Due to increasingly dry summers as a result of climate change and at the same time decreasing water availability (more difficult approvals for new wells by the counties), the nurseries' questions about precise and effective (water-saving) irrigation are increasing. Today, the management of the production factors water and nutrients is carried out by the farms almost exclusively according to the current situation of the crops and in the short term according to estimates or imprecise measured values. The only useful forecast is the weather report adapted to the agricultural sector. The farms themselves must draw the conclusions from this and implement them accordingly. The Predictive Plant Production project is essentially concerned with artificial intelligence to support plant-producing companies such as tree nurseries in targeted, resource-conserving plant growth.

The aim of the project is to develop a system for initially two model plants, the tree of life (Thuja) and the rhododendron, which monitors the environmental conditions of these plants with sensors and from this determines the care measures for plant growth that is as resource-efficient as possible or can be planned in time. For this purpose, substrate moisture, fertiliser concentration, soil temperature, local weather conditions, the addition of water and fertiliser and the shading and ventilation of greenhouses in a nursery are monitored with sensors and thus local conditions and influencing variables are learned individually for each location using artificial intelligence (AI) methods. The knowledge acquired is used to configure accurate prediction models of the water, fertiliser and temperature balance and, based on this, of plant growth, and then used to support the control of irrigation, fertilisation and temperature regulation and even to automate these.