Duy (Edward) Le
Machine Learning & Computational Modelling Researcher
Mulgrave, Melbourne, Australia
📧 Email: duytrangiale@gmail.com
đź”— LinkedIn: linkedin.com/in/duytrangiale
đź’» GitHub: github.com/duytrangiale
đź“š Google Scholar: scholar.google.com
About
I am a machine learning researcher with a PhD in computational modelling and deep learning, working at the intersection of:
- physics-based simulation
- scientific computing
- neural network surrogate models
My recent work focuses on developing deep-learning surrogates for granular flow simulations, replacing expensive Discrete Element Method (DEM) solvers with fast, data-driven models while preserving physical fidelity.
I am particularly interested in research and engineering roles involving ML for physical systems, AI for engineering applications, and scientific computing.
Research Interests
- Machine learning for physical and engineering systems
- Surrogate modelling for numerical simulations
- Discrete Element Method (DEM) and granular materials
- Scientific computing and high-performance computing (HPC)
- 3D geometry, rotations and particle dynamics
- Physics-informed and data-driven modelling
Highlights
-
🎓 PhD in Computational Modelling & Deep Learning
Federation University, Australia – thesis on accelerated surrogate modelling of granular materials using artificial neural networks. -
🧠Developed deep-learning surrogates achieving 70–120× speedups over DEM simulations while maintaining physically meaningful behaviour.
-
đź’» Built large-scale data pipelines and training frameworks for 3D particle simulations, using Python, PyTorch, NumPy/Pandas, and Slurm-based HPC workflows.
-
đź“„ First author of peer-reviewed publications in machine learning, computer vision, robotics, and granular flow modelling.
Selected Projects
1. Neural Surrogate for 3D Granular Flow
Keywords: Deep learning, DEM, surrogate modelling, 3D convolutions, industrial flows
- Developed a neural-network surrogate model to approximate 3D granular flow dynamics in industrial equipment such as hoppers, rotating drums and blade mixer.
- Designed 3D continuous convolutional neural network architectures to capture particle interactions and boundary effects.
- Achieved significant runtime acceleration (70–120×) compared to DEM while preserving key physical metrics such as mixing behaviour and energy trends.
- Implemented full training and evaluation pipeline, including data preprocessing, batching, model training, and physical post-processing.
Publication:
- “A Neural Network Surrogate for Modelling Granular Flow Dynamics in Industrial Applications with Dynamic Boundary Conditions”, Powder Technology, 2025 (Under review).
- “Machine Learning Accelerated Prediction of 3D Granular Flows in Hoppers”, The 33rd International Conference on Artificial Neural Networks, 2024.
2. DEM Data Tools & Physical Metrics
Keywords: Scientific computing, data analysis, physical validation
- Developed Python utilities to process DEM simulation outputs into ML-ready datasets.
- Implemented computation of physically relevant metrics:
- mixing entropy and composition profiles
- translational and rotational kinetic energy
- angular velocity fields and alignment measures
- collision-based metrics such as coefficients of restitution
- Used these tools to benchmark neural network surrogates against high-fidelity DEM baselines.
3. Low-Cost Pseudo-LiDAR for 3D Object Detection
Keywords: Computer vision, 3D perception, autonomous driving
- Proposed a cost-efficient pseudo-LiDAR approach based on simple linear iterative clustering (SLIC) to approximate 3D structure from 2D imagery.
- Evaluated the method for 3D object detection tasks, demonstrating the potential of low-cost perception pipelines for autonomous driving applications.
Publication:
“Simple linear iterative clustering based low-cost pseudo-LiDAR for 3D object detection in autonomous driving”, Multimedia Tools and Applications, 2023.
4. Haptic Hand Exoskeleton for Force Feedback
Keywords: Robotics, haptics, mechatronics
- Designed and evaluated a force-feedback hand exoskeleton for haptic and virtual reality applications.
- Focused on efficient mechanical design and control strategies to deliver realistic feedback while remaining lightweight and affordable.
Publications:
- “An Efficient Force-Feedback Hand Exoskeleton for Haptic Applications”, International Journal of Intelligent Robotics and Applications, 2021.
- “A Design of Haptic Hand Exoskeleton for Virtual Reality Applications”, ASYU 2021 (IEEE).
Selected Publications
Below are a few representative works:
-
A Neural Network Surrogate for Modelling Granular Flow Dynamics in Industrial Applications with Dynamic Boundary Conditions
Duy Le, Gary W. Delaney, Linh Nguyen, Truong Phung, David Howard, Gayan Kahandawa, Manzur Murshed
Powder Technology, 2025 (under review). -
Machine Learning Accelerated Prediction of 3D Granular Flows in Hoppers
Duy Le, Linh Nguyen, Truong Phung, David Howard, Gayan Kahandawa, Manzur Murshed, Gary W. Delaney
33rd International Conference on Artificial Neural Networks (ICANN), 2024. -
Simple linear iterative clustering based low-cost pseudo-LiDAR for 3D object detection in autonomous driving
Duy Le and Linh Nguyen
Multimedia Tools and Applications, 2023. -
An Efficient Force-Feedback Hand Exoskeleton for Haptic Applications
Duy Le and Linh Nguyen
International Journal of Intelligent Robotics and Applications, 2021. -
An Efficient Multi-Vehicle Routing Strategy for Goods Delivery Services
Duy Le, Ying Men, Yunkang Luo, Yixuan Zhou, Linh Nguyen
IEEE International Conference on Advanced Robotics and its Social Impacts, 2021.
Skills Overview
Languages: Python, C, MATLAB, Java
ML/AI: PyTorch, TensorFlow, Scikit-learn, Open3D
Data & Scientific Computing: NumPy, Pandas, SciPy, data pipelines
Simulation & Modelling: Discrete Element Method (DEM), numerical methods, optimisation
Tools: Git, Slurm, Linux, HPC clusters
Visualisation: Matplotlib, seaborn, ParaView
Other: CUDA (basic), LaTeX, scientific writing
CV & Contact
- 📄 CV / Résumé: Download PDF
- 📧 Email: duytrangiale@gmail.com
- đź”— LinkedIn: linkedin.com/in/duytrangiale
- đź’» GitHub: github.com/duytrangiale
- đź“š Google Scholar: scholar.google.com
Please feel free to reach out regarding opportunities in machine learning, scientific computing, and research engineering.