Ship weather routing optimization has evolved from deterministic great-circle navigation to sophisticated frameworks that account for dynamic environmental conditions and operational constraints. This paper presents a waypoint-sequencing Model Predictive Control (MPC) approach for energy-efficient ship weather routing under forecast uncertainty. The proposed rolling horizon framework integrates neural network-based vessel performance models with ensemble weather forecasts to enable real-time route adaptation while balancing fuel efficiency, navigational safety, and path smoothness objectives. The MPC controller operates with a 6 h control horizon and 24 h prediction horizon, re-optimizing every 6 h using updated meteorological forecasts. A multi-objective cost function prioritizes fuel consumption (60%), safety considerations (30%), and trajectory smoothness (10%), with an exponential discount factor (γ = 0.95) to account for increasing forecast uncertainty. The framework discretises planned routes into waypoints and optimizes heading angles and discrete speed options (12.0, 13.5, and 14.5 knots) at each control step. Validation using 21 transatlantic voyage scenarios with real hindcast weather data demonstrates the method’s capability to propagate uncertainties through ship performance models, yielding probabilistic estimates for attainable speed, fuel consumption, and estimated time of arrival (ETA). The methodology establishes a foundation for more advanced stochastic optimization approaches while offering immediate operational value through its computational tractability and integration with existing ship decision support systems.

This paper presents a data-driven framework for quantifying attainable ship speed uncertainty considering weather forecast uncertainty. The methodology integrates two parallel workflows: weather forecast processing and ship performance simulation. Weather forecast data from NOAA and GFS sources are collected at multiple lead times (0-24h, 24-72h, 72-120h, 120-168h). The data undergo spatial discretisation over a North Atlantic rectangular grid, extracting the main meteorological variables, including significant wave height, peak period, wave direction, wind speed, and wind direction. Ship performance simulations were done using W & auml;rtsil & auml; NaviTrainer NTPRO 5000 and HydroComp NavCad to generate attainable ship speed lookup tables under varying conditions: intended speeds (14.5, 13.5, 12.0 kn), wave heights (0-14 m according to WMO Sea State Codes 0-8), and wave encounter angles (0 degrees-180 degrees). Multiple metrics were used for uncertainty quantification, including RMSE, MAE, Bias, UGR, CRPS, IoA, and FSS for meteorological variables, alongside CMAE for directional parameters. These metrics are subsequently applied to estimated attainable ship speeds, establishing response variable uncertainties. Correlation analysis was conducted between the uncertainty of meteorological variables and the uncertainty in attainable ship speed, providing important insights for estimated time of arrival (ETA) calculations and voyage planning under weather uncertainty.

Accurate prediction of weather-induced ship speed loss requires understanding how meteorological forecast uncertainties propagate through vessel performance models. This study presents a comparative assessment of three computational approaches for attainable speed estimation: the Wärtsilä NTPRO 5000 navigation simulator with JONSWAP and Pierson-Moskowitz spectral implementations, and HydroComp NavCad hydrodynamic software. Over 2,000 simulations were conducted for a 28,050 DWT bulk carrier across varying wave heights (0-12 m), encounter angles (0°-180°), and operational speeds (12.0-14.5 knots). Correlation analysis between meteorological predictor variables and ship speed response uncertainties revealed that significant wave height errors exhibit the strongest coupling with speed prediction errors (r = 0.65-0.97), while encounter angle geometry substantially modulates uncertainty propagation patterns. The Pierson-Moskowitz implementation demonstrated the most balanced error characteristics, whereas JONSWAP produced more polarised correlations at extended forecast horizons. Results indicate that uncertainty quantification approaches must account for both model-specific sensitivities and spatially varying forecast skill degradation.

