Breeding Model Weight Tuning for Multi-Objective Parent Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing breeding programs face challenges in accurately determining the best parents to cross when selecting a set of breeding starts, especially with a large number of options, as they struggle to balance characteristics, commercial values, relatedness, and risks in plant breeding pipelines.

Innovation Solution

A system and method that automatically tunes weights associated with breeding models to select parents based on predicted commercial values, relatedness, and risks, using a multi-objective selection process and algorithms like simulated annealing or parallel tempering to enhance decision-making by aligning with human breeder selections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual selection of breeding parents is performed, then breeder expertise and judgment are utilized, but the process is time-consuming and subjective

Engineering Contradiction:

Improveselection accuracyVSAvoidselection time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical selection processes with automated computational algorithms. The system uses computer-implemented methods to automatically evaluate breeding candidates based on multiple criteria including genetic diversity, commercial value, and risk assessment, substituting human manual evaluation with algorithmic processing that is both faster and more consistent.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service automation where the breeding selection process serves itself through automated algorithms. The computational system independently evaluates all breeding candidates, adjusts weights based on performance feedback, and generates selections without requiring continuous human intervention, allowing the process to optimize itself over time.

Inventive Principle:

Principle #25Self-service

2Productivity

If automated selection algorithms are used, then processing speed increases, but accuracy in balancing multiple breeding objectives decreases

Engineering Contradiction:

Improveselection throughputVSAvoidselection accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system dynamically changes parameters including weight assignments to different breeding objectives based on performance feedback. The algorithm adjusts the relative importance of various criteria such as genetic diversity, commercial value, and risk factors, allowing it to optimize selections across multiple competing objectives rather than using fixed parameter settings.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The selection system transitions from static to dynamic operation by continuously adapting weight parameters based on performance feedback. The system learns from outcomes and adjusts its evaluation criteria in real-time, making the selection process dynamic rather than fixed, thereby improving accuracy while maintaining high throughput.

Inventive Principle:

Principle #15Dynamics

3Measurement precision

If comprehensive evaluation of all breeding candidates is performed, then selection quality improves, but computational complexity and resource requirements increase

Engineering Contradiction:

Improveevaluation accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the comprehensive evaluation process into distinct modular components: genetic diversity assessment, commercial value evaluation, risk analysis, and weight adjustment mechanisms. Each component handles a specific aspect of the evaluation independently, making the overall complex system manageable through functional segmentation while maintaining comprehensive assessment capabilities.

Inventive Principle:

Principle #1Segmentation

4Reliability

If traditional breeding programs evaluate all potential crosses, then no candidates are missed, but the number of crosses requiring testing becomes unmanageably large

Engineering Contradiction:

Improvecandidate coverageVSAvoidnumber of crosses

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The system applies partial evaluation action by using the comprehensive multi-criteria model to score and rank all candidates, then selectively advancing only the top-ranked candidates for actual breeding and testing. This allows the system to maintain full candidate coverage in evaluation while reducing the quantity of crosses that proceed to resource-intensive testing phases.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12423616B2Methods and systems for automatically tuning weights associated with breeding models

Publication Date: 2025.09.23 MONSANTO TECHNOLOGY LLC

AI summary

Systems and methods for use in identifying weights to be employed in a selection algorithm associated with plant advancement are disclosed. One example method includes identifying a start set of weights for a selection algorithm associated with a breeding program, and for each scale parameter value in a schedule, and for each of N iterations, modifying the start set of weights based on the scale parameter value, identifying a set of germplasm based on at least the modified set of weights, advancing the modified set of weights to a next iteration as the start set of weights when certain criteria are satisfied, and identifying the modified set of weights as an output when the iteration is equal to N.