Leveraging AIoT Visual Analytics for Optimizing Agricultural Sustainability and Efficiency

Bemisia tabaci is an essential pest in global agriculture, and its reproduction and distribution are affected by meteorological conditions, causing severe damage to economic crops.This study constructed a micro-meteorological station and a visualized weather alert system combining narrow-band Internet of Things (NB-IoT) and message queuing telemetry transmission (MQTT) technologies in an orchard to achieve precise pest monitoring and early warning.The micro-weather station can record high-resolution meteorological data (e.g., temperature, humidity, soil moisture, sunlight intensity, etc.) and transmit them stably and efficiently via NB-IoT and MQTT technologies to ensure real-time data updates over long distances.The early warning system combines artificial intelligence (AI) and geographic information system (GIS) to analyze the impact of meteorological conditions on Bemisia tabaci, make risk predictions, and provide prevention and control recommendations, such as adjusting pesticide application strategies to reduce losses and pollution.This study demonstrates an innovative agriculture solution based on NB-IoT and MQTT, which realizes data-driven and intelligent pest management in orchards, improves monitoring accuracy and control efficiency, and is not only applicable to whitefly control but can also be extended to other pests and diseases, providing an efficient and sustainable technology example for agricultural pest management.