A Machine Learning Approach to Predict Air Quality in California

Figure 11

(a) Sulfur dioxide forecasts in California using the produced SVR forecasting models as well as the observed SO₂ values. The black line shows the observed values and the red line shows the produced forecasts with the PCA model, whereas the yellow line shows the forecast produced with the normalized dataset. (b, c) Two scatter plots with model’s respective errors plotted against observed SO₂ values for the same period.

(a)

(b)

(c)