Hopfield Neural Network for Sea Surface Current Tracking from Tiungsat-1 Data

This is the first investigation for the use of TanDEM-X data, satellite for the Malaysian coastal waters. This aims at utilizing an optimization of the Hopfield neural network to retrieve variation of sea surface current along Malaysian coastal waters. In doing so, a multi-objective evolutionary algorithm based on the Pareto front is used to minimize the error produced due to non-linearity between TanDEM-X data and sea surface movements. This work aimed at retrieving sea surface current from TanDEM-X data along the coastal waters of Malaysia. Two approaches have been implemented, the Hopfield neural network algorithm and Pareto optimal solution. The study shows that the Pareto optimal solution has a higher performance than the Hopfield neural network algorithm with a lower RMSE of ±0.009. Furthermore, a Pareto optimal solution can determine the sea surface current pattern variation along the coastal water from TanDEM-X data. In conclusion, TanDEM-X data shows an excellent promise for retrieving sea surface currents.

Download Full-text

Simulation sea surface current from RADARSAT-2 SAR data using Hopfield neural network

2015 IEEE 5th Asia-Pacific Conference on Synthetic Aperture Radar (APSAR) ◽

10.1109/apsar.2015.7306326 ◽

2015 ◽

Cited By ~ 3

Author(s):

Maged Marghany

Keyword(s):

Neural Network ◽

Surface Current ◽

Hopfield Neural Network ◽

Sea Surface ◽

Sar Data

Download Full-text

The Use of the Hopfield Neural Network to Measure Sea-Surface Velocities From Satellite Images

IEEE Geoscience and Remote Sensing Letters ◽

10.1109/lgrs.2007.900700 ◽

2007 ◽

Vol 4 (4) ◽

pp. 624-628 ◽

Cited By ~ 5

Author(s):

StÉphane Cote ◽

Adrian R. L. Tatnall

Keyword(s):

Neural Network ◽

Satellite Images ◽

Hopfield Neural Network ◽

Sea Surface

Download Full-text

Prediction of geostrophic currents using big weather data archive and neural networks for the Aegean Sea

Global Journal of Computer Sciences Theory and Research ◽

10.18844/gjcs.v9i1.4091 ◽

2019 ◽

Vol 9 (1) ◽

pp. 10-20

Author(s):

Timur İnan ◽

Ahmet Fevzi BABA

Keyword(s):

Neural Network ◽

Surface Current ◽

Aegean Sea ◽

Current Data ◽

Sea Surface ◽

Weather Data ◽

Time Of Arrival ◽

Surface Currents ◽

Data Archive ◽

Wave Direction

Prediction of sea and weather environment variables like wind speed, wind direction, wave height, wave direction, sea surface current direction and magnitude has always been an important subject in marine engineering as they effect on ship speed and effect the time of arrival to destination point as well. In this study, we propose a neural network that can predict the latitudinal and longitudinal components of sea surface currents in the Aegean Sea. The system can predict the sea surface currents components using the wind components which are gathered from the INMARSAT weather report system. The neural network is trained using the historical data which is gathered from UCAR historical weather database and historical surface current data which is gathered from IFREMER database. Keywords: Sea surface current, weather report, prediction, neural network, big data archive.

Download Full-text