Search Results (38)

The growth and sustainability of today’s global economy heavily relies on smooth maritime operations. The increasing security concerns to marine environments pose complex security challenges, such as smuggling, illegal fishing, human trafficking, and environmental threats, for traditional surveillance methods due to their limitations. Artificial intelligence (AI), particularly deep learning, has offered strong capabilities for automating object detection, anomaly identification, and situational awareness in maritime environments. In this paper, we have reviewed the state-of-the-art deep learning models mainly proposed in recent literature (2020–2025), including convolutional neural networks, recurrent neural networks, Transformers, and multimodal fusion architectures. We have highlighted their success in processing diverse data sources such as satellite imagery, AIS, SAR, radar, and sensor inputs from UxVs. Additionally, multimodal data fusion techniques enhance robustness by integrating complementary data, yielding more detection accuracy. There still exist challenges in detecting small or occluded objects, handling cluttered scenes, and interpreting unusual vessel behaviours, especially under adverse sea conditions. Additionally, explainability and real-time deployment of AI models in operational settings are open research areas. Overall, the review of existing maritime literature suggests that deep learning is rapidly transforming maritime domain awareness and response, with significant potential to improve global maritime security and operational efficiency. We have also provided key datasets for deep learning models in the maritime security domain. Full article

The South Caspian Basin of Iran (SCBI), a vital ecosystem for unique and valuable fish species, is under severe threats due to anthropogenic activities that are rapidly deteriorating its fish biodiversity. The initial step to effectively combat or mitigate threats to biodiversity is to precisely identify these threats. While such threats are often categorized qualitatively, there is a lack of a comparative quantitative assessment of their severity. This means that although we may have a general understanding of the threats, we do not have a clear picture of how serious they are relative to one another. This study aimed to quantify and prioritize these threats using a modified quantitative “SWOT” (Strengths, Weaknesses, Opportunities, Threats) analysis. Twenty multidisciplinary experts identified and evaluated 26 threats, and we used multivariate cluster analysis to categorize them as “High”, “Medium”, and “Low” based on their quantitative contributions to overall threat. Invasive non-native species and global warming emerged as the most significant threats, followed by resource exploitation, habitat destruction, and pollution. We then used this information to develop a “Situation Model” and “Results Chains” to guide responses to the threats. According to the Situation Model, these threats are interconnected, driven by factors such as population growth, unsustainable resource use, and climate change. To address these challenges, we propose the Results Chains, including two strategies focused on scientific research, land-use planning, public awareness, and community engagement. Prioritizing these actions is crucial for conserving the Caspian Sea’s unique fish fauna and ensuring the region’s ecological and economic sustainability. Full article

This study presents a data-driven analysis of navigator stress and workload levels in simulated ship encounters within restricted waters, leveraging real-world automatic identification system (AIS) data from Makassar Port, Indonesia. Six close-quarter scenarios were recreated to reflect critical encounter geometries, and 24 Indonesian seafarers were evaluated using heart rate variability (HRV), perceived stress scale (PSS), and task load index (NASA-TLX) workload assessments. The results indicate that crossing angles, particularly 135° port and starboard encounters, significantly influence physiological stress levels, with age being a moderating factor. Although no consistent relationship was found between workload and HRV metrics, the findings underscore key human factors that may impair navigational performance under cognitively demanding conditions. By integrating AIS-derived traffic data with simulation-based human performance monitoring, this study supports the development of intelligent maritime training frameworks and adaptive decision support systems. The research contributes to broader efforts toward enhancing navigational safety and situational awareness amid increasing automation and traffic densities at sea. Full article

Despite the existence of standardized collision regulations such as the International Regulations for Preventing Collisions at Sea (COLREGs), ship collisions continue to occur, indicating persistent gaps in how navigators interpret and apply these rules. The COLREGs are globally adopted rules that govern vessel conduct to avoid collisions. Borderline encounter situations—such as those between head-on and crossing, or overtaking and crossing—pose particular challenges, often resulting in inconsistent or ambiguous interpretations. This study models navigator awareness as a probabilistic function of encounter angle, aiming to identify interpretive transition zones and cognitive uncertainty in rule application. A structured survey was conducted with 101 licensed navigators, each evaluating simulated ship encounter scenarios with varying relative bearings. Responses were collected using a Likert scale and analyzed in angular sectors known for interpretational ambiguity: 006–012° for head on to crossing (HC) and 100–160° for overtaking to crossing (OC). Gaussian curve fitting was applied to the response distributions, with the awareness center (μ) and standard deviation (σ) serving as indicators of consensus and ambiguity. The results reveal sharp shifts in awareness near 008° and 160°, suggesting cognitively unstable zones. Risk-averse interpretation patterns were also observed, where navigators tended to classify borderline situations more conservatively under uncertainty. These findings suggest that navigator awareness is not deterministic but probabilistically structured and context sensitive. The proposed awareness modeling framework helps bridge the gap between regulatory prescriptions and real world navigator behavior, offering practical implications for MASS algorithm design and COLREGs refinement. Full article

