We present an uncertainty-aware online ensemble method for handling non-stationary data streams in fusion science applications. The approach dynamically weights multiple models …
Talk Talk on developing robust adaptive digital twins with uncertainty awareness for fusion science applications.
This preprint presents a novel uncertainty-guided online ensemble learning approach for handling non-stationary data streams in fusion science. The method adaptively selects and …
This paper presents a distance-preserving machine learning approach for making uncertainty-aware predictions of accelerator capacitance. The method preserves geometric …
Invited Talk Current progress on machine learning applications for particle accelerators and its scope for Fusion Science.
Invited Talk Application of Machine Learning to improve accelerator operation, application of conditional models to predict anomalies at SNS accelerator.
Deep learning models for particle accelerator control and optimization can suffer from overconfidence when deployed to new operating conditions. This paper presents techniques for …
Surrogate models based on machine learning are increasingly used to accelerate optimization and control of particle accelerators. This paper presents methods for quantifying …
Uncertainty Quantification for Rare Events (Out-of-Distribution Detection) via Gaussian Process Approximation in Scientific Applications