Multi-Source Data Integration and IoT-Based Sensing for Crop Yield Modelling and Optimisation

This paper presents the development and implementation of an IoT-enabled environmental sensing system designed for crop yield modelling and optimisation across diverse agro-ecological zones in Nigeria. The system integrates in-situ soil and atmospheric sensors, drone-based observations, and farm-level data using a multi-layered communication architecture, including cellular, Long Range Wide Area Network (LoRaWAN), and novel UAV-based mesh networks. Preliminary analysis of the collected data reveals strong correlations between cassava fresh yield and environmental factors such as soil water content, temperature, and electrical conductivity. The system demonstrates the potential of data-driven approaches to inform site-specific agronomic decisions and breeding strategies. While the system is still in the early phase of data collection, future work will involve expanded data integration, AI-based predictive modelling, and enhanced decision support for climate-smart agriculture.