This paper presents an artificial intelligence-based model for the classification of maritime vessel images obtained by cameras operating in the visible part of the electromagnetic spectrum. It incorporates both the deep learning techniques for initial image representation and traditional image processing and machine learning methods for subsequent image classification. The presented model is therefore a hybrid approach that uses the Inception v3 deep learning model for the purpose of image vectorization and a combination of SVM, kNN, logistic regression, Naïve Bayes, neural network, and decision tree algorithms for final image classification. The model is trained and tested on a custom dataset consisting of a total of 2915 images of maritime vessels. These images were split into three subsections: training (2444 images), validation (271 images), and testing (200 images). The images themselves encompassed 11 distinctive classes: cargo, container, cruise, fishing, military, passenger, pleasure, sailing, special, tanker, and non-class (objects that can be encountered at sea but do not represent maritime vessels). The presented model accurately classified 86.5% of the images used for training purposes and therefore demonstrated how a relatively straightforward model can still achieve high accuracy and potentially be useful in real-world operational environments aimed at sea surveillance and automatic situational awareness at sea. Full article

Digitalization has revolutionized the maritime industry, particularly in navigation systems. The use of advanced tools such as the Electronic Chart Display and Information System (ECDIS) has increased the need for information processing. However, the complexity of these systems can be overwhelming for navigators. To address the concern of usability of these complex navigation systems, training with simulator data allows the crew to familiarize themselves with these systems, handle complex navigation scenarios effectively, support the transition from paper-based systems to digital systems, and help in improving their situational awareness (SA) at sea. We propose a tool that provides optimal conditions for assessing situational awareness and informing the development of intuitive systems and user interfaces. In the maritime safety domain, there is an inverse correlation between situational awareness and scenario/system complexity, highlighting the importance of effective training and assessments to improve SA. The proposed tool utilizes the Situational Awareness Global Assessment Technique (SAGAT) method, widely used in other domains, to calculate an individual’s SA score. It evaluates participants’ situational awareness in different navigational scenarios on Ship Handling Simulators, using dynamic questionnaires and contextual maps. Additionally, it integrates a rule-based system to assess participants’ performance and calculate a situational awareness score in real time, offering possibilities for assessing the SA of navigators. Full article

The Maldives is one of the few atoll countries in the world, with an average elevation of just 1.5 m above sea level. The country faces the possibility of submersion, without adequate adaptation measures, if the current trends persist. The present study aimed to examine the societal context of observed differences in perceptions regarding climate change impacts in the two locations in atoll islands of the Maldives: Hithadhoo and Kulhudhuffushi, situated in the southernmost and northernmost islands within the country, respectively. A questionnaire survey was conducted at both locations, with follow-up semi-structured interviews. With regard to Hithadhoo, a higher percentage of residents recognize the impacts of climate change and sea level rise (SLR) and are more likely to take individual actions and encourage government action. Residents of Kulhudhuffushi reported fewer observed impacts of climate change and SLR, with a significant majority not taking specific actions or relying more on broader measures. These findings highlight the differences in perceptions regarding and responses to climate change impacts between the two areas, which can be attributed to different environmental conditions, awareness levels, and socioeconomic factors, including culture and values. This also indicates the need for tailor-made strategies and policies for climate change adaptation in different regions of a single nation. Full article

The Arctic Seas are attractive for shipping, fisheries, and other marine activities due to the abundant resources of the Arctic. The shrinking ice cover allows for the opening of activities in increasingly larger areas of the Arctic. This paper evaluates the possibility of executing all-year complex marine activities, here termed “marine operations”, in the Norwegian Sea and the ice-free part of the Barents Sea. The approach used during the preparation of this review paper is to identify constraints to marine operations so users can be aware of the limitations of performing such operations. The weather conditions in the Norwegian Sea and the Barents Sea are well known, and these seas are considered representative of ice-free or partly ice-free Arctic Seas with considerable marine activities. Similar conditions could be expected for other Arctic Seas during periods without ice cover. Marine operations require safe and stable working conditions for several days. The characteristics of marine operations are discussed, and the particulars of the Norwegian Sea and the Barents Sea physical environments are highlighted. Emphasis is on the wind and wave conditions in unpredictable polar low-pressure situations. Furthermore, situations with fog are discussed. The large uncertainties in forecasting the initiation and the tracks of polar lows represent the main concern for executing marine operations all year. Improvements in forecasting the occurrence and the path of polar lows would extend the weather window when marine operations could be carried out. Discussions of the potential for similar conditions in the wider Arctic Seas during ice-free periods are presented. Full article

