AIS dataset containing weather and ocean conditions

The AIS dataset is provided by the National Oceanic and Atmospheric Administration (NOAA), spanning from January 2020 to December 2020. The trajectories of 140 individual vessels (including tankers and cargo) were collected. Weather and ocean conditions for the same period are obtained from the National Data Buoy Center (NDBC), collected from 15 buoys. Noise points were removed, and the linear interpolation method was applied to address the irregular time intervals and the absent points.   Then the time series were resampled at one-minute time steps.   The buoys data had undergone outlier cleaning, linear interpolation, and resampling at one-minute time steps. The time series of weather and ocean conditions were constructed by assigning the nearest buoy to the vessels along its trajectory.本自动识别系统（Automatic Identification System，AIS）数据集由美国国家海洋和大气管理局（National Oceanic and Atmospheric Administration，NOAA）提供，时间跨度为2020年1月至2020年12月。该数据集涵盖140艘独立船舶（包括油轮与货轮）的航行轨迹数据。同期的气象与海洋环境数据取自国家数据浮标中心（National Data Buoy Center，NDBC），由15个海洋浮标采集得到。首先对原始数据进行噪声点剔除，并采用线性插值方法处理不规则时间间隔与缺失数据点，随后将船舶轨迹时间序列以1分钟为步长进行重采样。浮标观测数据同样经过了异常值清洗、线性插值以及1分钟步长的重采样处理。最终通过为航行轨迹中的船舶匹配距离最近的浮标，构建得到对应船舶的气象与海洋条件时间序列。