A soil organic matter prediction method based on multi-feature fusion

By constructing a dual-stream low-rank interactive network model and combining chaotic features and vegetation index features, the problem of low prediction accuracy in soil organic matter prediction was solved, achieving high-precision soil organic matter prediction and improving the model's stability and anti-interference ability.

CN121935860BActive Publication Date: 2026-06-05KUNMING UNIV OF SCI & TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
KUNMING UNIV OF SCI & TECH
Filing Date
2026-03-27
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Existing technologies cannot fully characterize the complex nonlinear properties of soil in soil organic matter prediction, resulting in low prediction accuracy. Furthermore, multi-feature data exhibit significant heterogeneity in scale, distribution, and semantics, lacking effective alignment and coordination mechanisms, making it difficult to mine complementary information.

Method used

A multi-feature fusion-based approach is adopted. By preprocessing soil data, chaotic features and vegetation index features are extracted, and a dual-stream low-rank interactive network model, including residual network and KAN network, is constructed. Combined with the low-rank multimodal fusion mechanism, key spectral fluctuation information is deeply mined, and target signal and environmental noise are separated to achieve high-precision prediction of soil organic matter.

Benefits of technology

It improved the accuracy of soil organic matter prediction, reduced prediction errors in small samples, enhanced the model's anti-interference ability and stability, and improved the model's generalization performance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121935860B_ABST
    Figure CN121935860B_ABST
Patent Text Reader

Abstract

The application relates to a soil organic matter prediction method based on multi-feature fusion, and belongs to the technical field of soil organic matter prediction. The method comprises the following steps: pre-processing acquired soil data, obtaining spectral features, performing time domain reconstruction on frequency domain signals, and obtaining time domain data; obtaining an optimal delay time and an optimal embedding dimension based on the time domain data, and performing phase space reconstruction to obtain a phase space trajectory; extracting chaotic features based on the phase space trajectory, and taking the extracted chaotic features, the optimal delay time and the optimal embedding dimension as final chaotic features; obtaining a vegetation index based on the spectral features and taking the vegetation index as an index feature; and inputting the spectral features, the final chaotic features and the index feature into a constructed double-flow low-rank interaction network model to obtain a soil organic matter prediction result. The application aims to solve the technical problem that the spectral features extracted by the prior art cannot comprehensively represent the complex nonlinear characteristics of soil, thereby leading to low prediction accuracy.
Need to check novelty before this filing date? Find Prior Art