A detailed exhaust emission inventory of ships by using Automatic Identification System (AIS) data was developed for Tianjin Port, one of the top 10 world container ports and the largest port in ...North China. It was found that in 2014, ship emissions are 2.93 × 104, 4.13 × 104, 4.03 × 103, 3.72 × 103, 1.72 × 103 and 3.57 × 103 tonnes of SO2, NOx, PM10, PM2.5, NMVOC and CO respectively, which are equivalent to 11.07%, 9.40%, 2.43%, 3.10%, 0.43% and 0.16% respectively of the non-ship anthropogenic totals in Tianjin. The total CO2 emissions is approximately 1.97 × 106 tonnes. The container ships and dry bulk cargo ships contributed about 70% of the total ship emissions of NOx, SO2 and PM10. Pollutants were mainly emitted during cruise and hotelling modes, and the highest intensities of emissions located in the vicinity of fairways, berth and anchorage areas in Tianjin Port. Distinctive difference between the lowest (February) and the highest (September) monthly emissions is due to the adjustment of freight volume during the Chinese New Year and the months before and after it.
•First ship emission inventory with high temporal-spatial resolution in Tianjin Port.•Nearly all identified vessels equipped with AIS were included in the calculation.•Detailed spatial distribution and monthly variation of ship emissions were presented.
•First comprehensive ship emission inventory in China including OGVs, RVs and CVs•Full year AIS data of >15billion reports (166,546 vessels) were used for estimation.•Detailed spatial distribution ...and monthly variation of ship emissions were presented.•Emission differences of the major port clusters (BSA, YRD and PRD) were analyzed.•Emissions for the 24 major ports in China were presented.
Display omitted
Ship exhaust emissions have been considered a significant source of air pollution, with adverse impacts on the global climate and human health. China, as one of the largest shipping countries, has long been in great need of in-depth analysis of ship emissions. This study for the first time developed a comprehensive national-scale ship emission inventory with 0.005°×0.005° resolution in China for 2014, using the bottom-up method based on Automatic Identification System (AIS) data of the full year of 2014. The emission estimation involved 166,546 unique vessels observed from over 15billion AIS reports, covering OGVs (ocean-going vessels), CVs (coastal vessels) and RVs (river vessels). Results show that the total estimated ship emissions for China in 2014 were 1.1937×106t (SO2), 2.2084×106t (NOX), 1.807×105t (PM10), 1.665×105t (PM2.5), 1.116×105t (HC), 2.419×105t (CO), and 7.843×107t (CO2, excluding RVs), respectively. OGVs were the main emission contributors, with proportions of 47%–74% of the emission totals for different species. Vessel type with the most emissions was container (~43.6%), followed by bulk carrier (~17.5%), oil tanker (~5.7%) and fishing ship (~4.9%). Monthly variations showed that emissions from transport vessels had a low point in February, while fishing ship presented two emission peaks in May and September. In terms of port clusters, ship emissions in BSA (Bohai Sea Area), YRD (Yangtze River Delta) and PRD (Pearl River Delta) accounted for ~13%, ~28% and ~17%, respectively, of the total emissions in China. On the contrast, the average emission intensities in PRD were the highest, followed by the YRD and BSA regions. The establishment of this high-spatiotemporal-resolution ship emission inventory fills the gap of national-scale ship emission inventory of China, and the corresponding ship emission characteristics are expected to provide certain reference significance for the management and control of the ship emissions.
With a wide use of AIS data in maritime transportation, there is an increasing demand to develop algorithms to efficiently classify a ship’s AIS data into different movements (static, normal ...navigation and manoeuvring). To achieve this, several studies have been proposed to use labelled features but with the drawback of not being able to effectively extract the details of ship movement information. In addition, a ship movement is in a free space, which is different to a road vehicle’s movement in road grids, making it inconvenient to directly migrate the methods for GPS data classification into AIS data. To deal with these problems, a Convolutional Neural Network-Ship Movement Modes Classification (CNN-SMMC) algorithm is proposed in this paper. The underlying concept of this method is to train a neural network to learn from the labelled AIS data, and the unlabelled AIS data can be effectively classified by using this trained network. More specifically, a Ship Movement Image Generation and Labelling (SMIGL) algorithm is first designed to convert a ship’s AIS trajectories into different movement images to make a full use of the CNN’s classification ability. Then, a CNN-SMMC architecture is built with a series of functional layers (convolutional layer, max-pooling layer, dense layer etc.) for ship movement classification with seven experiments been designed to find the optimal parameters for the CNN-SMMC. Considering the imbalanced features of AIS data, three metrics (average accuracy, F1 score and Area Under Curve (AUC)) are selected to evaluate the performance of the CNN-SMMC. Finally, several benchmark classification algorithms (K-Nearest Neighbours (KNN), Support Vector Machine (SVM) and Decision Tree (DT)) are selected to compare with CNN-SMMC. The results demonstrate that the proposed CNN-SMMC has a better performance in the classification of AIS data.
