Potential of Unmanned Aerial Vehicle Red-Green-Blue Images for Detecting Needle Pests: A Case Study with Erannis jacobsoni Djak (Lepidoptera, Geometridae)

Liga Bai; Xiaojun Huang; Ganbat Dashzebeg; Mungunkhuyag Ariunaa; Shan Yin; Yuhai Bao; Gang Bao; Siqin Tong; Altanchimeg Dorjsuren; Enkhnasan Davaadorj

doi:10.3390/insects15030172

Potential of Unmanned Aerial Vehicle Red-Green-Blue Images for Detecting Needle Pests: A Case Study with Erannis jacobsoni Djak (Lepidoptera, Geometridae)

Insects. 2024 Mar 4;15(3):172. doi: 10.3390/insects15030172.

Authors

Liga Bai¹, Xiaojun Huang^{1

2

3}, Ganbat Dashzebeg⁴, Mungunkhuyag Ariunaa⁴, Shan Yin^{1

2}, Yuhai Bao^{1

2}, Gang Bao^{1

2}, Siqin Tong^{1

2}, Altanchimeg Dorjsuren⁵, Enkhnasan Davaadorj⁵

Affiliations

¹ College of Geographical Science, Inner Mongolia Normal University, Hohhot 010022, China.
² Inner Mongolia Key Laboratory of Remote Sensing & Geography Information System, Inner Mongolia Normal University, Hohhot 010022, China.
³ Inner Mongolia Key Laboratory of Disaster and Ecological Security on the Mongolia Plateau, Inner Mongolia Normal University, Hohhot 010022, China.
⁴ Institute of Geography and Geoecology, Mongolian Academy of Sciences, Ulaanbaatar 15170, Mongolia.
⁵ Institute of Biology, Mongolian Academy of Sciences, Ulaanbaatar 13330, Mongolia.

Abstract

Erannis jacobsoni Djak (Lepidoptera, Geometridae) is a leaf-feeding pest unique to Mongolia. Outbreaks of this pest can cause larch needles to shed slowly from the top until they die, leading to a serious imbalance in the forest ecosystem. In this work, to address the need for the low-cost, fast, and effective identification of this pest, we used field survey indicators and UAV images of larch forests in Binder, Khentii, Mongolia, a typical site of Erannis jacobsoni Djak pest outbreaks, as the base data, calculated relevant multispectral and red-green-blue (RGB) features, used a successive projections algorithm (SPA) to extract features that are sensitive to the level of pest damage, and constructed a recognition model of Erannis jacobsoni Djak pest damage by combining patterns in the RGB vegetation indices and texture features (RGB_VI&TF) with the help of random forest (RF) and convolutional neural network (CNN) algorithms. The results were compared and evaluated with multispectral vegetation indices (MS_VI) to explore the potential of UAV RGB images in identifying needle pests. The results show that the sensitive features extracted based on SPA can adequately capture the changes in the forest appearance parameters such as the leaf loss rate and the colour of the larch canopy under pest damage conditions and can be used as effective input variables for the model. The RGB_VI&TF-RF₄₄₀ and RGB_VI&TF-CNN₇₄₀ models have the best performance, with their overall accuracy reaching more than 85%, which is a significant improvement compared with that of the RGB_VI model, and their accuracy is similar to that of the MS_VI model. This low-cost and high-efficiency method can excel in the identification of Erannis jacobsoni Djak-infested regions in small areas and can provide an important experimental theoretical basis for subsequent large-scale forest pest monitoring with a high spatiotemporal resolution.

Keywords: Erannis jacobsoni Djak; RGB texture features; RGB vegetation indices; UAV images; damage level recognition; machine learning.

Grants and funding

41861056/National Natural Science Foundation of China