9:20 AM - 9:40 AM
[2A1-02] Predicting Eruptions of Sakurajima by Stacked Recurrent Neural Network
Keywords:deep learning, volcanic eruption prediction, RNN
Volcanic eruptions sometimes cause severe damage to many people.
This paper explains our attempts for predicting volcanic eruptions
from time series sensor data obtained from volcanic monitoring systems
(strainmeters) located in Sakurajima. Given the time series data of
strainmeters for 100 minutes, our goal is to predict future status of
the volcano which is either "explosive" or "not explosive" for the 60
minutes immediately after the 100 minutes. We use stacked recurrent
neural network for this task, and our method achieves 66.1% F-score
on average. We also propose a four-stage warning system that classifies
time series sensor data into the following categories: "Non-eruption",
"May-eruption", "Warning" and "Critial". The percentage of "explosive"
cases in "Critial" category is 51.9%.
This paper explains our attempts for predicting volcanic eruptions
from time series sensor data obtained from volcanic monitoring systems
(strainmeters) located in Sakurajima. Given the time series data of
strainmeters for 100 minutes, our goal is to predict future status of
the volcano which is either "explosive" or "not explosive" for the 60
minutes immediately after the 100 minutes. We use stacked recurrent
neural network for this task, and our method achieves 66.1% F-score
on average. We also propose a four-stage warning system that classifies
time series sensor data into the following categories: "Non-eruption",
"May-eruption", "Warning" and "Critial". The percentage of "explosive"
cases in "Critial" category is 51.9%.