Table 2 Performance comparison of Gradient Boosting Machine (GBM), Logistic Regression (LR), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Artificial Neural Network (ANN) in predicting susceptibility of debris flow based on cross-validation.

From: Assessing Susceptibility of Debris Flow in Southwest China Using Gradient Boosting Machine

Metric

GBM

LR

KNN

SVM

ANN

Accuracy (%)

82.0

79.5

78.6

81.8

80.5

AUCa

0.88

0.85

0.83

0.86

0.86

  1. aAUC: Area under curve (AUC) of receiver operating characteristic (ROC), with the best performance shown in bold.
Back to article page