Deep learning-based canopy gap detection using a cross-technological approach with airborne laser scanning and aerial imagery data

This repository contains the datasets and trained model used in the paper: Franz, F., Seidel, D., Beckschäfer, P., 2026. Deep learning-based canopy gap detection using a cross-technological approach with airborne laser scanning and aerial imagery data. Ecol. Informatics. 93, 103558. https://doi.org/10.1016/j.ecoinf.2025.103558.

The code to reproduce the analysis can be found in the linked GitHub repository: https://github.com/FloFranz/canopy-gap-detection. The scripts train_data_preparation.ipynb and test_data_preparation.ipynb were used to generate the datasets. They include spectral information from True Digital Orthophotos (RGBI), height information from Digital Aerial Photogrammetry-based Canopy Height Models (CHM), and gap masks derived from Airborne Laser Scanning-based CHMs. The train dataset allows for retraining the model, while the test datasets enable running the predictions. The trained model is also provided for direct use.

The raw data used to generate the datasets can be made available from the corresponding author upon reasonable request.