# Implementation of airborne ML models with semantics preservation

arXiv: https://arxiv.org/abs/2509.18681 · HTML: https://mlsanity.com/paper/2509.18681/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 33 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 4 of 4)

- [Robustness Assessment of a Runway Object Classifier for Safe Aircraft Taxiing](https://mlsanity.com/paper/2402.00035/) (2024)
- [Data-centric Operational Design Domain Characterization for Machine Learning-based Aeronautical Products](https://mlsanity.com/paper/2307.07681/) (2023)
- [Formal description of ML models for unambiguous implementation](https://mlsanity.com/paper/2307.12713/) (2023)
- [Efficient and Mathematically Robust Operations for Certified Neural Networks Inference](https://mlsanity.com/paper/2401.08225/) (2024)

## Built on by (most cited first, 1 of 1)

- [Towards On-Board Implementation of ML-Based Helicopter Weight Estimator](https://mlsanity.com/paper/2608.19210/) (2026)

## Abstract (arXiv)

Machine Learning (ML) may offer new capabilities in airborne systems. However, as any piece of airborne systems, ML-based systems will be required to guarantee their safe operation. Thus, their development will have to be demonstrated to be compliant with the adequate guidance. So far, the European Union Aviation Safety Agency (EASA) has published a concept paper and an EUROCAE/SAE group is preparing ED-324. Both approaches delineate high-level objectives to confirm the ML model achieves its intended function and maintains training performance in the target environment. The paper aims to clarify the difference between an ML model and its corresponding unambiguous description, referred to as the Machine Learning Model Description (MLMD). It then refines the essential notion of semantics preservation to ensure the accurate replication of the model. We apply our contributions to several industrial use cases to build and compare several target models.