In this study a variety of machine learning techniques are utilized to develop models for the prediction of the main engine brake power and rate of revolution for bulk carriers. The focus is on reducing noise in input and output data by applying a spline smoothing method. As a result, a data preprocessing workflow incorporating spline smoothing is proposed to improve the generalization ability of the machine learning models. A thorough comparative analysis is performed on different methods, assessing their accuracy and generalization performance. The results, based on the smoothed data, show that the hypertuned Gaussian process regression model achieves the highest accuracy for both the validation and testing data. Additionally, linear regression models with smoothed data provide adequate accuracy for practical applications, leading to the creation of simple predictive formulas for brake power and rate of revolution, suitable for preliminary ship design.

In the preliminary ship design process, key aspects such as machinery and powering must be specified, which involves estimating the brake power and rate of revolution of the main engine. Traditionally, these parameters are derived from existing ship databases; however, conventional estimation methods are often limited by outdated models, inadequate noise handling, and restricted capabilities for capturing nonlinear relationships, leading to reduced accuracy and generalization. This study employs a range of machine learning approaches to develop predictive models for estimating the brake power and rate of revolution of bulk carrier main engines. Special emphasis is placed on mitigating noise in both input and output data through the application of a spline smoothing technique. Accordingly, a data preprocessing workflow is proposed, incorporating spline smoothing to enhance the generalization potential of the machine learning models. A comprehensive comparative analysis is conducted across various methods, including four linear regression models, three regression trees, four Gaussian process regression models, two tree ensemble methods, and five neural network models. The performance of the employed machine learning models, evaluated using both raw and smoothed data, is compared in terms of accuracy and generalization capabilities. Results obtained using the smoothed data indicate that the hypertuned Gaussian process regression model exhibits superior accuracy in both validation and testing phases. Furthermore, linear regression models based on smoothed data demonstrated sufficient accuracy for practical implementation, leading to the development of simple predictive formulae for brake power and rate of revolution that are applicable in early-stage ship design.

Ship weather routing is heavily dependent on weather forecasts. However, the predictive nature of meteorological models introduces an unavoidable level of uncertainty which, if not accounted for, can compromise navigational safety, operational efficiency, and environmental impact. This study examines the temporal degradation of forecast accuracy across certain oceanographic and atmospheric variables, using a six-month dataset for the area of North Atlantic provided by the National Oceanic and Atmospheric Administration (NOAA). The analysis reveals distinct variable-specific uncertainty trends with wind speed forecasts exhibiting significant temporal fluctuation (RMSE increasing from 0.5 to 4.0 m/s), while significant wave height forecasts degrade in a more stable and predictable pattern (from 0.2 to 0.9 m). Confidence intervals also exhibit non-monotonic evolution, narrowing by up to 15% between 96–120-h lead times. To address these dynamics, a Python-based framework combines distribution-based modeling with calibrated confidence intervals to generate uncertainty bounds that evolve with forecast lead time (R2 = 0.87–0.93). This allows uncertainty to be quantified not as a static estimate, but as a function sensitive to both variable type and prediction horizon. When integrated into routing algorithms, such representations allow for route planning strategies that are not only more reflective of real-world meteorological limitations but also more robust to evolving weather conditions, demonstrated by a 3–7% increase in travel time in exchange for improved safety margins across eight test cases.

Decision-making in ship weather routing heavily relies on weather forecasts, but the inherent uncertainties in their predictions still remain a challenge. This study focuses on quantifying the uncertainty of weather forecasts over a considerable period of time for the North Atlantic Ocean area to enable their integration into ship routing systems. A comprehensive analysis of the collected weather data is presented, systematically accounting for the propagating forecast uncertainties. The proposed framework models forecast variability through probabilistic distributions of several relevant weather variables, such as wind speed and wave height, taking into account the degradation of forecast accuracy over time. For each chosen variable, uncertainty bounds and confidence intervals are estimated over different time horizons. These metrics are used as actionable insights that can potentially be integrated into on-board decision support systems. Ship weather routing often involves conflicting objectives, which further highlights the limitations of deterministic decision support systems as well. Adaptive adjustments to route planning must be considered in response to evolving weather conditions along the ship's route. A method for embedding the forecast uncertainty into optimization decision variables, including course and speed changes, to balance operational goals such as safety, efficiency and environmental impact is presented. To support the integration of raw weather forecast data with the operational needs of the vessel, this research provides the basis for better routing decisions. Incorporating weather forecast uncertainties into decision support tools allows them to identify routes that remain stable under realistic conditions.

