Skip to main content

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Automated compost monitoring with low-cost RFID, drones, and machine learning for improved control and pathogen safety

Objective

Composting transforms organic waste into nutrient-rich soil amendments but requires strict temperature and moisture control to ensure pathogen inactivation and regulatory compliance. Current monitoring methods—manual sampling or expensive wireless sensors (e.g., Reotemp, HOBO loggers) which limit data resolution and increase labor costs. Large windrows, often spanning hundreds of feet, exhibit spatiotemporal temperature and moisture variations, where cold spots allow pathogen survival and hotspots pose combustion risks. Conventional monitoring methods fail to capture these variations comprehensively, jeopardizing compost quality and regulatory compliance. This project will develop and validate an intelligent compost monitoring system that integrates low-cost, battery-free RFID sensors ($3–4/unit, 80–90% cheaper than existing solutions), drone-based readers, and machine learning analytics to enable real-time, high-density temperature and moisture monitoring. Drones equipped with RFID readers and LiDAR will autonomously collect geo-located sensor data, which will be processed through a digital dashboard for 3D compost pile visualization, risk hotspot detection, and decision support. This system also automates compliance reporting to meet FDA §112.60(b)(2) standards. The project has three key objectives: (1) Deploying a dense RFID sensor network to capture compost process indicators, (2) Developing a visualization and analytics platform for real-time monitoring and risk detection, and (3) Validating the system over five composting cycles at two Tennessee facilities. The systems will be assessed for its ability to accurately capture spatiotemporal temperature variations, reduce labor costs, and improve regulatory compliance. By enabling compost operators to detect cold spots, ensure uniform heating, and optimize turning schedules in real time, this solution will enhance process efficiency and streamline compliance documentation. Ultimately, this innovation supports safer, more sustainable composting operations by providing automated, data-driven decision support.

Investigators
Chetan Badgujar, Ph.D.; Sai Swaminathan, Ph.D.; Shawn Hawkins, Ph.D.
Institution
University of Tennessee
Start date
2026
End date
2027
Funding Source