Goal-Driven Adaptive Sampling Strategies for Machine Learning Models Predicting Fields

TL;DR

This paper introduces a novel active learning strategy for field prediction models that reduces computational costs while maintaining high accuracy, applicable across various model architectures.

Contribution

It extends active learning to field predictions, combining Gaussian processes with error reduction techniques, applicable to diverse models and scenarios.

Findings

Achieves high accuracy with fewer samples.

Reduces computational cost significantly.

Effective across different model types.

Abstract

Machine learning models are widely regarded as a way forward to tackle multi-query challenges that arise once expensive black-box simulations such as computational fluid dynamics are investigated. However, ensuring the desired level of accuracy for a certain task at minimal computational cost, e.g. as few black-box samples as possible, remains a challenges. Active learning strategies are used for scalar quantities to overcome this challenges and different so-called infill criteria exists and are commonly employed in several scenarios. Even though needed in various field an extension of active learning strategies towards field predictions is still lacking or limited to very specific scenarios and/or model types. In this paper we propose an active learning strategy for machine learning models that are capable if predicting field which is agnostic to the model architecture itself. For doing so, we combine a well-established Gaussian process model for a scalar reference value and simultaneously aim at reducing the epistemic model error and the difference between scalar and field predictions. Different specific forms of the above-mentioned approach are introduced and compared to each other as well as only scalar-valued based infill. Results are presented for the NASA common research model for an uncertainty propagation task showcasing high level of accuracy at significantly smaller cost compared to an approach without active learning.