Windrower Lodging Maps for Proactive Harvest Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile agricultural machines struggle to effectively detect lodged crop due to sensor limitations such as latency, visibility issues from debris or low light conditions, leading to reduced harvesting efficiency and yield loss.
Innovation Solution
A system that generates predictive crop lodging maps using in-situ sensors and historical or prior data to anticipate crop lodging across a field, enabling proactive machine control adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If in-situ sensors are used to detect crop lodging, then real-time detection capability is improved, but sensor latency and visibility issues from debris or low light conditions reduce detection reliability
Solution Approach 1:
The system generates predictive maps of crop lodging before the windrowing operation begins, using historical data and machine learning models. This preliminary action allows the system to anticipate lodged crop locations rather than reacting to real-time sensor detections, overcoming latency and visibility limitations.
Solution Approach 2:
The patent introduces an intermediary predictive map system that mediates between the physical sensor data and the windrowing machine control. The predictive map serves as an intermediate representation that combines historical sensor data, weather information, and machine learning models to forecast lodging conditions without being directly constrained by real-time sensor limitations.
2Loss of time
If real-time sensor detection is used, then response time is improved, but latency and visibility issues cause missed lodged crop
Solution Approach 1:
The system performs preliminary actions by generating predictive lodging maps before the harvesting operation. This allows the windrowing machine to be pre-configured with expected lodged crop locations, eliminating the need for real-time detection and response, thereby overcoming latency issues and improving harvesting efficiency.
Solution Approach 2:
The system uses feedback from historical sensor data and operational results to continuously improve the predictive models. This feedback mechanism allows the system to learn from past performance and refine its predictions, gradually reducing missed lodged crop despite not using real-time detection.
3Device complexity
If traditional sensor-based detection is used, then system complexity is kept low, but detection accuracy is reduced due to debris and low light conditions
Solution Approach 1:
The system creates a virtual copy of the field conditions through predictive maps generated from historical data. Instead of relying on direct optical sensing that is degraded by debris and low light, the system uses a computational model that replicates field conditions without being physically constrained by environmental factors affecting sensor accuracy.
Solution Approach 2:
The patent replaces the mechanical/optical sensor-based detection system with a computational predictive model. This substitution eliminates the physical limitations of sensors in detecting lodged crop through debris or low light, while maintaining relatively simple system architecture through the use of data processing and machine learning models.
Data Source
AI summary
One or more information maps are obtained by an agricultural system. The one or more information maps map one or more characteristic values at different geographic locations in a worksite. An in-situ sensor detects a crop lodging value as a mobile windrowing machine operates at the worksite. A predictive map generator generates a predictive map that maps predictive crop lodging values at different geographic locations in the worksite based on a relationship between the values in the one or more information maps and the crop lodging value detected by the in-situ sensor. The predictive map can be output and used in automated machine control.