An overview of maritime waterway quantitative risk assessment models

Using near misses, artificial intelligence, and machine learning to predict maritime incidents: A U.S. Coast Guard case study

Two recent trends made this project possible: (1) The recognition that near misses can be predictors of future negative events and (2) enhanced artificial intelligence (AI) and machine learning (ML) tools that make data analytics accessible for many organizations. Increasingly, organizations are learning from prior incidents to improve safety and reduce accidents. The U.S. Coast Guard (USCG) uses a reporting system called the Marine Information for Safety and Law Enforcement (MISLE) database. Because many of the incidents that appear in this database are minor ones, this project initially focused on determining if near misses in MISLE could be predictors of future accidents. The analysis showed that recent near-miss counts are useful for predicting future serious casualties at the waterway level. Using this finding, a predictive AI/ML model was built for each waterway type by vessel combination. Random forest decision tree AI/ML models were used to identify waterways at significant accident risk. An R-based predictive model was designed to be run monthly, using data from prior months to make future predictions. The prediction models were trained on data from 2007 to 2022 and tested on 10 months of data from 2022, where prior months were added to test the next month. The overall accuracy of the predictions was 92%-99.9%, depending on model characteristics. The predictions of the models were considered accurate enough to be potentially useful in future prevention efforts for the USCG and may be generalizable to other industries that have near-miss data and a desire to identify and manage risks.

Spatial Modeling of Maritime Risk Using Machine Learning

Managing navigational safety is a key responsibility of coastal states. Predicting and measuring these risks has a high complexity due to their infrequent occurrence, multitude of causes, and large study areas. As a result, maritime risk models are generally limited in scale to small regions, generalized across diverse environments, or rely on the use of expert judgement. Therefore, such an approach has limited scalability and may incorrectly characterize the risk. Within this article a novel method for undertaking spatial modeling of maritime risk is proposed through machine learning. This enables navigational safety to be characterized while leveraging the significant volumes of relevant data available. The method comprises two key components: aggregation of historical accident data, vessel traffic, and other exploratory features into a spatial grid; and the implementation of several classification algorithms that predicts annual accident occurrence for various vessel types. This approach is applied to characterize the risk of collisions and groundings in the United Kingdom. The results vary between hazard types and vessel types but show remarkable capability at characterizing maritime risk, with accuracies and area under curve scores in excess of 90% in most implementations. Furthermore, the ensemble tree-based algorithms of XGBoost and Random Forest consistently outperformed other machine learning algorithms that were tested. The resultant potential risk maps provide decisionmakers with actionable intelligence in order to target risk mitigation measures in regions with the greatest requirement.

Review of Probabilistic Risk Assessment Models for Ship Collisions with Structures

Researchers have always been concerned about collision risks between ships and structures on busy waterways, as the consequences can be catastrophic. The models for determining the probabilities of these accidents, however, vary widely, with discrepancies between different model results in the same assessment. The models sometimes lack critical elements or are inherently flawed, and therefore do not represent reality. This paper aims to review the existing probabilistic risk models for ship and structure collisions. The advantages and disadvantages of each model are discussed, which leads to a better method for future model development. This paper reviews the existing literature for the probabilistic risk assessment (PRA) between nautical traffic and offshore infrastructures. This paper differentiates the existing models into three categories: statistics of collision rates, statistical models, and simulation models, as the models are evolving from statistical models to simulation models to derive more accurate results. The advantages and disadvantages of the statistical models were evaluated by comparing the details of the elements contributing to risk. Simulation models with virtual autonomous ships can better reflect the reality and include more risk elements than those described in the existing models. The cores of simulation models and the advantages of different models are elaborated and compared, thus supporting future work in this area.

