Seed Selection System Using Genomic-Environmental Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Agricultural growers face challenges in selecting the optimal seeds for specific fields due to varying environmental conditions, leading to inconsistent yields, as existing methods do not effectively account for genetic characteristics and field-specific data to predict yield performance.

Innovation Solution

A computer-implemented system that utilizes genetic data and field-specific information to generate a dataset of seed properties, success probability scores, and risk values, recommending target seeds for optimal yield performance and risk management by integrating agronomic models, seed classification, and recommendation subsystems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If growers select seeds based on general yield ratings without considering field-specific conditions, then seed selection is simple and quick, but yield consistency and performance reliability deteriorate

Engineering Contradiction:

Improveseed selection processVSAvoidyield performance

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system transforms the seed selection process by changing the parameters considered from general yield ratings to field-specific predictions that incorporate environmental conditions, soil characteristics, and genetic data. This allows growers to make informed decisions tailored to each field's unique characteristics, improving yield consistency while maintaining an automated selection process.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system performs preliminary analysis of field conditions, seed genetics, and environmental factors before planting decisions are made. By pre-calculating success probability scores and generating field-specific recommendations, the system enables growers to select optimal seeds in advance, ensuring better yield performance without complicating the actual planting process.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If growers use diversified planting strategies to manage environmental fluctuations, then yield consistency improves, but decision complexity and data processing requirements increase

Engineering Contradiction:

Improveyield consistencyVSAvoiddecision support system

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system incorporates feedback loops that continuously monitor field performance, environmental conditions, and seed outcomes. This feedback mechanism allows the system to learn from past plantings and refine its predictions, enabling diversified planting strategies to be optimized automatically without requiring growers to manually complex decision-making processes.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system acts as an intermediary between complex agricultural data and grower decision-making. By processing genetic data, environmental information, and historical performance through automated algorithms, the system translates complex inputs into simple, actionable recommendations, reducing the perceived complexity for growers while maintaining sophisticated analysis.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Productivity

If existing seed selection methods are used without genetic data integration, then data processing is simpler and faster, but prediction accuracy and success probability assessment deteriorate

Engineering Contradiction:

Improvedata processing speedVSAvoidyield prediction accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system extracts and isolates the most critical genetic characteristics and field-specific factors from vast amounts of data, focusing computational resources on the most predictive variables. This extraction approach maintains processing efficiency by avoiding unnecessary computation while capturing the essential elements needed for accurate yield prediction and success probability assessment.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS20230177589A1Leveraging feature engineering to boost placement predictability for seed product selection and recommendation by field

Publication Date: 2023.06.08 MONSANTO TECHNOLOGY LLC

AI summary

An example computer-implemented method includes receiving a plurality of agricultural data records including yield properties of one or more products grown in a given field and continuous data indicative of multiple raw field features and specific to the given field. The method also includes transforming the raw field features into distinct feature classes and generating, using data from the plurality of agricultural data records and the distinct feature classes, genomic-by-environmental relationships between the one or more products. Further, the method includes generating, based at least in part on the genomic-by-environmental relationships, predicted yield performance for a set of products associated with one or more target environments, generating product recommendations for the one or more target environments based on the predicted yield performance for the set of products, and providing one or more instructions configured to cause display of the product recommendations.