Sv
S.E. van der Werff
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
6 records found
1
As the frequency and intensity of natural disasters increase, there is growing recognition of the need to address climate change and limit the increase in global average temperature. The shipping industry, which contributes 2.9% to global anthropogenic greenhouse gas emissions, plays a significant role by releasing substantial amounts of CO2, other harmful gases, and fine particles, negatively impacting climate change and the health of those near ports or waterways. As part of a wider initiative to reduce those effects, the International Maritime Organization has set the goal for the shipping industry to achieve net zero emissions by 2050. In order to accomplish this, accurate and comprehensive information on emissions is crucial.
Various methods have been developed to estimate emissions in the shipping industry. Top-down methods are applied using large-scale data to estimate emissions over a wide area. This approach provides a comprehensive overview but lacks the specific details required for local interventions. In contrast, bottom-up methods are applied and start with detailed data at the source and aggregate information to estimate the total emissions. Bottom-up methods offer more precise insights, however, more extensive data and complex modeling is required. To obtain more precise understandings, the modern bottom-up models use Automatic Identification System as input, a globally used system for tracking vessels. AIS data consists, among others, of time-dependent variables such as speed, location, and ship identification number. The data is used to assign an operational mode to the ship (sailing, maneuvering, anchoring, berthing). Based on this mode, it is determined if the main engines of the ship are on. If they are, the engine power is calculated from the resistance force acting on the moving ship. It is possible to convert engine power to fuel consumption and later to emissions with Specific Fuel Oil Consumption and emission factors.
Currently used emission models calculate engine power with the use of empirical formulas. So far, these models have mostly been validated by comparing them either to a noon report, or to another model. As a result, it gives no insight into the capability of a model to predict with a high spatial resolution, which is important in port areas and inland waterways.
There is little room for improvement in current semi-empirical bottom-up methods. However, in recent years, machine learning has shown the capability of replacing and often outperforming empirical models in other fields of research. This is due to the ability to model nonlinear behavior, find relations that humans can not, and work in higher dimensions. As a ship's engine power is reliant on a multitude of factors, machine learning might be the solution towards more accurate predictions.
This research aims to assess the capability of machine learning models to predict a ship's engine power with a high spatial resolution, with a focus on LSTM models. To do so, onboard sensor data from two ships was used; one sea-going container vessel and one inland tanker. The measured data was used to validate the semi-empirical method. Afterwards, the machine learning model was trained against the same sensor data. The predictions of the semi-empirical and machine learning models were then compared to one another.
Comparisons showed that the error for total energy used for the container vessel went from +62.87% to -0.82% when using a Bi-LSTM model with speed, acceleration, draught and depth as input. For the assessment of the spatiotemporal predictions, the MAE and RMSE were used. Based on these performance indicators, a normal LSTM network with speed, acceleration, draught and depth as input performed best. The MAE compared to the reference went down from 9542 to 2863, or about 7% of the maximum engine power.
The second case study highlighted the challenges that come with engine power prediction in inland waterways. Firstly, the fact that the speed over ground is used has a bigger influence in this case, as the ship will always sail with or against the current. Secondly, the influence of the blockage factor can
not be ignored without having higher losses. In addition to these two shortcomings, the model was trained on a diesel-electric ship. This ship has a much more constant power profile than ships with a more classical propulsion run on fossil fuels. This likely made the model more robust to changes. The combination of these three aspects caused less accurate predictions. Although there was more data available, errors were higher than for the case study. The best performing models showed a +3.41% error on total energy use and an MAE of 205.65, or about 12.8% of the maximum engine power.
This research has contributed new insights to the field of maritime emission modeling. The potential of machine learning models has been shown in comparison to an existing semi-empirical model. In addition, this model has now been validated using measurement data for a seagoing container vessel. Finally, shortcomings of the method using machine learning were exposed and a solution is proposed for a more complete, generalizable model. ...
Various methods have been developed to estimate emissions in the shipping industry. Top-down methods are applied using large-scale data to estimate emissions over a wide area. This approach provides a comprehensive overview but lacks the specific details required for local interventions. In contrast, bottom-up methods are applied and start with detailed data at the source and aggregate information to estimate the total emissions. Bottom-up methods offer more precise insights, however, more extensive data and complex modeling is required. To obtain more precise understandings, the modern bottom-up models use Automatic Identification System as input, a globally used system for tracking vessels. AIS data consists, among others, of time-dependent variables such as speed, location, and ship identification number. The data is used to assign an operational mode to the ship (sailing, maneuvering, anchoring, berthing). Based on this mode, it is determined if the main engines of the ship are on. If they are, the engine power is calculated from the resistance force acting on the moving ship. It is possible to convert engine power to fuel consumption and later to emissions with Specific Fuel Oil Consumption and emission factors.
Currently used emission models calculate engine power with the use of empirical formulas. So far, these models have mostly been validated by comparing them either to a noon report, or to another model. As a result, it gives no insight into the capability of a model to predict with a high spatial resolution, which is important in port areas and inland waterways.
There is little room for improvement in current semi-empirical bottom-up methods. However, in recent years, machine learning has shown the capability of replacing and often outperforming empirical models in other fields of research. This is due to the ability to model nonlinear behavior, find relations that humans can not, and work in higher dimensions. As a ship's engine power is reliant on a multitude of factors, machine learning might be the solution towards more accurate predictions.
This research aims to assess the capability of machine learning models to predict a ship's engine power with a high spatial resolution, with a focus on LSTM models. To do so, onboard sensor data from two ships was used; one sea-going container vessel and one inland tanker. The measured data was used to validate the semi-empirical method. Afterwards, the machine learning model was trained against the same sensor data. The predictions of the semi-empirical and machine learning models were then compared to one another.
Comparisons showed that the error for total energy used for the container vessel went from +62.87% to -0.82% when using a Bi-LSTM model with speed, acceleration, draught and depth as input. For the assessment of the spatiotemporal predictions, the MAE and RMSE were used. Based on these performance indicators, a normal LSTM network with speed, acceleration, draught and depth as input performed best. The MAE compared to the reference went down from 9542 to 2863, or about 7% of the maximum engine power.
The second case study highlighted the challenges that come with engine power prediction in inland waterways. Firstly, the fact that the speed over ground is used has a bigger influence in this case, as the ship will always sail with or against the current. Secondly, the influence of the blockage factor can
not be ignored without having higher losses. In addition to these two shortcomings, the model was trained on a diesel-electric ship. This ship has a much more constant power profile than ships with a more classical propulsion run on fossil fuels. This likely made the model more robust to changes. The combination of these three aspects caused less accurate predictions. Although there was more data available, errors were higher than for the case study. The best performing models showed a +3.41% error on total energy use and an MAE of 205.65, or about 12.8% of the maximum engine power.
This research has contributed new insights to the field of maritime emission modeling. The potential of machine learning models has been shown in comparison to an existing semi-empirical model. In addition, this model has now been validated using measurement data for a seagoing container vessel. Finally, shortcomings of the method using machine learning were exposed and a solution is proposed for a more complete, generalizable model. ...
As the frequency and intensity of natural disasters increase, there is growing recognition of the need to address climate change and limit the increase in global average temperature. The shipping industry, which contributes 2.9% to global anthropogenic greenhouse gas emissions, plays a significant role by releasing substantial amounts of CO2, other harmful gases, and fine particles, negatively impacting climate change and the health of those near ports or waterways. As part of a wider initiative to reduce those effects, the International Maritime Organization has set the goal for the shipping industry to achieve net zero emissions by 2050. In order to accomplish this, accurate and comprehensive information on emissions is crucial.
