Digitization of Weiss Aiand irrigation processes through artificial intelligence to reduce resource use Project leader Viktorija Zagorska Team of project Viktorija Zagorska Maksims Fiļipovičs Ieva Erdberga Guna Bundzēna Inta Jakobija Duration 2023 - 2026 Research focus 4. Development and adaptation of technologies for obtaining high-value agricultural and forest products, as well as in veterinary medicine Source of funding International project Project partners Weiss Aiand Ltd. (Osaühing Weiss Aiand) Description of project The aim of research The aim of the project is to develop a digital solution for which more detailed irrigation recommendations will be shared based on real-time data and artificial intelligence (AI). The tasks of project: To develop the concept of a data model through data analysis and mapping of the latest research, to then collect the necessary data from the growing environment from which a machine learning model will be developed to provide the grower with accurate irrigation recommendations.To create a software application that will collect information from greenhouse sensors and analyze it through the use of data monitoring and machine learning techniques.To focus on conducting a pilot test of the connection between the theoretical model and the machine learning and data analysis software application. Results In the project two systems were tested: standard irrigation (2 rows) and AI-based irrigation (2 rows). From 5 March to 25 September, a total of 76 tomato plants were grown. Parameters recorded on different sensors: (i) substrate drainage volume, (ii) plant weight, (iii) EC, pH and substrate temperature, (iv) greenhouse temperature and relative humidity, etc. More than 450 000 data records were collected during the study. The AI-based irrigation system proved to be fully automated and reliable. We plan to further improve its efficiency in the next pilot phase.
