Calibrated and Enhanced NRLMSIS 2.0 Model with Uncertainty Quantification

no code implementations • 24 Aug 2022 • Richard J. Licata, Piyush M. Mehta, Daniel R. Weimer, W. Kent Tobiska, Jean Yoshii

In this work, we develop an exospheric temperature model based in machine learning (ML) that can be used with NRLMSIS 2. 0 to calibrate it relative to high-fidelity satellite density estimates.

Uncertainty Quantification

Science through Machine Learning: Quantification of Poststorm Thermospheric Cooling

no code implementations • 12 Jun 2022 • Richard J. Licata, Piyush M. Mehta, Daniel R. Weimer, Douglas P. Drob, W. Kent Tobiska, Jean Yoshii

Machine learning (ML) is often viewed as a black-box regression technique that is unable to provide considerable scientific insight.

BIG-bench Machine Learning

Machine-Learned HASDM Model with Uncertainty Quantification

no code implementations • 16 Sep 2021 • Richard J. Licata, Piyush M. Mehta, W. Kent Tobiska, S. Huzurbazar

These models leverage Monte Carlo (MC) dropout to provide uncertainty estimates, and the use of the NLPD loss function results in well-calibrated uncertainty estimates without sacrificing model accuracy (<10% mean absolute error).

Dimensionality Reduction Uncertainty Quantification