Wróblewski et al. (2026) HydroBound-ML: Automated Water-Surface-Mask Generation for Airborne Lidar Bathymetry Processing Using Hybrid Machine Learning and Object-Based Image Analysis

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Sensors
• Year: 2026
• Date: 2026-09-24
• Authors: Patryk Wróblewski, Anna Fryśkowska
• DOI: 10.3390/s26196065

Research Groups

• Department of Geomatics Engineering, University of Calgary
• Department of Computer Science, University of British Columbia

Short Summary

This paper introduces HydroBound-ML, an open-source image-based tool that automates the generation of accurate water-surface masks for Airborne Lidar Bathymetry (ALB) processing. The tool achieves exceptional accuracy in complex river environments.

Objective

• Automate the water boundary vectorization process for ALB processing to prevent false target extraction over adjacent land areas.

Study Configuration

• Spatial Scale: HydroBound-ML operates at high-resolution spatial scales, utilizing multi-spectral imagery.
• Temporal Scale: The study focuses on static topographic databases and river dynamics, implying a focus on long-term or near-real-time monitoring applications.

Methodology and Data

• Models used: Random Forest classifier, Simple Linear Iterative Clustering (SLIC) superpixels via Object-Based Image Analysis (OBIA)
• Data sources: High-resolution multi-spectral imagery, Cloud Optimized GeoTIFFs (COGs)

Main Results

• HydroBound-ML achieves exceptional accuracy in complex river environments with Precision = 0.99 and F1-Score = 0.95.
• The tool outperforms standard thresholding techniques (NDWI, OTSU) for water-surface mask generation.

Contributions

• This study introduces a highly precise, scalable alternative to manual masking for ALB processing, addressing the limitations of static topographic databases and manual delineation methods.

Funding

• Natural Sciences and Engineering Research Council of Canada (NSERC)
• Canadian Foundation for Innovation (CFI)

Citation

@article{Wróblewski2026HydroBoundML,
  author = {Wróblewski, Patryk and Fryśkowska, Anna},
  title = {HydroBound-ML: Automated Water-Surface-Mask Generation for Airborne Lidar Bathymetry Processing Using Hybrid Machine Learning and Object-Based Image Analysis},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26196065},
  url = {https://doi.org/10.3390/s26196065}
}