Using Unsupervised and Supervised Machine Learning Methods to Correct Offset Anomalies in the GOES‐16 Magnetometer Data
Abstract This study uses supervised and unsupervised machine learning (ML) methods to correct unwanted offsets observed in the NOAA GOES‐16 magnetometer data. All GOES satellites have an inboard and outboard magnetometer sensor mounted along a long boom. Post‐launch testing of the GOES‐16 magnetomet...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-12-01
|
| Series: | Space Weather |
| Online Access: | https://doi.org/10.1029/2021SW002892 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536389726863360 |
|---|---|
| author | F. Inceoglu Paul T. M. Loto'aniu |
| author_facet | F. Inceoglu Paul T. M. Loto'aniu |
| author_sort | F. Inceoglu |
| collection | DOAJ |
| description | Abstract This study uses supervised and unsupervised machine learning (ML) methods to correct unwanted offsets observed in the NOAA GOES‐16 magnetometer data. All GOES satellites have an inboard and outboard magnetometer sensor mounted along a long boom. Post‐launch testing of the GOES‐16 magnetometers found that the inboard sensor suffers significant thermally induced magnetic contamination and currently only the outboard sensor is used in NOAA operations. The contamination varies both diurnally and seasonally making it very difficult to correct using basic statistical methods. For simplicity in explaining the offsets we are trying to correct, and methods used, we focus on correcting only one of the inboard vector components, the E‐component (Earthward). We start by applying the unsupervised k‐Shape method to the magnetic field vector E‐component outboard minus inboard sensor time series, ΔE, resulting in four clusters that are closely related to the time of year and the solar β angle, which is a measure of the amount of time that a satellite is in direct sunlight. We then utilized LSTM networks as regressors to correct the offsets observed in GOES‐16 inboard sensor E‐component data. We trained our LSTMs using GOES‐17 magnetometer data, which we show to exhibit much less variability compared with the GOES‐16 data. The correction results reduced the offsets in the clusters from between 3–5 nT and 0–2 nT standard deviations. The combining of unsupervised and supervised ML methods is a powerful technique that can be applied to space‐based instruments that produce time series data. |
| format | Article |
| id | doaj-art-24efd8bde0c7410c8dcbff99dac7ae18 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2021-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-24efd8bde0c7410c8dcbff99dac7ae182025-01-14T16:27:22ZengWileySpace Weather1542-73902021-12-011912n/an/a10.1029/2021SW002892Using Unsupervised and Supervised Machine Learning Methods to Correct Offset Anomalies in the GOES‐16 Magnetometer DataF. Inceoglu0Paul T. M. Loto'aniu1Cooperative Institute for Research in Environmental Sciences University of Colorado Boulder Boulder CO USACooperative Institute for Research in Environmental Sciences University of Colorado Boulder Boulder CO USAAbstract This study uses supervised and unsupervised machine learning (ML) methods to correct unwanted offsets observed in the NOAA GOES‐16 magnetometer data. All GOES satellites have an inboard and outboard magnetometer sensor mounted along a long boom. Post‐launch testing of the GOES‐16 magnetometers found that the inboard sensor suffers significant thermally induced magnetic contamination and currently only the outboard sensor is used in NOAA operations. The contamination varies both diurnally and seasonally making it very difficult to correct using basic statistical methods. For simplicity in explaining the offsets we are trying to correct, and methods used, we focus on correcting only one of the inboard vector components, the E‐component (Earthward). We start by applying the unsupervised k‐Shape method to the magnetic field vector E‐component outboard minus inboard sensor time series, ΔE, resulting in four clusters that are closely related to the time of year and the solar β angle, which is a measure of the amount of time that a satellite is in direct sunlight. We then utilized LSTM networks as regressors to correct the offsets observed in GOES‐16 inboard sensor E‐component data. We trained our LSTMs using GOES‐17 magnetometer data, which we show to exhibit much less variability compared with the GOES‐16 data. The correction results reduced the offsets in the clusters from between 3–5 nT and 0–2 nT standard deviations. The combining of unsupervised and supervised ML methods is a powerful technique that can be applied to space‐based instruments that produce time series data.https://doi.org/10.1029/2021SW002892 |
| spellingShingle | F. Inceoglu Paul T. M. Loto'aniu Using Unsupervised and Supervised Machine Learning Methods to Correct Offset Anomalies in the GOES‐16 Magnetometer Data Space Weather |
| title | Using Unsupervised and Supervised Machine Learning Methods to Correct Offset Anomalies in the GOES‐16 Magnetometer Data |
| title_full | Using Unsupervised and Supervised Machine Learning Methods to Correct Offset Anomalies in the GOES‐16 Magnetometer Data |
| title_fullStr | Using Unsupervised and Supervised Machine Learning Methods to Correct Offset Anomalies in the GOES‐16 Magnetometer Data |
| title_full_unstemmed | Using Unsupervised and Supervised Machine Learning Methods to Correct Offset Anomalies in the GOES‐16 Magnetometer Data |
| title_short | Using Unsupervised and Supervised Machine Learning Methods to Correct Offset Anomalies in the GOES‐16 Magnetometer Data |
| title_sort | using unsupervised and supervised machine learning methods to correct offset anomalies in the goes 16 magnetometer data |
| url | https://doi.org/10.1029/2021SW002892 |
| work_keys_str_mv | AT finceoglu usingunsupervisedandsupervisedmachinelearningmethodstocorrectoffsetanomaliesinthegoes16magnetometerdata AT paultmlotoaniu usingunsupervisedandsupervisedmachinelearningmethodstocorrectoffsetanomaliesinthegoes16magnetometerdata |