Data-centric Operational Design Domain Characterization for Machine Learning-based Aeronautical Products

TL;DR

This paper introduces a data-centric approach to defining Operational Design Domains for ML-based aeronautical systems, focusing on data categorization, system impact, and design requirements, exemplified by an aircraft flight envelope.

Contribution

It presents a novel data-centric framework for ODD characterization in aeronautics, emphasizing data categorization and system-level implications for ML-based products.

Findings

Data categories help determine ML model requirements

System impact varies with data types and categories

Framework aids in designing safer ML-based aeronautical systems

Abstract

We give a first rigorous characterization of Operational Design Domains (ODDs) for Machine Learning (ML)-based aeronautical products. Unlike in other application sectors (such as self-driving road vehicles) where ODD development is scenario-based, our approach is data-centric: we propose the dimensions along which the parameters that define an ODD can be explicitly captured, together with a categorization of the data that ML-based applications can encounter in operation, whilst identifying their system-level relevance and impact. Specifically, we discuss how those data categories are useful to determine: the requirements necessary to drive the design of ML Models (MLMs); the potential effects on MLMs and higher levels of the system hierarchy; the learning assurance processes that may be needed, and system architectural considerations. We illustrate the underlying concepts with an example of an aircraft flight envelope.