DesCartes Builder: Machine-Learning Based Digital Twins
Authors/Creators
-
1.
Nanyang Technological University
-
2.
CNRS@CREATE Ltd (Singapore)
-
3.
Centre National de la Recherche Scientifique
- 4. IPAL
Description
DesCartes Builder is a tool to create digital twin (DT) pipelines using the Function+Data Flow (FDF) domain-specific language for machine-learning-based DT modeling. It provides three high-level features:
- visual specification of the DT pipeline with implicit typing to detect common errors,
- automatic generation of executable models from the FDF specification,
- validation of design goals and ML models.
Installers for Windows/macOS/Linux are available alongside documentation (`BUILDER_DOC.pdf`).
The sources are available at:
The tool is described in details at E. de Conto, B. Genest, A. Easwaran, N. Ng and S. Menon, "DesCartes Builder: A Tool to Develop Machine-Learning Based Digital Twins," 2025 ACM/IEEE 28th International Conference on Model Driven Engineering Languages and Systems Companion (MODELS-C), Grand Rapids, MI, USA, 2025, pp. 129-133, doi: 10.1109/MODELS-C68889.2025.00028.
Acknowledgments
This research is part of the program DesCartes and is supported by the National Research Foundation, Prime Minister’s Office, Singapore, under its Campus for Research Excellence and Technological Enterprise (CREATE) program.
Technical info
To install DesCartes Builder, download the binary for your operating system and install it in the usual manner. You may need to bypass security checks as our binary is not yet signed (for Linux, we provide an AppImage that can be directly executed).
Files
BUILDER_DOC.pdf
Additional details
Related works
- Is supplement to
- Conference paper: 10.1145/3664646.3664759 (DOI)
- Conference paper: 10.1109/MODELS-C68889.2025.00028 (DOI)
Funding
- National Research Foundation
- DesCartes