Various methods have been developed to estimate emissions in the shipping industry. Top-down methods are applied using large-scale data to estimate emissions over a wide area. This approach provides a comprehensive overview but lacks the specific details required for local interventions. In contrast, bottom-up methods are applied and start with detailed data at the source and aggregate information to estimate the total emissions. Bottom-up methods offer more precise insights, however, more extensive data and complex modeling is required. To obtain more precise understandings, the modern bottom-up models use Automatic Identification System as input, a globally used system for tracking vessels. AIS data consists, among others, of time-dependent variables such as speed, location, and ship identification number. The data is used to assign an operational mode to the ship (sailing, maneuvering, anchoring, berthing). Based on this mode, it is determined if the main engines of the ship are on. If they are, the engine power is calculated from the resistance force acting on the moving ship. It is possible to convert engine power to fuel consumption and later to emissions with Specific Fuel Oil Consumption and emission factors.
Currently used emission models calculate engine power with the use of empirical formulas. So far, these models have mostly been validated by comparing them either to a noon report, or to another model. As a result, it gives no insight into the capability of a model to predict with a high spatial resolution, which is important in port areas and inland waterways.
There is little room for improvement in current semi-empirical bottom-up methods. However, in recent years, machine learning has shown the capability of replacing and often outperforming empirical models in other fields of research. This is due to the ability to model nonlinear behavior, find relations that humans can not, and work in higher dimensions. As a ship's engine power is reliant on a multitude of factors, machine learning might be the solution towards more accurate predictions.
This research aims to assess the capability of machine learning models to predict a ship's engine power with a high spatial resolution, with a focus on LSTM models. To do so, onboard sensor data from two ships was used; one sea-going container vessel and one inland tanker. The measured data was used to validate the semi-empirical method. Afterwards, the machine learning model was trained against the same sensor data. The predictions of the semi-empirical and machine learning models were then compared to one another.
Comparisons showed that the error for total energy used for the container vessel went from +62.87% to -0.82% when using a Bi-LSTM model with speed, acceleration, draught and depth as input. For the assessment of the spatiotemporal predictions, the MAE and RMSE were used. Based on these performance indicators, a normal LSTM network with speed, acceleration, draught and depth as input performed best. The MAE compared to the reference went down from 9542 to 2863, or about 7% of the maximum engine power.
The second case study highlighted the challenges that come with engine power prediction in inland waterways. Firstly, the fact that the speed over ground is used has a bigger influence in this case, as the ship will always sail with or against the current. Secondly, the influence of the blockage factor can
not be ignored without having higher losses. In addition to these two shortcomings, the model was trained on a diesel-electric ship. This ship has a much more constant power profile than ships with a more classical propulsion run on fossil fuels. This likely made the model more robust to changes. The combination of these three aspects caused less accurate predictions. Although there was more data available, errors were higher than for the case study. The best performing models showed a +3.41% error on total energy use and an MAE of 205.65, or about 12.8% of the maximum engine power.
This research has contributed new insights to the field of maritime emission modeling. The potential of machine learning models has been shown in comparison to an existing semi-empirical model. In addition, this model has now been validated using measurement data for a seagoing container vessel. Finally, shortcomings of the method using machine learning were exposed and a solution is proposed for a more complete, generalizable model.
Various methods have been developed to estimate emissions in the shipping industry. Top-down methods are applied using large-scale data to estimate emissions over a wide area. This approach provides a comprehensive overview but lacks the specific details required for local interventions. In contrast, bottom-up methods are applied and start with detailed data at the source and aggregate information to estimate the total emissions. Bottom-up methods offer more precise insights, however, more extensive data and complex modeling is required. To obtain more precise understandings, the modern bottom-up models use Automatic Identification System as input, a globally used system for tracking vessels. AIS data consists, among others, of time-dependent variables such as speed, location, and ship identification number. The data is used to assign an operational mode to the ship (sailing, maneuvering, anchoring, berthing). Based on this mode, it is determined if the main engines of the ship are on. If they are, the engine power is calculated from the resistance force acting on the moving ship. It is possible to convert engine power to fuel consumption and later to emissions with Specific Fuel Oil Consumption and emission factors.
Currently used emission models calculate engine power with the use of empirical formulas. So far, these models have mostly been validated by comparing them either to a noon report, or to another model. As a result, it gives no insight into the capability of a model to predict with a high spatial resolution, which is important in port areas and inland waterways.
There is little room for improvement in current semi-empirical bottom-up methods. However, in recent years, machine learning has shown the capability of replacing and often outperforming empirical models in other fields of research. This is due to the ability to model nonlinear behavior, find relations that humans can not, and work in higher dimensions. As a ship's engine power is reliant on a multitude of factors, machine learning might be the solution towards more accurate predictions.
This research aims to assess the capability of machine learning models to predict a ship's engine power with a high spatial resolution, with a focus on LSTM models. To do so, onboard sensor data from two ships was used; one sea-going container vessel and one inland tanker. The measured data was used to validate the semi-empirical method. Afterwards, the machine learning model was trained against the same sensor data. The predictions of the semi-empirical and machine learning models were then compared to one another.
Comparisons showed that the error for total energy used for the container vessel went from +62.87% to -0.82% when using a Bi-LSTM model with speed, acceleration, draught and depth as input. For the assessment of the spatiotemporal predictions, the MAE and RMSE were used. Based on these performance indicators, a normal LSTM network with speed, acceleration, draught and depth as input performed best. The MAE compared to the reference went down from 9542 to 2863, or about 7% of the maximum engine power.
The second case study highlighted the challenges that come with engine power prediction in inland waterways. Firstly, the fact that the speed over ground is used has a bigger influence in this case, as the ship will always sail with or against the current. Secondly, the influence of the blockage factor can
not be ignored without having higher losses. In addition to these two shortcomings, the model was trained on a diesel-electric ship. This ship has a much more constant power profile than ships with a more classical propulsion run on fossil fuels. This likely made the model more robust to changes. The combination of these three aspects caused less accurate predictions. Although there was more data available, errors were higher than for the case study. The best performing models showed a +3.41% error on total energy use and an MAE of 205.65, or about 12.8% of the maximum engine power.
This research has contributed new insights to the field of maritime emission modeling. The potential of machine learning models has been shown in comparison to an existing semi-empirical model. In addition, this model has now been validated using measurement data for a seagoing container vessel. Finally, shortcomings of the method using machine learning were exposed and a solution is proposed for a more complete, generalizable model.
Trajectory prediction for drifting ship allision probability calculations
A trajectory prediction-based method for probability calculations to improve our understanding of drifting ship allision risks in the Dutch North Sea region
Master thesis
(2024)
-
S.K.P. Eppenga, M. van Koningsveld, S.E. van der Werff, A.J. van der Hout, P.H.A.J.M. van Gelder, Simon Van Aartsen
The expansion of offshore wind farms in the North Sea has raised serious concerns about maritime safety, in particular the increased risk of collisions—or 'allisions'—where a ship adrift hits a stationary structure, such as a wind turbine. For Rijkswaterstaat, the executive agency of the Ministry of Infrastructure and Water Management, managing this expansion requires developing a comprehensive understanding of the integral image of allision risks of drifting ships in the Dutch North Sea region. This understanding must be valid, reliable, and insightful, and include factors such as dynamic weather conditions and shipping activity. Unfortunately, current state-of-the-art methods for estimating the probability of allision rely heavily on assumptions, leading to significant variations in risk estimates, as highlighted by Ellis et al. (2008). These methods usually lack a North Sea-wide perspective and instead focus on risks specific to individual turbines.
