M:3L research
M:3L develops machine-learning systems constrained and guided by physical laws for computational mechanics and scientific computing.
The laboratory combines differentiable finite element solvers, physics-informed neural networks, graph neural networks, neural fields, and generative methods. These approaches connect data-driven learning with governing equations and numerical simulation.
Current applications include virtual system modeling and diagnostics, inverse design of elastic metamaterials, wave-cloaking structures, and manufacturable microstructures.
Ordinary black-box machine learning can fit input-output observations without representing why a physical system behaves as it does. Physics-driven ML instead interacts with governing equations, numerical solvers, conservation laws, boundary conditions, or simulation data so predictions and designs can be assessed against physical constraints.
M:3L combines learned models with finite element simulation and numerical optimization. Depending on the problem, physics may enter through the architecture, loss function, differentiable solver, generated training data, or validation loop.
These are relevant application domains, not claims that every application is deployed.
David Aznaurov, Davit Piliposyan, Danila Rukhovich, Sébastien Guenneau
A neural-field and differentiable-FEM framework for designing broadband Rayleigh-wave carpet cloaks within realizable Cauchy materials and mapping the optimized fields to explicit manufacturable microstructures.
We have published a preprint on arXiv with Imperial College London collaborator Sébastien Guenneau. The paper presents a neural-field and differentiable-FEM framework for designing broadband Rayleigh-wave carpet cloaks using physically realizable Cauchy materials. It then maps the optimized fields to explicit manufacturable microstructures through conditional diffusion and inverse design. In finite element validation, the homogenized microstructure model recovers approximately 97% of the defect-free reference surface-displacement magnitude, while the fully resolved geometry recovers approximately 76%.
M:3L has received access to NVIDIA H100 GPUs through the AI Virtual Institute, a program of Armenia's Ministry of High-Tech Industry. This support expands our capacity to design elastic metamaterials and wave-cloaking structures. The research combines differentiable FEM, neural-field optimisation, and generative design to create manufacturable microstructures for broadband Rayleigh-wave cloaking and chiral metamaterials.
We are partnering with Yerevan State University's Physical-Technical Laboratory and Department of Radiophysics and Telecommunications to build a digital engineering platform for virtual system modeling and diagnostics. The platform will create digital twins of real experimental systems that scientists can query in plain language for fast, accurate answers, powered by machine-learning models trained on thousands of physics simulations. The project is funded by the Higher Education and Science Committee of RA MESCS, with co-financing from the Enterprise Incubator Foundation.