Vessel organizations are exposed to the risk of accidents due to the limited experience and intuition of the top decision makers in the organization in the special environment of the sea. This study aims to provide a direction for sustainable and rational decision-making in vessel organization through decision making process theory and case studies of actual vessel accidents. The results obtained from the actual case studies show that all three vessel accidents were caused by the arbitrary decision of the decision maker based on the Garbage Can model. This can be attributed to the closed nature of the vessel’s organization, which requires a decision-making process that is a hybrid of the Carnegie Decision model and Management Science model. Implications include the introduction of a ‘My Ship’ system, the de-subjectivization of top decision makers, situational awareness, and the need to provide top decision makers with the context and information relevant to their decisions. Limitations of this study include the fact that the case study was conducted only on Korean-flagged vessels and the study was limited to vessel accidents that occurred in the waters off Korea, China, and Japan, which limits the generalizability of the findings. In order to overcome these limitations, it would be interesting to conduct a follow-up study to include vessel accidents of different nationalities or to further investigate the characteristics of the decision-making process in vessel accidents by country. Full article

Vietnam is a country highly vulnerable to climate change. Specifically, climate change has seriously impacted all aspects of Vietnam’s economic and social life, especially agricultural production. In this article, we focus on analyzing the current situation and the impacts of climate change on agricultural production and food security in Vietnam, especially in the Mekong River Delta (MRD) region. Vietnam’s climate change scenarios (RCP4.5 and RCP 8.5) have warned of serious increases in temperature, rainfall, and sea level rises for the MRD in coming times. This will lead to a risk of flooding in nearly 50% of the region’s area and will seriously affect agricultural production in many aspects such as soil quality degradation, scarcity of water resources, increased droughts and floods, reduced crop productivity, and so on. These impacts will reduce Vietnam’s food supply capacity, but do not compromise national food security from a short-term perspective. Faced with this situation, the Government of Vietnam has implemented many comprehensive measures to transform agriculture towards ecology, sustainability, and low carbon emissions, with the goal of green growth and neutral carbon emissions by 2050. In particular, the focus is on combining nature-based solutions with the application of modern science and technology in agricultural production, raising awareness and the response capacity of domestic people, with international cooperation in addressing climate change issues. Full article

The Polar Operational Limit Assessment Risk Indexing System (POLARIS) has been established as a viable framework for assessing operational capabilities and associated risks in polar waters. Despite its inherent suitability for high-latitude territories, ships navigating through seasonal ice-infested waters at lower latitudes also encounter critical safety, environmental, and economic issues exacerbated by the presence of ice. This necessitates a reliable and adaptable methodology that can serve as a reference for devising effective countermeasures. This study evaluated the use of POLARIS in the intricate ice conditions prevalent in the northern navigable waters (channels and anchorages) within Liaodong Bay of the Bohai Sea, located at relatively low latitudes. Using GF-4 satellite imagery, ice conditions were collected, and the POLARIS methodology was employed to calculate Risk Index Outcome (RIO) values for non-ice-strengthened vessels during the winter season of 2021–2022. The results showed that sectors 3, 4, 5, 7, 9, 10, and 11 within the northern part of Liaodong Bay exhibited a higher risk, with sectors 5 and 10 exhibiting the most significant risk, while sectors 1 and 2 demonstrated relatively lower risk levels. The concurrence of these findings with acknowledged ice patterns and local maritime practices confirms the applicability of the POLARIS methodology in saline, seasonally ice-covered seas. Notably, the combination of POLARIS with high-resolution satellite imagery facilitated a more precise and rapid assessment of ice risk, thereby enhancing situational awareness and informing decision-making processes in maritime operations under icy conditions. In addition, this study provides preliminary evidence that POLARIS is suitable for fine-scale scenarios, in addition to being applicable to sparse-scale scenarios, such as polar waters, especially with high-resolution ice data. At the same time, this study highlights the potential of POLARIS as a disaster prevention strategy and a tool for the maritime industry to address ice challenges. Full article