A Chronological Overview of Scientific Research on Ship Grounding Frequency Estimation Models

In the global maritime industry, ship grounding represents about one-third of commercial groundings. Grounding is a type of accident where the hull of a ship strikes the seabed, causing damage to the hull. This type of accident can lead to damage to the hull and water penetration, but also to the pollution of the marine environment by the spillage of ship fuel or some liquid cargo carried by the ship. This paper presents a chronological overview of the contribution of ship grounding frequency, where one of the first ideas of grounding probability was presented by Macduff (1974) and Fuji (1974) in their models. Their ideas, such as grounding candidates and causing probability, laid the foundation for the development of future models. After their models, years later, other models continued to be developed; e.g., analytically (Macduff, Fujii, Amrowitcz, etc.) and statistically (Pedersen, Simonsen, etc.). To find the probability of grounding in an area of interest or in a scenario, it is necessary to have the number of grounding candidates and the causing probability. There are different internal and external factors that affect both probabilities, and in this paper, we analyze how various authors approach their grounding models and have tried to show the actual event as faithfully as possible and thus contribute to greater safety in maritime transport. The number of grounding frequency models significantly complicates their selection in practice; accordingly, the review of models in this paper should facilitate this, but also it should facilitate future research on this topic.

Methodology for Maritime Risk Assessment in Ports due to Meteo-oceanographic Factors: The Case of the port of Suape, Brazil

Exploring the effects of meteo-oceanographic (MO) events on ships' maneuverability and safety has great potential, since most maritime accidents occur in confined waters, where the speed of ships is low, and the forces of wind and current on ships have particular importance. Therefore, we put forward a methodology that will be used to qualify and classify the risks caused by MO factors to how ships maneuver, dock or undock in a port. The objective is to generate important information for managing risk. The methodology is validated and illustrated step-by-step by applying it in Suape, one of the most important ports in Brazil, where the docking of larger tankers (e.g., Suezmax) was not allowed until recently when dredging was done to fit the specifications of such ships, thereby expanding the port's operations. MO data on Suape were collected and recorded from September 2016 to November 2017 and used for the application. Based on expert opinion and discussion with a Suape pilot, 36 accidental scenarios (ASs) were identified and categorized using preliminary hazard analysis. From these, the seven most severe ASs were selected so as to assess in more detail the frequency and consequences of accidents on human health, the environment, and property, for which the MO statistics for the likelihood of an accident and/or dispersal of an oil spill were used. The results show that the methodology is viable to assess risks caused by bad weather and to communicate these to pilots and competent authorities, thus improving the safety of operations.

A risk management framework for maritime Pollution Preparedness and Response: Concepts, processes and tools

Several risk management frameworks have been introduced in the literature for maritime Pollution Preparedness and Response (PPR). However, in light of the actual needs of the competent authorities, there is still a lack of framework that is established on a sound risk conceptual basis, addresses the different risk management decision-making contexts of organizations, and provides tools for various risk management questions of this field. To alleviate the limits of existing approaches, this paper introduces a new risk management framework for this purpose, which was developed in cooperation with the competent authorities and other maritime experts. The framework adopts the risk-informed decision-making strategy and includes three aligned components. The first component provides a unified theoretical risk concept to the framework through an interpretation of the Society for Risk Analysis risk approach. The second consists of four ISO 31000:2018 standard based processes focused on different risk management decision-making contexts of the PPR organizations. The third comprises a set of practical risk assessment tools to generate the needed information. A case study provides an example of the functionality of this framework with integrated data from the northern Baltic Sea. To conclude, a risk concept is provided for the PPR authorities and their stakeholders as well as processes for managing the risk and tools for its assessment.

Quantitative Analysis on Risk Influencing Factors in the Jiangsu Segment of the Yangtze River

Quantitative risk influencing factors (RIFs) are proposed, using the Conjugate Bayesian update approach to analyze 945 collision accidents and incidents cases from the Jiangsu Segment of the Yangtze River over five years from 2012 to 2016. The accident probability is compared under a pairwise comparison mode in order to reflect the relative risk between accidental situations. The Bayesian update mode is constructed to quantitatively evaluate the relative importance of different RIFs. The riskiest segment of Jiangsu Waterways as well the main causations of collisions are identified based on the distributions of collision risk in the six segments of the waterways. The results can support managers to develop the most effective policies to mitigate the collision risk.

