Port State Control Research Articles

Equitable port state control in maritime transportation: A data-driven optimization approach

Construction of a multimodal knowledge graph for LNG carrier port state control inspections based on improved visual prompt tuning

We examine the ecotoxic risk classification of ballast water treatment chemicals by integrating global datasets—ECOTOX from the U.S. EPA and GISIS from the IMO—using a multivariate approach. The study aims to provide a practical decision-support tool to assist in ecological compliance, early warning, and regulatory prioritization. Grounded in ecological risk theory and precautionary policy frameworks, our work bridges empirical toxicological thresholds (e.g., LC50, NOEC, BCF) with practical decision-making systems for maritime chemical regulation. We apply Principal Component Analysis (PCA) to a curated dataset of 37 ballast water substances across three key dimensions: acute toxicity (LC50), chronic toxicity (NOEC), and bioaccumulation potential (BCF). A scoring matrix is then developed to construct a chemical risk heatmap supported by decision support system (DSS) logic. Notably, we observe that 43.24% of chemicals fall into the high-risk category, while only 8.11% qualify as low-risk. PCA explains 73.63% of the data variance with just two components, supporting dimensionality reduction without significant loss of ecological insight. A closer look at substances like Dibromoacetic acid and Dichloroacetonitrile reveals alarming risk profiles with high BCF and low NOEC values—chemicals that current regulations may be overlooking. Surprisingly, some widely used oxidizing agents demonstrate latent chronic toxicity previously underestimated. This finding may reflect policy inertia in updating risk evaluation metrics post-BWM Convention. Our findings contribute to both theoretical refinement in multivariate ecotoxicology modeling and policy design by suggesting a data-driven classification framework for Port State Control (PSC) and IMO risk flags. The visual heatmap tool further enables early-warning applications in smart port ecosystems. This study introduces a novel integration of ECOTOX–GISIS datasets using PCA for ecological risk visualization. Unlike prior works relying solely on laboratory thresholds or qualitative review, our approach enables real-time chemical risk ranking and supports cross-jurisdictional ballast water compliance. The methodological blend of theory and application provides a replicable model for other maritime pollutants in ASEAN and beyond.

The concept of competition is used in many areas from economy to health. As in all sectors, there is competition in the maritime transport industry. Although various Regional Memoranda of Understanding (MoU) have created risk assessment indexes for risk profile calculation, an index to measure competition in maritime transportation has not yet been used in the literature. Ships must successfully pass the inspections they face within the framework of international rules to maintain their commercial existence. The aim of this article is to provide a new perspective on measuring competition between ship types based on the results of inspections in maritime literature. In this context, for the first time in literature, the Ship Inspection Competition Index (SICI) is defined to examine the competition of ship types, flag states, recognized organizations, and ships subject to other inspection regimes. The SICI analysis was conducted using United States Coast Guard (USCG) Port State Control inspection results between 2020 and 2023. The results showed that tankers are more competitive than other ship types. At the same time, a competitiveness analysis of recognized organizations found that one organization was perfectly competitive (SICI = 0.0) compared to others. In the study, Cronbach's Alpha reliability test was conducted, and the result was 0.943 for the deficiency-based measure and 0.976 for the detention-based measure. Both results indicate a high level of reliability. It is considered that this study may provide valuable insights for future research.

For accurate and reliable monitoring, compliance monitoring devices (CMDs) in Port State Control must meet strict and uniform quality standards. This study evaluates how effectively CMDs, using variable fluorescence (VF) and fluorescein diacetate (FDA) technologies, detect live organisms in the 10–50 μm size range. Employing a detailed analytical framework, we analyzed key performance indicators, including accuracy, precision, sensitivity, specificity, trueness, detection limits, and reliability by comparing CMD outputs to those of traditional microscopic methods. Reliability assessments revealed that VF-type CMD and FDA-type CMD performed robustly, with a stability rate of 99% for both, surpassing the 90% verification threshold. Precision analysis indicated an average CV exceeding 0.25; however, some samples, especially those below the D-2 standard, achieved a CV of less than 0.25. Concordance evaluations revealed that VF-CMDs and FDA-CMDs achieved rates of 63% and 55%, respectively, falling short of the 80% verification standard and underscoring the need for further calibration or optimization. Structural equation modeling shows that organism density significantly influences CMD performance. These findings underscore the challenges of accurately detecting low organism concentrations, further complicated by biological diversity and environmental variability. Despite their limitations in assessing ballast water compliance, CMDs are effective initial screening tools.

