge and experience with experts, but also inspire agrotechnological startups to develop and promote their technologies and ideas along with large corporations. Their motto is “We strive to become an indispensable part of the progress of Russian agriculture.”
Team MondayLettuce is also from Korea with several members participating in the second edition of the challenge as well. This year, they participate with their key partners to evaluate their technology. Furthermore, by interacting with different teams worldwide and testing their skills, they hope to establish new relationships and explore undiscovered opportunities. Their motto is ‟The realization of the future agriculture we envision.”
VeggieMight is an international team with experienced lettuce growers from both China and the Netherlands, data scientists from both the Netherlands and Ukraine, digital innovators and students from Wageningen University and Research. Their motto is “Unlock the Value of Digital Agriculture.”
Team Koala from the U.S. has the ambition to advance greenhouse growing with an intelligent automation technology that is scalable across farms, crops, and even more broadly across process-based manufacturing industries. Team captain of team 'Koala' is Kenneth Tran, who also led the winning team 'Sonoma' in the first edition of the Autonomous Greenhouse Challenge in 2019. Their motto is ‟I have all the Koalifications.”
Who can benefit?
Wageningen University & Research (WUR) organises the challenge. “We expect that food production in greenhouse horticulture can be further improved by adding more artificial intelligence to the agricultural industry”, says Silke Hemming, who leads the scientific research team Greenhouse Technology at WUR. “We make connections with international partners through this unique challenge, so that we can take major steps. Dutch growers - who are probably the most experienced worldwide - will also benefit from the results of the challenge. They will get more knowledge and may eventually discover algorithms to contribute to better decisions in the future.
How can you follow the result?
The public can follow the competition and teams’ performance on our live dashboard. Here, we will let you follow the cultivation and you will discover which team has harvested the most lettuces or which has used energy most efficiently.
Visit www.autonomousgreenhouses.nl for more background information.