Methodology of Real-time Monitoring of the Crop Status Based on Internet of Things Technologies

• Published in: Russian agricultural sciences 2024, Vol.50 (1), p.59-63
• Main Authors: Savin, I. Yu, Blokhin, Yu. I., Chinilin, A. V.
• Format: Article
• Language: English
• Subjects: Agriculture; Biomedical and Life Sciences; Cameras; Crop production; Crops; Data analysis; Eye lens; Farming; Farming and Land Reclamation; Farming systems; Information management; Internet of Things; Life Sciences; Meteorological parameters; Methodology; Monitoring; Nodes; Plant Biochemistry; Precision farming; Radio equipment; Real time; Remote sensing; Sensors; Soil maps; Soil moisture; Spatial data; Spatial discrimination; Spatial resolution; System effectiveness; Wireless networks
• ISSN: 1068-3674; 1934-8037
• DOI: 10.3103/S1068367424010117

Digital technologies are being actively introduced into Russian agriculture at different levels of information analysis (from the plot to the field, farm, region, and whole country). One of the most important values in crop production at the field level is the introduction of systems for accurate, real-time, and automated monitoring of the crop status, the success of which largely predetermines the effectiveness of precision farming systems. The purpose of this research is to develop a methodology for using Internet of Things (IoT) technologies for noncontact monitoring of crops and related meteorological and soil-hydrological parameters. The basis for monitoring is a wireless network that includes sensor nodes equipped with sensors for meteorological parameters and soil moisture and cameras equipped with a fish-eye lens. Sensor nodes equipped with sensors and cameras are placed in the field according to a specially designed scheme individualized for each field. The development of the scheme of sensor placement in the field is based on analysis of long-term archives of satellite data with high spatial resolution and refined soil maps of large scale. Information from sensors is wirelessly transmitted to the network coordinator (or base station) and then to the remote server in the database, where it is automatically analyzed and interpolated to the entire field. The results of the analysis are used to form recommendations for correcting the agrotechnology of crop cultivation. The elements of the methodology have been tested on a number of test fields and have shown a high efficiency. The implementation of the proposed approaches can serve as an alternative to using remote sensing data for crop monitoring in offline precision farming systems.