Early Detection of Dendroctonus valens Infestation at Tree Level with a Hyperspectral UAV Image

Abstract

The invasive pest Dendroctonus valens has spread to northeast China, causing serious economic and ecological losses. Early detection and disposal of infested trees is critical to prevent its outbreaks. This study aimed to evaluate the potential of an unmanned aerial vehicle (UAV)-based hyperspectral image for early detection of D. valens infestation at the individual tree level. We compared the spectral characteristics of Pinus tabuliformis in three states (healthy, infested and dead), and established classification models using three groups of features (reflectance, derivatives and spectral vegetation indices) and two algorithms (random forest and convolutional neural network). The spectral features of dead trees were clearly distinct from those of the other two classes, and all models identified them accurately. The spectral changes of infested trees occurred mainly in the visible region, but it was difficult to distinguish infested from healthy trees using random forest classification models based on reflectance and derivatives. The random forest model using spectral vegetation indices and the convolutional neural network model performed better, with an overall accuracy greater than 80% and a recall rate of infested trees reaching 70%. Our results demonstrated the great potential of hyperspectral imaging and deep learning for the early detection of D. valens infestation. The convolutional neural network proposed in this study can provide a reference for the automatic detection of early D. valens infestation using UAV-based multispectral or hyperspectral images in the future.

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

“…However, the timing of canopy colour change after each insect infestation varied, a phenomenon which was related to insect population density, tree genetics, host vigour, and environmental conditions [ 72 , 73 ]. In turn, long-term field observations were needed to collect drone images and ground data at appropriate times for the accurate identification of pests [ 48 ].…”

“…(2) Analysis of the pest recognition potential of sensitive features A total of 75% of the trees from all the samples were randomly selected as the training data set (including a training set and a validation set) for modelling and optimal model selection, and the remaining 25% were used as the test data set to validate the model and analyse its pest recognition potential. To objectively evaluate the model's performance, the overall accuracy (OA), Kappa coefficient, and confusion matrix were calculated based on true positives (TP), false positives (FP), true negatives (TN), and false negatives (FN), the main metrics for model accuracy validation [21,47,48]. OA is the probability that the classification result for each random sample is consistent with the type of data tested, ranging from 0 to 1.…”

Design and Application of Bionic Camouflage Materials Simulating Spectral Reflection Characteristics of Plants: A Review

“…Liu et al obtained the spectral bands and first spectral derivatives of beetle-infected pine trees from hyperspectral images and completed a quantitative discriminant analysis of pine beetle damage [68]. Gao et al extracted three features (e.g., original spectrum, reflectance derivative, and vegetation index) of insect-infected pine trees in drone hyperspectral images and used a convolutional neural network to construct a recognition system that can distinguish healthy, infected, or dead pine trees [69].…”

Early-Stage Pine Wilt Disease Detection via Multi-Feature Fusion in UAV Imagery

“…In comparison to satellite images, limited by weather conditions and spatial resolution, UAV-based images provide greater flexibility [41]. UAV-based object detection tasks have been successfully applied to UAV-based pest and disease detection, such as red turpentine beetle (RTB; Dendroctonus valens LeConte) [42,43], rice pests (stem borer and Hispa) [44], and other forest insect pests [45]. The combination of frequency domain information and deep learning object detection models offers an operational, flexible, and cost-effective method for the early detection of pine trees affected by PWD.…”