Predictive Weed Mapping for Adaptive Harvester Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Agricultural harvesters face performance degradation when encountering weed patches, especially when weeds are wet, due to variations in weed intensity and type, which can impede machine operation and reduce efficiency.

Innovation Solution

The use of a predictive weed map generated from in-situ data combined with prior data, incorporating vegetative indices like NDVI, to control agricultural work machines by adjusting settings such as feed rate, machine speed, and operator commands, allowing for real-time adaptation to weed conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the harvester operates at normal speed through weed patches, then productivity is maintained, but performance degradation occurs due to wet weeds impeding machine operation

Engineering Contradiction:
Improveharvesting speedVSAvoidmachine performance
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system performs preliminary detection of wet weed patches using sensors (moisture sensors, optical sensors, thermal cameras) before the harvester reaches problematic areas. This advance detection allows the control system to pre-adjust operating parameters such as reducing speed or modifying header height before entering the weed patch, preventing performance degradation rather than reacting to it afterward

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The harvester's operating parameters are made dynamic and continuously adjustable based on real-time sensor feedback. The control system modifies speed, header height, and other parameters dynamically as the machine moves through different field zones with varying weed conditions, allowing optimal performance adaptation to each specific location

Inventive Principle:
Principle #15Dynamics

2Reliability

If the harvester slows down to avoid performance degradation in weed patches, then machine performance is maintained, but productivity decreases

Engineering Contradiction:
Improvemachine performanceVSAvoidharvesting speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system applies different operating parameters to different spatial zones within the field rather than using a uniform approach. Wet weed patches trigger specific local adjustments (speed reduction, header height modification) while dry areas or crop zones maintain normal operating conditions, ensuring performance is maintained only where necessary without unnecessarily reducing overall productivity

Inventive Principle:
Principle #3Local quality

3Difficulty of detecting and measuring

If the harvester uses traditional sensing methods to detect weeds, then detection capability is limited, but system complexity is reduced

Engineering Contradiction:
Improveweed detection accuracyVSAvoidsensing system complexity
Core Design Contradiction:
Difficulty of detecting and measuringVSDevice complexity

Solution Approach 1:

The system combines multiple sensing modalities (moisture sensors, optical sensors, thermal cameras, GPS) into an integrated sensing platform. These diverse sensors work together to detect various weed characteristics simultaneously, providing comprehensive detection capability while sharing data processing and control infrastructure to manage system complexity

Inventive Principle:
Principle #5Merging (Combining)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach enhances the performance of agricultural harvesters by accurately identifying and responding to weed intensity and type, improving operational efficiency and reducing the impact of wet conditions on harvesting operations.

Implementation Method 1

a forward-looking camera 366 to take images of the field

Methodology Applied
Scientific EffectOptical detection: Light

Data Source

PatentEP3861843B1Machine control using a predictive map
Publication Date: 2023.09.06 DEERE & CO
  • EP3861843B1 patent drawingFigure 1
  • EP3861843B1 patent drawingFigure 2
  • EP3861843B1 patent drawingFigure 3A

AI summary

One or more information maps are obtained by an agricultural work machine. The one or more information maps map one or more agricultural characteristic values at different geographic locations of a field. An in-situ sensor on the agricultural work machine senses an agricultural characteristic as the agricultural work machine moves through the field. A predictive map generator generates a predictive map that predicts a predictive agricultural characteristic at different locations in the field based on a relationship between the values in the one or more information maps and the agricultural characteristic sensed by the in-situ sensor. The predictive map can be output and used in automated machine control.