Rapid Plant Development Modelling System for Predictive Agriculture Based on Artificial Intelligence

• Published in: 2021 16th International Conference on Telecommunications (ConTEL) pp. 173 - 180
• Main Authors: Lesic, Vinko, Novak, Hrvoje, Ratkovic, Marko, Zovko, Monika, Lemic, Darija, Skendzic, Sandra, Tabak, Jelena, Polic, Marsela, Orsag, Matko
• Format: Conference Proceeding
• Language: English
• Published: University of Zagreb, Faculty of Electrical Engineering and Computing 30-06-2021
• Subjects: Agriculture; Artificial intelligence; Big data; Climate change; Cloud computing; Computational modeling; Data models; Mathematical model; Plant growth encapsulated design; Plants (biology); Predictive agriculture; Predictive models; Rapid plant development modelling
• DOI: 10.23919/ConTEL52528.2021.9495972

Actual and upcoming climate changes will evidently have the largest impact on agriculture crops cultivation in terms of reduced harvest, increased costs, and necessary deviation from the traditional farming. The aggravating factor for the successful applications of precision and predictive agriculture is the lack of big data, due to slow, year-round cycles of crops, as a prerequisite for further analysis and modelling. The goal of the system we propose is to enable rapid collection of data with respect to various climate conditions, which are artificially created and permuted in the encapsulated design, and correlated with plant development identifiers. The design is equipped with a large number of sensors and connected to the central database in a computer cloud. Such accumulated data is exploited to develop mathematical models of wheat in different growth stages by applying the concepts of artificial intelligence and utilize them for prediction of crop development and harvest. The paper presents a work in progress where the developed models will be publicly and interactively used through a portal for prediction of plant development in real and hypothetical climate conditions, with accumulated and archived feedback from farmers as additional data for tuning of the developed models.