ABSTRACT Port state control (PSC) inspections are essential for identifying substandard ships, enhancing safety, protecting the marine environment, and safeguarding crew welfare. Yet, correlations between ship features and deficiencies remain underexplored. This study develops a deficiency analysis framework using the Apriori algorithm to mine association rules between ship particulars and deficiencies, as well as among deficiencies. Using Paris MoU data, the results reveal overlooked deficiency clusters and ship type–deficiency patterns. The framework supports more targeted high-risk ship selection, improves PSC efficiency, and contributes to predictive models, maritime digitalization, and smart port development.

ABSTRACT Port State Control (PSC) serves as a crucial mechanism for enforcing maritime regulations and safeguarding against substandard shipping practices. Effective inspections by well-trained port state control officers (PSCOs) are essential to ensure compliance without causing undue delays or detentions, although some shipowners may attempt to evade inspections, complicating enforcement efforts. This review examines scholarly publications from 2017 and 2024 to identify prevailing research themes and methodological approaches in PSC studies. Four primary research themes emerged: (i) evaluation of the PSC regimes, (ii) strategies for effectively targeting substandard vessels, (iii) determinants of PSC inspection outcomes, and (iv) the impact of PSC inspections. A synthesis of these themes revealed nine critical issues, including disparities in regional enforcement practices, inconsistencies in inspector training and legal frameworks, limitations of current risk assessment models, data imbalance and generalizability challenges, integration of artificial intelligence (AI) and machine learning in inspection planning, influence of vessel characteristics and inspection history, impact of external shocks, effectiveness in improving compliance and safety, and stakeholder perceptions and enforcement gaps. The review identifies key knowledge gaps and offers directions for future research to strengthen PSC practices and enhance global maritime safety.

Abstract The international shipping industry played a role in climate change, responsible for a substantial share of GHG emissions, yet remains insuf9iciently regulated in terms of control and obligations. This article explores the evolving legal landscape in maritime environmental governance, particularly following recent advisory opinions from ITLOS and ICJ, which classify anthropogenic GHG emissions as a form of marine pollution under UNCLOS 1982. The discussion highlights the strategic role of Port State jurisdiction and Port State Control (PSC) under existing legal instruments like the UNCLOS 1982 and Annex VI of MARPOL. The article further considers how customary international law principles, including sovereignty and the obligation erga omnes reinforce state unilateral or regional enforcement efforts beyond the scope of existing international regulations. Ultimately, the paper argues for a more robust and cohesive legal approach that empowers Port States, strengthens liability allocation, and supports global climate mitigation objectives especially in international shipping sector.

Dynamics of port state control and impact on ship safety: Case studies of Tokyo and Indian Ocean Memorandum of understanding

Abstract The maritime sector facilitates 80% of global trade but contributes 3% of greenhouse gas emissions. To address climate challenges, Indonesia has enacted laws like Law 16/2016 (Paris Agreement ratification), Law 32/2009 (environmental protection), and Ministerial Decree KM 8/2023 to meet Nationally Determined Contributions (NDC) targets. However, evolving International Maritime Organization (IMO) regulations, such as MARPOL Annex VI and the Energy Efficiency Existing Ship Index (EEXI), raise concerns about potential misalignment between national and international standards, risking Port State Control restrictions. This study evaluates whether KM 8/2023 aligns with IMO regulations, identifying gaps that may hinder compliance. Through comparative policy analysis, legal benchmarking, and stakeholder engagement—including the Directorate General of Sea Transportation, shipping companies, and port authorities—it seeks to improve Indonesia’s sustainable maritime transport framework. The findings will highlight key areas for regulatory and operational enhancements, ensuring Indonesia remains competitive while advancing climate goals. By bridging policy gaps, this research supports Indonesia in meeting global standards, strengthening maritime sustainability, and fulfilling its climate commitments.

Abstrak: Work safety on board ships is a fundamental aspect in supporting smooth shipping operations. This study aims to identify the factors causing the suboptimal installation of gangway safety nets on the MT. Harmony Chemist ship when docked, analyze the impact caused, and formulate improvement strategies in accordance with international safety standards. A descriptive qualitative approach was used with data collection techniques through observation, interviews with key crew members including the Officer, Second Officer, and Bosun, and supported by documentation analysis. Data analysis was conducted using the Root Cause Analysis (RCA) method and the 5 Why approach, as well as problem ranking using the USG (Urgency, Seriousness, Growth) method. The research results indicate that the primary causes of suboptimal installation of gangway safety nets are the failure to conduct equipment suitability checks prior to use, the absence of a clear marking system, and weak communication among deck crew members. These conditions have implications for increased workplace accident risks, operational obstacles, and warnings from Port State Control (PSC) authorities. The USG analysis identified ineffective communication as the highest priority factor that needs to be improved. Recommendations for improvement include strengthening the communication system, conducting regular safety meetings, labeling damaged equipment, implementing double-check procedures, and conducting periodic inspections in accordance with the ISM Code and ISGOTT standards. This study underscores the importance of fully implementing a safety culture to achieve safe, professional, and internationally compliant ship operations.

