Table 2 Model adaptation performance results for predicting online TV, AdV, and PMMoV concentrations across different wastewater matrices
From: Viral particle prediction in wastewater treatment plants using nonlinear lifelong learning models
Model | Set | Total Virus | AdV | PMMoV | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
R² | RMSE | MAE | MSE | R² | RMSE | MAE | MSE | R² | RMSE | MAE | MSE | ||
LSTM | Train | 0.903 | 0.118 | 0.074 | 0.014 | 0.980 | 0.100 | 0.070 | 0.010 | 0.955 | 0.182 | 0.126 | 0.033 |
Test | 0.861 | 0.136 | 0.081 | 0.019 | 0.937 | 0.174 | 0.110 | 0.030 | 0.942 | 0.219 | 0.152 | 0.048 | |
Adaptation 1 (aerobic) | 0.955 | 0.020 | 0.015 | 0.001 | 0.940 | 0.186 | 0.138 | 0.038 | 0.942 | 0.213 | 0.155 | 0.050 | |
Adaptation 2 (sand) | 0.930 | 0.039 | 0.028 | 0.002 | 0.859 | 0.164 | 0.118 | 0.028 | 0.867 | 0.247 | 0.183 | 0.065 | |
Adaptation 3 (MBR) | 0.965 | 0.016 | 0.012 | 0.0008 | 0.907 | 0.080 | 0.059 | 0.007 | 0.935 | 0.111 | 0.082 | 0.014 | |
