Search

Society is concerned about maritime accidents since pollution, such as oil spills from ship accidents, adversely affects the marine environment. Operational and strategic pollution preparedness and response risk management are essential activities to mitigate such adverse impacts. Quantitative risk models and decision support systems (DSS) have been proposed to support these risk management activities. However, there currently is a lack of computationally fast and accurate models to estimate oil spill consequences. While resource-intensive simulation models are available to make accurate predictions, these are slow and cannot easily be integrated into quantitative risk models or DSS. Hence, there is a need to develop solutions to accelerate the computational process. A fast and accurate metamodel is developed in this work to predict damage and oil outflow in tanker collision accidents. To achieve this, multiobjective optimization is applied to three metamodeling approaches: Deep Neural Network, Polynomial Regression, and Gradient Boosting Regression Tree. The data used in these learning algorithms are generated using state-of-the-art engineering models for accidental damage and oil outflow dynamics. The multiobjective optimization approach leads to a computationally efficient and accurate model chosen from a set of optimized models. The results demonstrate the metamodel’s robust capacity to provide accurate and computationally efficient estimates of damage extents and volume of oil outflow. This model can be used in maritime risk analysis contexts, particularly in strategic pollution preparedness and response management. The models can also be linked to operational response DSS when fast, and reasonably accurate estimates of spill sizes are critical.

This paper presents a model to analyse the risk of two common marine accidents: collision and grounding. Attention is focused on oil tankers since they pose the highest environmental risks. A case study in selected areas of the Gulf of Finland in ice-free conditions is presented. The model utilizes a formula for risk calculation that considers both the probability of an unwanted event and its consequences. The model can be decomposed into a block representation in which blocks for the probability of a collision, probability of a grounding event, and the consequences of an accident are linked. The probability of vessel colliding is assessed in terms of a minimum-distance-to-collision-based model. The model defines the collision zone using a mathematical ship motion model and considers the traffic flow to be a non-homogeneous process. Calculations are performed using data for traffic flows in the Gulf of Finland with particular attention being paid to the crossing of the channel used by scheduled ferries between Helsinki and Tallinn, and the main shipping channel. For the assessment of a grounding probability, a new approach is proposed, which utilizes a gravity-like model, where a ship and navigational obstructions are perceived as interacting objects and their repulsion is modelled by a formulation inspired by gravitational force. The considered situation in this case is the movement of oil tankers in the approach channel to an oil terminal at Sköldvik, near Helsinki. The consequences of an accident are expressed in monetary terms, and concern the costs of cleaning up an oil spill, based on the statistics of compensation levels claimed from the International Oil Pollution Compensation Fund.