Autonomous Cultivation
In greenhouses and vertical farms, many aspects of growing can already be controlled in various ways. So, what if you could develop a fully autonomous cultivation method that could be applied to any indoor cultivation system, anywhere in the world? That’s the ambition of WUR researchers working in the field of Autonomous Cultivation.
What the future of ‘autonomous' looks like
Our world’s growing population and changing climate press us to find the most efficient production methods for our crops. Greenhouse horticulture plays an important role in the year-round production of fresh and healthy fruit and vegetables with a consistently high quality. Cultivation in greenhouses must be efficient in the use of natural resources, economically viable, and produce a high quality product according to tight planning. However, the limiting factor is becoming the availability of sufficient highly qualified staff with knowledge to cultivate a high-quality product and who can oversee all aspects of an efficient production system with minimal use of resources.
We are working towards an autonomous greenhouse in which cultivation is controlled remotely via artificial intelligence, with the help of intelligent sensors and measurements of crop characteristics, and in which automatic systems handle crops to achieve a sustainable and profitable cultivation system.
Our areas of expertise
We bring together all the knowledge needed to make the ultimate future-proof greenhouse a reality: one that requires minimal human labour, minimal inputs in terms of scarce resources like water and nutrients, but maximal efficiency and outputs, and is applicable all over the world.
As the international hub of fundamental knowledge in life sciences, our in-house experts work on plant physiology, sensor technology and vision, machine learning and robotics, and advanced new technologies such as digital twins. State-of-the-art research facilities in Wageningen and Bleiswijk allow us to combine system knowledge, integration, and validation under one WUR roof.
Plant physiology
To control the greenhouse system that consists of crop, climate and substrate, an understanding of plant physiology is vital. Plant physiology aims to understand plant growth and development, including the underlying plant processes, such as photosynthesis and transpiration, in response to changes in their environment.
Crop health
A full understanding of the development of ecology-based systems for plant health tailored to local conditions on water use and quality, substrate, and nutrient use are essential dimensions to reach the level of full autonomous cultivation.
Cultivation systems and crop management
Optimising plant development over time and ensuring high quality research trials and data, make human involvement necessary. This requires planning, organisation and quality management. The insights generated by large-scale experiments are essential to come to a thorough understanding which technologies can benefit autonomous cultivation systems the most.
Crop Modelling
Environmental factors (e.g. light) and management practices (e.g. row spacing, pruning, LEDs) affect crop growth and yield. We use (3d) crop simulation models to research the effects on a variety of crops grown in greenhouses and vertical farms.
Greenhouse and climate modelling
The application of physical models is a way to predict the greenhouse climate based on the principles of calculating heat and mass balances. Its components, such as absorption of solar and artificial light, heating, crop transpiration, condensation, and ventilation, follow well-known laws of physics. The parameters describing these physical processes are a major topic of our ongoing research. Moreover, the model is constantly updated with the development of climate control equipment like the newest lighting modules, dehumidification equipment, energy screens and cooling equipment. With computations based on these well-parameterized processes, we can define and implement resource-use-efficient climate control strategies.
Digital twins
Digital twins use data-integration, artificial intelligence (AI), and machine learning to create a virtual version of a crop. These simulation models are continuously fed real-time information from the actual circumstances in a greenhouse, making it possible to analyse and simulate processes and reactions of plants more accurately. With the help of digital twins, we can better monitor plants and predict future scenarios.
Vertical farming
Vertical farms are plant production systems where all environmental parameters are fully controllable. This gives an unprecedented ability to provide the crop with the resources it needs, when it needs them, to grow optimally. With fully enclosed high-wire or multi-layer research facilities, research on resource use and crop responses under different environments can be accurately quantified.
Spectral imaging
Spectral imaging camera systems are able to measure non-destructively chemical compounds, stress- and disease symptoms in plants and many other plant traits invisible to regular RGB cameras. Spectral imaging offers a wealth of information to detect object quality thanks to a whole spectrum analysis available per pixel. Using spectral imaging in combination with models, we can measure the spatial distribution of dry matter content, nitrogen status or sugar concentration, and even lycopene, chlorophyll concentration and much more.
