6 papers
Separable neural architectures as a primitive for unified predictive and generative intelligence
Reza T. Batley, Apurba Sarker, Rajib Mostakim +2
Intelligent systems across physics, language and perception often exhibit factorisable structure, yet are typically modelled by monolithic neural architectures that do not explicit…
Efficient Aircraft Design Optimization Using Multi-Fidelity Models and Multi-fidelity Physics Informed Neural Networks
Apurba Sarker
Aircraft design optimization traditionally relies on computationally expensive simulation techniques such as Finite Element Method (FEM) and Finite Volume Method (FVM), which, whil…
A Kernel-based Resource-efficient Neural Surrogate for Multi-fidelity Prediction of Aerodynamic Field
Apurba Sarker, Reza T. Batley, Darshan Sarojini +1
Surrogate models provide fast alternatives to costly aerodynamic simulations and are extremely useful in design and optimization applications. This study proposes the use of a rece…
Process Microstructure Coupling in Reduced Gravity Laser Welding via Open-Source Multiphysics Simulation Framework
Rakibul Islam Kanak, Taslima Hossain Sanjana, Apurba Sarker +1
Supplying spare parts from Earth for in space repair is economically prohibitive and logistically slow, posing a major barrier to sustainable space operations. As lunar and Martian…
Gravity and Composition Modulated Solidification and Mechanical Properties of Al-Cu Nanostructures
Apurba Sarker, Sourav Saha
The future of space exploration and human settlement beyond Earth hinges on a deeper understanding of in space manufacturing processes. The unique physical conditions and scarcity…
Graph neural network framework for energy mapping of hybrid monte-carlo molecular dynamics simulations of Medium Entropy Alloys
Mashaekh Tausif Ehsan, Saifuddin Zafar, Apurba Sarker +2
Machine learning (ML) methods have drawn significant interest in material design and discovery. Graph neural networks (GNNs), in particular, have demonstrated strong potential for…