Machine learning approaches for identifying substandard ships in port state control inspections with imbalanced data

This study developed a model to predict ships with high deficiency risk under Port State Control (PSC) through machine learning techniques, particularly the Random Forest algorithm. The study utilized actual ship inspection data from the Port of Singapore, comprehensively considering various operational and safety indicators of ships, including but not limited to flag state, ship age, past deficiencies, and detention history. By analyzing these factors in depth, this research enhances the efficiency and accuracy of PSC inspections, provides decision support for port authorities, and offers strategic guidance for shipping companies to comply with international safety standards. During the research process, I first conducted detailed data preprocessing, including data cleaning and feature selection, to ensure the effectiveness of model training. Using the Random Forest algorithm, I identified key factors influencing the detention risk of ships and established a risk prediction model accordingly. The model validation results indicated that factors such as ship age, tonnage, company performance, and flag state significantly affect whether a ship exhibits a high deficiency rate. In addition, this study explored the potential and limitations of applying the Random Forest model in predicting high deficiency risk under PSC, and proposed future research directions, including further model optimization and the development of real-time prediction systems. By achieving these goals, I hope to provide valuable experience for other global shipping hubs, promote higher international maritime safety standards, and contribute to the sustainable development of the global shipping industry. This research not only highlights the importance of machine learning in the maritime domain but also demonstrates the potential of data-driven decision-making in improving ship safety management and port inspection efficiency. It is hoped that this study will inspire more maritime practitioners and researchers to explore advanced data analytics techniques to address the increasingly complex challenges of global shipping.

Investment in chemical/oil tankers is crucial for enhancing operational performance and maintaining competitiveness in the global shipping industry. The background of this research is the need to provide solutions to challenges in ship investments that often fail to meet targets, whether in technical performance, compliance with international regulations, or cost efficiency. These conditions affect the competitiveness of companies, as most chemical/oil tanker fleets are over 15 years old, require high maintenance costs, and pose risks of detention by Port State Control (PSC) and rejection by major oil companies. The methodological approach is the integration of Decision-Making Trial and Evaluation Laboratory (DEMATEL) and Analytic Network Process (ANP) to analyze the selection of chemical/oil tanker ship investments. DEMATEL is used to identify cause-effect relationships so that dominant factors can be prioritized. Once the dominant factors are obtained, ANP processes the relationships and dependencies among criteria in the network model and determines more precise weighting. Subsequently, priority calculations are carried out by constructing a supermatrix that encapsulates the relationships among elements. This supermatrix is analyzed to produce final priorities for determining the best alternative. The research data were collected through questionnaires and interviews with stakeholders, including top management and experts. DEMATEL revealed key influencing factors such as Initial Investment, Operating Costs, Regulatory Compliance, Market and Geopolitical Risks, and Technological Risks. These factors are analyzed in the ANP method to obtain a model, network, and pairwise comparisons.

Maritime transport remains a fundamental pillar of international trade, and ship inspections are essential to ensuring navigational safety and environmental protection. Port State Control (PSC) is a regulatory mechanism used to examine foreign-flagged vessels to verify their compliance with international maritime conventions. Among the various elements assessed during PSC inspections, a ship’s type and age significantly influence the likelihood of identifying deficiencies. This study focuses on the PSC inspection data collected from the ports of Kocaeli, a major maritime hub in Turkey. The objective is to analyze how vessel age and type correlate with the frequency and severity of recorded deficiencies. Using the Analysis of Variance (ANOVA) statistical method, the research compares deficiency rates across various ship categories and age brackets. Additionally, the study examines inspection frequency regarding the risk profiles of different vessels. Findings indicate that ships aged 12 years or older exhibit a higher number of deficiencies, with general cargo vessels being particularly prone to non-compliance. While the overall effectiveness of PSC inspections is evident, the study highlights the need for improved efficiency in inspection protocols. It is suggested that risk assessment models be refined to include more detailed criteria and that inspection strategies be adapted based on vessel characteristics. Furthermore, enhancing pre-inspection preparedness by ship operators may contribute to better compliance outcomes. The study aims to support safer maritime operations by offering targeted recommendations for optimizing PSC inspections at Kocaeli Port.

Flag State Control (FSC) plays a critical role in ensuring maritime safety and preventing environmental pollution, serving as the first line of defense against substandard ships, while Port State Control (PSC) acts as a secondary safeguard. Therefore, effective FSC implementation is essential for ship inspections. This study investigates the impact of two key factors - inspection frequency and the number of inspectors - on FSC effectiveness. Using a factorial ANOVA, the analysis is based on data from 174 Turkish-flagged vessels inspected under the Paris Momerandum of Understanding (MoU) framework between 2021 and 2024. The findings indicate that both factors, as well as their interaction, significantly affect FSC effectiveness. These results emphasize the need for optimizing inspection schedules and ensuring sufficient inspector allocation to enhance flag state performance. The study provides valuable insights for maritime stakeholders in improving FSC practices to strengthen regulatory enforcement and maritime safety.

