Review of ship safety domains: Models and applications

An Advanced Method For Detecting Possible Near Miss Ship Collisions From AIS Data

https://research.aalto.fi/files/11777794/1_s2.0_S0925753516000102_main.pdf

An analysis of ship escort and convoy operations in ice conditions

An Analysis of Domain-Based Ship Collision Risk Parameters

A novel analytic framework of real-time multi-vessel collision risk assessment for maritime traffic surveillance

A critique of the use of domain analysis for spatial collision risk assessment

Domain analysis has a well-documented history in peer reviewed academic literature; however there are few instances of its application to facilitate the assessment of system specific navigation risk. This paper details one example of a practical approach to domain analysis for a busy section of the River Thames in Central London. The results correlate well to known high risk collision areas on the river and help to quantify and corroborate expert opinion and local knowledge. However a number of conditions must be accounted for in undertaking a robust study such as the geography of the study site, the purpose and audience of the research, and the availability of data and its limitations.

https://www.cambridge.org/core/services/aop-cambridge-core/content/view/S0373463313000684

Practical Application of Domain Analysis: Port of London Case Study

The development of offshore renewable energy installations can introduce additional hazards to the safe navigation of shipping in often already crowded waterways. Developers and decision makers must predict and properly manage the potential risks imposed on navigating vessels from wind farm developments, in a complex and uncertain environment. Considerable analysis has been undertaken to model navigational risks to vessel traffic around wind farms; however this work is generally predictive and there is little understanding as to whether the modelling, central to the consideration of navigation safety, accurately reflects the post-constructed navigation risks. It is therefore important for decision makers to understand the uncertainties present in the analysis, both in terms of the assessment of risk and the implementation of any risk reduction measures. This paper presents a comparative analysis of the change in vessel traffic in the Thames Estuary before and after the construction of five offshore wind farms. The analysis demonstrates how the impact on vessel traffic is specific to the location of each development, driven by traffic management measures and other local constraints. Therefore the accurate modelling of this impact requires the input of experienced navigators, regulators and other knowledgeable stakeholders. The results of this analysis can be used to improve the predictive modelling of vessel traffic around offshore wind farms and other offshore installations, leading to a reduction in the uncertainty of vessel traffic modelling in the future.

/pdf/assessing-the-impacts-to-vessel-traffic-from-offshore-wind-3qvnrs9w02.pdf

Assessing the impacts to vessel traffic from offshore wind farms in the Thames Estuary

A machine learning approach for monitoring ship safety in extreme weather events

Each year, accidents involving ships result in significant loss of life, environmental pollution and economic losses. The promotion of navigation safety through risk reduction requires methods to assess the spatial distribution of the relative likelihood of occurrence. Yet, such methods necessitate the integration of large volumes of heterogenous datasets which are not well suited to traditional data structures. This paper proposes the use of the Discrete Global Grid System (DGGS) as an efficient and advantageous structure to integrate vessel traffic, metocean, bathymetric, infrastructure and other relevant maritime datasets to predict the occurrence of ship groundings. Massive and heterogenous datasets are well suited for machine learning algorithms and this paper develops a spatial maritime risk model based on a DGGS utilising such an approach. A Random Forest algorithm is developed to predict the frequency and spatial distribution of groundings while achieving an R2 of 0.55 and a mean squared error of 0.002. The resulting risk maps are useful for decision-makers in planning the allocation of mitigation measures, targeted to regions with the highest risk. Further work is identified to expand the applications and insights which could be achieved through establishing a DGGS as a global maritime spatial data structure.

Andrew David Rawson

Papers

A critique of the use of domain analysis for spatial collision risk assessment

Practical Application of Domain Analysis: Port of London Case Study

Assessing the impacts to vessel traffic from offshore wind farms in the Thames Estuary

A machine learning approach for monitoring ship safety in extreme weather events

Intelligent Geospatial Maritime Risk Analytics Using The Discrete Global Grid System