Abstract
Water depth estimation in seaports is essential for effective port management. This paper presents an empirical approach for water depth determination from satellite imagery through the integration of multiple datasets and machine learning algorithms. The implementation details of the proposed approach are provided and compared against different existing machine learning algorithms with a single training set. For a single training set and a single machine learning method, our analysis shows that the proposed depth estimation method provides a better root-mean-square error (RMSE) and a higher coefficient of determination (R2) under turbid water conditions, with overall RMSE and R2 improvements of 1 cm and 0.7, respectively. The developed method may be employed in monitoring dredging activities, especially in areas with polluted water, mud and/or a high sediment content.
Highlights
Bathymetry or measurement of water depth in coastal areas is crucial in many fields such as coastal shipping, dredging activity monitoring, coastal ecosystem management, fishery development, mineral exploration, natural disaster management, as well as coastal research and modeling [1,2]
The aforementioned methods have generally improved the accuracy of bathymetry by utilizing remote-sensing images and algorithms
We investigated the accuracy of water depth estimation based on integrating multiple training datasets of Sentinel-2 images and machine learning algorithms
Summary
Bathymetry or measurement of water depth in coastal areas is crucial in many fields such as coastal shipping, dredging activity monitoring, coastal ecosystem management, fishery development, mineral exploration, natural disaster management, as well as coastal research and modeling [1,2]. The accuracy of the remotesensing bathymetry methods is typically limited for water depth estimation in shallow areas. Machine learning methods have been considered for constructing more general models for water depth estimation. These methods could be employed to better exploit the multi-dimensional characteristics of multi-spectral sensor data. Training and optimizing a water depth model is carried out with one set of multi-spectral images and a single machine learning algorithm [16]. In order to boost the accuracy and robustness of the current methods for water depth estimation, adaptive exploration of this type of information should be carried out in conjunction with ensemble machine learning algorithms. The feasibility of the proposed approach is demonstrated for a test site
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
