Single Ground Based AIS Receiver Vessel Tracking Dataset

Nowadays, a multitude of tracking systems produce massive amounts of maritime data on a daily basis. The most commonly used is the Automatic Identification System (AIS), a collaborative, self-reporting system that allows vessels to broadcast their identification information, characteristics and destination, along with other information originating from on-board devices and sensors, such as location, speed and heading. AIS messages are broadcast periodically and can be received by other vessels equipped with AIS transceivers, as well as by on the ground or satellite-based sensors. Since becoming obligatory by the International Maritime Organisation (IMO) for vessels above 300 gross tonnage to carry AIS transponders, large datasets are gradually becoming available and are now being considered as a valid method for maritime intelligence [4].There is now a growing body of literature on methods of exploiting AIS data for safety and optimisation of seafaring, namely traffic analysis, anomaly detection, route extraction and prediction, collision detection, path planning, weather routing, etc., [5]. As the amount of available AIS data grows to massive scales, researchers are realising that computational techniques must contend with difficulties faced when acquiring, storing, and processing the data. Traditional information systems are incapable of dealing with such firehoses of spatiotemporal data where they are required to ingest thousands of data units per second, while performing sub-second query response times. Processing streaming data seems to exhibit similar characteristics with other big data challenges, such as handling high data volumes and complex data types. While for many applications, big data batch processing techniques are sufficient, for applications such as navigation and others, timeliness is a top priority; making the right decision steering a vessel away from danger, is only useful if it is a decision made in due time. The true challenge lies in the fact that, in order to satisfy real-time application needs, high velocity, unbounded sized data needs to be processed in constraint, in relation to the data size and finite memory. Research on data streams is gaining attention as a subset of the more generic Big Data research field. Research on such topics requires an uncompressed unclean dataset similar to what would be collected in real world conditions. This dataset contains all decoded messages collected within a 24h period (starting from 29/02/2020 10PM UTC) from a single receiver located near the port of Piraeus (Greece). All vessels identifiers such as IMO and MMSI have been anonymised and no down-sampling procedure, filtering or cleaning has been applied. The schema of the dataset is provided below: · t: the time at which the message was received (UTC) · shipid: the anonymized id of the ship · lon: the longitude of the current ship position · lat: the latitude of the current ship position · heading: (see: https://en.wikipedia.org/wiki/Course_(navigation)) · course: the direction in which the ship moves (see: https://en.wikipedia.org/wiki/Course_(navigation)) · speed: the speed of the ship (measured in knots) · shiptype: AIS reported ship-type · destination: AIS reported destination如今，各类船舶追踪系统每日都会生成海量海事数据。其中应用最广泛的当属自动识别系统（Automatic Identification System, AIS），这是一种协作式自主报告系统，允许船舶播发自身识别信息、船舶属性与航行目的地，同时同步传输来自船载设备与传感器的其他数据，如实时位置、航速与航向。AIS报文会周期性播发，可被配备AIS收发机的其他船舶接收，也可由地面或星载传感器捕获。 自国际海事组织（International Maritime Organisation, IMO）要求总吨位300以上的船舶强制安装AIS应答机以来，大规模AIS数据集逐渐得以积累，如今该类数据已被视为海事情报研究的可靠数据源[4]。当前，针对利用AIS数据提升航海安全与优化航行效率的研究正日益增多，具体涵盖交通分析、异常检测、航线提取与预测、碰撞预警、路径规划、气象航线规划等诸多方向[5]。 随着可用AIS数据规模持续扩张至海量级别，研究者们意识到，相关计算技术亟需应对数据采集、存储与处理过程中的诸多挑战。传统信息系统无法应对这类近乎“洪流”的时空数据：既要实现每秒数千条数据的吞吐量，又要保证亚秒级的查询响应速度。 流数据处理与其他大数据挑战具有诸多共性，例如需应对高数据体量与复杂数据类型。尽管许多场景下，大数据批处理技术已能满足需求，但对于航海导航等应用而言，实时性才是首要目标：规避船舶危险的正确决策，唯有在恰当时机作出才具备实际价值。真正的难点在于，为满足实时应用需求，需在有限的数据存储与内存资源约束下，处理高速、无边界的流式数据。作为通用大数据研究领域的分支，数据流处理相关研究正受到广泛关注。 此类研究需要与真实采集场景一致的未压缩、未清洗数据集。本数据集包含2020年2月29日UTC22:00起24小时内，部署于希腊比雷埃夫斯港附近的单台接收器捕获的所有解码AIS报文。所有船舶标识符（如IMO与MMSI）均已完成匿名化处理，且未对数据进行下采样、过滤或清洗操作。 本数据集的字段结构如下： · t：报文接收时刻（UTC时间） · shipid：船舶匿名ID · lon：船舶当前位置经度 · lat：船舶当前位置纬度 · heading：（定义详见：https://en.wikipedia.org/wiki/Course_(navigation)） · course：船舶航行方向（定义详见：https://en.wikipedia.org/wiki/Course_(navigation)） · speed：船舶航速（单位：节） · shiptype：AIS报告的船舶类型 · destination：AIS报告的航行目的地