Soil heavy metal hyperspectral remote sensing inversion method and device, system and storage medium

By using a Transformer-based feature band selection method and an XGBoost model, the complexity and computational efficiency issues of feature band selection in soil heavy metal hyperspectral remote sensing inversion were resolved, achieving rapid and effective feature band identification and improved model accuracy.

CN121026989BActive Publication Date: 2026-07-24KUNMING UNIV OF SCI & TECH
2 Cites 0 Cited by

Patent Information

Application Number
CN202511129374.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-08-13
Publication Date
2026-07-24
Estimated Expiration
2045-08-13

AI Technical Summary

Technical Problem

Existing technologies for the selection of characteristic bands in soil heavy metal hyperspectral remote sensing inversion are computationally complex, unstable, and computationally expensive, making it difficult to quickly and effectively identify the characteristic bands of heavy metals, thus affecting the accuracy and efficiency of the model.

Method used

A Transformer-based feature band selection method was adopted, which uses fractional-order differential spectral transformation and self-attention mechanism, combined with multi-layer Transformer encoder and feature importance estimation, to screen out the hyperspectral feature bands of heavy metals in soil, and then uses XGBoost to build an inversion model.

Benefits of technology

It enables rapid and effective selection of feature bands, improves the accuracy and efficiency of quantitative inversion of soil heavy metal content by hyperspectral remote sensing, and provides technical support for deep learning algorithms in this field.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a soil heavy metal hyperspectral remote sensing inversion method and device, system and storage medium, and comprises the following steps: acquiring indoor hyperspectral data, heavy metal copper content and hyperspectral remote sensing image spectral data; performing SG spectral smoothing on the indoor hyperspectral data after removing noise bands; correcting the hyperspectral image spectral data according to the indoor hyperspectral data after SG spectral smoothing processing; performing fractional order differential spectral transformation on the corrected hyperspectral image spectral data; inputting the heavy metal copper content as a dependent variable and the fractional order differential spectral transformed hyperspectral image spectral data as an independent variable into a Transformer feature selection framework; and using XGBoost to establish a soil copper content inversion model to verify the effectiveness of the Transformer feature selection. According to the technical scheme, the feature wave of the heavy metal can be quickly and effectively identified and extracted.
Need to check novelty before this filing date? Find Prior Art