Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan.
Faculty of Biology-Oriented Science and Technology, Kindai University, Nishimitani 930, Kinokawa, Wakayama, 649-6493, Japan.
Sci Rep. 2020 Mar 24;10(1):5272. doi: 10.1038/s41598-020-62342-y.
Muography is a novel method of visualizing the internal structures of active volcanoes by using high-energy near-horizontally arriving cosmic muons. The purpose of this study is to show the feasibility of muography to forecast the eruption event with the aid of the convolutional neural network (CNN). In this study, seven daily consecutive muographic images were fed into the CNN to compute the probability of eruptions on the eighth day, and our CNN model was trained by hyperparameter tuning with the Bayesian optimization algorithm. By using the data acquired in Sakurajima volcano, Japan, as an example, the forecasting performance achieved a value of 0.726 for the area under the receiver operating characteristic curve, showing the reasonable correlation between the muographic images and eruption events. Our result suggests that muography has the potential for eruption forecasting of volcanoes.
μ 射线层析成像技术是一种利用高能近水平到达的宇宙 μ 射线来可视化活火山内部结构的新方法。本研究的目的是展示 μ 射线层析成像技术在卷积神经网络 (CNN) 的辅助下预测喷发事件的可行性。在这项研究中，将 7 张连续的每日 μ 射线层析图像输入到 CNN 中，以计算第 8 天喷发的概率，我们的 CNN 模型通过贝叶斯优化算法进行超参数调整来训练。通过使用日本樱岛火山采集的数据作为示例，该预测性能在接收器工作特性曲线下的面积上达到了 0.726，表明 μ 射线层析图像与喷发事件之间存在合理的相关性。我们的结果表明，μ 射线层析成像技术具有火山喷发预测的潜力。
