science_cases:iwf_science_case
Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
science_cases:iwf_science_case [2022/05/17 14:21] – admin | science_cases:iwf_science_case [2022/09/12 13:06] (current) – admin | ||
---|---|---|---|
Line 13: | Line 13: | ||
===== Main aim ===== | ===== Main aim ===== | ||
- | The main aim of this science case is to develop/ | + | The main aim of this science case is to develop/ |
Interplanetary coronal mass ejections (ICMEs) are one of the main drivers for space weather disturbances. In the past, different machine learning approaches have been used to automatically detect events in existing time series resulting from solar wind in situ data (e.g., Nguyen et al., 2019). However, classification, | Interplanetary coronal mass ejections (ICMEs) are one of the main drivers for space weather disturbances. In the past, different machine learning approaches have been used to automatically detect events in existing time series resulting from solar wind in situ data (e.g., Nguyen et al., 2019). However, classification, | ||
Line 19: | Line 19: | ||
===== Description of the machine learning problem and our approach ===== | ===== Description of the machine learning problem and our approach ===== | ||
- | The first step in this science case was the **reimplementation of a model proposed by Nguyen et al. (2019)**, which had previously been tested on WIND data and achieved a maximum recall and precision of around 84%. | + | The first step in this science case was the **reimplementation of a model proposed by Nguyen et al. (2019)**, which had previously been tested on WIND data and achieved a maximum |
- | After the reimplementation of this model, the model was tested on STEREO-A and STEREO-B data as well as on WIND data. All three contain less variables than the original data set used by Nguyen et al. At a similar recall as for the original set, the precision for all three datasets was only around 30% and the accuracy in delivering start and end times was limited. | + | After the reimplementation of this model, the model was tested on STEREO-A and STEREO-B data as well as on WIND data. All three contain less variables than the original data set used by Nguyen et al. At a similar |
The next step was to align all three data sets in order to process more training data for a combined model. It was tested on held out datasets for WIND, STEREO-A and STEREO-B. Surprisingly, | The next step was to align all three data sets in order to process more training data for a combined model. It was tested on held out datasets for WIND, STEREO-A and STEREO-B. Surprisingly, | ||
- | Starting from the reimplementation, | + | Starting from the reimplementation, |
- | We proposed a pipeline using a **UNet ** (Ronneberger et al., 2015) including residual blocks, squeeze and excitation blocks, Atrous Spatial Pyramidal Pooling (ASPP) and attention blocks, similar to the **ResUNet++** (Jha et al., 2019), for the automatic detection of ICMEs. Comparing it to our first results, we find that our model outperforms the baseline regarding GPU usage, training time and robustness to missing features, thus making it more usable for other data sets, as well as the three aligned data sets. The relatively fast training allows straightforward tuning of hyperparameters. Our proposed pipeline can be used for any time series segmentation problem. The straightforward implementation allows a simple extension to a multiclass | + | We proposed a pipeline using a **UNet ** (Ronneberger et al., 2015) including residual blocks, squeeze and excitation blocks, Atrous Spatial Pyramidal Pooling (ASPP) and attention blocks, similar to the **< |
- | Results of this science case were presented at the EGU21, at EPSC2021, at ESWW 2021, and at AGU21. This ML pipeline was presented in a workshop at EPSC2021 and is, together with a tutorial, available on our GitHub repository. A publication was submitted to the journal "Space Weather" | + | Results of this science case were presented at the {{: |
**References: | **References: |
science_cases/iwf_science_case.1652790067.txt.gz · Last modified: 2022/05/17 14:21 by admin