ClaudiaShu/wea_mts

WEA数据集是从WeatherBench仓库派生出来的，用于多变量时间序列预测，包含了伦敦、纽约、香港、开普敦和新加坡五个城市的气象数据，时间跨度为1979年至2018年。该数据集具有6小时的时间分辨率和5.625°的空间分辨率。每个城市与其在WeatherBench网格上最近的网格点匹配。预测任务是预测850 hPa温度（T850），这是一个广泛使用的中对流层气候指标。数据集包括一个目标变量和44个外生变量，分为本地变量和空间上下文变量。数据集分为训练集、验证集和测试集，分别对应不同的年份。

The WEA dataset is derived from the WeatherBench repository and designed for Multivariable Time Series (MTS) forecasting, containing meteorological data from five geographically diverse cities: London, New York, Hong Kong, Cape Town, and Singapore, spanning from 1979 to 2018. It has a temporal resolution of 6 hours and a spatial resolution of 5.625°. The task is to forecast the 850 hPa temperature (T850), a widely used mid-tropospheric climate indicator. The dataset includes one target variable and 44 exogenous variables, categorized into local variables and spatial context variables. The dataset is split into training, validation, and test sets corresponding to different years.