Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BARC) » Beltsville Agricultural Research Center » Food Quality Laboratory » Research » Research Project #444727

Research Project: Machine Learning-Enabled Produce Quality Monitoring Platform for Nondestructive Supply Chain Management

Location: Food Quality Laboratory

Project Number: 8042-43440-006-011-S
Project Type: Non-Assistance Cooperative Agreement

Start Date: Aug 1, 2023
End Date: Jul 31, 2025

This project seeks to develop machine learning-enabled produce quality monitoring platforms using E-nose method. Specifically, ARS and Cooperators will 1) develop nondestructive sensing platforms for volatile compound related to produce quality using an array of sensors; and 2) develop machine learning algorithms to enable produce quality monitoring and assess the maturity level of agricultural products rapidly and accurately.

The proposed work will develop an array of sensors for non-specific and multi-dimensional measurement of volatile compounds with a wide range of odor characteristics. AI algorithms can be developed and trained on extensive datasets, enabling them to learn the intricate patterns and relationships between volatile compounds and produce maturity stages. This allows for the development of predictive models that can rapidly and accurately assess the maturity level of agricultural products. The application of AI-enhanced E-nose with sensor arrays offers advantages such as real-time monitoring, scalability, and the ability to process large volumes of data. This technology can aid farmers and producers in making informed decisions about optimal harvest timing, post-harvest handling, and quality control measures. By leveraging AI-enhanced E-nose methods with an array of sensors, the agricultural industry can enhance its ability to assess produce maturity based on volatile compound profiles, leading to improved product quality, reduced waste, and enhanced consumer satisfaction.