使用MODIS近红外图像直接计算地表水汽压的研究——以贵州省为例

Study on Estimating Surface Vapor Pressure Directly from MODIS Near-infrared Images:A Case of Guizhou Region

为提高地形复杂区域地表水汽压的计算精度,同时避免间接法计算需要大气可降水量中间数据,以贵州省为例,研究使用MODIS近红外数据直接估算晴空地表水汽压。构建了指数、多项式、通道值线性组合、集成形式4种直接法模型,并分吸收通道、分遥感值(反射率与辐亮度)建立了24个回归公式,根据计算站的拟合结果筛选了最优的直接法模型,最后对比了直接法和间接法的计算精度。研究结果表明:采用集成第17通道与第2通道反射率比值和高程信息的直接法模型拟合精度最高,决定系数R^2为0.741,剩余标准差(RSE)为1.098 hpa;该直接法的绝对误差、相对误差的均值分别为1.234 hpa和8.2%,均低于间接法的1.806 hpa和12%。

In this paper,we present a method of obtaining instantaneous surface vapor pressure in complex terrain region.The proposed algorithm estimates surface vapor pressure over cloud-free land area using MODIS near-infrared data directly,instead of using MODIS total precipitable water data.Guizhou province is selected as study region.There are four direct models,exponential model,polynomial model,channels linear model and integrated model,are developed.In each model,we can choose one from three absorption channels(17,18 and 19),and choose one from two remote sensing images(reflectance and radiance).So twenty-four equations are built to calculate surface vapor pressure.According to the regression calculation of ground stations,we select the best fitting equation.We compare the errors between the direct method and the indirect method.The result shows the integrated model(equation 27)is the best fitting equation,which gives R^2 0.741 and residual standard error(RSE)1.098 hpa.This integrated model calculates surface vapor pressure using reflectance ratio of channel 17 to channel 2 and elevation information.The mean absolute error and mean relative error of this proposed direct method are 1.234 hpa and 8.2% respectively,which are lower than 1.806 hpa and 12% of indirect method.