Skip to main content

Table 5 Top 10 permutation importance features

From: Noise classification for the unified earthquake catalog using ensemble learning: the enhanced image of seismic activity along the Japan Trench by the S-net seafloor network

Feature

Importance

(a) Random forest

 M

0.002471

 σp4

0.000299

 σs11

0.000244

 σp1

0.000190

 σs10

0.000177

 σs14

0.000177

 σm19

0.000177

 σp5

0.000163

 σp2

0.000163

 θ1

0.000136

(b) AdaBoost

 M

0.003585

 lon

0.001439

 t0

0.001371

 Np14

0.001181

 Np5

0.001154

 Np20

0.000950

 Np19

0.000815

 Np10

0.000815

 Np11

0.000692

 Np4

0.000597