Fig. 2: The ROC–AUC curve of ML models.
From: Simulating flood risk in Tampa Bay using a machine learning driven approach
The X-axis represents the false positive rate (1 – specificity) and Y-axis represents the true positive rate (sensitivity). The red, blue, green, yellow, and black lines represent the AUC curves for the RF, XGBoost, AdaBoost, SVM, and DT models, respectively. The gray dotted line indicates the AUC curve for random guessing. This analysis was conducted and plotted using roc_curve function in Python 3.11.7.
