Beyond Accuracy: Evaluating Bayesian Neural Networks in a Real-world Application
This research evaluates Bayesian neural network models in a planetary science application to address challenges with data scarcity and distribution shift. The methods presented here are broadly applicable to scientific domains requiring trustworthy machine learning under uncertainty.
Authors
- Michaël Geyer (ORCID: https://orcid.org/0000-0003-0085-2521)
- Natalie Klein (ORCID: https://orcid.org/0000-0002-7532-4013)
- Scott Koermer (ORCID: https://orcid.org/0000-0002-0325-7034)
- Mark G. Hinds (ORCID: https://orcid.org/0000-0002-2856-5375)
Institutions
- Los Alamos National Laboratory (US)
Publication Details
- Journal
- The ITEA Journal of Test and Evaluation
- Published
- 2025-09-22
- DOI
- https://doi.org/10.61278/itea.46.3.1006
- Citations
- 2
- Primary Topic
- Fault Detection and Control Systems
- Type
- article
- Field-Weighted Citation Impact
- 2.43