Research Article
Forecasting Water Demand in Residential, Commercial, and Industrial Zones in Bogotá, Colombia, Using Least-Squares Support Vector Machines
Table 1
Statistical performance of LS-SVM and FNN-BPM models.
| Land use | LS-SVM | FNN-BP | RMSE | AARE (%) | | RMSE | AARE (%) | |
| R1 | 0.0081 | 6.45 | 0.93 | 0.0104 | 8.55 | 0.88 | R2 | 0.0023 | 3.54 | 0.96 | 0.0048 | 5.61 | 0.93 | R3 | 0.0089 | 7.5 | 0.92 | 0.0119 | 9.56 | 0.50 | R4 | 0.0194 | 11.58 | 0.91 | 0.0387 | 13.71 | 0.90 | R5 | 0.0078 | 7.65 | 0.98 | 0.1258 | 15,85 | 0.97 | R6 | 0.4005 | 23.0 | 0.8 | 0.598 | 25.87 | 0.67 | Industrial | 0.0043 | 5.86 | 0.94 | 0.0052 | 6.3 | 0.82 | Commercial | 0.0012 | 2.69 | 0.98 | 0.0034 | 4.47 | 0.84 |
|
|