The global population is increasing rapidly, together with the demand for healthy fresh food. The greenhouse industry can play an important role, but encounters difficulties finding skilled staff to manage crop production. Artificial intelligence (AI) has reached breakthroughs in several areas, however, not yet in horticulture. An international competition on “autonomous greenhouses” aimed to combine horticultural expertise with AI to make breakthroughs in fresh food production with fewer resources. Five international teams, consisting of scientists, professionals, and students with different backgrounds in horticulture and AI, participated in a greenhouse growing experiment. Each team had a 96 m2 modern greenhouse compartment to grow a cucumber crop remotely during a 4-month-period. Each compartment was equipped with standard actuators (heating, ventilation, screening, lighting, fogging, CO2 supply, water and nutrient supply). Control setpoints were remotely determined by teams using their own AI algorithms. Actuators were operated by a process computer. Different sensors continuously collected measurements. Setpoints and measurements were exchanged via a digital interface. Achievements in AI-controlled compartments were compared with a manually operated reference. Detailed results on cucumber yield, resource use, and net profit obtained by teams are explained in this paper. We can conclude that in general AI performed well in controlling a greenhouse. One team outperformed the manually-grown reference.
Greenhouses and indoor farming systems play an important role in providing fresh and nutritious food for the growing global population. Farms are becoming larger and greenhouse growers need to make complex decisions to maximize production and minimize resource use while meeting market requirements. However, highly skilled labor is increasingly lacking in the greenhouse sector. Moreover, extreme events such as the COVID-19 pandemic, can make farms temporarily less accessible. This highlights the need for more autonomous and remote-control strategies for greenhouse production. This paper describes and analyzes the results of the second “Autonomous Greenhouse Challenge”. In this challenge, an experiment was conducted in six high-tech greenhouse compartments during a period of six months of cherry tomato growing. The primary goal of the greenhouse operation was to maximize net profit, by controlling the greenhouse climate and crop with AI techniques. Five international teams with backgrounds in AI and horticulture were challenged in a competition to operate their own compartment remotely. They developed intelligent algorithms and use sensor data to determine climate setpoints and crop management strategy. All AI supported teams outperformed a human-operated greenhouse that served as reference. From the results obtained by the teams and from the analysis of the different climate-crop strategies, it was possible to detect challenges and opportunities for the future implementation of remote-control systems in greenhouse production.
The rapid urban growth seen globally in recent years has not been supported by a simultaneous increase in agricultural land and/or crop productivity. Producing crops in (peri‐)urban areas shows good potential to provide the vegetable products for a healthy and balanced diet for the growing population, but it has to deal with the local availability of resources. Thus, meeting the food requirements of the urban population as efficiently and robustly as possible is a challenge. This study developed a methodology to estimate the use of resources of urban farming systems to produce energy‐ and nutrient‐dense vegetables capable of meeting human dietary needs. The method was applied to two extremely different cultivation systems (an open field farm and a plant factory with artificial lighting) for the production of seven crops. The results on the resource efficiencies to meet the annual per‐capita vegetable requirements are discussed in relation to crop type, local climate and cultivation system. The application of this methodology can support farmers' decisions on the choice of crops and the type of urban farming systems that are most efficient in contributing to a plant‐based diet. The results can also be translated into water, energy, and surface area needed to meet the nutritional requirements at a city‐regional level.
25 March 2024 in Journal of the Science of Food and Agriculture