Integration of Crop Growth Models and Genomic Prediction

Onogi, Akio

doi:10.1007/978-1-0716-2205-6_13

Cited by 9 publications

(8 citation statements)

References 94 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have indicated that environmental information helps to enhance the prediction of phenotypic performance (Heslot et al 2014;Technow et al 2015;Costa-Neto et al 2021, 2022. When modeling GEI in maize with machine learning, Westhues et al (2021) did not observe much gain when predicting plant height, but the grain yield prediction improved after including environmental information.…”

Section: The Importance Of Environmental Information Should Not Be Un...mentioning

confidence: 98%

“…These environmental data can be applied in enviromics studies by envirotyping the testing locations (Costa-Neto et al 2021, 2022 or in a combined way with biological knowledge through crop growth models to increase accuracy in GP (Heslot et al 2014;Technow et al 2015). In this case, increases of up to 11% in prediction accuracy have been observed (Heslot et al 2014).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using machine learning to integrate genetic and environmental data to model genotype-by-environment interactions

Fernandes,

Vieira,

Dias

et al. 2024

Preprint

View full text Add to dashboard Cite

Complementing phenotypic traits and molecular markers with high-dimensional data such as climate and soil information is becoming a common practice in breeding programs. This study explored new ways to integrate non-genetic information in genomic prediction models using machine learning (ML). Using the multi-environment trial data from the Genomes To Fields initiative, different models to predict maize grain yield were adjusted using various inputs: genetic, environmental, or a combination of both, either in an additive (genetic-and-environmental; G+E) or a multiplicative (genotype-by-environment interaction; GEI) manner. When including environmental data, the mean predictive ability of machine learning genomic prediction models increased from 7-9% over the well-established Factor Analytic Multiplicative Mixed Model (FA) among the three cross-validation scenarios evaluated. Moreover, using the G+E model was more advantageous than the GEI model given the superior, or at least comparable, predictive ability, the lower usage of computational memory and time, and the flexibility of accounting for interactions by construction. Our results illustrate the flexibility provided by the ML framework, particularly with feature engineering. We show that the featured engineering stage offers a viable option for envirotyping and generates valuable information for machine learning-based genomic prediction models. Furthermore, we verified that the genotype-by-environment interactions may be considered using tree-based approaches without explicitly including interactions in the model. These findings support the growing interest in merging high-dimensional genotypic and environmental data into predictive modeling.

show abstract

Section: The Importance Of Environmental Information Should Not Be Un...mentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Using machine learning to integrate genetic and environmental data to model genotype-by-environment interactions

Fernandes,

Vieira,

Dias

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

“…While this study focused on growth curves represented by nonlinear equations, crop growth in response to the environment has been described by a physiological model known as a crop growth model (CGM) [22][23][24][25][26][27][28]. In the context of the CGM, there has been some discussion about the advantages of one-step and two-step models [27,28]. In the two-step model, CGM parameters are first estimated for each variety, and then models for specific genetic analysis, such as QTL analysis, genome-wide association study and genomic prediction, are applied to the estimated parameters.…”

Section: Introductionmentioning

confidence: 99%

“…In the one-step model, the genetic effects on the variation of CGM parameters is modeled from the onset and CGM parameters for all varieties are estimated simultaneously. In the one-step February 27, 2024 4/56 model, Bayesian modeling is used due to its complexity, and the CGM parameters are estimated using computational algorithms such as Markov chain Monte Carlo (MCMC) [25], approximate Bayesian computation (ABC) [22,24], and variational Bayes (VB) [23,27]. Although our study focused on nonlinear growth curve models, genetic modeling and estimation algorithms for parameters have been studied in CGM as well.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modeling soybean growth: A mixed model approach

Delattre

Toda

Tressou

et al. 2023

Preprint

View full text Add to dashboard Cite

The evaluation of plant and animal growth, separately for genetic and environmental effects, is necessary for genetic understanding and genetic improvement of environmental responses of plants and animals. We propose an original approach that combines nonlinear mixed-effects model (NLME) and the stochastic approximation of the Expectation-Maximization algorithm (SAEM) to analyze genetic and environmental effects on plant growth. These tools are widely used in many fields but very rarely in plant biology. During model formulation, a nonlinear mechanistic function describes the shape of growth, and random effects describe genetic and environmental effects and their variability. Genetic relationships among the varieties were also integrated into the model using a kinship matrix. The SAEM algorithm was chosen as an efficient alternative to MCMC methods, which are more commonly used in the domain. It was implemented to infer the expected growth patterns in the analyzed population and the expected curves for each variety through a maximum-likelihood and a maximum-a-posteriori approaches, respectively. The obtained estimates can be used to predict the growth curves for each variety. We illustrate the strengths of the proposed approach using simulated data and soybean plant growth data obtained from a soybean cultivation experiment conducted at the Arid Land Research Center, Tottori University. In this experiment, plant height was measured daily using drones, and the growth was monitored for approximately 200 soybean cultivars for which whole-genome sequence data were available. The NLME approach improved our understanding of the determinants of soybean growth and can be successfully used for the genomic prediction of growth pattern characteristics.

show abstract

Using machine learning to combine genetic and environmental data for maize grain yield predictions across multi-environment trials

Fernandes,

Vieira,

Dias

et al. 2024

Theor Appl Genet

View full text Add to dashboard Cite

Key message Incorporating feature-engineered environmental data into machine learning-based genomic prediction models is an efficient approach to indirectly model genotype-by-environment interactions. Abstract Complementing phenotypic traits and molecular markers with high-dimensional data such as climate and soil information is becoming a common practice in breeding programs. This study explored new ways to combine non-genetic information in genomic prediction models using machine learning. Using the multi-environment trial data from the Genomes To Fields initiative, different models to predict maize grain yield were adjusted using various inputs: genetic, environmental, or a combination of both, either in an additive (genetic-and-environmental; G+E) or a multiplicative (genotype-by-environment interaction; GEI) manner. When including environmental data, the mean prediction accuracy of machine learning genomic prediction models increased up to 7% over the well-established Factor Analytic Multiplicative Mixed Model among the three cross-validation scenarios evaluated. Moreover, using the G+E model was more advantageous than the GEI model given the superior, or at least comparable, prediction accuracy, the lower usage of computational memory and time, and the flexibility of accounting for interactions by construction. Our results illustrate the flexibility provided by the ML framework, particularly with feature engineering. We show that the feature engineering stage offers a viable option for envirotyping and generates valuable information for machine learning-based genomic prediction models. Furthermore, we verified that the genotype-by-environment interactions may be considered using tree-based approaches without explicitly including interactions in the model. These findings support the growing interest in merging high-dimensional genotypic and environmental data into predictive modeling.

show abstract

Integration of Crop Growth Models and Genomic Prediction

Cited by 9 publications

References 94 publications

Using machine learning to integrate genetic and environmental data to model genotype-by-environment interactions

Using machine learning to integrate genetic and environmental data to model genotype-by-environment interactions

Modeling soybean growth: A mixed model approach

Using machine learning to combine genetic and environmental data for maize grain yield predictions across multi-environment trials

Contact Info

Product

Resources

About