Deep learning approach for Sentinel-1 surface water mapping leveraging Google Earth Engine.
Published in ISPRS Open Journal of Photogrammetry and Remote Sensing, 2021
In this paper, we investigate two methods of automatic data labeling: 1. the Joint Research Centre (JRC) surface water maps; 2. an Edge-Otsu dynamic threshold approach. We deployed a U-Net convolutional neural network to map surface water from Sentinel-1 Synthetic Aperture Radar (SAR) data and tested the model performance using different hyperparameter tuning combinations to identify the optimal learning rate and loss function. The performance was then evaluated using an independent validation data set.
Recommended citation: Mayer, Timothy, Ate Poortinga, Biplov Bhandari, Andrea P. Nicolau, Kel Markert, Nyein Soe Thwal, Amanda Markert et al. "Deep learning approach for Sentinel-1 surface water mapping leveraging Google Earth Engine." ISPRS Open Journal of Photogrammetry and Remote Sensing 2 (2021): 100005.
Download Paper