### Table 2 Prediction of bed load transport rate within a factor of 2 and 5 of the measured values and root-mean-square errors using current data Author(s) All data All data except

2004

"... In PAGE 3: ... Since uncertainties already exist in the measurements of the bed load sediment transport (especially for field measurements), a prediction within a factor 2 of the experimental data is usually considered to be a satisfac- tory result. In Table2 , the percentage of predicted values included within a factor of 2 or a factor of 5 deviation is presented (Px2 and Px5, respectively), as well as the root-mean-square error defined as Erms Z 1/n P(log(qs,pred/qs,meas))2. To avoid any distortion in the calculation of Erms for very low transport (where qs,pred or qs,meas could be found equal to zero), a minimum value for qs,pred and qs,meas is used (qs,min Z 10C2558m2/s).... In PAGE 4: ... data), which increase the results by 10% compared to previous formulas (cf. Table2 ). The new relationship tends to overestimate the transport rate when qc(qcr (see Fig.... ..."

### TABLE IV IMPROVEMENTS (%) ON MEAN SQUARED ERROR

2005

Cited by 9

### Table 3. Mean Squared Error (MSE).

2001

Cited by 2

### Table 1. Mean Square Error on Test Dataset

2005

"... In PAGE 7: ... Note that this does not include the Bayesian moderated outputs as they are evaluated in a separate experiment. The results are shown in Table1 . For all four detectors, the Bayesian neural network consistently performs better regardless of type of input feature.... ..."