Evaluation of polarization modes and spatial resolution of PALSAR-2 for canal detection accuracy in Indonesia peatlands

Drainage canal inventories are vital for understanding peatland hydrology and mitigating CO2 emissions from drained peatlands. This study presents a deep learning approach to develop an ensemble classifier for canal segmentation using PALSAR-2, incorporating hyperparameter tuning, multi-polarization...

Full description

Bibliographic Details

Published in:	Geocarto International
Main Authors:	Muhammad Haidar, Wataru Takeuchi
Format:	Article
Language:	English
Published:	Taylor & Francis Group 2025-12-01
Subjects:	Deep learning semantic segmentation polarimetry SAR ensemble classifier multi-resolution tile-based accuracy assessment
Online Access:	https://www.tandfonline.com/doi/10.1080/10106049.2025.2509295