Journal Articles
- How to learn Physics: A practical review of scientific machine learning Chenaud, M., Alves, J., & Magoulès, F. (2026). Archives of Computational Methods in Engineering. DOI · PDF
- Physics-Informed Graph-Mesh Networks for PDEs: A hybrid approach for complex problems Chenaud, M., Magoulès, F., & Alves, J. (2024). Advances in Engineering Software, 197, 103758. DOI · arXiv
Conference Articles
- Certificates for complex-compatible learned cochain Laplacians Anwer, N., Chenaud, M., & Elizondo, D. (2026). International Conference on Machine Learning (ICML), main track. OpenReview
- Enhancing information flow in graph neural networks for scientific machine learning Chenaud, M., Alves, J., & Magoulès, F. (2025). The Seventh International Conference on Artificial Intelligence, Soft Computing, Machine Learning and Optimization in Engineering. DOI · HAL
- Physics-Informed Graph Convolutional Networks: Towards a generalized framework for complex geometries Chenaud, M., Alves, J., & Magoulès, F. (2023). The Sixth International Conference on Soft Computing, Machine Learning and Optimization in Civil, Structural and Environmental Engineering. DOI · arXiv
In Preparation & Under Review
- Pointwise error estimates for numerical physics-informed neural networks Chenaud, M., Anwer, N., Alves, J., & Magoulès, F. (2026). Submitted to Computer Methods in Applied Mathematics and Engineering. Under review.
- A numerical approach to physics-informed learning for non-analytic problems Chenaud, M., Alves, J., & Magoulès, F. (2026). Submitted to Computer Methods in Applied Mathematics and Engineering. Under review.
- Enhancing information flow in graph neural networks through geometry-preserving hierarchical connectivity Chenaud, M., Alves, J., & Magoulès, F. (2026). Submitted to Computers & Structures. Under review.