Assessing the Risk in Urban Public Transport for Epidemiologic Factors

Pandemics have presented new challenges for public transport organisers and operators. New diseases (e.g., influenza H1N1, severe acute respiratory syndrome—SARS, as well as, more recently, SARS-CoV-2) increase the need for new protection measures to prevent epidemic outbreaks in public transport infrastructure. The authors’ goal is to present a set of actions in the area of public transport that are adjusted to different levels of epidemic development. The goal goes back to the following question: how can the highest possible level of passenger safety be ensured and the losses suffered by urban public transport companies kept as low as possible? The sets of pro-active measures for selected epidemic scenarios presented in the article may offer support to local authorities and public transport operators. In the next steps, it is important to develop and implement tools for public transport management to ensure safety and tackle epidemic hazards.

Accident and pollution risk assessment for hazardous cargo in a port environment

The catastrophic environmental, life and monetary losses concomitant to the hazardous cargo accidents have remained a matter of critical concern for the maritime transportation officials. The factors that instigate these accidents while dealing with hazardous cargo in a port environment requires rigorous analysis and evaluation, which still remains in its infancy. In accord to these prevailing issues, this study focusses on the assessment of multifactor risks associated with the dealing of hazardous cargos inside a port. The methodology adopted is the amalgamation of expert judgment and literature review for the identification of factors and developing their causal relationship, while Bayesian Network (BN) for the inference, which was based on 348 past accident reports from the year 1990 to 2018. The results indicate that under normal circumstances, the probability of an accident with considerable consequences is 59.8, where human and management were found to be the highest contributing factors. Setting evidence at the environment and pollution accident to occur, the incidence probability of the "management" is raised by 7.06%. A sensitivity analysis was conducted to determine the most critical factors for the hazardous cargo accident. This study reveals that in order to evade the hazardous cargo accidents and curtail severity of the consequences, the port authorities, concerned government departments and other related institutions should pay specific attention to the qualification, training and attitude of the involved workforce. Moreover, the development and implementation of stringent safety protocols was also revealed to have critical prominence. This study holds practical vitality for enhancing safety and mitigating risks associated to hazardous cargo dealing in a port.

Quantitative Ship Collision Frequency Estimation Models: A Review

Ship collisions are one of the most common types of maritime accidents. Assessing the frequency and probability of ship collisions is of great importance as it provides a cost-effective and practical way to mitigate risk. In this paper, we present a review of quantitative ship collision frequency estimation models for waterway risk assessment, accompanied by a classification of the models and a description of their main modelling characteristics. Models addressing the macroscopic perspective in the estimation of ship collision frequency on waterways are reviewed in this paper with a total of 29 models. We extend the existing classification methodology and group the collected models accordingly. Special attention is given to the criteria used to detect potential ship collision candidates, as well as to causation probability and the correlation of models with real ship collision statistics. Limitations of the existing models and future improvement possibilities are discussed. The paper can be used as a guide to understanding current achievements in this field.

A Methodology for Assessing the Probability of Occurrence of Undesired Events in the Tietê-Paraná Inland Waterway Based on Expert Opinion

The market share of Tietê-Paraná inland waterway (TPIW) in the transport matrix of the São Paulo state, Brazil, is currently only 0.6%, but it is expected to increase to 6% over the next 20 years. In this scenario, to identify and explore potential undesired events a risk assessment is necessary. Part of this involves assigning the probability of occurrence of events, which usually is accomplished by a frequentist approach. However, in many cases, this approach is not possible due to unavailable or nonrepresentative data. This is the case of the TPIW that even though an expressive accident history is available, a frequentist approach is not suitable due to differences between current operational conditions and those met in the past. Therefore, a subjective assessment is an option as allows for working independently of the historical data, thus delivering more reliable results. In this context, this article proposes a methodology for assessing the probability of occurrence of undesired events based on expert opinion combined with fuzzy analysis. This methodology defines a criterion to weighting the experts and, using the fuzzy logic, evaluates the similarities among the experts' beliefs to be used in the aggregation process before the defuzzification that quantifies the probability of occurrence of the events based on the experts' opinion. Moreover, the proposed methodology is applied to the real case of the TPIW and the results obtained from the elicited experts are compared with a frequentist approach evidencing the impact on the results when considering different interpretations of the probability.

