Wheat stripe rust remote sensing monitoring method based on optimized hyperspectral vegetation index

By optimizing the hyperspectral vegetation index and PLSR model, the problem of decreased accuracy in wheat stripe rust monitoring technology in field environments was solved, achieving high-precision and stable cross-scale monitoring that is adaptable to complex field environments.

CN122116123APending Publication Date: 2026-05-29SHANDONG ACADEMY OF AGRICULTURAL SCIENCES
0 Cites 0 Cited by

Patent Information

Application Number
CN202610088911.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-01-22
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

The accuracy of existing hyperspectral monitoring technology for wheat stripe rust drops significantly when it is transferred from controlled experimental fields to real fields. It cannot cope with complex interferences such as soil background heterogeneity, environmental fluctuations and differences in agronomic conditions, resulting in insufficient monitoring accuracy and adaptability.

Method used

Samples were collected using a five-point sampling method to record the severity of the disease. Hyperspectral data were acquired using a ground-based portable hyperspectral instrument and a drone platform. The stripe rust-specific vegetation index YRVI was screened and optimized using the PLSR model. Combined with leave-one-out cross-validation and stratified sampling, an optimized vegetation index was generated to achieve cross-scale monitoring.

Benefits of technology

It improved monitoring accuracy and stability, reduced spectral noise, enhanced anti-interference capabilities, and achieved stable technology transfer from experimental fields to commercial fields, significantly improving the reliability and adaptability of monitoring results.

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

Abstract

The invention belongs to the technical field of plant disease monitoring, and particularly relates to a wheat stripe rust remote sensing monitoring method based on an optimized hyperspectral vegetation index. The method comprises the steps of test design and sample collection, multi-scale spectral data acquisition, vegetation index screening and optimization, PLSR monitoring model construction, model verification and disease space inversion, and result output. Sensitive vegetation indexes are screened and optimized in a test field, model adaptability is verified in a real field, and finally the problems that when an existing wheat stripe rust hyperspectral monitoring technology is transplanted to the real field from a controllable test field, precision is remarkably reduced, and complex interference such as soil background heterogeneity, environmental fluctuation and agronomic condition difference cannot be handled are solved.
Need to check novelty before this filing date? Find Prior Art