针对温瑞塘河水质监测中成本较高、监测点有限等特点,基于遥感技术和数理分析的基本理论,以温瑞塘河为研究对象,利用高分辨率遥感数据和实测水质数据建立了总氮和总磷两个水质参数的遥感反演模型,并对温瑞塘河的主要超标指标总磷和总氮进行了遥感反演。结果表明,对于总氮,多元线性回归模型和人工神经网络模型预测结果与实测值平均相对误差分别为15.45%和6.70%;对于总磷,平均相对误差分别为13.91%和13.62%。两种反演模型均能有效地监测温瑞塘河水质状况和空间分布情况,水质遥感反演模型具有深入研究和推广的价值。
Aiming at the disadvantages of high-cost and limited monitoring sites of Wenzhou water quality monitoring and taking Wenruitang River as a study area, this paper develops multiple linear regressions (MLR) and artificial neural network (ANN) models to estimate TN and TP concentrations from high spatial resolution remote sensing imagery and in-situ water samples collected concurrently with an over-passing satellite.The average relative errors of MLR and ANN are respectively 15.45% and 6.70% for TN, while 13.91% and 13.62% for TP. Two models are effective for monitoring water quality state and spatial distribution of Wen-Rui Tang River with the value of in-depth research and extension.