基于城市化偏差订正的中国大陆1961-2015年月平均地面气温网格数据集

Monthly Mean Surface Air Temperature 2°×2° Grid Dataset in China(1961-2015)

基于中国气象局国家气象信息中心提供的国家级地面气象站均一化气温月值数据,选择763个国家站的数据;以目标站周围300 km范围内的站点为参考站,利用参考站和目标站去线性趋势年平均气温序列的相关系数判定,取相关系数最大,并且显著性水平为0.005的显著性检验的4个参考站作为该目标站的参考站;然后,以各个参考站与其目标站年平均气温序列相关系数的平方为权重,计算参考站月平均气温加权平均值,即为参考序列;再利用城市站序列趋势和参考序列趋势的差值作为订正值,对目标站进行线性订正;最后,利用反距离权重插值法将全国范围763个站点的气温数据插值成2°×2°的格点数据。以北京、武汉、银川、深圳作为华北、华中、西北和华南地区的大城市代表站,发现其在过去55年的相对城市化偏差分别为67.0%、75.4%、32.7%和50.3%,与前人针对单站评估城市化影响的结果基本一致。该数据集存储为.txt格式,每个文件按照年月命名,每个文件由头文件和18行、32列的平均气温(℃)数据组成,前6行是头文件,分别为列数,行数,左下角格点经度,左下角格点纬度,网格大小,缺测值。数据集由660个数据文件组成,数据量为2.75 MB(压缩为1个文件,895 KB)。

Based on the national surface meteorological station homogenized monthly temperature dataset provided by the National Meteorological Information Center of China Meteorological Administration,the 684 meteorological stations were selected as the target stations.First,establish a reference sequence for each target station.Then,use the difference between the target station sequence trend and the reference sequence trend as the correction value to linearly correct the temperature series of target station,using the corrected 684 target stations plus 79 rural stations for a total of 763 stations.Finally,the inverse distance weight interpolation method was used to interpolate the temperature data of 763 stations nationwide into 2°x 2°grid point data.The research results shows that taking Beijing,Wuhan,Yinchuan,and Shenzhen as representative stations of large cities in North China,Central China,Northwest China,and South China,it was found that their relative urbanization bias in the past 55 years were 67.0%,75.4%,32.7%,and 50.3%,respectively.This matched the results of assessing of the impact of urbanization on a single station by predecessors basically.The dataset was archived in.txt format.Each file name was titled according to the year and month.Each file consisted of a header file and 18 rows and 32 columns of average temperature(oC)data.The first 6 rows were header files,which were the number of columns and rows,the longitude of the bottom left grid point,the latitude of the bottom left grid point,the grid size,and the missing value.The dataset consisted of 660 data files with data size of 2.75 MB(compressed into 1 file,895 KB).