Skip to main content

Table 4 Fitting statistics of the LURF models trained to predict NO2 concentrations on Milan and Rome according to the different scenarios

From: A multi-step machine learning approach to assess the impact of COVID-19 lockdown on NO2 attributable deaths in Milan and Rome, Italy

  

OOB-R2

RMSE

pred-R2

RMSPE

Inter

slope

Milan

Scenario 1

0.42

4.5

0.42

3.4

19.4

0.42

Scenario 2

0.42

5.1

0.42

3.9

21.9

0.42

Rome

Scenario 1

0.46

6.6

0.46

5.2

22.6

0.42

Scenario 2

0.46

7.8

0.46

6.2

26.7

0.41