Assessing airborne laser scanning and aerial photogrammetry for convolutional neural network-based semantic segmentation of forest stands

Abstract

Forest stands are widely used units in forest inventory and provide a convenient basis for forest management; however, despite attempts at automation, their delineation remains largely manual, subjective, and time-consuming. Recent research has shown that convolutional neural networks 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 by providing topographic context, its contribution remains largely 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, with overall accuracy ranging from 90% to 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 suggest that DAP-derived CHMs can serve as a practical alternative to ALS-derived CHMs for CNN-based stand delineation, while the inclusion of a DTM provides little additional benefit under the examined conditions.