Abstract—With the increasing impact of climate change and population growth, enhancing crop productivity and ensuring food security have become more crucial than ever. To address this, new technologies are being introduced in the agricultural sector, and recent research has been conducted using machine learning and deep learning to analyze the relationships between crop genes and traits, aiming to boost productivity by selecting beneficial genetic information and predicting crop characteristics. In this study, we introduce machine learning-based methods for analyzing the correlation between crop genotype and phenotype, predicting phenotypes, and applying these techniques using data from tomato crops. Our results demonstrate the feasibility of predicting specific crop traits using various machine learning algorithms. Notably, we highlight the effectiveness of a semi-supervised learning approach, where synthetic genotypic data are generated to address the lack of genotype-phenotype-based datasets. Additionally, machine learning models showed similar predictive accuracy for populations cultivated in the same location over multiple years, underscoring the robustness of our approach across consistent environmental conditions.
 
Keywords—digital breeding, artificial intelligence, genomic selection, phenotype prediction


Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).