Explainable Artificial Intelligence for Soybean Seed Classification

• Grant number: 25/20861-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: October 01, 2025
• End date: September 30, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Renato Tinós
• Grantee: Sabrina Sousa Carvalho
• Host Institution: Faculdade de Filosofia, Ciências e Letras de Ribeirão Preto (FFCLRP). Universidade de São Paulo (USP). Ribeirão Preto , SP, Brazil
• Associated research grant: 24/15430-5 - Machine Learning-Based Multi-modal Data Fusion and Growth Modeling for Soybean Production Improvement, AP.PFPMCG.TEM

Abstract

This project focuses on developing and evaluating Explainable Artificial Intelligence (XAI) methods for soybean seed classification, aiming to combine high predictive accuracy with transparent, interpretable insights. Soybean seed morphology influences yield, but current computational tools for analysis are limited. The study will utilize RGB and hyperspectral seed image datasets, starting with an existing dataset and extending to new collections that reflect practical breeding conditions. Convolutional Neural Networks (CNNs) will be implemented and evaluated, while explainability techniques, such as Grad-CAM, will be applied to identify the image regions and features most relevant for classification decisions. By combining accurate classification with interpretable outputs, the project aims to enhance trust, usability, and adoption of Machine Learning tools in soybean breeding and agricultural applications.