TIE‐GCM ROPE ‐ Dimensionality Reduction: Part I
Abstract Physics‐based models of the ionosphere‐thermosphere system have been touted as the next big thing in the context of drag modeling and space operations for decades. However, the computational complexity of such models have primarily kept them being used operationally. We recently demonstrate...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Space Weather |
| Online Access: | https://doi.org/10.1029/2024SW004185 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583569734631424 |
|---|---|
| author | Piyush M. Mehta Richard J. Licata |
| author_facet | Piyush M. Mehta Richard J. Licata |
| author_sort | Piyush M. Mehta |
| collection | DOAJ |
| description | Abstract Physics‐based models of the ionosphere‐thermosphere system have been touted as the next big thing in the context of drag modeling and space operations for decades. However, the computational complexity of such models have primarily kept them being used operationally. We recently demonstrated a proof‐of‐concept for developing what we call a reduced order probabilistic emulator (ROPE) for the thermosphere using the thermosphere ionosphere electrodynamics ‐ general circulation model (TIE‐GCM). The methodology uses a page out of dynamical systems theory to first reduce the order of the state using dimensionality reduction and then modeling the temporal dynamics in the reduced state space. The methodology uses an ensemble of temporal dynamic models to provide uncertainty estimates in the prediction. This work focuses on the dimensionality reduction step of the ROPE development process and addresses three limitations of the proof‐of‐concept: (a) extending the altitude upper boundary from 450 km to nearly 1000 km, (b) employing deep learning for nonlinear dimensionality reduction over principal component analysis (PCA) for improved performance during storm periods, and (c) maintaining the spatial resolution of the physical TIE‐GCM model, without down‐sampling, to preserve the spatial scales and variations. Results show overall performance boost over PCA for the high‐resolution and extrapolated data set as well as reduced reconstruction errors during storm‐time conditions. This work represents a major step toward operationalization. |
| format | Article |
| id | doaj-art-03649a44f1cf46e4b932ca1f49b4aa06 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-03649a44f1cf46e4b932ca1f49b4aa062025-01-28T10:40:44ZengWileySpace Weather1542-73902025-01-01231n/an/a10.1029/2024SW004185TIE‐GCM ROPE ‐ Dimensionality Reduction: Part IPiyush M. Mehta0Richard J. Licata1Department of Mechanical Materials and Aerospace Engineering West Virginia University Morgantown WV USADepartment of Mechanical Materials and Aerospace Engineering West Virginia University Morgantown WV USAAbstract Physics‐based models of the ionosphere‐thermosphere system have been touted as the next big thing in the context of drag modeling and space operations for decades. However, the computational complexity of such models have primarily kept them being used operationally. We recently demonstrated a proof‐of‐concept for developing what we call a reduced order probabilistic emulator (ROPE) for the thermosphere using the thermosphere ionosphere electrodynamics ‐ general circulation model (TIE‐GCM). The methodology uses a page out of dynamical systems theory to first reduce the order of the state using dimensionality reduction and then modeling the temporal dynamics in the reduced state space. The methodology uses an ensemble of temporal dynamic models to provide uncertainty estimates in the prediction. This work focuses on the dimensionality reduction step of the ROPE development process and addresses three limitations of the proof‐of‐concept: (a) extending the altitude upper boundary from 450 km to nearly 1000 km, (b) employing deep learning for nonlinear dimensionality reduction over principal component analysis (PCA) for improved performance during storm periods, and (c) maintaining the spatial resolution of the physical TIE‐GCM model, without down‐sampling, to preserve the spatial scales and variations. Results show overall performance boost over PCA for the high‐resolution and extrapolated data set as well as reduced reconstruction errors during storm‐time conditions. This work represents a major step toward operationalization.https://doi.org/10.1029/2024SW004185 |
| spellingShingle | Piyush M. Mehta Richard J. Licata TIE‐GCM ROPE ‐ Dimensionality Reduction: Part I Space Weather |
| title | TIE‐GCM ROPE ‐ Dimensionality Reduction: Part I |
| title_full | TIE‐GCM ROPE ‐ Dimensionality Reduction: Part I |
| title_fullStr | TIE‐GCM ROPE ‐ Dimensionality Reduction: Part I |
| title_full_unstemmed | TIE‐GCM ROPE ‐ Dimensionality Reduction: Part I |
| title_short | TIE‐GCM ROPE ‐ Dimensionality Reduction: Part I |
| title_sort | tie gcm rope dimensionality reduction part i |
| url | https://doi.org/10.1029/2024SW004185 |
| work_keys_str_mv | AT piyushmmehta tiegcmropedimensionalityreductionparti AT richardjlicata tiegcmropedimensionalityreductionparti |