Application of machine learning techniques and the Internet of Things for smart, sustainable agriculture

Abstract

The integration of the Internet of Things (IoT) and Artificial Intelligence (AI) has been extensively utilized in the agricultural sector for an extended duration in conjunction with various other sophisticated computing technologies. In the past few years, there has been a notable advancement in greenhouse development within the agricultural sector, driven by the guidance of information technology and resulting in increased productivity. The IoT encompasses a range of intelligent systems and remote monitoring technologies, including those that support sustainable development. This study examines the accessibility of information technology in the context of training and developing smart systems and forecasting models within organizations, focusing on real-time applications using Machine Learning (ML) and AI techniques. This paper aims to enhance the efficacy of agricultural sustainable growth governance by investigating the Smart Sustainable Agriculture (SSA) platform, utilizing IoT and ML technology as its foundation. Hence, a proposed system called Remote Sensing Aided Framework for Smart Sustainable Agriculture (RSAF-SSA) aims to enhance the fulfillment of greenhouse agriculture prerequisites by applying ML techniques and the IoT. The proposed methodology employs AI and ML technologies to strengthen the green development prospective industry’s capacity to manage financial resources and foster innovative trends in agricultural product development. Also, this study integrates the requirements for sustainable development in the field of SSA by establishing a Smart Agriculture (SA) platform that utilizes IoT and ML. Additionally, experimental designs are devised to assess the effectiveness of the system platform developed in this work. With 50 IoT devices, the Irrigation Control Ratio (ICR) and Agricultural Production Ratio (APR) for the proposed RSAF-SSA achieve a noteworthy efficiency rate of 95.8% and 95.3%, respectively.