This study proposes an approach based on trajectory prediction using the OpenDrift model, which is simple and accessible for simulating ship drift trajectories based on wind, wave, and current data. A method is developed to estimate the probability of allision by combining the probability of a ship drifting into a wind farm, analysed through a ship's potential trajectories, with ship density data for specific locations. This method facilitates the calculation of allision risks under the influence of different environmental conditions and can be applied to multiple wind farms, providing a detailed assessment of the origins of potential threats and available response times.
Overall, the assumptions in state-of-the-art methods might not sufficiently capture the risks associated with drifting ships. In addition, the established method broadens the ability to improve monitoring accuracy and optimise the positioning of ERTVs, even for specific environmental conditions. As a next step, this method should be extended to estimate actual risk levels by considering the potential consequences of an allision. With this approach, decision-making regarding allision threats can be contextualised alongside other maritime safety risks, facilitating the development of a robust risk mitigation strategy that enables Rijkswaterstaat to responsibly exploit the abundant potential the North Sea has to offer. ...
This study proposes an approach based on trajectory prediction using the OpenDrift model, which is simple and accessible for simulating ship drift trajectories based on wind, wave, and current data. A method is developed to estimate the probability of allision by combining the probability of a ship drifting into a wind farm, analysed through a ship's potential trajectories, with ship density data for specific locations. This method facilitates the calculation of allision risks under the influence of different environmental conditions and can be applied to multiple wind farms, providing a detailed assessment of the origins of potential threats and available response times.
Overall, the assumptions in state-of-the-art methods might not sufficiently capture the risks associated with drifting ships. In addition, the established method broadens the ability to improve monitoring accuracy and optimise the positioning of ERTVs, even for specific environmental conditions. As a next step, this method should be extended to estimate actual risk levels by considering the potential consequences of an allision. With this approach, decision-making regarding allision threats can be contextualised alongside other maritime safety risks, facilitating the development of a robust risk mitigation strategy that enables Rijkswaterstaat to responsibly exploit the abundant potential the North Sea has to offer. ...
The expansion of offshore wind farms in the North Sea has raised serious concerns about maritime safety, in particular the increased risk of collisions—or 'allisions'—where a ship adrift hits a stationary structure, such as a wind turbine. For Rijkswaterstaat, the executive agency of the Ministry of Infrastructure and Water Management, managing this expansion requires developing a comprehensive understanding of the integral image of allision risks of drifting ships in the Dutch North Sea region. This understanding must be valid, reliable, and insightful, and include factors such as dynamic weather conditions and shipping activity. Unfortunately, current state-of-the-art methods for estimating the probability of allision rely heavily on assumptions, leading to significant variations in risk estimates, as highlighted by Ellis et al. (2008). These methods usually lack a North Sea-wide perspective and instead focus on risks specific to individual turbines.
This study proposes an approach based on trajectory prediction using the OpenDrift model, which is simple and accessible for simulating ship drift trajectories based on wind, wave, and current data. A method is developed to estimate the probability of allision by combining the probability of a ship drifting into a wind farm, analysed through a ship's potential trajectories, with ship density data for specific locations. This method facilitates the calculation of allision risks under the influence of different environmental conditions and can be applied to multiple wind farms, providing a detailed assessment of the origins of potential threats and available response times.
Overall, the assumptions in state-of-the-art methods might not sufficiently capture the risks associated with drifting ships. In addition, the established method broadens the ability to improve monitoring accuracy and optimise the positioning of ERTVs, even for specific environmental conditions. As a next step, this method should be extended to estimate actual risk levels by considering the potential consequences of an allision. With this approach, decision-making regarding allision threats can be contextualised alongside other maritime safety risks, facilitating the development of a robust risk mitigation strategy that enables Rijkswaterstaat to responsibly exploit the abundant potential the North Sea has to offer.
This study proposes an approach based on trajectory prediction using the OpenDrift model, which is simple and accessible for simulating ship drift trajectories based on wind, wave, and current data. A method is developed to estimate the probability of allision by combining the probability of a ship drifting into a wind farm, analysed through a ship's potential trajectories, with ship density data for specific locations. This method facilitates the calculation of allision risks under the influence of different environmental conditions and can be applied to multiple wind farms, providing a detailed assessment of the origins of potential threats and available response times.
Overall, the assumptions in state-of-the-art methods might not sufficiently capture the risks associated with drifting ships. In addition, the established method broadens the ability to improve monitoring accuracy and optimise the positioning of ERTVs, even for specific environmental conditions. As a next step, this method should be extended to estimate actual risk levels by considering the potential consequences of an allision. With this approach, decision-making regarding allision threats can be contextualised alongside other maritime safety risks, facilitating the development of a robust risk mitigation strategy that enables Rijkswaterstaat to responsibly exploit the abundant potential the North Sea has to offer.
Improving maritime safety at the North Sea by anomaly detection
Master of Science Thesis
Master thesis
(2024)
-
J.J. van den Heuvel, S.E. van der Werff, M. van Koningsveld, P. Mares Nasarre, F. Baart, L. de Boom
The Dutch government has set an ambitious target of reducing CO2 emissions by 55% by 2030, primarily through the development of offshore wind farms in the North Sea. While this transition supports sustainability, it also reduces available space for maritime traffic, increasing the risk of incidents. In response, this research aims to improve the detection of anomalous behaviour in the North Sea using machine learning, assisting Dutch Coast Guard operators in their monitoring tasks.
The primary focus of this study is to detect anomalous cargo vessel behaviour, specifically drifting, which has safety implications, as evidenced by the Julietta D. incident in January 2022. The research uses Automatic Identification System (AIS) data to monitor vessel trajectories and apply a machine learning-based anomaly detection model. This model uses features extracted from ship motion (e.g., speed, rate of turn), spatial properties (e.g. presence in anchorage area) and metocean condition (e.g., wave height) to detect anomalous behavior. The Local Outlier Factor (LOF) algorithm is employed to identify local outliers in a two-dimensional embedding of vessel trips, which is created using a density-preserving dimension reduction technique called densMAP.
The model successfully detects anomalous vessel behaviour within 30 minutes of occurrence, demonstrating its potential for real-time monitoring. In a case study of the cargo vessel Julietta D. incident, the model identified the drifting behaviour of this vessel, validating its effectiveness. The model also shows promise in detecting other types of anomalous behaviour, such as sudden changes in speed, and presence in defined areas.
While the model performs well in detecting a drifting incident and certain anomalies, it does not account for global outliers or identify other types of anomalous behaviour. Additionally, due to the limitations of AIS data, heading information was not incorporated. The research contributes to the safety monitoring of maritime traffic by providing a scalable, interpretable, and operationally feasible machine learning approach for the detection of anomalous cargo vessel behaviour.
