Extracting Coastal Water Depths from Multi-Temporal Sentinel-2 Images Using Convolutional Neural Networks

Extracting Coastal Water Depths from Multi-Temporal Sentinel-2 Images Using Convolutional Neural Networks

Lumban-Gaol, Yustisi (Student TU Delft; National Research and Innovation Agency)
Arroyo Ohori, G.A.K. (TU Delft Urban Data Science)
Peters, R.Y. (TU Delft Urban Data Science)

2022

Satellite-Derived Bathymetry (SDB) can be calculated using analytical or empirical approaches. Analytical approaches require several water properties and assumptions, which might not be known. Empirical approaches rely on the linear relationship between reflectances and in-situ depths, but the relationship may not be entirely linear due to bottom type variation, water column effect, and noise. Machine learning approaches have been used to address nonlinearity, but those treat pixels independently, while adjacent pixels are spatially correlated in depth. Convolutional Neural Networks (CNN) can detect this characteristic of the local connectivity. Therefore, this paper conducts a study of SDB using CNN and compares the accuracies between different areas and different amounts of training data, i.e., single and multi-temporal images. Furthermore, this paper discusses the accuracies of SDB when a pre-trained CNN model from one or a combination of multiple locations is applied to a new location. The results show that the accuracy of SDB using the CNN method outperforms existing works with other methods. Multi-temporal images enhance the variety in the training data and improve the CNN accuracy. SDB computation using the pre-trained model shows several limitations at particular depths or when water conditions differ.

CNN
include these here if the journal requires them
multi-temporal images
SDB
Sentinel-2
shallow water
transfer model

http://resolver.tudelft.nl/uuid:a20fa3bb-65d0-49a5-93b5-81eca0120c93

https://doi.org/10.1080/01490419.2022.2091696

0149-0419

Marine Geodesy: an international journal of ocean surveys, mapping and sensing, 45 (6), 615-644

Institutional Repository

journal article

© 2022 Yustisi Lumban-Gaol, G.A.K. Arroyo Ohori, R.Y. Peters