science_cases:lmsu_science_case
Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
science_cases:lmsu_science_case [2022/02/17 10:38] – admin | science_cases:lmsu_science_case [2022/09/12 13:44] (current) – admin | ||
---|---|---|---|
Line 22: | Line 22: | ||
===== Description of the machine learning problem and our approach ===== | ===== Description of the machine learning problem and our approach ===== | ||
- | Based on data from the mission, several global models of the magnetosphere were proposed (e.g., Winslow et al., 2013; Philpott et al., 2020). However, they could only describe an average shape of the bow shock and magnetopause crossings and can be prone to missing the statistical nuances in the data. Given large data, neural networks can be expected to approximate complex functions, which often surpass deterministic and rule-based methods, in a variety of time series tasks like classification (Fawaz et al., 2019), time series forecasting (Lim and Bohren, 2021), and rare time series event detection (Nguyen et al., 2018). We leverage these to develop a predictor that can be used in real-time during orbit to predict magnetic region for each step in a short window of observation. Figure 3 illustrates the different crossing labels for an exemplary orbit. | + | Based on data from the mission, several global models of the magnetosphere were proposed (e.g., Winslow et al., 2013; Philpott et al., 2020). However, they could only describe an average shape of the bow shock and magnetopause crossings and can be prone to missing the statistical nuances in the data. Given large data, [[: |
- | The use of statistical neural networks allows us to explore another aspect: | + | The use of **statistical neural networks** allows us to explore another aspect: |
- | The dataset | + | The data set was **manually labelled with the boundary crossings**. To identify bow shocks, we first subtracted planetary dipole magnetic field components from the magnetometer measurements, |
- | The distribution of the different | + | The distribution of the different regions, after annotation, is reported in the following |
- | As a first step in pre-processing, | + | ^Label^Region^Statistical distribution |
+ | |0|Interplanetary magnetic field|65.4| | ||
+ | |1|Bow shock crossing|3.7| | ||
+ | |2|Magnetosheath|14.5| | ||
+ | |3|Magnetopause crossing|2.3| | ||
+ | |4|Magnetosphere|14.1| | ||
- | In the feature preparation stage, a sliding window | + | The boundaries |
- | The windowed features are fed first into a block of 3 Convolutional layers with 1D filters, each followed by Batch Normalisation and ReLu activations. The activations obtained at the end of the CNN block are then passed to the Recurrent block with two layers | + | As a first step in pre-processing, [[: |
- | The sample results in Figures 4 and 5 are from a model trained | + | In the feature preparation stage, |
- | The window size used in these experiments is 30 seconds. Overall, | + | The windowed features are fed first into a block of 3 [[: |
- | The results from the active learning experiment are still not complete. We are currently | + | The window size used in these experiments is 30 seconds. Overall, |
- | Results of this science case were presented at the EGU21 as well as at EPSC2021 | + | Results of this science case were presented at the {{: |
**References: | **References: |
science_cases/lmsu_science_case.1645090720.txt.gz · Last modified: 2022/02/17 10:38 by admin