SGGW scientists work on an innovative system for determining the mineral requirements of plants

Professor Hazem M. Kalaji conducts research on creating a biological mechanism that allows for identifying nutrient deficiency in plants. This is a real revolution in agriculture and horticulture. The advantage of the system over other similar ones is the fact that the received signals indicate the plants’ demand for minerals long before these deficiencies become visible to the naked eye.

Currently, the experiments conducted in controlled laboratory settings may be applied in greenhouse and open-field conditions. Using advanced research techniques and the ability to conduct non-invasive measurements, such as chlorophyll fluorescence signals, we can obtain a huge amount of data from plants. Data providing information about the health and physiological state of plants is extremely valuable for tools using artificial intelligence and machine learning. The systems based on these technologies can diagnose the condition of plants and prevent many agricultural problems that have previously been difficult to detect.

Professor Kalaji, Institute of Biology, SGGW, conducts intensive research on developing a system for diagnosing mineral deficiency in crops such as wheat, barley, corn, and rapeseed, as well as horticultural crops, i.e., tomato, cucumber, basil, and lettuce in cooperation with private and industrial sectors.

A prototype of such a system is under construction. It could be assembled, e.g. in greenhouses, or on mobile devices and machines, such as drones, autonomous platforms or agricultural machines.

This is a breakthrough innovation in diagnosing mineral deficiencies in crop plants, regardless of where they grow; in the field, in a greenhouse, or in the laboratory. Before the symptoms of deficiency become noticeable, the device will be able to precisely determine the needs of plants by analyzing data related to photosynthesis, in particular chlorophyll fluorescence signals.

The key advantage is the ability to perform quick and non-invasive measurements, lasting from a few seconds to a few minutes. The collected data is then processed using artificial intelligence and machine learning technologies.

The real-time information delivers updated data on the optimal fertilization, missing elements, and the amount of supplement needed.

This is a significant improvement over traditional methods based on destructive and time-consuming chemical analyses, and spectral signals, which result mainly from morphological changes, or satellite images. The solutions used so far are expensive, less precise, and dependent on weather conditions. Introducing that innovative device to the market will undoubtedly contribute to savings in fertilization and an increase in the quality and quantity of harvests.