Future work should focus on integrating time components, and supervised learning with labeled incident data to further refine the model. Ultimately, this research offers significant potential for enhancing operational safety and supporting the Coast Guard in the monitoring of maritime traffic in the North Sea.
...
The primary focus of this study is to detect anomalous cargo vessel behaviour, specifically drifting, which has safety implications, as evidenced by the Julietta D. incident in January 2022. The research uses Automatic Identification System (AIS) data to monitor vessel trajectories and apply a machine learning-based anomaly detection model. This model uses features extracted from ship motion (e.g., speed, rate of turn), spatial properties (e.g. presence in anchorage area) and metocean condition (e.g., wave height) to detect anomalous behavior. The Local Outlier Factor (LOF) algorithm is employed to identify local outliers in a two-dimensional embedding of vessel trips, which is created using a density-preserving dimension reduction technique called densMAP.
The model successfully detects anomalous vessel behaviour within 30 minutes of occurrence, demonstrating its potential for real-time monitoring. In a case study of the cargo vessel Julietta D. incident, the model identified the drifting behaviour of this vessel, validating its effectiveness. The model also shows promise in detecting other types of anomalous behaviour, such as sudden changes in speed, and presence in defined areas.
While the model performs well in detecting a drifting incident and certain anomalies, it does not account for global outliers or identify other types of anomalous behaviour. Additionally, due to the limitations of AIS data, heading information was not incorporated. The research contributes to the safety monitoring of maritime traffic by providing a scalable, interpretable, and operationally feasible machine learning approach for the detection of anomalous cargo vessel behaviour.
Future work should focus on integrating time components, and supervised learning with labeled incident data to further refine the model. Ultimately, this research offers significant potential for enhancing operational safety and supporting the Coast Guard in the monitoring of maritime traffic in the North Sea.
...
The Dutch government has set an ambitious target of reducing CO2 emissions by 55% by 2030, primarily through the development of offshore wind farms in the North Sea. While this transition supports sustainability, it also reduces available space for maritime traffic, increasing the risk of incidents. In response, this research aims to improve the detection of anomalous behaviour in the North Sea using machine learning, assisting Dutch Coast Guard operators in their monitoring tasks.
The primary focus of this study is to detect anomalous cargo vessel behaviour, specifically drifting, which has safety implications, as evidenced by the Julietta D. incident in January 2022. The research uses Automatic Identification System (AIS) data to monitor vessel trajectories and apply a machine learning-based anomaly detection model. This model uses features extracted from ship motion (e.g., speed, rate of turn), spatial properties (e.g. presence in anchorage area) and metocean condition (e.g., wave height) to detect anomalous behavior. The Local Outlier Factor (LOF) algorithm is employed to identify local outliers in a two-dimensional embedding of vessel trips, which is created using a density-preserving dimension reduction technique called densMAP.
The model successfully detects anomalous vessel behaviour within 30 minutes of occurrence, demonstrating its potential for real-time monitoring. In a case study of the cargo vessel Julietta D. incident, the model identified the drifting behaviour of this vessel, validating its effectiveness. The model also shows promise in detecting other types of anomalous behaviour, such as sudden changes in speed, and presence in defined areas.
While the model performs well in detecting a drifting incident and certain anomalies, it does not account for global outliers or identify other types of anomalous behaviour. Additionally, due to the limitations of AIS data, heading information was not incorporated. The research contributes to the safety monitoring of maritime traffic by providing a scalable, interpretable, and operationally feasible machine learning approach for the detection of anomalous cargo vessel behaviour.
Future work should focus on integrating time components, and supervised learning with labeled incident data to further refine the model. Ultimately, this research offers significant potential for enhancing operational safety and supporting the Coast Guard in the monitoring of maritime traffic in the North Sea.
The primary focus of this study is to detect anomalous cargo vessel behaviour, specifically drifting, which has safety implications, as evidenced by the Julietta D. incident in January 2022. The research uses Automatic Identification System (AIS) data to monitor vessel trajectories and apply a machine learning-based anomaly detection model. This model uses features extracted from ship motion (e.g., speed, rate of turn), spatial properties (e.g. presence in anchorage area) and metocean condition (e.g., wave height) to detect anomalous behavior. The Local Outlier Factor (LOF) algorithm is employed to identify local outliers in a two-dimensional embedding of vessel trips, which is created using a density-preserving dimension reduction technique called densMAP.
The model successfully detects anomalous vessel behaviour within 30 minutes of occurrence, demonstrating its potential for real-time monitoring. In a case study of the cargo vessel Julietta D. incident, the model identified the drifting behaviour of this vessel, validating its effectiveness. The model also shows promise in detecting other types of anomalous behaviour, such as sudden changes in speed, and presence in defined areas.
While the model performs well in detecting a drifting incident and certain anomalies, it does not account for global outliers or identify other types of anomalous behaviour. Additionally, due to the limitations of AIS data, heading information was not incorporated. The research contributes to the safety monitoring of maritime traffic by providing a scalable, interpretable, and operationally feasible machine learning approach for the detection of anomalous cargo vessel behaviour.
Future work should focus on integrating time components, and supervised learning with labeled incident data to further refine the model. Ultimately, this research offers significant potential for enhancing operational safety and supporting the Coast Guard in the monitoring of maritime traffic in the North Sea.
Master thesis
(2023)
-
B.G.H. van Engelen, M. van Koningsveld, L. de Boom, F. Baart, S.E. van der Werff, P. Mares Nasarre
Currently, inland waterway safety assessments rely heavily on historic accident data and expert opinions, often lacking comprehensive qualitative and quantitative information. Addressing this gap, this thesis introduces a method based on Automatic Identification System (AIS) data to identify anomalous vessel behaviour for enhancing safety assessments.
The proposed methodology establishes definitions of normal vessel behaviour and identifies deviations from these norms as anomalies. Analysing vessel trips recorded in AIS data logs, various features—including speed, acceleration, direction, manoeuvrability, and positional attributes—are extracted to define vessel behaviour.
The Uniform Manifold Approximation and Projection (UMAP) algorithm reduces the multidimensional features into a two-dimensional embedding to condense the vessel behaviour into a manageable form. This reduction technique preserves the inherent behaviour while representing similarities within a 2-dimensional space. Subsequently, the K-means clustering algorithm is applied to group vessels displaying similar behavioural patterns. The hyperparameters for clustering are determined using the elbow method and multiple scoring metrics.
Application of this methodology to the Moerdijkbrug at the Hollands Diep and Schellingwouderbrug at the IJ reveals clusters with similarities in vessel direction and paths. Several atypical patterns were observed and further investigated, analysing less than 1% of the data set in both cases, revealing two distinct patterns classified as probable accidents in the IJ case. These findings demonstrate the potential of the proposed method in identifying specific vessel behavioural anomalies with implications for safety assessment on inland waterways.
...
The proposed methodology establishes definitions of normal vessel behaviour and identifies deviations from these norms as anomalies. Analysing vessel trips recorded in AIS data logs, various features—including speed, acceleration, direction, manoeuvrability, and positional attributes—are extracted to define vessel behaviour.
The Uniform Manifold Approximation and Projection (UMAP) algorithm reduces the multidimensional features into a two-dimensional embedding to condense the vessel behaviour into a manageable form. This reduction technique preserves the inherent behaviour while representing similarities within a 2-dimensional space. Subsequently, the K-means clustering algorithm is applied to group vessels displaying similar behavioural patterns. The hyperparameters for clustering are determined using the elbow method and multiple scoring metrics.
