Table 3 Result of the R\(^2\), MAE and MSE metrics applied to the forecast results for the analyzed models.
From: A machine learning approach to analyse ozone concentration in metropolitan area of Lima, Peru
Station/model | R\(^2\) | MAE | MSE |
|---|---|---|---|
ATE station | |||
LR | 0.9923 | 0.0724 | 0.0058 |
SVM | 0.9913 | 0.0643 | 0.0065 |
DT | 0.9478 | 0.1648 | 0.0392 |
RF | 0.8753 | 0.2373 | 0.0937 |
MLP | 0.906 | 0.2481 | 0.0706 |
CDM station | |||
LR | 0.9892 | 0.0486 | 0.0036 |
SVM | 0.9844 | 0.0702 | 0.0052 |
DT | 0.873 | 0.1915 | 0.0424 |
RF | 0.7576 | 0.2286 | 0.0809 |
MLP | 0.9246 | 0.1352 | 0.0251 |
SB station | |||
LR | 0.9849 | 0.0847 | 0.0087 |
SVM | 0.9814 | 0.0923 | 0.0107 |
DT | 0.8728 | 0.199 | 0.0729 |
RF | 0.9699 | 0.096 | 0.0172 |
MLP | 0.419 | 0.5149 | 0.3332 |
STA station | |||
LR | 0.9909 | 0.0758 | 0.006 |
SVM | 0.9933 | 0.0501 | 0.0044 |
DT | 0.8349 | 0.2497 | 0.1081 |
RF | 0.8203 | 0.2842 | 0.1176 |
MLP | 0.9452 | 0.1783 | 0.0359 |
