一种基于多光谱卫星遥感数据的土壤有机碳空间分布预测方法及系统
By fusing multi-source data from multispectral satellite remote sensing data and optimizing it with deep learning, and by employing the random forest algorithm and convolutional neural network in combination with adaptive grid partitioning, the accuracy and resolution issues of predicting the spatial distribution of soil organic carbon in complex surface environments were solved, and high-precision prediction of the spatial distribution of soil organic carbon was achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- INSTITUTE OF ENVIRONMENT AND SUSTAINABLE DEVELOPMENT IN AGRICULTURE CAAS
- Filing Date
- 2025-12-10
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods struggle to achieve high-resolution and accurate predictions of the spatial distribution of soil organic carbon when dealing with complex surface environments, especially in areas with mixed land use types. Existing technologies also struggle to balance the relationship between grid resolution and prediction accuracy, leading to unstable prediction results.
By fusing multi-source data from multispectral satellite remote sensing data and optimizing it with deep learning, a random forest algorithm and a convolutional neural network are used in conjunction with an adaptive grid partitioning method to dynamically adjust the grid size in order to achieve high-precision prediction of the spatial distribution of soil organic carbon.
It significantly improves the prediction accuracy and spatial resolution of soil organic carbon distribution in complex surface environments, providing efficient technical support for precision agriculture and environmental monitoring.
Smart Images
Figure CN121685982B_ABST
Abstract
Citation Information
Patent Citations
Soil organic carbon high-precision inversion method based on habitat plaque earth surface unit division
CN118916768A
Ecological system carbon sink assessment method
CN120654945A