Abstract Eye-tracking technology has become increasingly popular in studying consumer behavior and decision-making as a part of the marketing research area. The paper highlights the importance of eye tracking in the study of consumer behavior including the use of eye tracking in virtual reality environments, the integration of eye tracking with other physiological measures, and the development of more sophisticated analytical techniques. By observing eye movements and fixations researchers can gain insight into the visual and cognitive processes underlying consumer choices. For this reason, a literature review of relevant studies provides a detailed synthesis of the development of eye-tracking experiments. This paper contributes to the latest findings on consumer behavior in the field of eye-tracking technology.

Optimal ship routing is crucial for enhancing safety, reducing travel time, and minimizing fuel consumption. This paper introduces and examines recent advancements in stochastic optimization techniques, emerging methods and models for weather-aware ship routing. As marine transportation faces increasing challenges due to climate change and extreme weather events, the need for robust and efficient routing strategies has become imperative. A ship route that is subject to uncertainties is considered stochastic. Therefore, a comprehensive overview of emerging stochastic optimization methods that address the inherent uncertainties in weather forecasting and their impact on optimal routing is presented. The paper explores various approaches, including Markov decision processes, stochastic dynamic programming, and scenario-based optimization, highlights their applications in fuel consumption minimization, ensuring safety and improving time reliability. The integration of ensemble weather forecasts and probabilistic models to capture the stochastic nature of oceanic and atmospheric conditions is discussed. Additionally, computational challenges associated with these methods are analyzed along with recent algorithmic improvements that enhance their scalability and real-time applicability. The inclusion of multiple objectives, such as environmental impact and economic factors, within the stochastic framework is also addressed. Finally, a promising research direction is identified and potential synergies with machine learning techniques to further account for an increasingly uncertain marine environment.

The global maritime industry has undergone tremendous change due to a number of circumstances that require more environmentally friendly and effective shipping methods. With an intention of contributing to the broader discussion on sustainable shipping practices, this paper addresses the topics of weather routing and the ongoing attempts to minimize the industry's environmental impact. Weather routing determines the optimum route for a ship, subject to fuel consumption, ship characteristics, behavior and weather forecasts. Significant risks and uncertainties associated with weather routing still must be further considered. Weather forecasts are essential for ship weather routing and therefore need to be as accurate as possible. However, the initial data for weather forecasts calculation is subject to a fair amount of uncertainties. In this paper, two main objectives are discussed, i.e. how to model forecast uncertainties and how to implement that model into an optimal ship routing problem.

Exhaust gas emissions from ships are an aspect of the global maritime industry which has been given great importance in recent years. Increasing the efficiency of maritime transport regarding fuel consumption and exhaust gas emissions is an ongoing effort which requires a detailed analysis of all ship systems that have an effect on the aforementioned issue. One aspect that can be analyzed in this regard are the various machinery faults which influence the ships exploitation efficiency. This paper will focus on the analysis of the two stroke slow speed diesel main engine with early and late fuel injection faults. This analysis is based on a set of data acquired from a simulation model of a LCC tanker vessel including fuel consumption and emission pollutants such as carbon monoxide (CO), sulphur oxides (SOX) and carbon dioxide (CO2) as a greenhouse gas with early and late fuel injection fault introduced to different number of main engine cylinders. This methodology of research has the advantage of analyzing various scenarios which are not as easily reproduced on actual vessels.

