Monitoring of in-field risk of infection events by foliar pathogens using smart IoT nodes

In precision agriculture, risk of infection has emerged as a critical approach to optimize crop yields and resource usage. However, the current paradigm largely relies on massive data collection which expends energy resources and gathers a substantial amount of non-essential data. This paper challenges this paradigm by proposing a localized approach to precision agriculture through the deployment of Internet of Things (IoT) technology for real-time crop monitoring and resource management. The primary objective is experimenting local analysis depending on the environmental data collected by an implemented Wireless Sensor Network (WSN), and addressing a power consumption study for a long-lasting experimentation. We propose a test scenario based on a well-known infection model. Our results demonstrate the feasibility and efficiency of a localized approach over massive data collection by a robust and scalable monitoring system, showcasing the positive impact of orchestrated homogeneity among nodes in a local analysis, and the associated power consumption efficiency gains.