Time-Varying Risk Measurement for Ship Collision Prevention

We propose an innovative time-varying collision risk (TCR) measurement for ship collision prevention in this article. The proposed measurement considers the level of danger of the approaching ships and the capability of a ship to prevent collisions. We define the TCR as the probability of the overlap of ships' positions in the future, given the uncertainty of maneuvers. Two sets are identified: (1) the velocity obstacle set as the maneuvers of the own ship that lead to collisions with target ships, and (2) the reachable velocity set as the maneuvers that the own ship can reach regarding its maneuverability. We then measure the TCR as the time-dependent percentage of overlap between these two sets. Several scenarios are presented to illustrate how the proposed measurement identifies the time-varying risk levels, and how the approach can be used as an intuitively understandable tool for collision avoidance.

Risk Assessment Methodology for Vessel Traffic in Ports by Defining the Nautical Port Risk Index

Ports represent a key element in the maritime transportation chain. Larger vessels and higher traffic volumes in ports might result in higher risks at the navigational level. Thus, the dire need for a comprehensive and efficient risk assessment method for ports is felt. Many methodologies have been proposed so far, but their application to aggregated vessel traffic risks for the overall assessment of ports is not developed yet. Hence, the development of an approach for the appraisal of the vessel traffic risks is still a challenging issue. This research aims to develop an assessment methodology to appraise the potential risk of accident occurrence in port areas at an aggregated level by creating a ‘Nautical Port Risk Index’ (NPRI). After identifying the main nautical risks in ports, the Analytic Network Process (ANP) is used to derive the risk perception (RP) weights for each criterion from data collected through surveys to expert navigators. The consequences related to each nautical risk are identified in consultation with risk experts. By combining the RP values and the consequence of each criterion for a time period, the NPRI is calculated. The risks in the Port of Rotterdam are presented in a case study, and the method has been validated by checking the results with experts in assessing nautical port risks from the Port of Rotterdam Authority. This method can be used to assess any new port design, the performance of different vessel traffic management measures, changes in the fleet composition, or existent ports using the Automatic Identification System (AIS) data.

Dynamics Simulation for Process Risk Evolution on the Bunker Operation of an LNG-fueled Vessel with Catastrophe Mathematical Models

Liquefied nature gas (LNG) is a green energy. LNG-fueled vessels are extremely complex engineering systems. In view of the inherent hazardous properties of LNG fuel, LNG fueling is not only an important part, but it is also full of high risks in the operation of LNG-fueled vessels (LNGFVs). Therefore, it is necessary to study the risk factors, and the intrinsic relationship among them between the LNG and the vessel, and to simulate the system dynamics in the process of LNGFV operation. During the process of fueling of LNGFV, at every moment the vessel interacts with the energy and information of the surrounding environment. First, the impact of the three interactions of the fueling operation process, ship factors, and environmental factors were analyzed on the risk of fueling operation, and a complete node system was proposed as to the complex system dynamics mode. Second, by analyzing the boundary conditions of the system, the relationship of factors was established via the tools of system dynamics (SD). Based on the catastrophe theory (CA), the dynamics model for the fueling of LNG is set up to study the system’s risk mutation phenomenon. Third, combined with the simulation results of the case analysis, the risk evolution mode of the LNGFV during the fueling process was obtained, and constructive opinions were put forward for improving the safe fueling of the LNGFV. Application examples show that formal description of risk emergence and transition is a prerequisite for the quantitative analysis of the risk evolution mode. In order to prevent accidents, the coupling synchronization of risk emergence should be weakened, and meanwhile risk control should be implemented.