Increasingly stringent environmental requirements for marine engines imposed by the International Maritime Organisation and the European Union require that marine engines have the lowest possible emissions of greenhouse and harmful exhaust gases into the atmosphere. In this research, exhaust gas emissions were measured on three Ro-Pax vessels sailing in the Adriatic Sea. Testo 350 Maritime exhaust gas analyser was used for monitoring the dry exhaust gas concentrations of CO2 and O2 in percentage, concentrations of CO and NOx in ppm and exhaust gas temperature in °C after the turbocharger at different engine loads. In order to compare and validate measured values, exhaust gas measurement data were also obtained from a Wartsila-Transas simulator model of a similar Ro-Pax vessel during the joint operation of the engine room and navigational simulators. All analysed main engines on three vessels had complete combustion processes in the cylinders with small differences which should be further investigated. Comparison of on board measured parameters with simulated parameters showed that significant fuel oil reduction per voyage could be accomplished by voyage and/or engine operation optimization procedures. Results of this analysis could be used for creating additional emission database and data-driven models for further analysis and improved estimation of exhaust gasses under various marine engine conditions. Additionally, the results could be useful to all interested parties in reducing the fuel oil consumption and emissions of greenhouse and harmful exhaust gases from vessels into the atmosphere.

Purpose: The modern concepts of contemplating joint dynamics of monetary policy effects on economic growth and its indicators require an indirect approach based on empirical research of mainly financial infrastructure, competitiveness of the financial markets and current economic conditions. Meanwhile, the problems of unemployment and the structure of employment within these concepts are most frequently linked with the polarization of the labor market and two important factors, that is, the effects of growth on unemployment and the fact that technological changes affect the changes in salary ranges. Methodology: By using the Adaptive Neuro-Fuzzy Inference System (ANFIS) and the set of data from 1995 to 2016, this paper analyzes these issues through a prism of established balances between the labor and financial markets, i.e., the monetization of economy (M1/GDP), financial development (Loans/GDP) and the share of gross government debt in GDP (government gross debt/GDP). Results: The proposed model suggests that the rate of unemployment is conditioned by the financial cycle and monetary policy (M1/GDP, Loans/GDP), as well as the business cycle and fiscal policy (gross d/BDP) and that a controlled and properly directed level of monetization of the economy (M1/BDP) and financial development measured as Loans/GDP can be “sufficient” for economic growth. Conclusion: Waiting in the “monetary union lobby”, i.e., waiting for the ERM II exchange mechanism can last longer than the set deadlines, leading to the need for Croatian economic policy to optimize monetary and fiscal policy measures in order to increase economic growth and reduce unemployment.

Recently, the application of machine learning has been explored to assess the main damage consequences without employing flooding sensors. This method can be the base of a new generation of onboard decision support systems to help the master during the progressive flooding of the ship. In particular, the application of random forests has been found suitable to assess the final fate of the ship and the damaged compartments’ set and estimate the time-to-flood. Random forests have to be trained using a database of precalculated progressive flooding simulations. In the present work, multiple options for database generation were tested and compared: three based on Monte Carlo (MC) sampling based on different probability distributions of the damage parameters and a parametric one. The methods were tested on a barge geometry to highlight the main effects on the damage consequences’ assessment in order to ease the further development of flooding-sensor-agnostic decision support systems for flooding emergencies.

Recently, progressive flooding simulations have been applied onboard to support decisions during emergencies based on the outcomes of flooding sensors. However, only a small part of the existing fleet of passenger ships is equipped with flooding sensors. In order to ease the installation of emergency decision support systems on older vessels, a flooding-sensor-agnostic solution is advisable to reduce retrofit cost. In this work, the machine learning algorithms trained with databases of progressive flooding simulations are employed to assess the main consequences of a damage scenario (final fate, flooded compartments, time-to-flood). Among the others, several classification techniques are here tested using as predictors only the time evolution of the ship floating position (heel, trim and sinkage). The proposed method has been applied to a box-shaped barge showing promising results. The promising results obtained applying the bagged decision trees and weighted k-nearest neighbours suggests that this new approach can be the base for a new generation of onboard decision support systems.