Automatic Detection of Interplanetary Coronal Mass Ejections in Solar Wind In Situ Data

• Published in: Space Weather 2022-10, Vol.20 (10), p.n/a
• Main Authors: Rüdisser, H. T., Windisch, A., Amerstorfer, U. V., Möstl, C., Amerstorfer, T., Bailey, R. L., Reiss, M. A.
• Format: Article
• Language: English
• Subjects: Algorithms; Coronal mass ejection; Corotating Interaction Regions (CIR); Datasets; Image segmentation; Machine learning; Medical imaging; Solar corona; Solar wind; Space weather; Spacecraft; Time series; Training; Weather forecasting; Wind data; Wind spacecraft
• ISSN: 1542-7390; 1539-4964; 1542-7390
• DOI: 10.1029/2022SW003149

Interplanetary coronal mass ejections (ICMEs) are one of the main drivers for space weather disturbances. In the past, different approaches have been used to automatically detect events in existing time series resulting from solar wind in situ observations. However, accurate and fast detection still remains a challenge when facing the large amount of data from different instruments. For the automatic detection of ICMEs we propose a pipeline using a method that has recently proven successful in medical image segmentation. Comparing it to an existing method, we find that while achieving similar results, our model outperforms the baseline regarding training time by a factor of approximately 20, thus making it more applicable for other datasets. The method has been tested on in situ data from the Wind spacecraft between 1997 and 2015 with a True Skill Statistic of 0.64. Out of the 640 ICMEs, 466 were detected correctly by our algorithm, producing a total of 254 false positives. Additionally, it produced reasonable results on datasets with fewer features and smaller training sets from Wind, STEREO‐A, and STEREO‐B with TSSs of 0.56, 0.57, and 0.53, respectively. Our pipeline manages to find the start of an ICME with a mean absolute error (MAE) of around 2 hr and 56 min, and the end time with a MAE of 3 hr and 20 min. The relatively fast training allows straightforward tuning of hyperparameters and could therefore easily be used to detect other structures and phenomena in solar wind data, such as corotating interaction regions. Plain Language Summary Interplanetary coronal mass ejections (ICMEs) are part of space weather and can have severe effects on human technology. Since the detection of these events is often difficult, experts are usually needed to detect them in time series from different spacecraft. Even though, there have been attempts to solve this problem using machine learning, it is far from being solved. We propose a machine learning model, that manages to find the start and end times with improved accuracy and takes less time to train. Even though our results are quite promising, it is important to notice that there are many different catalogs documenting ICMEs, that do not always agree. Therefore, there is no unique solution to this problem, which makes it difficult for a machine learning method to learn the features of an ICME. Nevertheless, our model can be expected to make a substantial contribution to the area of space weather forecast in the f