Shallow Water Bathymetry Derived by Machine Learning and Multitemporal Satellite Images

Shallow water bathymetry is essential information for coastal science and nautical navigation. In this study, a satellite derived bathymetry (SDB) map, considered suitable for shallow water, was created using random forests (RF) and multi-temporal satellite images from Google Earth Engine. RF perfor...

Full description

Saved in:
Bibliographic Details
Main Authors: Sagawa, Tatsuyuki, Yamashita, Yuta, Okumura, Toshio, Yamanokuchi, Tsutomu
Format: Conference Proceeding
Language:English
Subjects:
Earth
machine learning
multi-temporal
Radio frequency
random forest
Remote sensing
satellite derived bathymetry
Satellites
shallow water
Tides
Training
Training data
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Shallow water bathymetry is essential information for coastal science and nautical navigation. In this study, a satellite derived bathymetry (SDB) map, considered suitable for shallow water, was created using random forests (RF) and multi-temporal satellite images from Google Earth Engine. RF performance was assessed with a training dataset varying in size. The root mean square error (RMSE) of the SDB map created by the RF model decreased with an increase in training dataset size. Tide-level correction methods are proposed and satellite-image based correction methods improved accuracy significantly. For our Hateruma case study, the average RMSE for the SDB map created using 25 satellite images was 1.79 m.
ISSN:2153-7003
DOI:10.1109/IGARSS.2019.8899043