Application of this methodology to the Moerdijkbrug at the Hollands Diep and Schellingwouderbrug at the IJ reveals clusters with similarities in vessel direction and paths. Several atypical patterns were observed and further investigated, analysing less than 1% of the data set in both cases, revealing two distinct patterns classified as probable accidents in the IJ case. These findings demonstrate the potential of the proposed method in identifying specific vessel behavioural anomalies with implications for safety assessment on inland waterways.
...
Currently, inland waterway safety assessments rely heavily on historic accident data and expert opinions, often lacking comprehensive qualitative and quantitative information. Addressing this gap, this thesis introduces a method based on Automatic Identification System (AIS) data to identify anomalous vessel behaviour for enhancing safety assessments.
The proposed methodology establishes definitions of normal vessel behaviour and identifies deviations from these norms as anomalies. Analysing vessel trips recorded in AIS data logs, various features—including speed, acceleration, direction, manoeuvrability, and positional attributes—are extracted to define vessel behaviour.
The Uniform Manifold Approximation and Projection (UMAP) algorithm reduces the multidimensional features into a two-dimensional embedding to condense the vessel behaviour into a manageable form. This reduction technique preserves the inherent behaviour while representing similarities within a 2-dimensional space. Subsequently, the K-means clustering algorithm is applied to group vessels displaying similar behavioural patterns. The hyperparameters for clustering are determined using the elbow method and multiple scoring metrics.
Application of this methodology to the Moerdijkbrug at the Hollands Diep and Schellingwouderbrug at the IJ reveals clusters with similarities in vessel direction and paths. Several atypical patterns were observed and further investigated, analysing less than 1% of the data set in both cases, revealing two distinct patterns classified as probable accidents in the IJ case. These findings demonstrate the potential of the proposed method in identifying specific vessel behavioural anomalies with implications for safety assessment on inland waterways.
The proposed methodology establishes definitions of normal vessel behaviour and identifies deviations from these norms as anomalies. Analysing vessel trips recorded in AIS data logs, various features—including speed, acceleration, direction, manoeuvrability, and positional attributes—are extracted to define vessel behaviour.
The Uniform Manifold Approximation and Projection (UMAP) algorithm reduces the multidimensional features into a two-dimensional embedding to condense the vessel behaviour into a manageable form. This reduction technique preserves the inherent behaviour while representing similarities within a 2-dimensional space. Subsequently, the K-means clustering algorithm is applied to group vessels displaying similar behavioural patterns. The hyperparameters for clustering are determined using the elbow method and multiple scoring metrics.
Application of this methodology to the Moerdijkbrug at the Hollands Diep and Schellingwouderbrug at the IJ reveals clusters with similarities in vessel direction and paths. Several atypical patterns were observed and further investigated, analysing less than 1% of the data set in both cases, revealing two distinct patterns classified as probable accidents in the IJ case. These findings demonstrate the potential of the proposed method in identifying specific vessel behavioural anomalies with implications for safety assessment on inland waterways.
The ship domain in port areas
A case study in the Port of Rotterdam
Increased complexity on the waterway asks for more insight into distances between vessels. A method is created to determine the ship domain in a port area based on AIS data analysis. The method includes location, encounter types, relative position and ship-specific parameters.
...
Increased complexity on the waterway asks for more insight into distances between vessels. A method is created to determine the ship domain in a port area based on AIS data analysis. The method includes location, encounter types, relative position and ship-specific parameters.
Estimate vessel emissions in ports using AIS data
A study to identify emission distribution patterns in ports and evaluate emission reduction strategies
Master thesis
(2022)
-
R.D.D. van den Berg, M. van Koningsveld, S.E. van der Werff, T.M. de Boer, P.A.L. de Vries, J.A. Álvarez Antolínez
The shipping industry is responsible for almost 3% of the world's greenhouse gas emissions and is looking for possibilities to reduce their share. The demand for lowering the emissions of the maritime industry creates the need for insight in the emissions. Currently a generic method to specify emissions in space and time, as a function of vessel and waterway properties is not available.
Although most of the emissions of vessels take place at sea, the most noticeable part takes place in ports since they are located close to urbanized areas. Therefore, this research focuses specifically on emissions in ports. The study investigates the impact of sea-going vessels. By gaining insight in the emissions of sea-going vessels, the big polluters can be tackled. Due to the scope of the research, not all vessel types and emission types are taken into account. Ten vessel types are selected and only CO2, NOx, SOx and PM10 emissions are estimated. These are the most relevant polluters in the shipping industry since they cause health and environmental related issues, both locally as more widely.
To provide insight in the emissions, the objective of this study is to develop a generalized method to calculate and map the emission of a single vessel in space and time in ports based on reliable data. To reduce these emissions, emission reduction strategies have to be drawn up, targeting the largest emission sources and the most crucial locations. Therefore, the developed method must not only quantify the emission sources, but must also provide insight in emission patterns in ports and indicate emission hotspots.
A bottom-up method is developed to estimate the emission of a single vessel in space and time. To derive the emission rate of a vessel, the fuel and energy consumption of the vessel is multiplied by a vessel-specific emission factor. The CO2 and SOx emissions follow a fuel-based approach, in which the emissions produced are directly proportional to the fuel consumption and therefore depend on the engine load. The energy-based approach is used for estimating NOx and PM10 emissions, which cannot be directly related to the fuel consumption but depend on engine characteristics. The fuel consumption is determined by multiplying the energy consumption of the engine with a fuel consumption factor specific to each vessel, meaning the fuel consumption is related to the energy consumption.
The amount of energy the main engines of a vessel consume, is the energy needed to overcome the resistance a ship experiences from sailing through the water and is therefore related to the vessel's speed. This speed is derived from AIS data. AIS data represents real-life vessel tracking data and is gathered automatically, which makes it a reliable and realistic data source. It also provides the ability to make the emission estimations time dependent. Due to the global coverage, AIS data is a good data source to develop a generic method applicable to ports all around the world.
However, in ports the vessel's speed alone is not a good indicator of the energy consumption, since this neglects the amount of energy the auxiliary engines consume. Their energy consumption is dependent on how much energy the electrical systems of a vessel require at that moment, which can be high when a vessel is for example at berth or manoeuvring. The energy consumption is therefore related to the operations a vessel performs. This leads to an approach which takes into account the vessel's resistance and operational modes.
Four operational modes are important to distinguish in ports: 'sailing', 'manoeuvring', 'anchoring' and 'berthing'. According to the operational mode, the main engine power is either estimated with the resistance calculation from Holtrop and Mennen when the vessel is sailing or manoeuvring, or assumed zero when laying still at anchor or berth. According to the operational mode, the auxiliary engine power can be derived from values of the IMO fourth GHG research. Depending on the emission type and vessel characteristics, the emission factor is determined.
The algorithm to determine the emission of a single vessel in space and time is implemented in a model. The model's input consists of AIS data providing the speed and position of the vessel, a vessel database containing vessel characteristics based on information from the Sea-web Ships database, and a FISgraph of the port network. This graph contains the fairway characteristics needed to calculate the resistance. The calculated emissions will also be displayed on the FIS graph for a detailed insight in the emission distribution in space.
