Estimation of Suspended Sediment Concentration Using Remote Sensing Technique and M5 Model Tree

Estimation of suspended sediment concentration (SSC) is one of the most important issues of river engineering, which can be used as an indicator of land use change, water quality studies and all projects related to constructions in the rivers. In this research, M5 model tree and the Moderate Resolution Imaging Spectroradiometer (MODIS) data have been used to estimate the SSC at Ahvaz station on the Karun River. In this study, 135 cloud free images of the MODIS sensor on the Terra satellite were obtained for days corresponding to field measurements of SSC for the years 2000 to 2015. Input parameters of the model tree in this study were flow discharge derived from hydrological data and red (R), near infrared (NIR) bands and NIR/R ratio extracted from MODIS imagery. Three regression equations have been developed by M5 model tree to estimate SSC at Ahvaz station, which can be employed in different conditions of discharge and NIR/R ratio. The results of statistical analysis illustrates that the M5 model outperforms the sediment rating curve (SRC) method, which is the most common method of estimating suspended sediment load. Nash-Sutcliffe efficiency index for the M5 model tree of 0.58 has been achieved which was much better than that of SRC method (0.24). At high fluxes, the efficiency of the SRC method is significantly reduced, while the model tree provides acceptable results. Global sensitivity analysis on M5 model showed that, 93% of output variance just determined by the main effects of input parameters and less than 7% belong to the interaction effects. 73% and 12% of output variance specified by the main effects of flow discharge and NIR/R ratio, respectively.