Assessing airborne laser scanning and aerial photogrammetry for deep learning-based stand delineation

2026-02-25

AI Summary

This study addresses the long-standing reliance on subjective manual delineation of forest management units and the challenges posed by temporal inconsistencies in multi-source remote sensing data, which have hindered the large-scale application of deep learning. Building upon a U-Net semantic segmentation framework, it presents the first systematic comparison of canopy height models (CHMs) derived from airborne laser scanning (ALS) and digital aerial photogrammetry (DAP) for automated forest stand delineation, while also evaluating the added value of digital terrain models (DTMs). Experiments across six municipalities in southeastern Norway demonstrate that all input data combinations achieve consistently high overall accuracies of 0.90–0.91. The results indicate that DAP-derived CHMs can effectively substitute ALS-derived CHMs, whereas the inclusion of DTMs yields no significant improvement, thereby confirming the robustness and generalizability of the proposed approach across varying input modalities.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Ensemble Methods
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate forest stand delineation is essential for forest inventory and management but remains a largely manual and subjective process. A recent study has shown that deep learning can produce stand delineations comparable to expert interpreters when combining aerial imagery and airborne laser scanning (ALS) data. However, temporal misalignment between data sources limits operational scalability. Canopy height models (CHMs) derived from digital photogrammetry (DAP) offer better temporal alignment but may smoothen canopy surface and canopy gaps, raising the question of whether they can reliably replace ALS-derived CHMs. Similarly, the inclusion of a digital terrain model (DTM) has been suggested to improve delineation performance, but has remained untested in published literature. Using expert-delineated forest stands as reference data, we assessed a U-Net-based semantic segmentation framework with municipality-level cross-validation across six municipalities in southeastern Norway. We compared multispectral aerial imagery combined with (i) an ALS-derived CHM, (ii) a DAP-derived CHM, and (iii) a DAP-derived CHM in combination with a DTM. Results showed comparable performance across all data combinations, reaching overall accuracy values between 0.90-0.91. Agreement between model predictions was substantially larger than agreement with the reference data, highlighting both model consistency and the inherent subjectivity of stand delineation. The similar performance of DAP-CHMs, despite the reduced structural detail, and the lack of improvements of the DTM indicate that the framework is resilient to variations in input data. These findings indicate that large datasets for deep learning-based stand delineations can be assembled using projects including temporally aligned ALS data and DAP point clouds.

Problem

• forest stand delineation
• airborne laser scanning
• digital aerial photogrammetry
• canopy height model
• deep learning

Innovation

• deep learning
• forest stand delineation
• digital aerial photogrammetry
• airborne laser scanning
• U-Net