The model provides an insight in the emissions patterns in a port. The fairway sections which are subjected to high emissions can be identified immediately and so the emission hotspots are determined. The source of the emissions can be identified by down-drilling of the emissions. The model can drill down to vessel types, operational modes and all the way down to a single vessel in space and time.
The model is illustrated by means of two case studies concerning the Port of Rotterdam and the Port of Constanța. These case studies indicate that the port basins hosting the largest vessels have the highest estimated emissions. These basins are indicated as an emission hotspot by the model when the emissions are projected on the FIS graph. In ports generally, high emissions are observed at places with a high traffic intensity, such as the port entrance. Junctions of fairway sections or port basin entrances also show locally higher emissions. The rise in emissions, is probably due to the fact that vessels are slowing down when approaching a junction. This increases the emission rate of a vessel due to more inefficient engine use, but also since they spend a larger amount of time at this fairway section.
By indicating the location and source of the emission hotspots, targeted emission reduction measures can be taken. Three of these measures are demonstrated on one of the case studies. The first strategy concerns installing shore power. The model is able to simulate vessels connected to shore power, by setting their emission rate at berth to zero. This simulation is compared to the original situation without using shore power. Out of the evaluated reduction measures, this seems the best strategy to reduce emissions since it shows the largest reduction of the total emissions. Besides that, it is an effective measure especially for ports, since the largest emissions reduction takes place at berth. The second evaluated strategy shows also good results and is about switching from a normal tugboat fleet to a zero-emission tugboat fleet. The model simulates this switch by eliminating all the tugboats from the fleet since their emissions will be zero. This new case is compared to the original situation with normal tugboats. The third option to reduce emissions is applying ECA limits which do not seem to have a lot of effect on reducing emissions except for the SOx emissions. This is derived from comparing the original situation without ECA limits, to a new case study where a situation with ECA limits is simulated. This means that the fuel types of the vessels are changed from the most economical fuel type to the lightest fuel type on board and that the sulphur content in the fuel is altered.
However, the model has some limitations. The method does not take into account the effect of currents or variations in time of the water depth. The accuracy of the resistance calculation can be improved by adding these. Furthermore, the emission pattern of tugboats needs further examination as it could not be demonstrated that the split of emissions into operational modes is correctly. The research has also shown that the method to estimate the energy consumption is not suitable for tankers at berth, since their energy consumption pattern is different. The quantity of emissions in the case study of the Port of Rotterdam is far from the expected amount of emissions. The quantification of emissions is assumed to be unreliable and further research should focus on validating these results.
Concluding, the developed model makes use of AIS data, local waterway properties, empirical emission factors and operational modes. This data is used in a physics-based method to estimate the resistance and the energy consumption. If this information is available, all this combined makes the approach in principle applicable to any port. The developed model provides an insight in the emission distribution patterns and provides the ability for down-drilling to find the source of the emission hotspots. A targeted emission reduction strategy can be proposed as a result of this and the model has the ability to evaluate specific emission reduction strategies. The strategies can be simulated with the developed model and the effect of these measures can be quantified by comparing the emission reduction strategy to a situation without these measures. ...
Although most of the emissions of vessels take place at sea, the most noticeable part takes place in ports since they are located close to urbanized areas. Therefore, this research focuses specifically on emissions in ports. The study investigates the impact of sea-going vessels. By gaining insight in the emissions of sea-going vessels, the big polluters can be tackled. Due to the scope of the research, not all vessel types and emission types are taken into account. Ten vessel types are selected and only CO2, NOx, SOx and PM10 emissions are estimated. These are the most relevant polluters in the shipping industry since they cause health and environmental related issues, both locally as more widely.
To provide insight in the emissions, the objective of this study is to develop a generalized method to calculate and map the emission of a single vessel in space and time in ports based on reliable data. To reduce these emissions, emission reduction strategies have to be drawn up, targeting the largest emission sources and the most crucial locations. Therefore, the developed method must not only quantify the emission sources, but must also provide insight in emission patterns in ports and indicate emission hotspots.
A bottom-up method is developed to estimate the emission of a single vessel in space and time. To derive the emission rate of a vessel, the fuel and energy consumption of the vessel is multiplied by a vessel-specific emission factor. The CO2 and SOx emissions follow a fuel-based approach, in which the emissions produced are directly proportional to the fuel consumption and therefore depend on the engine load. The energy-based approach is used for estimating NOx and PM10 emissions, which cannot be directly related to the fuel consumption but depend on engine characteristics. The fuel consumption is determined by multiplying the energy consumption of the engine with a fuel consumption factor specific to each vessel, meaning the fuel consumption is related to the energy consumption.
The amount of energy the main engines of a vessel consume, is the energy needed to overcome the resistance a ship experiences from sailing through the water and is therefore related to the vessel's speed. This speed is derived from AIS data. AIS data represents real-life vessel tracking data and is gathered automatically, which makes it a reliable and realistic data source. It also provides the ability to make the emission estimations time dependent. Due to the global coverage, AIS data is a good data source to develop a generic method applicable to ports all around the world.
However, in ports the vessel's speed alone is not a good indicator of the energy consumption, since this neglects the amount of energy the auxiliary engines consume. Their energy consumption is dependent on how much energy the electrical systems of a vessel require at that moment, which can be high when a vessel is for example at berth or manoeuvring. The energy consumption is therefore related to the operations a vessel performs. This leads to an approach which takes into account the vessel's resistance and operational modes.
Four operational modes are important to distinguish in ports: 'sailing', 'manoeuvring', 'anchoring' and 'berthing'. According to the operational mode, the main engine power is either estimated with the resistance calculation from Holtrop and Mennen when the vessel is sailing or manoeuvring, or assumed zero when laying still at anchor or berth. According to the operational mode, the auxiliary engine power can be derived from values of the IMO fourth GHG research. Depending on the emission type and vessel characteristics, the emission factor is determined.
The algorithm to determine the emission of a single vessel in space and time is implemented in a model. The model's input consists of AIS data providing the speed and position of the vessel, a vessel database containing vessel characteristics based on information from the Sea-web Ships database, and a FISgraph of the port network. This graph contains the fairway characteristics needed to calculate the resistance. The calculated emissions will also be displayed on the FIS graph for a detailed insight in the emission distribution in space.
The model provides an insight in the emissions patterns in a port. The fairway sections which are subjected to high emissions can be identified immediately and so the emission hotspots are determined. The source of the emissions can be identified by down-drilling of the emissions. The model can drill down to vessel types, operational modes and all the way down to a single vessel in space and time.
The model is illustrated by means of two case studies concerning the Port of Rotterdam and the Port of Constanța. These case studies indicate that the port basins hosting the largest vessels have the highest estimated emissions. These basins are indicated as an emission hotspot by the model when the emissions are projected on the FIS graph. In ports generally, high emissions are observed at places with a high traffic intensity, such as the port entrance. Junctions of fairway sections or port basin entrances also show locally higher emissions. The rise in emissions, is probably due to the fact that vessels are slowing down when approaching a junction. This increases the emission rate of a vessel due to more inefficient engine use, but also since they spend a larger amount of time at this fairway section.
