Data Analytics Enables Advanced AIS Applications

Improving maritime traffic surveillance in inland waterways using the robust fusion of AIS and visual data

AIS (Automatic Identification System) data received from moving vessels over an area of interest can be of very much interest for deriving maritime trajectory patterns. In this paper, a novel approach to extract course patterns from AIS data of vessels is presented. From machine learning and natural language processing principles, a topic model might be used for extracting implicit patterns underlying massive and unstructured collection of incoming data. To apply topic model to AIS data, PQk-means vector quantization to convert AIS data record to code documents is introduced. Then, a topic model is applied to extract course patterns from AIS data. In fact, courses, not only encompasses trajectory locations, but also headings and speeds, are recognized by the proposed algorithm. The performance of PQk-means is evaluated using the relative root mean square error and elapsed time. The potential of the approach is illustrated by a series of experimental results derived from practical AIS data set in a region of North West France.

A ship movement classification based on Automatic Identification System (AIS) data using Convolutional Neural Network

We investigated ship navigation records known as Automatic Identification System (AIS) data near the source region of the 2011 Tohoku, Japan, tsunami. The AIS data of 16 ships in the offshore navigation could be compiled by about 40 min after the tsunami generation. Most of the AIS data showed notable deviation of the ship heading from the course over ground during the tsunami passage. There was good agreement in terms of amplitude/phase between the ship velocity and the simulated tsunami velocity in the direction normal to the ship heading. An equation of motion due to wave drag and inertia forces was examined for an offshore movable floating body. We explain that the ship movement in the direction normal to the heading immediately responds to the tsunami current, and relative velocity between the ship and the tsunami current asymptotically become zero. This indicates the movement velocity of navigating ships in the direction normal to the heading derived from AIS data will work as an offshore tsunami current meter. We examined the AIS data during the 2011 Tohoku tsunami and showed these data could be useful for tsunami source estimation and forecast. The AIS data in the current framework will possibly be a crowd-sourced tool for monitoring offshore tsunami current and tsunami forecast.

Modeling is a promising approach to understand and predict the safety and efficiency of maritime traffic in ports and waterways. Different types of models have been developed over the years. Nevertheless, several important scientific challenges still remain. For instance, few models consider vessel behavior in ports and waterways under the influence of internal factors including vessel type and size, and external factors, such as wind and visibility. More data and research are needed to understand the influence of internal and external factors on vessel behavior including speed, course and path in ports and waterways; more research is also needed to explore human behavior of the bridge team for vessel maneuvering in ports and waterways. To address the needs listed, this thesis focuses on analyzing the influence of wind, visibility, current and vessel encounters on vessel speed, course and path using Automatic Identification System (AIS) data. Based on this analysis a new maritime traffic model has been developed that considers both internal and external factors, and aims to better predict the individual vessel behavior. The model can be used to provide data for the safety and efficiency assessment of vessel traffic in ports and inland waterways. In the last decades, the AIS system, which is an onboard autonomous and continuous broadcast system that transmits vessel data between nearby vessels and shore stations, has been developed. This is used now by almost all vessels. Therefore, AIS data, including vessel speed, course and path, can serve as a valuable data source to investigate vessel behavior. In this thesis, AIS data from a part of the port of Rotterdam is analyzed to investigate influences of different factors, such as vessel size and type, external conditions and vessel encounters, on vessel behavior. Firstly, vessels are distinguished into influenced and unhindered vessels based on certain thresholds that we obtained from the AIS data. The influenced vessel behavior is compared with the behavior of unhindered vessels, which are not influenced by other vessels or strong external influences of wind, visibility and current. The analysis provides evidence showing that the vessel behavior including vessel speed, course and path is influenced by various factors. Ship speed and path is influenced by internal factors (including vessel type, size, waterway geometry and navigation direction) and external factors (including wind, visibility, current, overtaking and head-on encounters), while ship course is only influenced by overtaking and head-on encounters. It can also be concluded that the AIS data is a useful source to get insights into vessel behavior.