•A novel neural network-based classification model called CNN-Ship Movement Modes Classification (CNN-SMMC) proposed.•A new Ship Movement Image Generation and Labelling (SMIGL) algorithm to represent different ship movements designed.•Extensive experiments conducted to find optimal parameters for the CNN-SMMC.•Algorithms’ performance demonstrated via comparisons with conventional machine learning classification algorithms.
Ship emissions contribute significantly to air pollution and impose health risks to residents along the coastal area. By using the refined data from the Automatic Identification System (AIS), this ...study developed a highly resolved ship emission inventory for the Pearl River Delta (PRD) region, China, home to three of ten busiest ports in the world. The region-wide SO2, NOX, CO, PM10, PM2.5, and VOC emissions in 2013 were estimated to be 61,484, 103,717, 10,599, 7155, 6605, and 4195t, respectively. Ocean going vessels were the largest contributors of the total emissions, followed by coastal vessels and river vessels. In terms of ship type, container ship was the leading contributor, followed by conventional cargo ship, dry bulk carrier, fishing ship, and oil tanker. These five ship types accounted for >90% of total emissions. The spatial distributions of emissions revealed that the key emission hot spots all concentrated within the newly proposed emission control area (ECA) and ship emissions within ECA covered >80% of total ship emissions in the PRD, highlighting the importance of ECA in emissions reduction in the PRD. The uncertainties of emission estimates of pollutants were quantified, with lower bounds of −24.5% to −21.2% and upper bounds of 28.6% to 33.3% at 95% confidence intervals. The lower uncertainties in this study highlighted the powerfulness of AIS data in improving ship emission estimates. The AIS-based bottom-up methodology can be used for developing and upgrading ship emission inventory and formulating effective control measures on ship emissions in other port regions wherever possible.
Display omitted
•A comprehensive database with >12,000 ships information was established.•A yearlong AIS dataset was used to develop time-in-mode and spatiotemporal surrogates.•A bottom-up approach was used to estimate emissions from major ship source sectors.•The ECA region covered over 80% of the total ship emissions in the PRD region.•Application of AIS data reduced uncertainty in ship emission estimates.
COLREGs-based collision risk awareness model is urgently needed in real-time operating conditions. However, this is a complicated problem under various encounter situations, some of which are very ...complex. In order to quantify the collision risk in real operating conditions, a novel risk-informed collision risk awareness approach is proposed for real-time operating conditions. Firstly, the ship's actions are identified based on the Automatic Identification System (AIS) data. Secondly, the uncertainty of ship action patterns is analyzed by regarding the target ships as velocity obstacles. Then, the collision risk model is utilized to assess the collision risk level based on the uncertainty in the non-linear velocity obstacles algorithm considering responsibility. Finally, some case studies are carried out based on the proposed model. In the model, the dynamic and uncertainty features of the ship action dynamics in real operating conditions are considered, which could benefit on reducing ship collision accidents and improving the development of technologies on intelligent collision avoidance decision makings.
•A novel risk-informed collision risk awareness approach is proposed for real-time operating conditions.•An improved velocity obstacles method called Uncertainty Non-Linear Velocity Obstacles (UNLVO) is raised.•Ship motions are identified by different compression thresholds based on AIS data in real operating conditions.•The dynamic and uncertainty characteristics of ship motion patterns in real operating conditions are considered.
Vessel operations at port play a particular role in port-related air emissions. Hotelling, manoeuvring and cruising operations in the harbour areas generate a large share of local and global ...pollution, external costs and public health issues. Emission abatement demands effective regulation for vessel compliance and enforcement adequacy in despite of geographic differences in jurisdiction. A connecting relation between regulatory frameworks and atmospheric pollution from vessels operations at port is so far, missing in literature. This paper aims at filling in this gap by addressing exhaust gasses (NOx, SOx, CO, CO2) and particles (PM2.5) released from operative vessels in port with differing regulatory frameworks (Las Palmas, St. Petersburg, and Hong Kong). Estimations are based on the Ship Traffic Emission Assessment Model (STEAM) and AIS traffic information over a twelve-month timeframe. Contribution of this paper relates to revealing emission patterns of vessel operations in port and the assessment of current regulatory frameworks. Results and lower emission profiles shed light to sulphur regulation differences and the potential benefits in new policy measures (polluter pays principle, cold ironing and others) of accounting operative modes and shipping sub-sectors.
•Shipping emission in ports under diverse geographical and regulatory framework.•Emissions patterns at port from general and passenger vessel traffic.•Results show how disaggregation of emission inventory can provide policy support.•Port emission patterns cannot be solely explained by regulatory differences.•Policy recommendations based on regulation, port governance and emission results.
