Soybean Variety Placement Mapping With Regression Models

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Growers and trusted advisors face challenges in understanding soybean variety growth behavior due to subjective and unreliable conventional characterization methods, leading to uncertainty in variety selection and inefficient field management practices.

Innovation Solution

A computing system using regression machine learning models processes spatial and machine data to generate environment-specific varietal responses and multi-genetics planting recommendations, displayed via a graphical user interface, enabling objective soybean variety placement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional subjective characterization methods are used to evaluate soybean varieties, then the evaluation process is simple and quick, but the reliability and objectivity of the results deteriorate

Engineering Contradiction:

Improvereliability of variety characterizationVSAvoidcomplexity of evaluation system

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces manual visual inspection and subjective assessment with automated machine learning models that process satellite imagery and spatial data. This substitution of mechanical/visual evaluation with computational algorithms objectively quantifies soybean variety performance, eliminating human bias while maintaining operational feasibility through automated processing pipelines.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces machine learning models and spatial data processing systems as intermediaries between the soybean fields and the evaluation results. These intermediaries automatically extract and analyze variety characteristics from satellite imagery, providing reliable objective measurements without requiring direct human intervention in the field assessment process.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If intensive manual labor is used for crop sample preparation and field characterization, then detailed variety information can be obtained, but the time consumption and labor requirements increase significantly

Engineering Contradiction:

Improveprecision of variety characterizationVSAvoidtime for sample preparation and collection

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual sample collection, preparation, and analysis with remote sensing technology and automated machine learning processing. Satellite imagery captures field data without physical sample collection, and algorithms automatically process this data to extract variety characteristics, eliminating time-consuming manual laboratory procedures while maintaining measurement precision.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent performs preliminary data collection through satellite imagery acquisition before any analysis is needed. By continuously monitoring fields with satellite data and pre-processing this imagery through machine learning models, the system has variety characterization data ready before planting decisions must be made, eliminating last-minute sample preparation delays.

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If conventional field management recommendations based on intuition and anecdote are used, then the recommendation process is quick and easy, but the accuracy and reproducibility of recommendations deteriorate

Engineering Contradiction:

Improveaccuracy of planting recommendationsVSAvoidcomplexity of recommendation system

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements feedback loops where machine learning models continuously learn from historical field performance data, variety trial results, and environmental conditions. This feedback mechanism refines the accuracy of planting recommendations over time by adjusting model parameters based on actual observed outcomes, making the system both accurate and reproducible while maintaining automated operation.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent transforms subjective qualitative assessments into objective quantitative parameters through machine learning models. By converting variety performance into measurable spatial patterns from satellite imagery and encoding recommendations as data-driven parameters rather than intuitive judgments, the system achieves high accuracy and reproducibility through parameterized algorithms.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12354345B2Methods and systems for visualizing soybean variety placement using variety profile index

Publication Date: 2025.07.08 ADVANCED AGRILYTICS HOLDINGS LLC

AI summary

A computing system includes processors and computer-readable media having stored instructions that, when executed, cause the system to receive a machine data set, retrieve one or more spatial data files, process the spatial data files and the machine data set using a regression machine learning model to generate predicted values, determine a plurality of environment-specific varietal responses for each agricultural field, generate a multi-genetics planting recommendation and a map layer showing respective predicted variety profile index values for each agricultural field, and display the multi-genetics planting recommendation and the map layer via a graphical user interface.