Robot-Assisted Minimally Invasive Surgery (RAMIS) marks a paradigm shift in surgical procedures, enhancing precision and ergonomics. Concurrently it introduces complex stress dynamics and ergonomic challenges regarding the human–robot interface and interaction. This study explores the stress-related aspects of RAMIS, using the da Vinci XI Surgical System and the Sea Spikes model as a standard skill training phantom to establish a link between technological advancement and human factors in RAMIS environments. By employing different physiological and kinematic sensors for heart rate variability, hand movement tracking, and posture analysis, this research aims to develop a framework for quantifying the stress and ergonomic loads applied to surgeons. Preliminary findings reveal significant correlations between stress levels and several of the skill-related metrics measured by external sensors or the SURG-TLX questionnaire. Furthermore, early analysis of this preliminary dataset suggests the potential benefits of applying machine learning for surgeon skill classification and stress analysis. This paper presents the initial findings, identified correlations, and the lessons learned from the clinical setup, aiming to lay down the cornerstones for wider studies in the fields of clinical situation awareness and attention computing. Full article

Coastal zones, despite their contribution to global economies, continue to suffer the negative impacts of climate variability, which limit the livelihoods of people, particularly small-scale fishermen. This study examined climate variability, coastal livelihoods, and the influence of ocean change on the total annual fish catch in Ghana’s Coastal Savannah zone. The mixed-methods approach was used to analyze primary data (semi-structured questionnaires and interviews), secondary data (sea surface temperature (SST) and salinity (SSS), and fish catch), and statistical tests (chi-square, binary logistic regression, and multiple regression). Findings revealed a significant increase in climate variability awareness among fishermen, attributed to the influence of broadcast media. However, they lack sufficient information regarding the transformation of cities, the urbanization process, and its impact on the global climate. Increasing temperatures and sea level rise emerged as the most prevalent impacts of climate variability over the past two decades in the zone. Although the fishermen lack awareness regarding the changes in SSS and their effects on fish, the findings of the multiple regression analysis established that changes in SSS exert a more pronounced effect on the decreasing fishing catch in the zone compared to those in SST. Empirical fish catch records supported the fishermen’s claim of a substantial decrease in total fish catch in the zone over the past 20 years. Aside from climate variability impacts, the involvement of many people and light fishing emerged as additional factors contributing to the decreasing fish catch in the zone. High premix fuel prices or shortages and “saiko” activities were the main obstacles that hindered the fishermen’s activities. “Saiko” is an unlawful activity in which foreign industrial trawlers sell fish directly to Ghanaian canoes or small-scale fishermen at sea. The fishermen lack sufficient means of supporting their livelihoods, as there is a lack of viable alternative livelihood options. Additionally, the majority of the fishermen experience symptoms of fever and headaches. The binary logistic regression analysis showed that the fishermen’s income insufficiency could be substantially reduced if they were to have their own houses, canoes, or fish all year. This situation highlights the need for heightened support from policymakers for improved sustainable livelihood prospects as well as health and well-being. Full article

In an effort to improve short-sea shipping in Europe, we present a 3D world interpreter (3DWI) system as part of a robotic container-handling system. The 3DWI is an advanced sensor suite combined with AI-based software and the communication infrastructure to connect to both the crane control and the shore control center. On input of LiDAR data and stereo captures, the 3DWI builds a world model of the operating environment and detects containers. The 3DWI and crane control are the core of an autonomously operating crane that monitors the environment and may trigger an emergency stop while alerting the remote operator of the danger. During container handling, the 3DWI scans for human activity and continuously updates a 3D-Twin model for the operator, enabling situational awareness. The presented methodology includes the sensor suite design, creation of the world model and the 3D-Twin, innovations in AI-detection software, and interaction with the crane and operator. Supporting experiments quantify the performance of the 3DWI, its AI detectors, and safety measures; the detectors reach the top of VisDrone’s leaderboard and the pilot tests show the safe autonomous operation of the crane. Full article

Climate change and rising sea levels present significant challenges for geotourism destinations and activities. Accelerated changes in geomorphological processes threaten or diminish both the physical existence and aesthetic qualities of geoheritage assets, and hence the visitor experience, as well as presenting increased or new risks from natural hazards. This is particularly a concern in mountain and coastal areas, and also where greater extremes of temperature and precipitation affect visitor comfort. A literature review was conducted to assess the extent to which the consequences of climate change have been recognised in geotourism research. With the exception of glacier-based geotourism, few studies have considered the impacts of climate change and reported the planning or development of adaptation measures. However, the didactic potential of geotourism in raising awareness of climate change has been commonly recognised. A review of the wider tourism literature identified additional destination-supply and visitor-demand issues that will affect the sustainability of geotourism in the face of climate change. These include changes in visitor motivations, travel behaviour, perceptions of destination image, and reactions to local, national, and international mitigation and adaptation responses, as well as geoethical considerations around carbon footprints and sustainable modes of travel. Situating geotourism within a broader body of multidisciplinary tourism research should help inform adaptation strategies in conjunction with measures to adapt to the physical impacts of climate change on geotourism sites. Full article