Optical Remote Sensing and Machine Learning for Crop Residue Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for measuring crop residue cover (CRC) and determining tillage practice type in agronomic fields are time-consuming, labor-intensive, and difficult to deploy due to geographic limitations, requiring on-ground measurements and subjective grower input.

Innovation Solution

Utilizing trained machine learning models that integrate optical remote sensing data, measured field data, and precipitation data to predict agronomic field properties such as CRC, employing preprocessing techniques to filter out noise and cloud interference, and generating graphical representations for easy scaling and geographic flexibility.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If on-ground measurement methods (line-transect or meter-stick) are used to measure crop residue cover, then measurement precision can be achieved, but the process becomes time-consuming and labor-intensive

Engineering Contradiction:

Improvecrop residue cover measurement precisionVSAvoidtime required for measurement

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces mechanical on-ground measurement systems (line-transect methods, meter-stick methods) with an optical remote sensing system using satellites. The satellite captures optical images of fields, and machine learning models predict crop residue cover from these images, eliminating the need for physical measurement tools and manual field operations while maintaining measurement accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a digital copy of the field measurement process by using satellite remote sensing to capture field conditions from above. Instead of physically measuring in the field, the system uses optical copies (satellite images) combined with machine learning to derive crop residue cover data, significantly reducing time and labor while preserving measurement precision.

Inventive Principle:

Principle #26Copying

2Measurement precision

If on-ground measurement methods are used to determine tillage practice type, then accurate determination can be achieved, but the process becomes difficult to deploy due to geographic limitations

Engineering Contradiction:

Improvetillage practice type determination accuracyVSAvoidgeographic deployability

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent replaces mechanical on-ground assessment methods with satellite-based optical remote sensing. The satellite system can access any geographic location without physical constraints, and machine learning models analyze the optical data to determine tillage practice types, achieving both accuracy and universal geographic deployability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a universal measurement system that can operate across all geographic locations. The satellite-based approach eliminates location-specific limitations of ground methods, allowing the same system to accurately assess crop residue cover and tillage practices in diverse terrains and accessible areas worldwide.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Reliability

If direct input from growers is required for measuring agronomic field properties, then subjective local knowledge is incorporated, but the process becomes labor-intensive and difficult to scale

Engineering Contradiction:

Improveinclusion of grower knowledgeVSAvoidscaling capability

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent replaces manual data collection from growers with automated satellite-based optical sensing and machine learning. The system independently measures crop residue cover and determines tillage practices without requiring grower participation, eliminating the labor-intensive nature of current methods while enabling unlimited scaling across multiple fields and regions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250245532A1Using Optical Remote Sensors And Machine Learning Models To Predict Agronomic Field Property Data

Publication Date: 2025.07.31 MONSANTO TECHNOLOGY LLC

AI summary

In some embodiments, a computer-implemented method for predicting agronomic field property data for one or more agronomic fields using a trained machine learning model is disclosed. The method comprises receiving, at an agricultural intelligence computer system, agronomic training data; training a machine learning model, at the agricultural intelligence computer system, using the agronomic training data; in response to receiving a request from a client computing device for agronomic field property data for one or more agronomic fields, automatically predicting the agronomic field property data for the one or more agronomic fields using the machine learning model configured to predict agronomic field property data; based on the agronomic field property data, automatically generating a first graphical representation; and causing to display the first graphical representation on the client computing device.