A soil thickness inversion method, system, and apparatus

By combining geographically weighted regression and extreme gradient boosting models, the spatial nonstationarity and nonlinearity problems of soil thickness prediction in complex terrain areas are solved, and high-precision soil thickness inversion is achieved.

CN122153318APending Publication Date: 2026-06-05CENT SOUTH UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CENT SOUTH UNIV
Filing Date
2026-03-04
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Existing technologies struggle to simultaneously account for spatial nonstationarity and complex nonlinear characteristics in complex terrain areas, resulting in insufficient accuracy in soil thickness prediction, incomplete feature factor systems, unstable model parameter estimation, and a tendency to overfit or lose important information.

Method used

The geographically weighted regression (GWR) model is used to capture the spatial trend of soil thickness, and the extreme gradient boosting (XGBoost) model is combined to perform nonlinear correction on the regression residuals. By introducing a regularization term and a subsampling strategy for feature selection, a spatial-nonlinear coupled inversion model is constructed.

Benefits of technology

It significantly improves the accuracy of soil thickness prediction and the rationality of spatial mapping, enhances the model's generalization ability and spatial extrapolation reliability, and achieves high-precision soil thickness inversion.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122153318A_ABST
    Figure CN122153318A_ABST
Patent Text Reader

Abstract

The application provides a soil thickness inversion method, system and device, and belongs to the technical field of soil thickness calculation. The method comprises the following steps: acquiring environmental factor data and soil thickness measured point data of a target area and constructing a modeling data set; adopting a series connection strategy of spatial trend-nonlinear residual correction, first capturing the spatial non-stationary trend of soil thickness by using a GWR model, then performing nonlinear fitting and correction on the GWR residual by using an XGBoost model, and introducing a regularization term and a subsampling strategy in the training process to perform sparse processing and adaptive screening on the environmental factors; finally, superimposing the trend component and the residual correction component to generate a high-precision soil thickness spatial distribution map. The application couples the spatial modeling capability of GWR and the nonlinear learning advantage of XGBoost, and introduces key environmental factors such as slope relative position index, thereby improving the precision and reliability of soil thickness inversion in complex terrain areas.
Need to check novelty before this filing date? Find Prior Art