Multispectral airborne laser scanning for tree species classification: a benchmark of machine learning and deep learning algorithms

2025-04-19

AI Summary

Accurate identification of rare tree species remains challenging due to data scarcity and poor compatibility between multispectral point clouds and deep learning architectures. Method: This study establishes a benchmark for fine-grained tree species classification using multispectral airborne laser scanning (ALS) point clouds, systematically evaluating native point cloud models—particularly Point Transformer—on high-density three-band ALS data (FGI HeliALS: >1000 pts/m²; Optech Titan: 35 pts/m²), and proposing a hierarchical multispectral feature fusion strategy. Contribution/Results: On a dataset of 5,000 samples, Point Transformer achieves a macro-averaged accuracy of 87.9%—a 14.9 percentage-point improvement over single-band input—and significantly outperforms DetailView (84.3%) and Random Forest (83.2%). These results demonstrate the efficacy of native point cloud models synergized with multispectral information for rare species identification, providing a novel methodological foundation for climate-smart forestry and biodiversity conservation.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Climate-smart and biodiversity-preserving forestry demands precise information on forest resources, extending to the individual tree level. Multispectral airborne laser scanning (ALS) has shown promise in automated point cloud processing and tree segmentation, but challenges remain in identifying rare tree species and leveraging deep learning techniques. This study addresses these gaps by conducting a comprehensive benchmark of machine learning and deep learning methods for tree species classification. For the study, we collected high-density multispectral ALS data (>1000 pts/m$^2$) at three wavelengths using the FGI-developed HeliALS system, complemented by existing Optech Titan data (35 pts/m$^2$), to evaluate the species classification accuracy of various algorithms in a test site located in Southern Finland. Based on 5261 test segments, our findings demonstrate that point-based deep learning methods, particularly a point transformer model, outperformed traditional machine learning and image-based deep learning approaches on high-density multispectral point clouds. For the high-density ALS dataset, a point transformer model provided the best performance reaching an overall (macro-average) accuracy of 87.9% (74.5%) with a training set of 1065 segments and 92.0% (85.1%) with 5000 training segments. The best image-based deep learning method, DetailView, reached an overall (macro-average) accuracy of 84.3% (63.9%), whereas a random forest (RF) classifier achieved an overall (macro-average) accuracy of 83.2% (61.3%). Importantly, the overall classification accuracy of the point transformer model on the HeliALS data increased from 73.0% with no spectral information to 84.7% with single-channel reflectance, and to 87.9% with spectral information of all the three channels.

Problem

• Classifying tree species using multispectral ALS data
• Benchmarking ML and DL for rare species identification
• Improving accuracy with point transformer models

Innovation

• Multispectral ALS for high-density point clouds
• Point transformer model for species classification
• Deep learning outperforms traditional machine learning