SPECTRAL FEATURES OF THE MAIN SPRING WHEAT PESTS (EURYGASTER INTEGRICEPS AND AELIA ACUMINATA) IN MACHINE RECOGNITION

2026

Closed access Metadata (CSL-JSON)
DOI 10.52081/bkaku.2026.v78.i3.367
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

For the first time, the article presents the spectral characteristics of the entomofauna of Kazakhstan, using the wheat pests Eurygaster integriceps and Aelia acuminata as examples. Spectral analysis revealed how insects reflect and absorb light. Patterns in the formation of spectral curves and key factors associated with morphological features, pigmentation, and exoskeleton structure were identified. Differences in spectral intensity are attributed to variations in melanin and chitin content among different parts of the insects and between different insect species. It is shown that in the 550 nm range, reflectance is determined by pigment composition, while in the 700-750 nm region, it is determined by the structural components of the integument; at the same time, the reflectance coefficients of Aelia acuminata are higher than those of Eurygaster integriceps. Based on spectral and morphological characteristics, a classification model was developed using the Random Forest algorithm, achieving an identification accuracy of 89 %. The results obtained expand the understanding of the ultrastructure of the insect exoskeleton and demonstrate the potential of using hyperspectral imaging in agriculture for monitoring cereal crop pests. Furthermore, the generated spectral profiles can serve as references for the creation of regional spectral libraries of insects. The study opens up new opportunities for implementing sustainable practices in the agro-industrial sector.