Understanding the distribution of fishing activity is fundamental to quantifying its impact on the seabed. Vessel monitoring system (VMS) data provides a means to understand the footprint (extent and intensity) of fishing activity. Automatic Identification System (AIS) data could offer a higher resolution alternative to VMS data, but differences in coverage and interpretation need to be better understood. VMS and AIS data were compared for individual scallop fishing vessels. There were substantial gaps in the AIS data coverage; AIS data only captured 26% of the time spent fishing compared to VMS data. The amount of missing data varied substantially between vessels (45–99% of each individuals' AIS data were missing). A cubic Hermite spline interpolation of VMS data provided the greatest similarity between VMS and AIS data. But the scale at which the data were analysed (size of the grid cells) had the greatest influence on estimates of fishing footprints. The present gaps in coverage of AIS may make it inappropriate for absolute estimates of fishing activity. VMS already provides a means of collecting more complete fishing position data, shielded from public view. Hence, there is an incentive to increase the VMS poll frequency to calculate more accurate fishing footprints.

In the field of underwater target detection, the passive sonar is an important means of long‐distance target detection. The sonar detection information typically includes both surface and underwater targets, whereas it is a great challenge on effectively distinguishing between surface and underwater targets solely based on sonar information. Effective fusion of sonar and AIS (Automatic Identification System) data can leverage their complementary nature to compensate for the limitation of sonar information. However, the sonar information and AIS information are acquired based on different detection principles and systems, which are essentially multi‐source heterogeneous information with obvious spatio‐temporal misalignment in nature. Existing fusion methods normally struggle to effectively align sonar and AIS data in both time and space subject to the complexity of the problem. In this study, the Dynamic Time Warping (DTW) algorithm is applied to align sonar and AIS data in the time domain. In addition, a deep learning algorithm with multi‐head attention mechanism is proposed to achieve the spatial alignment of sonar and AIS data, where the matching between the surface targets in AIS data and the same surface targets in sonar data can also be successfully achieved. It provides a priori knowledge to enhance the underwater target detection of the passive sonar by eliminating the interference of the surface targets. Based on the attention mechanism, the abstract features extracted from the intermediate‐layer of the neural networks are found to be effective to represent the typical features of the target motion trajectories, which also demonstrates the effectiveness of the attention mechanism. The experiment results show that the proposed method can successfully achieve a MatchingSucccessRate of over 95% between the AIS targets and sonar detection targets.

Maritime situational awareness at over-the-horizon (OTH) distances in exclusive economic zones can be achieved by deploying networks of high-frequency OTH radars (HF-OTHR) in coastal countries along with exploiting automatic identification system (AIS) data. In some regions the reception of AIS messages can be unreliable and with high latency. This leads to difficulties in properly associating AIS data to OTHR tracks. Long history records about the previous whereabouts of vessels based on both OTHR tracks and AIS data can be maintained in order to increase the chances of fusion. If the quantity of data increases significantly, data cleaning can be done in order to minimize system requirements. This process is performed prior to fusing AIS data and observed OTHR tracks. In this paper, we use fuzzy functional dependencies (FFDs) in the context of data fusion from AIS and OTHR sources. The fuzzy logic approach has been shown to be a promising tool for handling data uncertainty from different sensors. The proposed method is experimentally evaluated for fusing AIS data and the target tracks provided by the OTHR installed in the Gulf of Guinea.

Determination of AIS Position Accuracy and Evaluation of Reconstruction Methods for Maritime Observation Data

Low quality automatic identification system (AIS) data often mislead analysts to a misunderstanding of ship behavior analysis and to making incorrect navigation risk assessments. It is therefore necessary to accurately understand and judge the quality problems in AIS data before a further analysis of ship behavior. Outliers were filtered in the existing methods of AIS quality analysis based only on mathematical models where AIS data related quality problems are not utilized and there is a lack of visual exploration. Thus, the human brain’s ability cannot be fully utilized to think visually and for reasoning. In this regard, a visual analytics (VA) approach called AIS Data Quality visualization (ADQvis) was designed and implemented here to support evaluations and explorations of AIS data quality. The system interface is overviewed and then the visualization model and corresponding human-computer interaction method are described in detail. Finally, case studies were carried out to demonstrate the effectiveness of our visual analytics approach for AIS quality problems.

