Development and Multi-Objective Optimization of Water Use and Plant Nutrition on Crop Performance Using an Artificial Intelligence-Based Digital Twin

Mohadeseh Eslami Kanafi¹ Abbas Hajipour²

1) Lecturer, University of Applied Science and Technology, Alborz Province, Karaj, Iran,
2) Student at Ershad Boys Non-Governmental Lower Secondary School, Lahijan, Gilan Province, Iran;

IOI Code : ABEB-ACZHAA
Publication : 4th International Conference on Recent Advances in Engineering, Innovation and Technology - Belgium(eitconf.com)
Abstract :
    Today, modern agriculture faces challenges such as limited water resources, increasing costs, climate variability, and the need to enhance productivity and production sustainability. In general, the development of precision agriculture technologies, the Internet of Things (IoT), and artificial intelligence (AI) enables real-time monitoring and analysis of field conditions. However, many existing systems still face limitations in data integration, crop condition prediction, and the conversion of monitoring data into multi-objective management decisions. Therefore, Digital Twin technology, as a dynamic digital representation of a physical agricultural system, has emerged as a promising approach for monitoring, prediction, and decision support. Recent studies have shown that integrating Digital Twins with the Internet of Things and artificial intelligence can provide a foundation for intelligent and data-driven agricultural management. Accordingly, the aim of the present study is to analytically investigate the potential of integrating Digital Twin and artificial intelligence technologies for the simultaneous optimization of water consumption, plant nutrition, and crop yield, as well as to propose a framework for the development of intelligent systems in precision agriculture. Within this framework, data obtained from soil and environmental sensors, IoT-based systems, and crop growth monitoring are integrated into the Digital Twin environment. These data are then processed using artificial intelligence models to predict irrigation requirements, nutritional status, and crop yield. Subsequently, multi-objective optimization algorithms, considering conflicting objectives such as reducing water and fertilizer consumption while increasing crop yield, provide a set of optimal management strategies. The results of this review indicate that an intelligent Digital Twin can evolve from a system focused solely on monitoring into an environment capable of prediction, simulation, and decision support, thereby enabling the evaluation of different management scenarios before their implementation in the actual field. Accordingly, the development of integrated frameworks based on Digital Twin and AI technologies can provide important pathways for the transition from precision agriculture toward intelligent and sustainable agriculture.

Keywords : internet of things multi objective optimization plant nutrition digital twin water management artificial intelligence