Search for: All records

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. 

Abstract Machine learning (ML) has been applied to space weather problems with increasing frequency in recent years, driven by an influx of in-situ measurements and a desire to improve modeling and forecasting capabilities throughout the field. Space weather originates from solar perturbations and is comprised of the resulting complex variations they cause within the numerous systems between the Sun and Earth. These systems are often tightly coupled and not well understood. This creates a need for skillful models with knowledge about the confidence of their predictions. One example of such a dynamical system highly impacted by space weather is the thermosphere, the neutral region of Earth’s upper atmosphere. Our inability to forecast it has severe repercussions in the context of satellite drag and computation of probability of collision between two space objects in low Earth orbit (LEO) for decision making in space operations. Even with (assumed) perfect forecast of model drivers, our incomplete knowledge of the system results in often inaccurate thermospheric neutral mass density predictions. Continuing efforts are being made to improve model accuracy, but density models rarely provide estimates of confidence in predictions. In this work, we propose two techniques to develop nonlinear ML regression models to predict thermospheric density while providing robust and reliable uncertainty estimates: Monte Carlo (MC) dropout and direct prediction of the probability distribution, both using the negative logarithm of predictive density (NLPD) loss function. We show the performance capabilities for models trained on both local and global datasets. We show that the NLPD loss provides similar results for both techniques but the direct probability distribution prediction method has a much lower computational cost. For the global model regressed on the Space Environment Technologies High Accuracy Satellite Drag Model (HASDM) density database, we achieve errors of approximately 11% on independent test data with well-calibrated uncertainty estimates. Using an in-situ CHAllenging Minisatellite Payload (CHAMP) density dataset, models developed using both techniques provide test error on the order of 13%. The CHAMP models—on validation and test data—are within 2% of perfect calibration for the twenty prediction intervals tested. We show that this model can also be used to obtain global density predictions with uncertainties at a given epoch.