Artificial Intelligence Based Prediction of Seawater Level: A Case Study for Bosphorus Strait

Sea level prediction is an important phenomenon for making reliable oceanographic and ship traffic management decisions especially for Bosphorus Strait that has no permanent sea level measurement stations due to high cost. This study presents artificial intelligence (AI) techniques, such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVM) to predict the seawater level in the Bosphorus Strait. In addition, the Multiple Linear Regression model (MLR) is constructed and employed as a benchmark. The dataset employed in developing the models are wind speed, atmospheric pressure, water surface salinity, and temperature data, which were measured between September 2004 and January 2006. The results reveal that all ANN and SVM models outperform MLR and can predict the water levels quite accurately. ANN has a better performance than SVM for predicting sea level in the Bosphorus by coefficient of correlation (R) = 0.76 and root mean square error (RMSE) = 0.059. Moreover, the influence of the Danube River discharge in the prediction is investigated in the present study. The discharge of the Danube River by the lag time of 70 days yields the highest performance on ANN by increasing R to 0.82 and decreasing RMSE to 0.048.

Modeling of the Turkish Strait System Using a High Resolution Unstructured Grid Ocean Circulation Model

The Turkish Strait System, which is the only connection between the Black Sea and the Mediterranean Sea, is a challenging region for ocean circulation models due to topographic constraints and water mass structure. We present a newly developed high resolution unstructured finite element grid model to simulate the Turkish Strait System using realistic atmospheric forcing and lateral open boundary conditions. We find that the jet flowing from the Bosphorus Strait into the Marmara creates an anticyclonic circulation. The eddy kinetic energy field is high around the jets exiting from the Bosphorus Strait, Dardanelles Strait, and also the leeward side of the islands in the Marmara Sea. The model successfully captures the two-layer structure of the Sea of Marmara. The volume transport at the Bosphorus is around 120 km3/year which is consistent with the recent observations. The largest bias in the model is at the interface depth due to the shallower mixed layer.

HARBOR AGITATION DUE TO OFFSHORE SHIP WAVES USING SWASH: A CASE STUDY OF KUMKAPI YACHT PARK, ISTANBUL

This study presents the results of a numerical modeling study on the harbor agitation in case of offshore ship waves using SWASH (acronym for Simulating WAves till SHore), a numerical model developed for the simulating unsteady, non-hydrostatic, free-surface, rotational flow and transport phenomena in coastal waters as driven by waves, tides, buoyancy and wind forces (Zijlema et al. 2011). The study area is the Kumkapi Yacht Park, at the Marmara coast of Istanbul, 2.5 km west of the southern entrance of Bosphorus strait. The yacht park is currently used as a fishery harbor, which is severely affected by the ship waves of ferries and sea buses passing nearby almost parallel to the main breakwater of the harbor (aligned from west to east). The park is planned to berth a total of 140 yachts varying from 5 m to 40 m in length (Figure 1). For this purpose, the present harbor layout together with several alternative plans have been studied numerically to investigate agitation due to ship waves of ferries and sea buses considering the design safety requirements of ASCE (2012) for the safe mooring and berthing of yachts.

MACROZOOBENTHIC COMMUNITIES IN THE EASTERN PART OF THE EASTERN BOSPHORUS STRAIT (PETER THE GREAT BAY, JAPAN SEA)

In total, 146 species of macrozoobenthos belonged to 11 taxonomic groups are found in the surveyed area in the eastern part of the Eastern Bosphorus Strait. Polychaetes have the highest species number, followed by bivalves and amphipods with five times less number of species. Polychaetes and bivalves have the highest occurrence, too, gastropods and amphipods occur frequently, as well. Bivalves dominate by biomass, but polychaetes — by their abundance. Benthos of the Patrokl Bight at the northern coast is poor relatively to the southern part of the strait at Russky Island because of low species diversity of amphipods, gastropods and decapods. Four macrozoobenthic communities are defined with the following titular species: Acila insignis + Scalibregma inflatum, Ophiura sarsi + Scoloplos armiger, Ennucula tenuis + Nicolea sp., and Dipolydora cardalia + (Melinna elisabethae or Maldane sarsi). Besides, Echinocardium cordatum dominates at the single station in the internal Patrokl Bight and Protocallithaca adamsi dominates at the single station in the Zhitkov Inlet. Majority of these communities are quite diverse and abundant. All of them, except the last case, are undisturbed or slightly disturbed and possess in good or moderate ecological state. In the case of the Zhitkov Inlet, the impoverished community of P. adamsi is considerably disturbed due to anthropogenic impact. Differentiation between the majority of communities is noted along gradients of natural environmental factors, as depth and fractional composition of bottom sediments. All conclusions are statistically significant and based on the results of consequential use of the factor and cluster analysis, non-metric multidimensional scaling and constrained correspondence analysis with bootstrap and randomization procedures. There is noted that the bottom communities in this area are subjected to rather significant contamination that supposedly causes decreasing of their stability and they may change their species composition and abundance under additional negative impact.