Application of Regularized Logistic Regression and Artificial Neural Network model for Ozone Classification across El Paso County, Texas, United States

This paper focuses on ozone prediction in the atmosphere using a machine learning approach. We utilize air pollutant and meteorological variable datasets from El Paso area to classify levels as high or low. The LR ANN algorithms are employed train datasets. models demonstrate remarkably classification accuracy of 89.3% predicting given day. Evaluation metrics reveal that both exhibit accuracies 88.4%, respectively. Additionally, AUC values for comparable, with achieving 95.4% obtaining 95.2%. lower cross-entropy loss (log loss), higher model’s performance. Our model yields log 3.74, while shows 6.03. time is approximately 0.00 seconds, whereas takes 0.02 seconds. odds ratio analysis indicates features such “Solar radiation”, “Std. Dev. Wind Direction”, “outdoor temperature”, “dew point “PM10” contribute Paso, Texas. Based accuracy, error rate, loss, time, proves be faster more suitable Texas area.