Skip to main content
Earth, Planets and Space

Table 1 Matrix for the training and validation data of EQ–T–N events

From: A convolutional neural network-based classification of local earthquakes and tectonic tremors in Sanriku-oki, Japan, using S-net data

  

Actual label

Training data

EQ (N = 210)

T (N = 531)

N (N = 468)

Validation data

 

EQ (N = 91)

T (N = 208)

N (N = 118)

Predicted label

EQ

91 (100%)

2 (1%)

0 (0%)

 T

0 (0%)

200 (96%)

2 (2%)

N

0 (0%)

6 (3%)

116 (98%)

  1. We used 210, 531, and 468 images of EQ, T, and N events, respectively. We also used 91, 208, and 118 validation images with actual (true) EQ, T, and N labels, respectively
Back to article page