By indicating the location and source of the emission hotspots, targeted emission reduction measures can be taken. Three of these measures are demonstrated on one of the case studies. The first strategy concerns installing shore power. The model is able to simulate vessels connected to shore power, by setting their emission rate at berth to zero. This simulation is compared to the original situation without using shore power. Out of the evaluated reduction measures, this seems the best strategy to reduce emissions since it shows the largest reduction of the total emissions. Besides that, it is an effective measure especially for ports, since the largest emissions reduction takes place at berth. The second evaluated strategy shows also good results and is about switching from a normal tugboat fleet to a zero-emission tugboat fleet. The model simulates this switch by eliminating all the tugboats from the fleet since their emissions will be zero. This new case is compared to the original situation with normal tugboats. The third option to reduce emissions is applying ECA limits which do not seem to have a lot of effect on reducing emissions except for the SOx emissions. This is derived from comparing the original situation without ECA limits, to a new case study where a situation with ECA limits is simulated. This means that the fuel types of the vessels are changed from the most economical fuel type to the lightest fuel type on board and that the sulphur content in the fuel is altered.
However, the model has some limitations. The method does not take into account the effect of currents or variations in time of the water depth. The accuracy of the resistance calculation can be improved by adding these. Furthermore, the emission pattern of tugboats needs further examination as it could not be demonstrated that the split of emissions into operational modes is correctly. The research has also shown that the method to estimate the energy consumption is not suitable for tankers at berth, since their energy consumption pattern is different. The quantity of emissions in the case study of the Port of Rotterdam is far from the expected amount of emissions. The quantification of emissions is assumed to be unreliable and further research should focus on validating these results.
Concluding, the developed model makes use of AIS data, local waterway properties, empirical emission factors and operational modes. This data is used in a physics-based method to estimate the resistance and the energy consumption. If this information is available, all this combined makes the approach in principle applicable to any port. The developed model provides an insight in the emission distribution patterns and provides the ability for down-drilling to find the source of the emission hotspots. A targeted emission reduction strategy can be proposed as a result of this and the model has the ability to evaluate specific emission reduction strategies. The strategies can be simulated with the developed model and the effect of these measures can be quantified by comparing the emission reduction strategy to a situation without these measures. ...
The shipping industry is responsible for almost 3% of the world's greenhouse gas emissions and is looking for possibilities to reduce their share. The demand for lowering the emissions of the maritime industry creates the need for insight in the emissions. Currently a generic method to specify emissions in space and time, as a function of vessel and waterway properties is not available.
Although most of the emissions of vessels take place at sea, the most noticeable part takes place in ports since they are located close to urbanized areas. Therefore, this research focuses specifically on emissions in ports. The study investigates the impact of sea-going vessels. By gaining insight in the emissions of sea-going vessels, the big polluters can be tackled. Due to the scope of the research, not all vessel types and emission types are taken into account. Ten vessel types are selected and only CO2, NOx, SOx and PM10 emissions are estimated. These are the most relevant polluters in the shipping industry since they cause health and environmental related issues, both locally as more widely.
To provide insight in the emissions, the objective of this study is to develop a generalized method to calculate and map the emission of a single vessel in space and time in ports based on reliable data. To reduce these emissions, emission reduction strategies have to be drawn up, targeting the largest emission sources and the most crucial locations. Therefore, the developed method must not only quantify the emission sources, but must also provide insight in emission patterns in ports and indicate emission hotspots.
A bottom-up method is developed to estimate the emission of a single vessel in space and time. To derive the emission rate of a vessel, the fuel and energy consumption of the vessel is multiplied by a vessel-specific emission factor. The CO2 and SOx emissions follow a fuel-based approach, in which the emissions produced are directly proportional to the fuel consumption and therefore depend on the engine load. The energy-based approach is used for estimating NOx and PM10 emissions, which cannot be directly related to the fuel consumption but depend on engine characteristics. The fuel consumption is determined by multiplying the energy consumption of the engine with a fuel consumption factor specific to each vessel, meaning the fuel consumption is related to the energy consumption.
The amount of energy the main engines of a vessel consume, is the energy needed to overcome the resistance a ship experiences from sailing through the water and is therefore related to the vessel's speed. This speed is derived from AIS data. AIS data represents real-life vessel tracking data and is gathered automatically, which makes it a reliable and realistic data source. It also provides the ability to make the emission estimations time dependent. Due to the global coverage, AIS data is a good data source to develop a generic method applicable to ports all around the world.
However, in ports the vessel's speed alone is not a good indicator of the energy consumption, since this neglects the amount of energy the auxiliary engines consume. Their energy consumption is dependent on how much energy the electrical systems of a vessel require at that moment, which can be high when a vessel is for example at berth or manoeuvring. The energy consumption is therefore related to the operations a vessel performs. This leads to an approach which takes into account the vessel's resistance and operational modes.
Four operational modes are important to distinguish in ports: 'sailing', 'manoeuvring', 'anchoring' and 'berthing'. According to the operational mode, the main engine power is either estimated with the resistance calculation from Holtrop and Mennen when the vessel is sailing or manoeuvring, or assumed zero when laying still at anchor or berth. According to the operational mode, the auxiliary engine power can be derived from values of the IMO fourth GHG research. Depending on the emission type and vessel characteristics, the emission factor is determined.
The algorithm to determine the emission of a single vessel in space and time is implemented in a model. The model's input consists of AIS data providing the speed and position of the vessel, a vessel database containing vessel characteristics based on information from the Sea-web Ships database, and a FISgraph of the port network. This graph contains the fairway characteristics needed to calculate the resistance. The calculated emissions will also be displayed on the FIS graph for a detailed insight in the emission distribution in space.
The model provides an insight in the emissions patterns in a port. The fairway sections which are subjected to high emissions can be identified immediately and so the emission hotspots are determined. The source of the emissions can be identified by down-drilling of the emissions. The model can drill down to vessel types, operational modes and all the way down to a single vessel in space and time.
The model is illustrated by means of two case studies concerning the Port of Rotterdam and the Port of Constanța. These case studies indicate that the port basins hosting the largest vessels have the highest estimated emissions. These basins are indicated as an emission hotspot by the model when the emissions are projected on the FIS graph. In ports generally, high emissions are observed at places with a high traffic intensity, such as the port entrance. Junctions of fairway sections or port basin entrances also show locally higher emissions. The rise in emissions, is probably due to the fact that vessels are slowing down when approaching a junction. This increases the emission rate of a vessel due to more inefficient engine use, but also since they spend a larger amount of time at this fairway section.
By indicating the location and source of the emission hotspots, targeted emission reduction measures can be taken. Three of these measures are demonstrated on one of the case studies. The first strategy concerns installing shore power. The model is able to simulate vessels connected to shore power, by setting their emission rate at berth to zero. This simulation is compared to the original situation without using shore power. Out of the evaluated reduction measures, this seems the best strategy to reduce emissions since it shows the largest reduction of the total emissions. Besides that, it is an effective measure especially for ports, since the largest emissions reduction takes place at berth. The second evaluated strategy shows also good results and is about switching from a normal tugboat fleet to a zero-emission tugboat fleet. The model simulates this switch by eliminating all the tugboats from the fleet since their emissions will be zero. This new case is compared to the original situation with normal tugboats. The third option to reduce emissions is applying ECA limits which do not seem to have a lot of effect on reducing emissions except for the SOx emissions. This is derived from comparing the original situation without ECA limits, to a new case study where a situation with ECA limits is simulated. This means that the fuel types of the vessels are changed from the most economical fuel type to the lightest fuel type on board and that the sulphur content in the fuel is altered.