Data-driven methods open up unprecedented possibilities for maritime surveillance using automatic identification system (AIS) data. In this work, we explore deep learning strategies using historical ...AIS observations to address the problem of predicting future vessel trajectories with a prediction horizon of several hours. We propose novel sequence-to-sequence vessel trajectory prediction models based on encoder–decoder recurrent neural networks (RNNs) that are trained on historical trajectory data to predict future trajectory samples given previous observations. The proposed architecture combines long short-term memory RNNs for sequence modeling to encode the observed data and generate future predictions with different intermediate aggregation layers to capture space-time dependencies in sequential data. Experimental results on vessel trajectories from an AIS dataset made freely available by the Danish Maritime Authority (DMA) show the effectiveness of deep learning methods for trajectory prediction based on sequence-to-sequence neural networks, which achieve better performance than baseline approaches based on linear regression or on the multilayer perceptron architecture. The comparative evaluation of results shows: first, the superiority of attention pooling over static pooling for the specific application, and second, the remarkable performance improvement that can be obtained with labeled trajectories, i.e., when predictions are conditioned on a low-level context representation encoded from the sequence of past observations, as well as on additional inputs (e.g., port of departure or arrival) about the vessel's high-level intention, which may be available from AIS.
This paper proposes a novel data-driven approach to estimate the navigable capacity of busy waterways, focusing on ships entering and leaving port, based on the structural characteristics of traffic ...flow driven by the Automatic Identification System (AIS) data. First, we collect the ship traffic flow in a busy waterway by processing the original AIS data and then identify the structural characteristics of the traffic flow using the K-means clustering algorithm. The clusters are constructed based on the spatiotemporal consumption of waterway resources of different ships and the waste of waterway resources caused by navigational mode conversion, taking ship domain into consideration. We apply the proposed approach to estimate the navigable capacity of the Dagusha Channel of Tianjin Port, China. The empirical results reveal that the maximum daily traffic capacity of the Dagusha Channel is about 109 ship times/day. A comparison of waterway capacity estimation methods demonstrates that our proposed approach is more accurate and able to quantify the waterway capacity of different types of ships in a busy waterway, taking the structural characteristics of traffic flow explicitly into account. The proposed approach provides support for the design of channel and determination of scheduling schemes for ships in busy waterways.
•Incorporating structural characteristics of traffic flow and various constraints in navigable capacity estimation.•Identifying structural characteristics of traffic flow using K-means based on real operational conditions.•Quantifying ship safety domains and spatial-temporal resource consumptions for each cluster of ships.•Offering a novel approach to estimate the navigable capacity of busy waterways.
The trajectory of the inland waterway ship is important and useful in analysing the features of the ship behaviour and simulating traffic flows. In the proposed research, a method is designed to ...restore the trajectory of an inland waterway ship based on the Automatic Identification System (AIS) data. Firstly, three rules are developed to identify and remove the inaccurate data, based on the reception range of the received AIS data and the manoeuvring characteristics of the inland waterway ship. Secondly, the method of restoring the full trajectory incorporating navigational features of the inland waterway ship is proposed to model the ship trajectory. The trajectory is characterised by three types (line, curve and arc) and five steps (line, curve, arc, curve and line) during the turning section. In order to validate the proposed method, the AIS data of two inland waterway ships collected from three AIS-base-stations is selected for the analysis, all inaccurate AIS data is identified and removed by the use of three cleansing rules. The results show that the three developed rules can effectively identify the inaccurate AIS data. The AIS data collected by an AIS-shipboard-unit is then used to: (1) restore the ship trajectory, and (2) validate the proposed method by comparing the reconstituted trajectories with the actual trajectory. This actual trajectory is determined from intermediate higher frequency Global Positioning System (GPS) data and collected from the AIS-shipboard-unit. The residual errors are calculated as the differences between the estimated latitude values of the restored trajectory functions and the real latitude values of the GPS data. Three alternative methods of trajectory restoring are also evaluated. The results show that the proposed method can be used to restore the full trajectory in an effective manner by using AIS data.
•Three rules are built to identify the inaccurate data and cleanse AIS data.•These three rules can effectively identify and remove the inaccurate data.•The trajectory of the inland ship can be characterised by three trajectory types.•A novel method of restoring the full trajectory is designed.•The proposed method can be used to restore a trajectory in an effective manner.
Proactive traffic management is increasingly critical in maritime intelligent transportation systems. Central to this is maritime traffic forecasting, which leverages specific structures and ...properties of the problem. This study focuses on the traffic dynamics within convergent areas of inland waterways and proposes a method based on data mining followed by prediction using Automatic Identification System (AIS) data. This approach addresses uncertainties in ship voyage destinations and optimizes predictions for temporary stops in inland waterways. AIS data is processed to depict complete ship motion trajectories, grouping them into trajectory sets based on shared origin, destination, and route. These groups help represent maritime traffic patterns using the entrance and exit points of channels and the boundaries of the study area. Additionally, a stop detection model is applied to these trajectories to identify nodes within maritime traffic networks. A decision tree algorithm is then employed to train a classifier for predicting traffic patterns. The method was validated in the convergent area of the Yangtze River and the Hanjiang River, demonstrating effective pattern extraction from inland maritime traffic and high accuracy in predicting single ship trajectories, achieving a 96.7% accuracy rate and 80.9% precision. The findings suggest that the proposed method (1) effectively extracts and predicts traffic patterns, (2) identifies congestion in convergent waters, and (3) supports traffic management strategies.