This paper proposes initially to apply convolutional neural network (CNN) for detecting the equatorial plasma bubbles on the ASI images. The considered CNN model is the YOLO v3 tiny model under a deep learning API (Keras), running on top of the machine learning platform (TensorFlow). Our program for EPB detection is written in Python that is extended easily to combine into a space weather web site for detecting and notifying EPBs in our next step. The results show that the YOLO v3-based CNN can detect the EPBs in ASI images with different intensities obtained from many countries. The threshold is tested and selected to be 0.40 suitably for detecting the anomaly (EPB existence). The maximum anomalous value is selected to decide the EPB occurrence.
CITATION STYLE
Srisamoodkham, W., Shiokawa, K., Otsuka, Y., Ansari, K., & Jamjareegulgarn, P. (2022). Detecting Equatorial Plasma Bubbles on All-Sky Imager Images Using Convolutional Neural Network. In Lecture Notes in Networks and Systems (Vol. 461, pp. 481–487). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-19-2130-8_38
Mendeley helps you to discover research relevant for your work.