Development and Field Evaluation of an IoT-based Multi Sensor Monitoring System for Large-Scale Sugarcane Cultivation

The lack of an energy-efficient, reliable wireless sensor network that integrates multiple heterogeneous sensors (soil, water, atmosphere, and plant canopy) with adaptive noise filtering remains a gap for large-scale tall crops like sugarcane. This study presents the design, implementation, and field validation of an energy-efficient, IoT-based multi-sensor monitoring system that addresses this gap for large-scale precision agriculture. The proposed system employs a multi-hop star topology to improve communication reliability while minimizing energy consumption in extensive field conditions. Each sensing node integrates an ESP32 microcontroller with heterogeneous sensors, including air temperature and humidity, leaf temperature, soil moisture, groundwater level, and LiDAR-based plant height measurement. A key contribution of this work is the integration of a LiDAR sensor for non-contact plant height estimation combined with a robust interquartile range (IQR)-based filtering algorithm to mitigate wind-induced noise. The communication framework utilizes NRF24L01+ modules for intra-cluster transmission and Wi-Fi for cloud connectivity, enabling efficient data aggregation and reduced power demand at the node level. The system was deployed and evaluated over a six-month period in a 12,000-ha sugarcane field. Results demonstrated high communication reliability (98.5%) and system uptime (>98%), despite environmental and operational challenges. A strong inverse correlation (r = −0.94) between communication reliability and energy consumption highlights the impact of retransmissions on power efficiency. Sensor validation against manual measurements gave R² ranging from 0.94 to 0.98, with no significant differences (p > 0.05) across most parameters. The IQR filter reduced plant height standard deviation by 65% (from 23.5 cm to 8.2 cm). The system provides a real-time multi-parameter monitoring and alerting platform supporting irrigation scheduling and stress detection in large-scale, resource-constrained environments.