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 10:36] – admin | science_cases:lmsu_science_case [2022/09/12 13:44] (current) – admin | ||
---|---|---|---|
Line 12: | Line 12: | ||
===== Aim of the science case ===== | ===== Aim of the science case ===== | ||
- | The MESSENGER spacecraft has completed over 4000 orbits around Mercury. The initial orbit had a 200 km periapsis altitude, 82.5 inclination, | + | The MESSENGER |
During each orbit, MESSENGER typically spent 1–2 h inside the magnetosphere; | During each orbit, MESSENGER typically spent 1–2 h inside the magnetosphere; | ||
Line 18: | Line 18: | ||
Magnetic field data are analyzed in Mercury solar orbital (MSO) coordinates. In MSO coordinates, | Magnetic field data are analyzed in Mercury solar orbital (MSO) coordinates. In MSO coordinates, | ||
- | The goal of this case is to improve our understanding of Mercury' | + | The goal of this case is to improve our understanding of Mercury' |
- | Based on data from the mission, several global models | + | ===== Description |
- | The use of statistical neural networks allows us to explore another aspect: with the help of active learning, it is possible to add samples to the training process incrementally. With this, we can examine how the model scales its predictive capacity with increasing data, and thus study how the variations such as changing solar wind and environmental conditions affects | + | Based on data from the mission, several global models |
- | The dataset was manually labelled with the boundary crossings. To identify bow shocks, we first subtracted planetary dipole magnetic field components from the magnetometer measurements, | + | The use of **statistical neural networks** allows us to explore another aspect: With the help of **[[: |
- | The distribution of the different | + | The data set was **manually labelled with the boundary crossings**. To identify bow shocks, we first subtracted planetary dipole |
- | As a first step in pre-processing, | + | The distribution |
- | In the feature preparation stage, a sliding window of variable sizes (3 seconds to 3 minutes) with a hop size of 1 second was computed on the time series signal to obtain feature vectors. Finally, the features were normalised to have mean of 0 and a standard deviation of 1. No other pre-processing or engineering was applied in order to allow the deep learning model to engineer features implicitly. | + | ^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| | ||
- | The windowed features | + | The boundaries of critical interest - bow shock and magnetopause - are minorities with only 3.7 and 2.3 % representation. The table highlights |
- | The sample results in Figures 4 and 5 are from a model trained with two Mercury years of data, which is about 300 orbits. | + | As a first step in pre-processing, |
- | The window size used in these experiments is 30 seconds. Overall, the predictor achieves a macro F1 score of about 80% on the bow shock and the magnetopause crossings on a randomly sampled test of 300 orbits. None of the orbits overlap | + | In the feature preparation stage, a sliding |
- | The results from the active learning experiment | + | The windowed features |
- | Results of this science case were presented at the EGU21 as well as at EPSC2021 | + | The window size used in these experiments is 30 seconds. Overall, the [[: |
+ | |||
+ | Results of this science case were presented at the {{: | ||
**References: | **References: |
science_cases/lmsu_science_case.1645090608.txt.gz · Last modified: 2022/02/17 10:36 by admin