PHENO_MaizE: UAV-based high-throughput field phenotyping in temperate maize breeding

Abstract

High-throughput field phenotyping (HTFP) has become an important approach for improving the efficiency and objectivity of phenotypic evaluation in modern plant breeding. Within the PHENO_MaizE project the practical application of UAV-based RGB phenotyping in temperate maize breeding under field conditions is investigated. The project integrates repeated drone imaging, extraction of image-derived traits, and predictive modeling in order to evaluate the potential of digital phenotyping for the selection of superior maize genotypes. Experimental material includes maize inbred lines and their corresponding testcrosses evaluated across multiple environments in Serbia. UAV surveys conducted during the growing season will enable monitoring of temporal crop development and extraction of traits such as plant height, canopy cover, vegetation indices, and growth dynamics. The research within the project will also assess the potential of phenomic prediction models for estimating important agronomic traits, including grain yield, flowering time, and grain moisture at harvest. Special emphasis is placed on developing a practical, cost-effective, and scalable HTFP framework adapted to medium-sized breeding programs. The expected outcomes may support wider implementation of digital phenotyping and data-driven selection strategies in maize breeding.

Code and data availability

This is a review/project-concept paper describing the planned PHENO_MaizE UAV phenotyping project. No phenotype datasets, UAV images, author code repositories, trained models, or supplements with data are provided; the only URLs are citations to prior work (e.g., FIELDimageR/UASTools are generic libraries, not authors'

No evidence-backed public reproduction asset is currently recorded.