薄板光顺样条插值与中国气候空间模拟

Modeling Spatial Distribution of Climate in China Using Thin Plate Smoothing Spline Interpolation

利用720个气象台网的长期平均气象数据拟合具有三维地理空间的气候曲面,并与1km空间分辨率的数字高程模型相结合,对气候变量的规则栅格进行插值估计。对各月平均最低温度、平均最高温度和降水量的插值结果构成了基础数字气候空间,以满足地理信息系统的数据分析需求。插值过程提供的误差统计表明插值的温度误差普遍小于0.6度,降水误差范围在8%～15%,明显优于其它插值方法。样条法利用线性模型反映地形对气候的影响,并提供了简便的误差诊断程序,具有良好的实用性。

Understanding of climate spatial distribution depending on topography is the key to environmental and resource management. However, there is a limit to factor climate into ecological study because most climatic data are obtained from a sparse, irregularly distributed meteorological network with unchecked data errors. Interpolation technique for estimating climate at any location from data points is demanded. This paper demonstrated the generation of gridded climate data in regular space by coupling thin plate smoothing spline surfaces of monthly mean minimum temperature, mean maximum temperature and precipitation to underlying 1 km resolution digital elevation model (DEM) for China. The thin plate smoothing spline involves topographically dependence of climate with linear sub-model for accurate interpolation. It provides a series of diagnostic procedures for data error detection and correction. The predictive errors of temperature are within 0.6℃ and for precipitation in range of 6%-12%. The data of other climate variables with biological meanings can be derived directly from interpolated surfaces and grids. The developed regular grid of climate will be used primarily as unchanged climate condition for study of climate change. There are various potential applications in spatial prediction of flora species, identifying priority areas of biodiversity and development of ecoregions.