Regression approaches for modelling genotype-environment interaction and making predictions into unseen environments

2025-07-24

AI Summary

This study addresses the challenge of improving prediction accuracy for crop cultivar performance in unobserved environments while rigorously quantifying predictive uncertainty. We propose a unified prediction framework grounded in linear mixed models, systematically integrating Finlay–Wilkinson regression, latent-variable regression, and reduced-rank regression—unifying them under a common modeling paradigm assuming random genotype-by-environment (G×E) interactions. Methodologically, we innovatively combine factor analysis, kernel functions, genomic relationship matrices, and random-coefficients modeling, augmented with Bayesian and resampling-based uncertainty quantification. Through rigorous multi-fold cross-validation on long-term rice trial data from Bangladesh, the framework demonstrates significantly improved across-environment prediction accuracy and yields well-calibrated prediction intervals. The results provide an interpretable, generalizable, and uncertainty-aware statistical foundation for environment-adaptive breeding decisions.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Graphical Models
• Multiagent Systems: Multiagent Systems under Uncertainty

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

In plant breeding and variety testing, there is an increasing interest in making use of environmental information to enhance predictions for new environments. Here, we will review linear mixed models that have been proposed for this purpose. The emphasis will be on predictions and on methods to assess the uncertainty of predictions for new environments. Our point of departure is straight-line regression, which may be extended to multiple environmental covariates and genotype-specific responses. When observable environmental covariates are used, this is also known as factorial regression. Early work along these lines can be traced back to Stringfield & Salter (1934) and Yates & Cochran (1938), who proposed a method nowadays best known as Finlay-Wilkinson regression. This method, in turn, has close ties with regression on latent environmental covariates and factor-analytic variance-covariance structures for genotype-environment interaction. Extensions of these approaches - reduced rank regression, kernel- or kinship-based approaches, random coefficient regression, and extended Finlay-Wilkinson regression - will be the focus of this paper. Our objective is to demonstrate how seemingly disparate methods are very closely linked and fall within a common model-based prediction framework. The framework considers environments as random throughout, with genotypes also modelled as random in most cases. We will discuss options for assessing uncertainty of predictions, including cross validation and model-based estimates of uncertainty. The methods are illustrated using a long-term rice variety trial dataset from Bangladesh.

Problem

• Model genotype-environment interaction for better predictions
• Assess prediction uncertainty in new plant breeding environments
• Link disparate methods under a unified prediction framework

Innovation

• Linear mixed models for genotype-environment interaction
• Factorial regression with environmental covariates
• Extended Finlay-Wilkinson regression methods