Wheat Kernel Moisture Monitoring via Satellite Spectral Inversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring wheat kernel moisture content are inefficient for pre-harvest field monitoring, lacking non-destructive and scalable solutions, which hinders agricultural decision-making and resource management.
Innovation Solution
A method utilizing PlanetScope satellite imagery and gradient boosting decision tree (GBDT) models to estimate wheat kernel moisture content by extracting and ranking spectral features, constructing broad-band vegetation indices, and applying permutation importance for feature selection, enabling precise in-field monitoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If direct methods (drying or chemical methods) are used to measure wheat kernel moisture content, then measurement accuracy is improved, but measurement efficiency deteriorates
Solution Approach 1:
The patent replaces mechanical/chemical drying methods with optical remote sensing technology. Satellite imagery captures spectral reflectance data from wheat fields, which is then processed through vegetation indices and machine learning models to estimate moisture content non-destructively and at large scale, simultaneously improving both accuracy and efficiency
Solution Approach 2:
The patent transforms the measurement approach by changing from direct physical/chemical measurement to indirect spectral parameter analysis. By monitoring changes in spectral reflectance across different wavelengths and deriving vegetation indices, the system estimates moisture content without altering the wheat kernels, achieving high efficiency while maintaining measurement precision
2Productivity
If non-destructive monitoring methods are used for wheat kernel moisture content, then measurement efficiency is improved, but applicability to pre-harvest field monitoring deteriorates
Solution Approach 1:
The patent creates a universal monitoring system using satellite remote sensing that can measure wheat kernel moisture content across diverse field conditions and at different growth stages. The methodology combines spectral analysis with machine learning models trained on field data, enabling the same system to effectively monitor pre-harvest wheat in various environments, thus improving adaptability while maintaining efficiency
Solution Approach 2:
The patent introduces vegetation indices and machine learning models as intermediaries between satellite spectral data and wheat moisture content. These intermediaries translate remote sensing data into meaningful moisture estimates for pre-harvest field conditions, bridging the gap between non-destructive measurement capability and practical field monitoring applicability
3Area of stationary object
If satellite remote sensing methods are used for large-scale crop quality monitoring, then monitoring scale is improved, but research data support for specific quality parameters deteriorates
Solution Approach 1:
The patent performs preliminary field measurements and collects training data before implementing the large-scale satellite monitoring system. By pre-training machine learning models with ground-based moisture content data and spectral measurements, the system ensures that satellite-based estimates are calibrated and accurate for specific quality parameters like wheat kernel moisture content, preventing information loss while achieving large-scale coverage
Solution Approach 2:
The patent segments the monitoring approach by combining broad satellite remote sensing coverage with targeted ground-based validation and analysis. The system divides the problem into satellite data collection at large scale, regional processing through vegetation indices, and specific parameter estimation through machine learning models, thereby maintaining both extensive coverage and detailed research-quality data for specific quality parameters
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 provides accurate and efficient large-scale monitoring of wheat kernel moisture content, bridging the gap in pre-harvest data support and enhancing agricultural decision-making with rich information for resource management.
Implementation Method 1
obtaining PlanetScope eight-band surface reflectance imagery covering the target farmland
Data Source
AI summary
The monitoring method for wheat kernel moisture content in-field based on PlanetScope satellite imagery in this disclosure comprises: (1) data collection and database establishment; (2) feature engineering: constructing various broad-band indices on the original bands provided by PlanetScope to expand the feature domain, and evaluate the importance of each feature to rank the features based on the comprehensive importance calculated by permutation importance based on regressors; (3) model construction: progressively adding the spectral features one by one as independent variables to the GBDT model according to the ranking results, and screen out the optimal spectral feature domain and inversion model for wheat kernel moisture content; (4) wheat kernel moisture content mapping. The disclosure utilizes machine learning inversion models based on spectral features and PlanetScope satellite imagery to obtain the wheat kernel moisture content at any position of the target farmland.