Activate high contrast
To main content
Latest news
16 June 2020
Autonomous greenhouse: computer grows the best tomatoes and beats professional growers
A team of researchers and students from TU Delft and the companies Van der Hoeven Horticultural Projects, KeyGene and Hoogendoorn Growth Management has won the international Autonomous Greenhouse Challenge. The Automatoes team, with the help of artificial intelligence (AI) in a fully automated greenhouse, not only achieved the best tomato harvest after six months, but also scored best on sustainability. The Automatoes team not only competed against other international teams who also had to control their greenhouse remotely. At the same time, all teams also competed with a team of professional tomato growers who were allowed to enter their greenhouse. Remarkably, the algorithms of all teams beat the professionals. Cherry tomatoes The competition, organised by Wageningen University & Research and IT company Tencent, was about growing cherry tomatoes remotely , using in-house developed algorithms. Each team had access to a high-tech greenhouse compartment, equipped with the same installations, for controlling temperature, light, humidity and the amount of CO2, among other things. The young tomato plants were placed in the greenhouse in December 2019, and the control of the greenhouse and the crop was taken over remotely by the various teams a few days later. The last tomatoes were harvested at the end of May, after which all data could be analysed. The team did not attempt to create one complex AI system that controls everything, but divided the problem into bite-sized chunks. Best AI strategy Automatoes came out on top in all areas: the team not only achieved the highest net yield - high production and high quality - but also used the least resources (water / energy) per kilo of tomato and therefore also scored highest on sustainability. The team's AI strategy was also rated best on the following criteria: autonomous, innovative, robust and therefore implementable among commercial growers around the globe. The team did not attempt to create one complex AI system that controls everything, but divided the problem into bite-sized chunks. Team captain Leonard Baart de la Faille: “We looked at what a horticulturist is actually trying to achieve. It is essential to objectify and quantify this. This allows you to select a suitable AI method for each target. ” "We tried not to use data from other greenhouses," he continues. “You never see exactly the same greenhouse, in exactly the same climate with exactly the same crop. That is why we have also tried a new data-driven control technique that runs purely on the data of the greenhouse itself, without the use of training data from other greenhouses or a detailed simulation model. ” Optimal climate conditions Historical data from previous crops remains important, for example to determine the optimal climate conditions for these specific tomatoes. Researcher Tamas Keviczky from TU Delft: “The strive towards completely autonomous greenhouses offers excellent opportunities for the application and further development of data-driven control approaches that combine engineering models based on first-principles with online optimisation and machine learning. A key aspect is how to use a combination of real-time data from various sensors and weather predictions together with earlier records from the same greenhouse and crop cycle." Link between greenhouse and control system Data scientist Niek Bouman of KeyGene formed the link between the images from the greenhouse and the control of the system. He extracted relevant information from the images, in order to further improve the control algorithms. Bouman: “I had a great time with our team. Usually, I support plant breeders. At the Automatoes, I have been able to apply my knowledge and experience in a completely different area, with fantastic results. ” Personalised dashboard All data from team Automatoes was available ‘at a glance’ on a central platform. "This personalised dashboard contains both short- and long-term data, statistics and timelapses," says Evripidis Papadopoulos of Hoogendoorn Growth Management. "This meant that all relevant information was always available to everyone." Moreover, this data has been used for the algorithms, Rene Beerkens adds. "The team has therefore experienced all the benefits of data driven growing." TU Delft AgTech Institute In the run-up to the challenge, the recently founded TU Delft AgTech Institute , together with Van der Hoeven, formed the winning team of private parties and experts within the Delft University of Technology in the field of AI and Systems & Control, Business Developer Liselotte de Vries says. “The AgTech Institute is aimed at stimulating research and innovation around agri-food technology”, De Vries states. “The Autonomous Greenhouse Challenge is a great example of promoting public-private partnerships by connecting industry with our researchers and technology. In this way we contribute to the transition to a sustainable horticultural sector. ” The AgTech Institute is aimed at stimulating research and innovation around agri-food technology The future TU Delft and the companies are already working together on a new project, an extension of the Autonomous Greenhouse Challenge. The goal is to further automate the management of greenhouses using data-driven AI. This allows the Netherlands to maintain its leading position in agritech. At the same time, the companies will start to market parts of this approach as commercial products. TU Delft researcher Neil Yorke-Smith : "Winning was a team effort and the background and skills of the individual team members are also likely to be the key to a successful future collaboration!" More information Liselotte de Vries +31 6 41 63 45 27 Liselotte.deVries@tudelft.nl Tamas Keviczky +31 15 27 82928 T.Keviczky@tudelft.nl Contact page n.yorke-smith@tudelft.nl Contact page