In this paper, we present an automated process for detecting the anomaly in Automatic Identification System (AIS) data. Machine learning approaches have been employed to automatically detect anomalies in the AIS data. The opensource AIS data is been used to evaluate the performance of the proposed approach. Supervised machine learning approaches like K Nearest Neighbor, Random Forest, Support Vector Machine classifier is employed to predict the anomalies in the AIS data. The AIS data does not contain the ground truth labels and supervised learning algorithms need labelling data, to address this issue, we employed an unsupervised approach to label the data based on the prior information and characteristics of the AIS data. The labelled data is then used to train the supervised machine learning models. The proposed approach with support vector machine classifier has classified the AIS data into normal and anomaly with an accuracy of 96.5%.KeywordsAISMachine learningCourse Over Ground (COG)International Maritime Organization (IMO)Maritime Mobile Service Identity (MMSI)Ship attacksSpeed Over Ground (SOG)

Automatic Identification System (AIS) data stream analysis is based on the AIS data of different vessel’s behaviours, including the vessels’ routes. When the AIS data consists of outliers, noises, or are incomplete, then the analysis of the vessel’s behaviours is not possible or is limited. When the data consists of outliers, it is not possible to automatically assign the AIS data to a particular vessel. In this paper, a clustering method is proposed to support the AIS data analysis, to qualify noises and outliers with respect to their suitability, and finally to aid the reconstruction of the vessel’s trajectory. In this paper, clustering results have been obtained using selected algorithms, including k-means, k-medoids, and fuzzy c-means. Based on the clustering results, it is possible to decide on the qualification of data with outliers and on their usefulness in the reconstruction of the vessel trajectory. The main aim of this paper is to answer how different distance measures during a clustering process can influence AIS data clustering quality. The main core question is whether or not they have an impact on the process of reconstruction of the vessel trajectories when the data are damaged. The research question during the computational experiments asked whether or not distance measure influence AIS data clustering quality. The computational experiments have been carried out using original AIS data. In general, the experiment and the results confirm the usefulness of the cluster-based analysis when the data include outliers that are derived from the natural environment. It is also possible to monitor and to analyse AIS data using clustering when the data include outliers. The computational experiment results confirm that the k-means with Euclidean distance has the best performance.

New developments in small spacecraft capabilities will soon enable formation-flying constellations of small satellites, performing cooperative distributed remote sensing at a fraction of the cost of traditional large spacecraft missions. As part of ongoing research into applications of formation-flight technology, recent work has developed a mission concept based on combining synthetic aperture radar (SAR) with automatic identification system (AIS) data. Two or more microsatellites would trail a large SAR transmitter in orbit, each carrying a SAR receiver antenna and one carrying an AIS antenna. Spaceborne AIS can receive and decode AIS data from a large area, but accurate decoding is limited in high traffic areas, and the technology relies on voluntary vessel compliance. Furthermore, vessel detection amidst speckle in SAR imagery can be challenging. In this constellation, AIS broadcasts of position and velocity are received and decoded, and used in combination with SAR observations to form a more complete picture of maritime traffic and identify potentially non-cooperative vessels. Due to the limited transmit power and ground station downlink time of the microsatellite platform, data will be processed onboard the spacecraft. Herein we present the onboard data processing portion of the mission concept, including methods for automated SAR image registration, vessel detection, and fusion with AIS data. Georeferencing in combination with a spatial frequency domain method is used for image registration. Wavelet-based speckle reduction facilitates vessel detection using a standard CFAR algorithm, while leaving sufficient detail for registration of the filtered and compressed imagery. Moving targets appear displaced from their actual position in SAR imagery, depending on their velocity and the image acquisition geometry; multiple SAR images acquired from different locations are used to determine the actual positions of these targets. Finally, a probabilistic inference model combines the SAR target data with transmitted AIS data, taking into account nearest-neighbor position matches and uncertainty models of each observation.

A novel method for restoring the trajectory of the inland waterway ship by using AIS data

This paper develops a Takagi-Sugeno fuzzy observer gain design algorithm to estimate ship motion based on Automatic Identification System (AIS) data. Nowadays, AIS data is widely applied in the maritime field. To solve the problem of safety, it is necessary to accurately estimate the trajectory of ships. Firstly, a nonlinear ship dynamic system is considered to represent the dynamic behaviors of ships. In the literature, nonlinear observer design methods have been studied to estimate the ship path based on AIS data. However, the nonlinear observer design method is challenging to create directly since some dynamic ship systems are more complex. This paper represents nonlinear ship dynamic systems by the Takagi-Sugeno fuzzy model. Based on the Takagi-Sugeno fuzzy model, a fuzzy observer design method is developed to solve the problem of estimating using AIS data. Moreover, the observer gains of the fuzzy observer can be adjusted systemically by a novel algorithm. Via the proposed algorithm, a more suitable or better observer can be obtained to achieve the objectives of estimation. Corresponding to different AIS data, the better results can also be obtained individually. Finally, the simulation results are presented to show the effectiveness and applicability of the proposed fuzzy observer design method. Some comparisons with the previous nonlinear observer design method are also given in the simulations.