汉江中下游典型河段水环境遥感评价  

Remote Sensing Assessment of Water Quality for Typical Segments in the Middle and Lower Reaches of Hanjiang River

作　　者：肖潇[1,2] 徐坚[2] 赵登忠[2] 胡承芳[2] 汪朝辉[2] 程学军[2] 

机构地区：[1]武汉大学资源环境与科学学院,武汉430079 [2]长江科学院空间信息技术应用研究所,武汉430010

出　　处：《长江科学院院报》2016年第1期31-37,共7页Journal of Changjiang River Scientific Research Institute

基　　金：国家自然科学基金项目(41201452;41301435);科技部国家国际合作专项项目(2012DFR70760);国家软科学研究计划项目(2012GXS2B008);长江科学院中央级公益性科研院所基本科研业务费(CKSF2012029/KJ;CKSF2014035/KJ;CKSF2014032/KJ)

摘　　要：选择汉江中下游典型河段作为研究区域,利用2012年春、夏、秋3季水质采样结果及HJ1A卫星CCD同步多光谱数据,建立了研究区总氮浓度BP神经网络反演模型,并根据反演结果对研究区进行水质状况评价。研究结果表明:基于弹性BP训练算法(启发式训练算法)的BP神经网络模型反演精度高,适用性强,可真实反映研究区总氮浓度在不同河段及不同季节中的变化情况,可较好地利用国产卫星数据开展流域水质评价工作。水质评价结果表明研究区在不同季节和不同区域水质差异较大,研究区春季总氮指标严重超标,夏、秋2季指标优于春季,下游指标优于上游。Typical segments in the middle and lower reaches of Hanjiang River were taken as study areas for water quality. According to sampling results and synchronized multi-spectral CCD data of HJ-1A satellite in spring,summer and autumn of 2012,we establish a retrieval model of BP neural network for TN（ total nitrogen） concentration,and assess water quality of the study areas based on the retrieval results. The results show that,on the basis of resilient BP training algorithm（ heuristic-based training algorithm）,the retrieval model of BP neural network established is of high accuracy and wide application fields,which can truly reflect the changes in TN concentration in different reaches and different seasons,and is easy to utilize domestic satellite data to carry out assessment work of water quality; furthermore,assessment results indicate that water quality of the research areas varies a lot with seasons and reaches： the value of TN indicator in spring significantly exceeds standard value,in other words,value of this indicator in summer or autumn is lower than that in spring. Finally,concentration of TN of downstream area is lower than that of upstream area.

关 键 词：汉江中下游 典型河段 水质评价 神经网络 多光谱数据 遥感反演模型 

分 类 号：X87[环境科学与工程—环境工程] X824