Bai Liga, Huang Xiaojun, Dashzebeg Ganbat, Ariunaa Mungunkhuyag, Yin Shan, Bao Yuhai, Bao Gang, Tong Siqin, Dorjsuren Altanchimeg, Davaadorj Enkhnasan
College of Geographical Science, Inner Mongolia Normal University, Hohhot 010022, China.
Inner Mongolia Key Laboratory of Remote Sensing & Geography Information System, Inner Mongolia Normal University, Hohhot 010022, China.
Insects. 2024 Mar 4;15(3):172. doi: 10.3390/insects15030172.
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 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 Djak pest damage by combining patterns in the RGB vegetation indices and texture features (RGB) with the help of random forest (RF) and convolutional neural network (CNN) algorithms. The results were compared and evaluated with multispectral vegetation indices (MS) 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-RF and RGB-CNN models have the best performance, with their overall accuracy reaching more than 85%, which is a significant improvement compared with that of the RGB model, and their accuracy is similar to that of the MS model. This low-cost and high-efficiency method can excel in the identification of 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.
Djak（鳞翅目，尺蛾科）是蒙古特有的食叶害虫。这种害虫的爆发会导致落叶松针叶从顶部逐渐脱落直至树木死亡，从而严重破坏森林生态系统的平衡。在这项研究中，为满足低成本、快速且有效地识别这种害虫的需求，我们以蒙古肯特省宾德尔地区落叶松林的实地调查指标和无人机图像作为基础数据，该地区是Djak害虫爆发的典型地点。我们计算了相关的多光谱和红-绿-蓝（RGB）特征，使用连续投影算法（SPA）提取对害虫危害程度敏感的特征，并借助随机森林（RF）和卷积神经网络（CNN）算法，结合RGB植被指数和纹理特征（RGB）中的模式，构建了Djak害虫危害的识别模型。将结果与多光谱植被指数（MS）进行比较和评估，以探索无人机RGB图像在识别针叶害虫方面的潜力。结果表明，基于SPA提取的敏感特征能够充分捕捉害虫危害条件下森林外观参数的变化，如落叶率和落叶松树冠颜色的变化，可作为模型的有效输入变量。RGB-RF和RGB-CNN模型表现最佳，总体准确率超过85%，与RGB模型相比有显著提高，且其准确率与MS模型相近。这种低成本、高效率的方法在小面积Djak虫害区域识别方面表现出色，可为后续高时空分辨率的大规模森林害虫监测提供重要的实验理论依据。
