Table 2.
Results of the ordinary least-squares polynomial regression (POLY) and artificial neural network (ANN). All statistics and metrics were derived from predictions on the left-out test experiment, i.e., measured concentrations that the model has never seen. Means of the metrics are provided with their standard deviation (SD). The root-mean-square error (RMSE) between the predictions and experimental measurements was less than 6% for all experiments.
| POLY | ANN | |||
|---|---|---|---|---|
| Experiment Number | RMSE (%) | R 2 | RMSE (%) | R 2 |
| E1 (0.44 mg/L) | 5.68 | 0.868 | 3.60 | 0.909 |
| E2 (4.38 mg/L) | 3.03 | 0.948 | 2.91 | 0.949 |
| E3 (17.5 mg/L) | 4.24 | 0.922 | 4.15 | 0.926 |
| E4 (35.1 mg/L) | 3.89 | 0.950 | 3.75 | 0.953 |
| E5 (52.6 mg/L) | 4.49 | 0.928 | 4.25 | 0.941 |
| E6 (70.1 mg/L) | 3.43 | 0.962 | 3.14 | 0.967 |
| E7 (87.6 mg/L) | 3.93 | 0.945 | 3.03 | 0.970 |
| Mean ± SD | 4.10 ± 0.850 | 0.932 ± 0.031 | 3.55 ± 0.539 | 0.945 ± 0.022 |