ABSTRACT Limited port state control (PSC) inspection resources pose an urgent need to enhance PSC inspection efficiency. While existing PSC officers (PSCOs) assignment randomly assign ships with PSCOs, this study aims to predict ship deficiency numbers under various deficiency categories (types of non-compliance) using machine learning (ML) models. Moreover, not all foreign visiting ships to a port are inspected by PSC, which leads to a large amount of unlabeled data remaining unexplored. Using the port of Singapore as a case study, this paper utilizes both labeled and unlabeled data to predict ship deficiency numbers under the six deficiency categories of individual ships. A semi-supervised multi-target regression (SSMTR) framework is developed, which innovates in using prediction performance on the validation dataset to judge the reliability of unlabeled data. The SSMTR framework is extended to various ML regression methods, such as decision tree (DT), support vector regression (SVR), extreme gradient boosting (XGBoost), and multilayer perceptron (MLP), resulting in DT-SSMTR, SVR-SSMTR, XGBoost-SSMTR, and MLP-SSMTR. Across four experiment groups with different numbers of labeled data samples, the mean squared error improves on average by 13.65% for DT-SSMTR, 1.62% for SVR-SSMTR, 4.39% for XGBoost-SSMTR, and 2.65% for MLP-SSMTR compared to models that only use labeled data.

Background: Contemporary maritime management requires integration of SOLAS, STCW, MARPOL, and Port State Control regulations with operational decisions. Educational effectiveness in developing maritime law management competencies remains under-examined. Objectives: Investigated how effectively IMO-based maritime legal education develops management competencies for coordinating SOLAS compliance, STCW leadership, MARPOL stewardship, and PSC readiness. Methodology: Qualitative study with ten maritime professionals examining maritime law management effectiveness across regulatory domains. Results: Strong theoretical foundation (7.6/10) but significant management application gaps in SOLAS decision-making (1.6-point expert-graduate gap), STCW team management (1.4-point gap), and PSC preparedness (1.5-point gap). Conclusions: Enhanced maritime law management integration training could significantly improve regulatory management competency development.

This literature review provides a structured quantitative analysis of existing research on the application of machine learning models (MLMs) and multi-criteria decision-making methods (MCDM) in the context of port state control (PSC). The aim of the study is to capture current research trends, identify thematic priorities, and demonstrate how these analytical tools have been used to support decision-making and risk assessment in the maritime domain. Rather than evaluating the effectiveness of individual models, the study focuses on the distribution and frequency of their use and provides insights into the development of methodological approaches in this area. Although several studies suggest that the integration of MLMs and MCDM techniques can improve the objectivity and efficiency of PSC inspections, this report does not provide a comparative assessment of their performance. Instead, it lays the groundwork for future qualitative studies that will assess the practical benefits and challenges of such integration. The findings suggest a fragmented but growing research interest in data-driven approaches to PSC and highlight the potential of advanced analytics to support maritime safety and regulatory compliance.

Port State Control (PSC) inspections play a crucial yet challenging role in detecting substandard ships. However, the process becomes more complicated when several states in large geographical regions agree to collaborate with the same rules. This study addresses this challenge by proposing an innovative hybrid methodology that combines content analysis of PSC appeal cases with the Fuzzy Analytical Hierarchy Process (F-AHP) to assess regulatory inconsistencies within the Asia–Pacific region. A total of 43 PSC appeal cases from the Tokyo MoU were analysed to identify key areas of regulatory disputes. The findings indicate that SOLAS (53%) and MARPOL (26%) regulations are the most frequently contested, followed by document validity and equipment maintenance issues. Notably, in 84% of successful appeals, PSC officers were found to have applied overly strict interpretations or detained ships without conducting sufficient additional tests. Post-2015, successful appeals favouring shipowners increased to 68%, primarily due to deficiencies related to the International Safety Management (ISM) Code. By applying F-AHP and expert reviews, the study prioritised the most problematic areas of disputes, assigning a combined weight of 0.728 to procedural non-compliance and PSC officers' omissions. Key examples include expired ship equipment certificates (0.159), disagreements on regulatory interpretation and allegations of hidden defects by the crew (0.145), and failure to perform detailed examinations or additional tests (0.131). To address these challenges, the paper recommends adopting digital tools for recording inspections and real-time verification of certificates. Furthermore, clear communication of PSC procedures to seafarers may reduce disputes in ship detentions. These findings offer practical insights for policymakers and port authorities to reduce unnecessary delays and improve compliance through inspection consistency.