Verification and Validation for Trustworthy Scientific Machine Learning

Scientific machine learning (SciML) integrates machine learning (ML) into scientific workflows to enhance system simulation and analysis, with an emphasis on computational modeling of physical systems. This field emerged from Department of Energy workshops and initiatives starting in 2018, which also identified the need to increase "the scale, rigor, robustness, and reliability of SciML necessary for routine use in science and engineering applications" [5]. The field's subsequent growth through funding initiatives, conference themes, and high-profile publications stems from its ability to unite ML's predictive power with the domain knowledge and mathematical rigor of computational science and engineering (CSE). However, this surge in SciML development has outpaced good practices and reporting standards for building trust [66, 51, 109, 117]. SciML models must demonstrate trustworthiness to be safe and useful [44]. Organizational and computational trust definitions [92, 106] inform our criteria for trustworthy SciML: competence in basic performance, reliability across conditions, transparency about processes and limitations, and alignment with scientific objectives. These criteria span technical attributes (correctness, reliability, safety) and human-centric qualities (comprehensibility, transparency).