Browsing by Author "Sahin, Volkan"

Now showing 1 - 4 of 4

Determination of Wastewater Behavior of Large Passenger Ships Based on Their Main Parameters in the Pre-Design Stage
(Mdpi, 2020) Sahin, Volkan; Vardar, Nurten
Wastewater formed on ships is divided into blackwater and graywater. While blackwater refers to wastewater from toilets, graywater defines wastewater from sinks, laundry and restaurants. Even though some treatments are applied onboard before discharge, wastewater contains significant amounts of fecal bacteria, heavy metals, etc., in excess of water quality standards. Dilution is a secondary natural treatment in the ship-wake region, which occurs after wastewater discharging. According to the Environmental Protection Agency (EPA), the natural treatment process is quantified by dilution factor, which is strongly dependent on vessel width, draft, speed and wastewater discharge rate. In this study, an Artificial Neural Network (ANN) model linked with the main ship parameters was developed to estimate the dilution factors while the ship is in the preliminary design stage. Gross ton, deadweight ton, passenger number, freeboard, engine power, propeller number and block coefficient values of 1041 large cruise ships were used to estimate the likely dilution factors. The best ANN estimation model was determined by Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) methods. A decision tree was created for the results and the most important parameters affecting the dilution factors were determined. The main ship dimensions are needed for the dilution factor formulation of EPA whereas in the model created in this study only the gross ton or engine power of the ship is sufficient to estimate the dilution. Moreover, this new model is also usable for the estimation of dilution factors even if the main dimensions of the ship are not known.
Estimation of Dilution Factor for Moving Cruise Ships by Artificial Neural Networks
(Springer int Publ Ag, 2022) Sahin, Volkan; Bilgili, Levent; Vardar, Nurten
Although domestic wastewater originating from ships is discharged to the sea after being treated in the treatment system, it cannot meet the wastewater concentration standards determined by the authorities in terms of some pollutant concentrations. This problem is more important on cruise ships, which can carry much more people than other commercial ships. After the wastewater treated in the treatment system on the ship is discharged to the sea, it is subjected to a secondary natural treatment due to the turbulence that occurs on the ship's trail. This phenomenon, called dilution, helps the pollutant concentrations in high concentrations to reach the wastewater standards determined by the authorities in a short time. The magnitude of this dilution is called the dilution factor. In this study, gross ton, deadweight ton, passenger number, freeboard, engine power, propeller number, and block coefficient data of a total of 1942 passenger ships, 941 of which were small and 1041 of which were large passenger ships, were used in artificial neural networks to determine which parameter was more effective in calculating the dilution factor. Engine power and gross ton value were determined as the most effective parameters for the dilution factor, and it was seen that by using these parameters alone in artificial neural networks, the dilution factor could be successfully predicted regardless of whether the ship was small or large. Finally, the effect of dilution was assessed in terms of sustainable development goals and life cycle perspective.
Explainable Machine Learning-Based Prediction of CO2 Emissions From Passenger Vessels
(Pergamon-Elsevier Science Ltd, 2025) Sahin, Volkan
Accurate prediction of CO2 emissions from maritime transportation is critically important for environmental sustainability and effective regulatory action. In this study, hourly CO2 emissions were estimated using Random Forest and Extreme Gradient Boosting algorithms, trained on structural and operational data from approximately 2000 passenger ships-including Gross Tonnage, Speed, Length, Beam, Net Tonnage, Draft, and Deadweight Tonnage. Both models demonstrated high predictive accuracy (R2 = 0.92), with Extreme Gradient Boosting achieving lower Root Mean Square Error and Mean Absolute Error values. To enhance transparency, SHapley Additive Explanations analysis was applied, identifying Gross Tonnage, Speed, and Length as the most influential features. A simplified model using only these three variables achieved comparable performance to the full model, offering a more efficient alternative. Furthermore, the ability to predict emissions using only structural ship data provides a practical and cost-effective solution for shipowners and regulators to comply with the European Union's Monitoring, Reporting and Verification System and the International Maritime Organization's Data Collection System. It also supports strategic planning for carbon pricing schemes and Emission Control Areas, where stricter environmental regulations apply. These findings enhance the practical and policy relevance of explainable artificial intelligence-based emission models in the maritime sector.
A Literature Analysis on Environmental Impacts and Relevant International Legislation of Shipyards
(Univ Dubrovnik, 2024) Sahin, Volkan; Bilgili, Levent
Shipyards are the place where the life cycle of a ship begins and ends. The life cycle of a ship, which starts with painting, blasting, and welding processes during the construction, is completed with the recycling of the steel parts and other equipment after the ship is scrapped. In this study, the harmful waste generated during the construction and recycling of ships in the shipyard and the environmental damage caused by this waste were investigated through a literature analysis. The content, implementation procedures and development processes of the relevant regulations are also examined. To fully evaluate the cumulative and holistic environmental impacts of shipyard processes, it is recommended to make greater use of the life cycle assessment approach. In this way, it will be possible to determine which process is more environmentally harmful during the shipbuilding, operation, and recycling phases, and to accurately determine the overall impact.