Spatial Modeling of Asthma-Prone Areas Using Remote Sensing and Ensemble Machine Learning Algorithms

In this study, asthma-prone area modeling of Tehran, Iran was provided by employing three ensemble machine learning algorithms (Bootstrap aggregating (Bagging), Adaptive Boosting (AdaBoost), and Stacking). First, a spatial database created with 872 locations asthma patients affecting factors (particulate matter (PM10 PM2.5), ozone (O3), sulfur dioxide (SO2), carbon monoxide (CO), nitrogen (NO2), rainfall, wind speed, humidity, temperature, distance to street, traffic volume, normalized difference vegetation index (NDVI)). We four using remote sensing (RS) imagery, including air pollution (O3, SO2, CO, NO2), altitude, NDVI. All criteria were prepared geographic information system (GIS). For validation, 70% 30% the data used, respectively. The weight evidence (WOE) model used assess relationship between dependent independent data. Finally, perform areas mapping. According Gini index, most influential on occurrence NDVI, volume. under curve (AUC) receiver operating characteristic (ROC) values for AdaBoost, Bagging, Stacking 0.849, 0.82, 0.785, findings, AdaBoost algorithm outperforms Bagging in areas.