Enhancing Tree Species Classification: Insights from YOLOv8 and Explainable AI Applied to TLS Point Cloud Projections

2025-12-17

AI Summary

Distinguishing visually similar tree species in forest remote sensing remains challenging due to high inter-class appearance similarity and limited interpretability of deep learning models. Method: This study proposes an interpretable classification framework integrating multi-view projections of Terrestrial Laser Scanning (TLS) point clouds with YOLOv8-based object detection. We introduce Finer-CAM—a novel technique mapping class activation heatmaps onto biologically structured tree parts (canopy, trunk, fine branches)—to enable biologically grounded interpretation of model decisions. The method combines k-fold cross-validation with structured saliency analysis. Results: Evaluated on 2,445 individual trees across seven European species, the framework achieves a mean accuracy of 96.0% (SD = 0.24%). Analysis of 630 saliency maps reveals canopy dominance in most classifications, while fine-branch features prove critical for discriminating key species. This work establishes, for the first time, semantic alignment between deep model responses and domain-expert botanical knowledge, delivering a high-accuracy, interpretable, and verifiable paradigm for remote sensing–based tree species identification.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Interpretability, Explainability, and Transparency
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Classifying tree species has been a core research area in forest remote sensing for decades. New sensors and classification approaches like TLS and deep learning achieve state-of-the art accuracy but their decision processes remain unclear. Methods such as Finer-CAM (Class Activation Mapping) can highlight features in TLS projections that contribute to the classification of a target species, yet are uncommon in similar looking contrastive tree species. We propose a novel method linking Finer-CAM explanations to segments of TLS projections representing structural tree features to systemically evaluate which features drive species discrimination. Using TLS data from 2,445 trees across seven European tree species, we trained and validated five YOLOv8 models with cross-validation, reaching a mean accuracy of 96% (SD = 0.24%). Analysis of 630 saliency maps shows the models primarily rely on crown features in TLS projections for species classification. While this result is pronounced in Silver Birch, European Beech, English oak, and Norway spruce, stem features contribute more frequently to the differentiation of European ash, Scots pine, and Douglas fir. Particularly representations of finer branches contribute to the decisions of the models. The models consider those tree species similar to each other which a human expert would also regard as similar. Furthermore, our results highlight the need for an improved understanding of the decision processes of tree species classification models to help reveal data set and model limitations, biases, and to build confidence in model predictions.

Problem

• Classifying tree species using TLS and deep learning
• Understanding decision processes in species classification models
• Identifying key structural features for species discrimination

Innovation

• Using YOLOv8 models for tree species classification
• Applying Finer-CAM to explain TLS projection features
• Linking saliency maps to structural tree segments