讲座时间：2019年2月27日 下午4：00-6：00
讲座嘉宾：刘佳佳, 英国谢菲尔德大学
讲座题目：Application of Machine Learning and AI techniques in CME arrival time prediction
讲座地点：物理楼N415
Abstract
Coronal Mass Ejections (CMEs) are one of the most violent eruptions in the Solar system. Fast and accurate prediction of CME arrival time is then vital to minimize the losts CMEs may cost when hitting the Earth. Here, we present the application of machine learning & AI techniques in CME arrival time prediction. Via detailed analysis of the CME features and solar wind parameters, we build a model (CAT-PUMA) taking advantage of 182 previously observed geo-effective (partial-) halo CMEs using the Support Vector Machines (SVMs). Predictions using the model on a test set, that is unknown to our model, shows a mean absolute prediction error of less than 6 hours of the CME arrival time. Comparisons with other models reveal that CAT-PUMA has a more accurate prediction for 73% events. We have further developed a Convolution Neural Network using a single image of the SOHO LASCO C2 observations as input to make arrival time predictions of CMEs. Results on the test set have shown that, the average prediction error is around 12.5 hours, comparable to the average performance of previous studies on this subject. In 63% events, our model gives less prediction errors than the average of traditional models.
个人简介
2010年本科毕业于中国科学技术大学。
2013-2014年美国高山天文台联合培养博士研究生。
2015年博士毕业于中国科学技术大学地球和空间科学学院。
2015年至2017年于中国科学技术大学先后任职博士后及特任副研究员。
2017年起任谢菲尔德大学Research Associate。
2018年获英国议院STEM for Britain Award。
主要研究方向包括太阳大气喷流、MHD波动和涡旋的观测和数值模拟，以及机器学习在太阳物理和空间天气预报中的应用。
