Hybrid Corn Seeding Rate Modeling by Row Width

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Determining an optimal seeding rate for corn is challenging due to the complex interaction of hybrid seed types, soil productivity, weather conditions, and sowing row width, which affects yield and resource competition among plants, and existing methods fail to account for these factors effectively.

Innovation Solution

A computer-implemented system that utilizes agronomic models and data from various sources to recommend an optimal seeding rate based on hybrid seed type and sowing row width, incorporating regression and mixture models to generate a distribution of optimal seeding rates across fields.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If higher seeding rate is used to increase plant density, then total yield may increase, but resource competition between plants intensifies reducing individual plant yield

Engineering Contradiction:
Improvetotal yieldVSAvoidinter-plant competition
Core Design Contradiction:
ProductivityVSObject-generated harmful factors

Solution Approach 1:

The system changes the parameter of seeding rate based on multiple factors including hybrid seed type, sowing row width, soil productivity, and weather conditions. By dynamically adjusting this parameter rather than using a fixed rate, the system optimizes the balance between plant density and resource competition for each specific agricultural context.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system applies different seeding rates to different local conditions within the agricultural field. By considering variations in soil productivity, weather conditions, and specific hybrid seed characteristics, the system tailors seeding recommendations to local conditions rather than applying a uniform rate across the entire field.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If more data factors are considered in seeding rate determination, then accuracy of recommendation improves, but system complexity increases

Engineering Contradiction:
Improveseeding rate recommendation accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the complex determination process into distinct components: hybrid seed type classification, sowing row width measurement, soil productivity assessment, and weather condition evaluation. Each component processes specific data independently before integrating results to produce the final seeding rate recommendation, making the overall complex system more manageable and systematic.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3981237B1A method for recommending seeding rate for corn seed using seed type and sowing row width
Publication Date: 2025.09.17 CLIMATE LLC
  • EP3981237B1 patent drawingFigure 1
  • EP3981237B1 patent drawingFigure 2(a)~2(b)
  • EP3981237B1 patent drawingFigure 3

AI summary

Computer-implemented techniques for determining and presenting improved seeding rate recommendations for sowing hybrid seeds in a field. In an embodiment, seeding query logic receiving digital data representing planting parameters including seed type and sowing row width. The seeding query logic retrieves a set of one or more seeding models from a data repository based on planting parameters. Mixture model logic generates an empirical mixture model in digital computer memory that represents a composite distribution of the set of one or more seeding models. The mixture model logic then generates an optimal seeding rate distribution dataset in digital computer memory based upon the empirical mixture model, where the optimal seeding rate distribution dataset represents the optimal seeding rate across all measure fields. Optimal seeding rate recommendation logic calculates and presents on a digital display device an optimal seeding rate recommendation that is based upon the optimal seeding rate distribution dataset.