Machine learning for the harsh environment: applications in sea ice classification and satellite magnetic fault recovery
This thesis presents the development of two machine learning navigation modules for harsh environment applications. The first application investigates semantic segmentation using neural networks for sea ice detection and classification in polar oceans. Two popular generic architectures, SegNet and P...
Main Author: | |
---|---|
Format: | Text |
Language: | English |
Published: |
Memorial University of Newfoundland
2022
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48336/gbw3-1p84 https://research.library.mun.ca/15342/ |
id |
ftdatacite:10.48336/gbw3-1p84 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48336/gbw3-1p84 2023-05-15T13:37:10+02:00 Machine learning for the harsh environment: applications in sea ice classification and satellite magnetic fault recovery Dowden, Benjamin R. 2022 https://dx.doi.org/10.48336/gbw3-1p84 https://research.library.mun.ca/15342/ en eng Memorial University of Newfoundland article-journal ScholarlyArticle Text 2022 ftdatacite https://doi.org/10.48336/gbw3-1p84 2022-04-01T13:29:14Z This thesis presents the development of two machine learning navigation modules for harsh environment applications. The first application investigates semantic segmentation using neural networks for sea ice detection and classification in polar oceans. Two popular generic architectures, SegNet and PSPNet101 are used to segment images. Transfer learning is performed using two custom datasets, one with four classes: ice, ocean, vessel, and sky, i.e., sea ice detection dataset, and the second with eight classes: ocean, vessel, sky, lens artifacts, first-year ice, new ice, grey ice, and multiyear ice, i.e., sea ice classification dataset. The Nathaniel B. Palmer imagery, which captured 2-month footage of the icebreaker completing an Antarctic expedition was used in the creation of both datasets. A subset of the dataset was labeled to generate a 240-image training set for sea ice detection achieving an accuracy of 98% classification for the 26-image test set. The sea ice classification dataset consists of 1,090 labeled images achieving accuracies of 98.3% or greater for all ice types for the 104-image test set. The second application investigates a new attitude error parameterization and a machine learning regression model for small satellite attitude fault recovery systems experiencing magnetometer bias faults. A simulation environment is developed to mimic an orbit of the international space station, and simulates both the magnetometer and the fine sun sensor on-board a small satellite. A right quaternion error parameterization is presented to ensure consistent error bound growth during the eclipse period of orbits where only a subset of sensor data is available. Using the improved error bounds a fault detection method using Mahalanobis distance is implemented to ag any faults in the system. After the fault detection, the fault recovery uses a regression sliding window optimizer to determine the unknown magnetometer bias that the sensor encounters. The proposed method demonstrates improved root mean squared error and error bound consistency achievable using the right error formulation for magnetic bias fault detection and recovery applications of small satellites. Text Antarc* Antarctic Sea ice DataCite Metadata Store (German National Library of Science and Technology) Antarctic |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
English |
description |
This thesis presents the development of two machine learning navigation modules for harsh environment applications. The first application investigates semantic segmentation using neural networks for sea ice detection and classification in polar oceans. Two popular generic architectures, SegNet and PSPNet101 are used to segment images. Transfer learning is performed using two custom datasets, one with four classes: ice, ocean, vessel, and sky, i.e., sea ice detection dataset, and the second with eight classes: ocean, vessel, sky, lens artifacts, first-year ice, new ice, grey ice, and multiyear ice, i.e., sea ice classification dataset. The Nathaniel B. Palmer imagery, which captured 2-month footage of the icebreaker completing an Antarctic expedition was used in the creation of both datasets. A subset of the dataset was labeled to generate a 240-image training set for sea ice detection achieving an accuracy of 98% classification for the 26-image test set. The sea ice classification dataset consists of 1,090 labeled images achieving accuracies of 98.3% or greater for all ice types for the 104-image test set. The second application investigates a new attitude error parameterization and a machine learning regression model for small satellite attitude fault recovery systems experiencing magnetometer bias faults. A simulation environment is developed to mimic an orbit of the international space station, and simulates both the magnetometer and the fine sun sensor on-board a small satellite. A right quaternion error parameterization is presented to ensure consistent error bound growth during the eclipse period of orbits where only a subset of sensor data is available. Using the improved error bounds a fault detection method using Mahalanobis distance is implemented to ag any faults in the system. After the fault detection, the fault recovery uses a regression sliding window optimizer to determine the unknown magnetometer bias that the sensor encounters. The proposed method demonstrates improved root mean squared error and error bound consistency achievable using the right error formulation for magnetic bias fault detection and recovery applications of small satellites. |
format |
Text |
author |
Dowden, Benjamin R. |
spellingShingle |
Dowden, Benjamin R. Machine learning for the harsh environment: applications in sea ice classification and satellite magnetic fault recovery |
author_facet |
Dowden, Benjamin R. |
author_sort |
Dowden, Benjamin R. |
title |
Machine learning for the harsh environment: applications in sea ice classification and satellite magnetic fault recovery |
title_short |
Machine learning for the harsh environment: applications in sea ice classification and satellite magnetic fault recovery |
title_full |
Machine learning for the harsh environment: applications in sea ice classification and satellite magnetic fault recovery |
title_fullStr |
Machine learning for the harsh environment: applications in sea ice classification and satellite magnetic fault recovery |
title_full_unstemmed |
Machine learning for the harsh environment: applications in sea ice classification and satellite magnetic fault recovery |
title_sort |
machine learning for the harsh environment: applications in sea ice classification and satellite magnetic fault recovery |
publisher |
Memorial University of Newfoundland |
publishDate |
2022 |
url |
https://dx.doi.org/10.48336/gbw3-1p84 https://research.library.mun.ca/15342/ |
geographic |
Antarctic |
geographic_facet |
Antarctic |
genre |
Antarc* Antarctic Sea ice |
genre_facet |
Antarc* Antarctic Sea ice |
op_doi |
https://doi.org/10.48336/gbw3-1p84 |
_version_ |
1766088729750929408 |