ANALYSIS AND MODELING OF COMPLEX LIVING SYSTEMS

Advanced neural network models for UAV-based image analysis in remote pathology monitoring of coniferous forests

C. Machuca, N. G. Markov

National Research Tomsk Polytechnic University, 30 Lenina ave., Tomsk, 634050, Russia

Abstract: The key problems of remote forest pathology monitoring for coniferous forests affected by insect pests have been analyzed. It has been demonstrated that addressing these tasks requires the use of multiclass classification results for coniferous trees in high- and ultra-high-resolution images, which are promptly obtained through monitoring via satellites or unmanned aerial vehicles (UAVs). An analytical review of modern models and methods for multiclass classification of coniferous forest images was conducted, leading to the development of three fully convolutional neural network models: Mo-U-Net, At-Mo-U-Net, and Res-Mo-U-Net, all based on the classical U-Net architecture. Additionally, the Segformer transformer model was modified to suit the task. For RGB images of fir trees Abies sibirica affected by the four-eyed bark beetle Polygraphus proximus, captured using a UAV-mounted camera, two datasets were created: the first dataset contains image fragments and their corresponding reference segmentation masks sized $256\times256\times3$ pixels, while the second dataset contains fragments sized $480\times480\times3$ pixels. Comprehensive studies were conducted on each trained neural network model to evaluate both classification accuracy for assessing the degree of damage (health status) of Abies sibirica trees and computation speed using test datasets from each set. The results revealed that for fragments sized $256\times256\times3$ pixels, the At-Mo-U-Net model with an attention mechanism is preferred alongside the Modified Segformer model. For fragments sized $480\times480\times3$ pixels, the Res-Mo-U-Net hybrid model with residual blocks demonstrated superior performance. Based on classification accuracy and computation speed results for each developed model, it was concluded that, for production-scale multiclass classification of affected fir trees, the Res-Mo-U-Net model is the most suitable choice. This model strikes a balance between high classification accuracy and fast computation speed, meeting conflicting requirements effectively.

Keywords: coniferous forests pathological monitoring, unmanned aerial vehicle, small spruce bark beetle Polygraphus proximus, multiclass classification of Siberian fir trees Abies sibirica images, fully convolutional neural networks, transformers

UDC: 004.415.2:004.932.1:582.47

Received: 19.05.2025
Revised: 12.07.2025
Accepted: 21.07.2025

Language: English

DOI: 10.20537/2076-7633-2025-17-4-641-663