Maritime Transportation Risk Assessment of Tianjin Port with Bayesian Belief Networks

This article develops a Bayesian belief network model for the prediction of accident consequences in the Tianjin port. The study starts with a statistical analysis of historical accident data of six years from 2008 to 2013. Then a Bayesian belief network is constructed to express the dependencies between the indicator variables and accident consequences. The statistics and expert knowledge are synthesized in the Bayesian belief network model to obtain the probability distribution of the consequences. By a sensitivity analysis, several indicator variables that have influence on the consequences are identified, including navigational area, ship type and time of the day. The results indicate that the consequences are most sensitive to the position where the accidents occurred, followed by time of day and ship length. The results also reflect that the navigational risk of the Tianjin port is at the acceptable level, despite that there is more room of improvement. These results can be used by the Maritime Safety Administration to take effective measures to enhance maritime safety in the Tianjin port.

Dependence Assessment in Human Reliability Analysis Using Evidence Theory and AHP

Dependence assessment among human errors in human reliability analysis (HRA) is an important issue. Many of the dependence assessment methods in HRA rely heavily on the expert's opinion, thus are subjective and may sometimes cause inconsistency. In this article, we propose a computational model based on the Dempster-Shafer evidence theory (DSET) and the analytic hierarchy process (AHP) method to handle dependence in HRA. First, dependence influencing factors among human tasks are identified and the weights of the factors are determined by experts using the AHP method. Second, judgment on each factor is given by the analyst referring to anchors and linguistic labels. Third, the judgments are represented as basic belief assignments (BBAs) and are integrated into a fused BBA by weighted average combination in DSET. Finally, the CHEP is calculated based on the fused BBA. The proposed model can deal with ambiguity and the degree of confidence in the judgments, and is able to reduce the subjectivity and improve the consistency in the evaluation process.

A risk analysis of winter navigation in Finnish sea areas

Winter navigation is a complex but common operation in north-European sea areas. In Finnish waters, the smooth flow of maritime traffic and safety of vessel navigation during the winter period are managed through the Finnish-Swedish winter navigation system (FSWNS). This article focuses on accident risks in winter navigation operations, beginning with a brief outline of the FSWNS. The study analyses a hazard identification model of winter navigation and reviews accident data extracted from four winter periods. These are adopted as a basis for visualizing the risks in winter navigation operations. The results reveal that experts consider ship independent navigation in ice conditions the most complex navigational operation, which is confirmed by accident data analysis showing that the operation constitutes the type of navigation with the highest number of accidents reported. The severity of the accidents during winter navigation is mainly categorized as less serious. Collision is the most typical accident in ice navigation and general cargo the type of vessel most frequently involved in these accidents. Consolidated ice, ice ridges and ice thickness between 15 and 40cm represent the most common ice conditions in which accidents occur. Thus, the analysis presented in this article establishes the key elements for identifying the operation types which would benefit most from further safety engineering and safety or risk management development.

Stochastic measures of network resilience: applications to waterway commodity flows

Given the ubiquitous nature of infrastructure networks in today's society, there is a global need to understand, quantify, and plan for the resilience of these networks to disruptions. This work defines network resilience along dimensions of reliability, vulnerability, survivability, and recoverability, and quantifies network resilience as a function of component and network performance. The treatment of vulnerability and recoverability as random variables leads to stochastic measures of resilience, including time to total system restoration, time to full system service resilience, and time to a specific α% resilience. Ultimately, a means to optimize network resilience strategies is discussed, primarily through an adaption of the Copeland Score for nonparametric stochastic ranking. The measures of resilience and optimization techniques are applied to inland waterway networks, an important mode in the larger multimodal transportation network upon which we rely for the flow of commodities. We provide a case study analyzing and planning for the resilience of commodity flows along the Mississippi River Navigation System to illustrate the usefulness of the proposed metrics.