However, the model has some limitations. The method does not take into account the effect of currents or variations in time of the water depth. The accuracy of the resistance calculation can be improved by adding these. Furthermore, the emission pattern of tugboats needs further examination as it could not be demonstrated that the split of emissions into operational modes is correctly. The research has also shown that the method to estimate the energy consumption is not suitable for tankers at berth, since their energy consumption pattern is different. The quantity of emissions in the case study of the Port of Rotterdam is far from the expected amount of emissions. The quantification of emissions is assumed to be unreliable and further research should focus on validating these results.
Concluding, the developed model makes use of AIS data, local waterway properties, empirical emission factors and operational modes. This data is used in a physics-based method to estimate the resistance and the energy consumption. If this information is available, all this combined makes the approach in principle applicable to any port. The developed model provides an insight in the emission distribution patterns and provides the ability for down-drilling to find the source of the emission hotspots. A targeted emission reduction strategy can be proposed as a result of this and the model has the ability to evaluate specific emission reduction strategies. The strategies can be simulated with the developed model and the effect of these measures can be quantified by comparing the emission reduction strategy to a situation without these measures.
Although most of the emissions of vessels take place at sea, the most noticeable part takes place in ports since they are located close to urbanized areas. Therefore, this research focuses specifically on emissions in ports. The study investigates the impact of sea-going vessels. By gaining insight in the emissions of sea-going vessels, the big polluters can be tackled. Due to the scope of the research, not all vessel types and emission types are taken into account. Ten vessel types are selected and only CO2, NOx, SOx and PM10 emissions are estimated. These are the most relevant polluters in the shipping industry since they cause health and environmental related issues, both locally as more widely.
To provide insight in the emissions, the objective of this study is to develop a generalized method to calculate and map the emission of a single vessel in space and time in ports based on reliable data. To reduce these emissions, emission reduction strategies have to be drawn up, targeting the largest emission sources and the most crucial locations. Therefore, the developed method must not only quantify the emission sources, but must also provide insight in emission patterns in ports and indicate emission hotspots.
A bottom-up method is developed to estimate the emission of a single vessel in space and time. To derive the emission rate of a vessel, the fuel and energy consumption of the vessel is multiplied by a vessel-specific emission factor. The CO2 and SOx emissions follow a fuel-based approach, in which the emissions produced are directly proportional to the fuel consumption and therefore depend on the engine load. The energy-based approach is used for estimating NOx and PM10 emissions, which cannot be directly related to the fuel consumption but depend on engine characteristics. The fuel consumption is determined by multiplying the energy consumption of the engine with a fuel consumption factor specific to each vessel, meaning the fuel consumption is related to the energy consumption.
The amount of energy the main engines of a vessel consume, is the energy needed to overcome the resistance a ship experiences from sailing through the water and is therefore related to the vessel's speed. This speed is derived from AIS data. AIS data represents real-life vessel tracking data and is gathered automatically, which makes it a reliable and realistic data source. It also provides the ability to make the emission estimations time dependent. Due to the global coverage, AIS data is a good data source to develop a generic method applicable to ports all around the world.
However, in ports the vessel's speed alone is not a good indicator of the energy consumption, since this neglects the amount of energy the auxiliary engines consume. Their energy consumption is dependent on how much energy the electrical systems of a vessel require at that moment, which can be high when a vessel is for example at berth or manoeuvring. The energy consumption is therefore related to the operations a vessel performs. This leads to an approach which takes into account the vessel's resistance and operational modes.
Four operational modes are important to distinguish in ports: 'sailing', 'manoeuvring', 'anchoring' and 'berthing'. According to the operational mode, the main engine power is either estimated with the resistance calculation from Holtrop and Mennen when the vessel is sailing or manoeuvring, or assumed zero when laying still at anchor or berth. According to the operational mode, the auxiliary engine power can be derived from values of the IMO fourth GHG research. Depending on the emission type and vessel characteristics, the emission factor is determined.
The algorithm to determine the emission of a single vessel in space and time is implemented in a model. The model's input consists of AIS data providing the speed and position of the vessel, a vessel database containing vessel characteristics based on information from the Sea-web Ships database, and a FISgraph of the port network. This graph contains the fairway characteristics needed to calculate the resistance. The calculated emissions will also be displayed on the FIS graph for a detailed insight in the emission distribution in space.
The model provides an insight in the emissions patterns in a port. The fairway sections which are subjected to high emissions can be identified immediately and so the emission hotspots are determined. The source of the emissions can be identified by down-drilling of the emissions. The model can drill down to vessel types, operational modes and all the way down to a single vessel in space and time.
The model is illustrated by means of two case studies concerning the Port of Rotterdam and the Port of Constanța. These case studies indicate that the port basins hosting the largest vessels have the highest estimated emissions. These basins are indicated as an emission hotspot by the model when the emissions are projected on the FIS graph. In ports generally, high emissions are observed at places with a high traffic intensity, such as the port entrance. Junctions of fairway sections or port basin entrances also show locally higher emissions. The rise in emissions, is probably due to the fact that vessels are slowing down when approaching a junction. This increases the emission rate of a vessel due to more inefficient engine use, but also since they spend a larger amount of time at this fairway section.
By indicating the location and source of the emission hotspots, targeted emission reduction measures can be taken. Three of these measures are demonstrated on one of the case studies. The first strategy concerns installing shore power. The model is able to simulate vessels connected to shore power, by setting their emission rate at berth to zero. This simulation is compared to the original situation without using shore power. Out of the evaluated reduction measures, this seems the best strategy to reduce emissions since it shows the largest reduction of the total emissions. Besides that, it is an effective measure especially for ports, since the largest emissions reduction takes place at berth. The second evaluated strategy shows also good results and is about switching from a normal tugboat fleet to a zero-emission tugboat fleet. The model simulates this switch by eliminating all the tugboats from the fleet since their emissions will be zero. This new case is compared to the original situation with normal tugboats. The third option to reduce emissions is applying ECA limits which do not seem to have a lot of effect on reducing emissions except for the SOx emissions. This is derived from comparing the original situation without ECA limits, to a new case study where a situation with ECA limits is simulated. This means that the fuel types of the vessels are changed from the most economical fuel type to the lightest fuel type on board and that the sulphur content in the fuel is altered.
However, the model has some limitations. The method does not take into account the effect of currents or variations in time of the water depth. The accuracy of the resistance calculation can be improved by adding these. Furthermore, the emission pattern of tugboats needs further examination as it could not be demonstrated that the split of emissions into operational modes is correctly. The research has also shown that the method to estimate the energy consumption is not suitable for tankers at berth, since their energy consumption pattern is different. The quantity of emissions in the case study of the Port of Rotterdam is far from the expected amount of emissions. The quantification of emissions is assumed to be unreliable and further research should focus on validating these results.
Concluding, the developed model makes use of AIS data, local waterway properties, empirical emission factors and operational modes. This data is used in a physics-based method to estimate the resistance and the energy consumption. If this information is available, all this combined makes the approach in principle applicable to any port. The developed model provides an insight in the emission distribution patterns and provides the ability for down-drilling to find the source of the emission hotspots. A targeted emission reduction strategy can be proposed as a result of this and the model has the ability to evaluate specific emission reduction strategies. The strategies can be simulated with the developed model and the effect of these measures can be quantified by comparing the emission reduction strategy to a situation without these measures.