GIS-based G × E modeling of maize hybrids through enviromic markers engineering

Area of Science:

• Agricultural Science
• Genetics
• Environmental Science

Background:

• Precision breeding aims to improve crop yield and genetic gains by tailoring varieties to specific environments.
• Enviromics integrates environmental data with genetic information to understand genotype-environment interactions.
• Traditional breeding methods may not fully capture the complex interplay between crop genotypes and diverse environmental conditions.

Purpose of the Study:

• To leverage enviromics and geotechnologies for precision breeding in maize.
• To develop and evaluate machine learning models for predicting maize grain yield based on envirotypic data.
• To identify optimal genotype-environment combinations and minimize genotype-environment interactions for enhanced crop performance.

Main Methods:

• Collected data from 183 field trials across Brazil, including 164 maize genotypes (phenotyped hybrids and their parents).
• Engineered 10K synthetic enviromic markers using 1342 covariates from weather, soil, sensor, and satellite sources via machine learning.
• Applied an enviromic ensemble-based random regression model and clustering analysis to assess predictive performance and identify regions with minimal genotype-environment interactions.

Main Results:

• Soil, radiation, and temperature variations significantly influence genotype-specific maize grain yield, indicating ecophysiological adaptations.
• The enviromic ensemble model demonstrated superior predictive performance and efficiency over baseline and kernel models.
• Clustering analysis successfully identified regions that minimize genotype-environment interactions, facilitating targeted breeding strategies.

Conclusions:

• Enviromics offers a powerful approach to enhance the precision and efficiency of maize breeding programs.
• Utilizing envirotypic information allows for better selection of hybrids suited to specific environments, leading to improved crop performance.
• This study underscores the potential of enviromics in developing superior parental combinations for higher-yielding hybrid crops.