Self-Organizing Maps-based ocean currents forecasting system

I. Vilibić, J. Šepić, H. Mihanović, H. Kalinić, Simone Cosoli, Ivica Janekovic, N. Žagar, B. Jesenko, M. Tudor, V. Dadić, D. Ivanković

Research output: Contribution to journalArticlepeer-review

29 Citations (Scopus)


An ocean surface currents forecasting system, based on a Self-Organizing Maps (SOM) neural network algorithm, high-frequency (HF) ocean radar measurements and numerical weather prediction (NWP) products, has been developed for a coastal area of the northern Adriatic and compared with operational ROMS-derived surface currents. The two systems differ significantly in architecture and algorithms, being based on either unsupervised learning techniques or ocean physics. To compare performance of the two methods, their forecasting skills were tested on independent datasets. The SOM-based forecasting system has a slightly better forecasting skill, especially during strong wind conditions, with potential for further improvement when data sets of higher quality and longer duration are used for training.
Original languageEnglish
Article number22924
Pages (from-to).22924
JournalScientific Reports
Publication statusPublished - 16 Mar 2016


Dive into the research topics of 'Self-Organizing Maps-based ocean currents forecasting system'. Together they form a unique fingerprint.

Cite this