Rice seed integrity evaluation: Developing a rapid onsite system to check seed fraud using a portable NIR spectroscopic device coupled with smartphone technology

Abstract

Rice seed integrity is critical in ensuring high yield and grain quality; however, seed fraud, particularly the misrepresentation of rice paddy (unhusked rice grain) as rice seed, is a growing concern that threatens sustainability efforts. This study investigates using a portable NIR spectroscopic device, combined with chemometric analysis, for rapid onsite identification of rice seed and paddy varieties for real-time verification of seed authenticity. A total of 280 rice samples, representing four varieties (Agra, Amankwatia, Legon 1, and Jasmine 85) across two categories (seeds and paddy), were analyzed. After applying various pre-processing techniques and principal component analysis (PCA), linear discriminant functions 1 and 2 successfully revealed distinct clustering patterns for both the varieties and categories (rice seed and paddy). Among the classification algorithms used, Random Forest (RF) achieved 100 % accuracy for rice seed identification and 97.38 % for paddy identification in the test sets. Support Vector Machine (SVM) demonstrated 98.15 % accuracy in distinguishing between rice seed and paddy for detecting seed fraud. These results suggest that a portable NIR device can reliably perform varietal identification and seed authenticity checks within the agricultural value chain. This technology has significant potential for use by seed inspectors, farmers, and regulatory officers, offering a non-destructive, real-time solution for the rice industry.