# Function+Data Flow: A Framework to Specify Machine Learning Pipelines for Digital Twinning

arXiv: https://arxiv.org/abs/2406.19670 · HTML: https://mlsanity.com/paper/2406.19670/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 40 references that are in the map.
- First posted on arXiv 28 Jun 2024.

## Builds on (most cited first, 3 of 3)

- [To Type or Not to Type? A Systematic Comparison of the Software Quality of JavaScript and TypeScript Applications on GitHub](https://mlsanity.com/paper/2203.11115/) (2022)
- [Learning stable reduced-order models for hybrid twins](https://mlsanity.com/paper/2106.03464/) (2021)
- [Tierkreis: A Dataflow Framework for Hybrid Quantum-Classical Computing](https://mlsanity.com/paper/2211.02350/) (2022)

## Built on by (most cited first, 2 of 2)

- [DesCartes Builder: A Tool to Develop Machine-Learning Based Digital Twins](https://mlsanity.com/paper/2508.17988/) (2025)
- [Building real-time digital twin instances with Function+Data Flow: user evaluation and extension for iterative pipelines](https://mlsanity.com/paper/2608.18480/) (2026)

## Abstract (arXiv)

The development of digital twins (DTs) for physical systems increasingly leverages artificial intelligence (AI), particularly for combining data from different sources or for creating computationally efficient, reduced-dimension models. Indeed, even in very different application domains, twinning employs common techniques such as model order reduction and modelization with hybrid data (that is, data sourced from both physics-based models and sensors). Despite this apparent generality, current development practices are ad-hoc, making the design of AI pipelines for digital twinning complex and time-consuming. Here we propose Function+Data Flow (FDF), a domain-specific language (DSL) to describe AI pipelines within DTs. FDF aims to facilitate the design and validation of digital twins. Specifically, FDF treats functions as first-class citizens, enabling effective manipulation of models learned with AI. We illustrate the benefits of FDF on two concrete use cases from different domains: predicting the plastic strain of a structure and modeling the electromagnetic behavior of a bearing.