30 April 2020
Investment of 14 million for better use of micro-organisms
Microorganisms can perform many processes useful to mankind, such as converting milk to cheese, keeping human and animal intestines healthy, and cleaning our water and environment. Together with Wageningen University & Research and Delft University of Technology, the Dutch Research Council (NWO) will invest almost 25 million euros in a research facility for investigating mixed microbial communities and their application. The research facility – called UNLOCK (UNLOCKing Microbial Diversity for Society) - consists of equipment and human resources that will be used to gather knowledge on micro-organisms effectively. Team-players Micro-organisms are natural team-players. They are essential for human health via the intestinal microbiome, and for processes like waste water treatment, soil fertilization for plant growth, and food preparation such as cheese or beer through fermentation. However, even though natural and man-made ecosystems are characterized by an enormous microbial diversity, research on microbial communities and their application in biotechnological processes historically has been conducted with a very limited number of strains isolated from these ecosystems. We are currently using no more than 1 per cent of the microbiological potential available in nature Ecosystem Besides that, research on micro-organisms usually focuses on a limited number of specific strains of organisms, while in nature micro-organisms always operate in ecosystems consisting of different species. ‘You could compare it to building a house’, says Robbert Kleerebezem, who is the Delft scientist involved in the project. ‘To build one, you need different experts, like masons, roofers, electricians and plumbers. You can pick out any one of them, and study what they are doing, but that won’t tell you anything about what the resulting house will look like.’ Eagerly awaited Wageningen and Delft have launched the new research facility UNLOCK to study mixed microbial cultures extensively. Various sub-areas of research will be integrated through UNLOCK. This development has been eagerly awaited by researchers studying mixed microbial communities. This integration will make significant scientific and societal breakthroughs possible. NWO's approval will make a 14.5 million euro funding available for the next decade, of which a third will go to TU Delft. Automated cultivation of ecosystems "In Delft we will be working on making automated systems in which we can cultivate ecosystems of micro-organisms in mixed compositions, and monitor them’, says Kleerebezem. ‘This makes UNLOCK a unique facility, because we will be able to do comparative studies on a large scale and in an efficient manner, in order to gain important insights into the interactions between micro-organisms’. New persepectives A total of 24.8 million euros will be invested in UNLOCK. Lead petitioner, Prof. Hauke Smidt is delighted with the approval. ‘This is fantastic. UNLOCK opens up entirely new perspectives for the discovery of new micro-organisms and ground-breaking research on mixed microbial communities’. UNLOCKing Microbial Diversity for Society In UNLOCK, Wageningen and Delft have joined forces towards full integration of all relevant fields of expertise in four complementary platforms: · The Biodiscovery platform (WUR-Microbiology) allows its users to discover and characterize new micro-organisms. In addition, there is a processing unit that allows for fully automated unlocking of biological samples for biomolecular analysis. · The Modular bioreactor platform (WUR-Environmental Technology) facilitates research for sustainable solutions to environmental issues, such as the degradation of (micro) pollutants, sustainable energy generation and reclaiming resources from complex waste streams. · With the Parallel Bioreactor platform (TU Delft -Biotechnology), users can simultaneously conduct dozens of experiments in bioreactors for comparative analysis on how process variables affect system development. · The FAIR data platform (WUR-Systems & Synthetic Biology) takes care of the storage, processing and interpretation of large quantities of data flowing from the experimental systems in a cloud-based infrastructure based on the FAIR principles (Findable, Accessible, Interoperable, Reusable). Large-scale Scientific Infrastructure NWO has allocated a total of 93 million euros to seven projects. The Ministry of Culture and Education makes funds available to NWO for the National Roadmap for a Large-scale Scientific Infrastructure. These funds enable the building and overhaul of essential research infrastructures. The awarded scientific infrastructures are of critical importance to innovative scientific research, and as a stimulus for economic and societal innovations across all scientific disciplines. Robbert Kleerebezem +31 15 2781091 r.kleerebezem@tudelft.nl
Upcoming events
Past events
