Tailor-made support for operators in greenhouse horticulture

Problem Context

For decades, greenhouse horticulture in the Netherlands has been leading the world in terms of food and flower production in greenhouses. Every day, the greenhouse operator makes many decisions to control the greenhouse in such a way that its crops can grow under the best conditions. These decisions are often based on personal experience. Increasingly, the operator uses decision-support systems to do this. However, these systems assess greenhouse processes differently from the operator. As a consequence, they give different recommendations for greenhouse control than the operator would. The system’s recommendations depend on an intended objective, rather than the experience of the operator, and as such, the implicit knowledge of the operator is usually not taken into account in such systems.

Ideally, a decision-support system applied in the greenhouse horticulture should be able to learn from the experience of greenhouse operators. Simultaneously, greenhouse operators can benefit from the knowledge an AI system can provide. For example, it could autonomously assess the different control processes in the greenhouse through applied sensors. An ideal system in horticulture would thus be a system where the AI and the operator can learn from each other, a co-learning process.


To this end, this project is developing the Greenhouse AI Accumulator (GAIA). GAIA will use input from sensors in the greenhouse, such as data on crop development, to design a collective control strategy. This control strategy allows various underlying existing sub-controllers to work together to achieve a good balance in the greenhouse control processes. GAIA will furthermore use existing and new AI technologies, like Model-based Predictive Control and/or Reinforcement Learning, to provide setpoint advice. This advice will always be accompanied by a good explanation through explainable AI techniques. The operator can learn from the decisions of the system and will also be enabled to give feedback with substantiation about the correctness of an advice. The feedback will be used by the AI system to create improved future advice. In this way, the system learns from the operator, who makes decisions based on ‘green fingers’ founded on years of experience.

Through GAIA, this project aims to support the greenhouse operator in making the correct decisions to achieve maximum yield and product quality in greenhouses at minimum cost and impact on the environment. In the longer term, this should lead to largely autonomously functioning greenhouses, making food production in greenhouses easier and more feasible in large parts of the world. The intended result of this project is to deliver a proof-of-concept of a first version of GAIA in which AI techniques are applied and fine-tuned for optimal greenhouse control. Additionally, a mechanism will be delivered for explainability and a hybrid-AI approach for co-learning between the greenhouse operator and GAIA. Finally, it is the intent to generate experimental results of the GAIA proof-of-concept for a specific greenhouse to test the usability for the operator.

From an overarching viewpoint, the development of GAIA helps the Dutch greenhouse horticulture sector to stay ahead in the development of high-tech greenhouses. The application of AI systems is especially important for high-tech greenhouses at locations in the world with less agronomic expertise. In those places, in-depth expertise will more often be located at a distance (‘remote control’), therefore it is required that one can rely more on autonomous systems.


A prototype of GAIA has been realized, based on a hybrid framework which includes an AI Neural Network component to predict the greenhouse climate, a physical plant model to predict the plant state, and a knowledge graph to take in the feedback and expertise from the operator.

GAIA works with any given set of objectives. For concreteness, two main objectives were defined, namely maximizing the yield and minimizing the energy cost. A Model-based Predictive Control optimization algorithm is responsible for finding the optimal control setpoints which can involve multiple objectives (optimal crop growth and minimal energy cost). GAIA works with the climate and energy-management settings and uses its built-in plant model to predict the crop-mass. These predictions can be compared with measurements of the crop mass on a regular basis.

The operator has the possibility to add his knowledge and expertise in the form of control rules. They express relationships between parameters in the greenhouse, regarding plant, climate, and outside weather. By adding rules to the system, the knowledge of the operator is explicitly added and can be used as guidance for the GAIA setpoint calculation. The rules from the operator are stored in a knowledge base in terms of the CGO (Common Greenhouse Ontology). This ontology is used because it formulates the weather, the climate in the greenhouse, and the control setpoints in a structured and common manner.

To train GAIA’s AI model, simulated timeseries generated by SIOM, a greenhouse simulation model, have been used. In addition, SIOM was also used to evaluate how well GAIA performs. The evaluation showed that the AI model is able to generate reliable predictions for the whole growing period in terms of optimal setpoints for day and night temperatures, maximum CO2 concentration, maximum relative humidity, and the control of the energy screen.

To show how the GAIA system works and to present the results, a mock-up dashboard was developed. Besides the generated setpoint predictions, also the effects of using these setpoints on the performance objectives is shown graphically. The operator has the option to give feedback to the advice given by the system and to add control rules to the knowledge base. After this, the GAIA system updates its calculations and presents the newly obtained results.

This project will continue into 2022. The work to be carried out has as main goal to make the current GAIA prototype practically applicable in existing greenhouses or small test compartments with actual growers or crop managers. To realize this goal, the following objectives are set for 2022. The explanation of the advice given by GAIA will be improved and extended. This will be done in such a way that the grower can understand what the reason was for the advice to apply changes in greenhouse control. Besides an advice on greenhouse control, this also could give the grower new insights, beyond his own experience. By feeding the reaction of the grower to GAIA in return, continuous two-way learning between the operator and the GAIA system will be realized and existing knowledge and expertise of the grower can be taken into account. The last objective is to make the step from training GAIA with simulated data to real greenhouse data. In addition, it is intended to test and evaluate GAIA in a setting with an actual greenhouse and a grower.


This project is part of the Appl.AI programme of TNO and is partly funded by the start impulse the NL AIC received from the Dutch government for research and development of AI applications. GAIA is developed by TNO in cooperation with Ridder and Hortivation (through the adjacent project AGROS, co-funded by TKI “Tuinbouw en Uitgangsmaterialen”).


  • Jack Verhoosel, Sr. Business Consultant & Architect, e-mail: