Figures & data
Table 1. Land use and soil types for the study watersheds.
Table 2. Meteorological and hydrometric stations used in this study.
Figure 2. Architecture of an ANFIS model (adapted from Jang Citation1993).
![Figure 2. Architecture of an ANFIS model (adapted from Jang Citation1993).](/cms/asset/f048a199-9e43-40ba-9de4-677a997f0c24/thsj_a_1367396_f0002_b.gif)
Table 3. Values of parameters for all rivers in the equation: SSC = a[turbidity]b.
Table 4. Performance of river-specific models using total flow (Qt), precipitation (P), surface runoff (qR), and watershed vulnerability index (Kr).
Figure 7. Scatter plots of observed vs computed SSC (validation phase) for input variables (a) P and Qt, and (b) P, Qt and Kr.
![Figure 7. Scatter plots of observed vs computed SSC (validation phase) for input variables (a) P and Qt, and (b) P, Qt and Kr.](/cms/asset/da0c4e1e-1c55-45a1-9102-68f55bbfc734/thsj_a_1367396_f0007_oc.jpg)
Table 5. Performance of the multi-watershed ANFIS model.
Figure 9. Boxplot of NS coefficient values obtained using 20 different random subsamples of input data to train the multi-watershed ANFIS model.
![Figure 9. Boxplot of NS coefficient values obtained using 20 different random subsamples of input data to train the multi-watershed ANFIS model.](/cms/asset/b41999c5-eecf-4c19-b4dc-a2ecb02c6995/thsj_a_1367396_f0009_oc.jpg)