Multi-year Crop Yield Analysis Using Remotely-Sensed Imagery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for creating variable rate applications in agriculture face challenges due to insufficient or missing yield event data, which can lead to inaccurate results, as they often rely on limited historical data and may not account for missing information effectively.
Innovation Solution
The use of remotely-sensed imagery to fill in missing yield event information, allowing for a more comprehensive multi-year crop yield analysis and generation of site-specific prescription maps by analyzing vegetation indices and normalizing data to represent yield coverage and uniformity, enabling more accurate agricultural planning and decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multi-year yield analysis is performed using traditional logged crop yield data, then variable rate applications can be created for precision agriculture, but the analysis becomes inaccurate when yield event data is missing or insufficient
Solution Approach 1:
The patent uses remotely-sensed imagery as an intermediary data source to substitute for missing yield event information. The system retrieves imagery from external sources (satellites, aerial photography) and processes it through vegetation indices to generate proxy yield data, thereby mediating the information gap when traditional yield monitors fail to capture complete field history
Solution Approach 2:
The patent creates a copy or representation of yield event data by analyzing remotely-sensed imagery. Instead of relying on direct measurements from yield monitors, the system generates proxy yield information by processing satellite or aerial images through vegetation indices, effectively copying the essential yield patterns from visual data
2Productivity
If only limited historical yield data is available (last few years or single year), then variable rate applications can still be generated, but the reliability and confidence in the analysis decreases
Solution Approach 1:
The patent performs preliminary data gathering by retrieving remotely-sensed imagery for multiple years before conducting the yield analysis. This advance collection of imagery data ensures that sufficient historical information is available to build reliable multi-year yield profiles, even when traditional yield monitor data is limited
Solution Approach 2:
The patent transforms the analysis by changing from relying on traditional yield monitor parameters to using vegetation index parameters derived from remotely-sensed imagery. This parameter substitution allows the system to maintain analysis reliability by using alternative data sources with different characteristics that can be processed to yield comparable agricultural insights
3Loss of information
If remotely-sensed imagery is used to replace missing yield event information, then a more complete multi-year yield history can be constructed, but the complexity of data processing increases
Solution Approach 1:
The patent segments the complex imagery processing task into distinct components: retrieving imagery from external sources, processing individual images through vegetation indices, normalizing the resulting data, and integrating it with existing yield data. This segmentation makes the overall complex system more manageable and systematic
4Measurement precision
If remotely-sensed imagery data is retrieved and processed through vegetation indices, then yield coverage and uniformity data can be normalized for accurate analysis, but the time and computational resources required increase
Solution Approach 1:
The patent changes the state of the imagery data by applying vegetation indices that transform raw image data into normalized yield coverage and uniformity parameters. This parameter transformation enables direct comparison and integration with traditional yield data while maintaining accuracy, reducing the need for extensive manual processing
Data Source
AI summary
A multi-year yield analysis in precision agriculture characterizes variables affecting crop yield to enable site-specific prescription mapping for a bounded field. Remotely-sensed imagery of the bounded field is incorporated as a replacement for, or in addition to, one or more of coverage data, uniformity data, age data, and weather data that comprise variables in the multi-year yield analysis. The multi-year yield analysis enables recommendations for variable-rate applications to the bounded field such as seeding, fertilizing, and applying crop treatments.