Sensor technology
Non-invasive sensors can measure and monitor a variety of plant traits, plant cultivation and climate conditions in greenhouses. The data provides insights to constantly improve the conditions in the greenhouse and support management decisions. There is a wide range of robust sensors available, and novel sensors and improvements are constantly released.
Robotics and Automation
Robotic systems in greenhouses need to be able to work in a highly challenging environment and deal with complex products that show a lot of variation and change in time (grow or ripen, for example). We design robotic systems combining hardware and software to a functioning robot that can think, sense, and act in such conditions with a key focus on replacing expensive labour for dull, repetitive, and unpleasant tasks.
Visit the website
AI & (3D) imaging
AI is rapidly becoming ubiquitous, largely due to the standardization of deep learning model training. The next frontier lies in standardizing deployment, tracking model performance, and maximizing efficiency through active learning-annotating only the most informative images. Success in applying AI, however, hinges on integrating system knowledge.
In greenhouse environments, an increasing number of traits can now be measured thanks to advancements in sensor technology. Yet, growers often struggle to translate these measurements into actionable feedback for their crops. This is where collaboration between crop growth and AI experts becomes crucial. Together, we focus on identifying traits that are not only measurable and relevant but also directly linked to crop growth models.
Curious about optimizing AI for your application? Reach out to our team of experts, we’re here to help.
Novel Non-destructive Sensors
The traits we need to measure in agriculture are varied and often, traditionally, require us to manipulate and sometimes harm the plant in order to get accurate ideas of its biomass, root structure, or protein content. Non-destructive imaging allows us to measure these attributes while the plant alive giving additional functional information about how to plant reacts in real time to stresses. Non destructive imaging involves a large array of technologies from Radar and electric impedance tomography to map underground structures, to radioactive Carbon labelling to investigate the plants' metabolism to X-ray imaging which can see fine structures in the plant tissue.
Synthetic data
AI models need to be trained with lots of high-quality data. In cases where it is not possible to get enough annotated training data, synthetic data can be used to complement real world data. We create realistic 3d models of plants, which have both the looks and variety as seen in the real world. With this data we can create virtual environments which provide high quality annotated data. We can also add robots to this environment, which results in a virtual playground where robots can be tested and trained to do the complex tasks we encounter in agri-food.
Fruit, bulbs, and flower quality
The timely and accurate monitoring of defects in fruits, vegetables, bulbs and flowers is crucial to guarantee high quality to consumers. However, delivering defect-free products remains a challenge because quality inspections are still largely performed by humans, which can introduce errors. Could automated systems and smart data collection be key to detecting and predicting the development of defects in a timely manner?
Autonomous control
Growers play an essential role in adjusting the climate to optimal crop growth conditions. They keep a constant keen eye on their
plants throughout their development until harvest, ensuring high yields, profit, and turnover. Autonomous control is the next step in supporting growers to take a step back from this demanding process, enabling them to focus on other aspects of crop production optimisation.
Fertigation
Fertigation plays a crucial role in delivering two essential elements to plants: water and nutrients. Its success lies in the ability to provide these elements in the right quantities, at the right time, and in the right place. However, this seemingly straightforward concept involves complex interactions. Like climate control, fertigation must adapt to changing environmental conditions and the plant's growth stages. To achieve this adaptability, accurate data and reliable models are indispensable, enabling precise and timely adjustments. Mistakes in this process can compromise the entire cultivation effort. At our Root Zone Dynamics team, we employ the principles of Integrated Rootzone Management (IRM) to drive innovation and advancements in applied science, continuously refining fertigation techniques for optimal results.
Contact our experts
Microbiology
Microorganisms are everywhere around us and provide many essential functions, such as supporting the growth of plants, suppressing pathogens in the root zone and the transformation of nutrients. In our research we study how to steer the microbiome to support the growth of plants, to suppress rootzone pathogens, and to make nutrients available when moving to organic fertilizers. Measuring the effects of beneficial micro-organisms on plant growth and functioning can be integrated in future autonomous systems.