Building Trustworthy Machine Learning Models for Astronomy

TL;DR

This paper discusses the importance of building trust in machine learning models within astronomy, emphasizing methods to foster community confidence and ensure reliable scientific discoveries.

Contribution

It provides an overview of strategies to enhance trust in ML models, addressing a critical but often overlooked aspect of deploying AI in astronomy.

Findings

Trust-building methods improve community acceptance of ML

Enhanced trust leads to more robust data analysis

Trust strategies facilitate broader adoption of ML in astronomy

Abstract

Astronomy is entering an era of data-driven discovery, due in part to modern machine learning (ML) techniques enabling powerful new ways to interpret observations. This shift in our scientific approach requires us to consider whether we can trust the black box. Here, we overview methods for an often-overlooked step in the development of ML models: building community trust in the algorithms. Trust is an essential ingredient not just for creating more robust data analysis techniques, but also for building confidence within the astronomy community to embrace machine learning methods and results.