High / multi-spectral collaborative chlorophyll-a retrieval method based on feature-level residual learning

By employing a feature-level residual learning method, combined with multispectral and hyperspectral data, regularized regression and multivariate dimensionality reduction regression models are trained, solving the problem of low chlorophyll a inversion accuracy of multispectral sensors in complex water bodies and achieving high-precision chlorophyll a concentration recovery.

CN122173902APending Publication Date: 2026-06-09HANGZHOU NORMAL UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
HANGZHOU NORMAL UNIVERSITY
Filing Date
2026-05-12
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing technologies cannot effectively decouple the radiation spatial stability and high-frequency spectral fidelity of multispectral sensors, resulting in low chlorophyll a inversion accuracy in complex inland water bodies and problems such as signal saturation, radiation homogenization traps, and noise amplification traps.

Method used

A feature-level residual learning-based approach is adopted, which decouples the inversion process into macroscopic spatial baseline anchoring and high-frequency spectral residual refinement through multispectral macroscopic baseline anchoring and hyperspectral high-frequency residual prediction. Regularized regression and multivariate dimensionality reduction regression models are trained using multispectral feature matrices and hyperspectral derivative feature matrices, and combined with soft threshold function constraints, to achieve high-precision prediction of chlorophyll a concentration.

Benefits of technology

It improves the accuracy of chlorophyll a inversion in eutrophic water bodies, solves the problems of signal saturation and noise amplification, and achieves high-precision spatial gradient recovery of chlorophyll a in water bodies.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122173902A_ABST
    Figure CN122173902A_ABST
Patent Text Reader

Abstract

This invention discloses a hyperspectral / multispectral chlorophyll-a inversion method based on feature-level residual learning. First, a regularized regression model is trained using multispectral broadband features and measured chlorophyll-a ground truth values. The difference between the ground truth and predicted values ​​is used to construct a residual error vector. Then, using this residual as the target, a multivariate dimensionality-reduction regression model is trained using hyperspectral high-frequency derivative features. The multispectral feature matrix of each pixel in the target water body is input into the trained regularized regression model to obtain the baseline predicted value of chlorophyll-a concentration for each pixel. The hyperspectral derivative feature matrix of each pixel is input into the trained multivariate dimensionality-reduction regression model to obtain the high-frequency residual correction value for each pixel. Finally, the two values ​​are summed and post-processed using a hyperbolic tangent soft thresholding function to obtain the final predicted value of chlorophyll-a concentration, and the inversion map is output. This invention achieves a fundamental breakthrough in the multi-source fusion paradigm, possesses strong physical noise resistance, and improves the accuracy of high-concentration chlorophyll inversion.
Need to check novelty before this filing date? Find Prior Art