黑河流域土壤含水量遥感反演及不同地类土壤水分效应分析

The study of the soil moisture retrieval and effects of different land-use types in Heihe River Basin

利用NASA提供的MOD IS数据产品和黑河流域的野外实测数据,在充分考虑研究区的下垫面特征、数据的时间特性和遥感反演土壤含水量的模型与算法的基础上,采用了热惯量法,计算了表观热惯量,并与实测数据进行回归分析建模,反演了整个黑河流域的土壤含水量。随后构建了三个区域土壤水分效应评价指标:土壤水分单元权重指数、区域土壤水分单元权重指数和土壤水分效应贡献度,结合黑河流域的土地利用状况,定量评价了不同土地利用类型的土壤水分效应。研究表明:利用MOD IS数据产品,反演参量获取简单,可降低反演土壤含水量的复杂性,有利于大、中尺度的实际应用;利用当地积累的季节标准日变化曲线将温差修正到最大值,使反演的表观热惯量更接近真实,可提高模型精度;用多个地面采样点的土壤含水量均值与一个像元对应建模,能改善因MOD IS数据空间分辨率低而存在大量混合像元致使反演精度降低的问题;在黑河流域,中覆盖度草地、有林地、高覆盖度草地、水田等用地类型的土壤水分效应最为明显,贡献最大。

The research used the MODIS data products provided by NASA and the soil moisture data measured from the field data in Heihe River Basin. Taking full account of the surface feature of the study area, time feature of the data and the model and algorithm of soil moisture retrieval by remote sensing, the thermal inertia was adopted to calculate the apparent thermal inertia （ATI）. Then ATI and soil moisture were used to build experience model by regression analysis. At last the soil moisture of whole Heihe River Basin was successfully retrieved by this model. Then three soil moisture effect estimating indices （soil moisture pixels proportion index, regional soil moisture pixels proportion index, soil moisture effect contribution index） were designed to quantitatively evaluate soil moisture effects of the different land - use types by combination of the Heihe River Basin land - use map. The results showed that： using MODIS products provided by NASA could predigest the retrieval parameters and reduce the complex of soil moisture retrieval, and ensure the application for large, middle - scale region ; using the local standards accumulation season temperature curves to modify the temperature range could make Apparent Thermal Inertia （ATI） more realistic and improve the accuracy of the model ; the average of a number of the spots soil moisture corresponding to a pixel to build experiential model building could, improve the lower accuracy problem of the retrieval model due to many mixed pixel because low spatial resolution of MODIS data. For Heihe River Basin, the soil moisture effect of middle coverage grasslands, woodland, high coverage grassland and paddy fields are the most obvious and they make the biggest contributions.