Sydney, New South Wales, Australia
I am a lecturer of Computational Mechanics at the School of Civil and Environmental Engineering, UNSW Sydney, Australia. I have received my PhD in computational geomechanics at the Department of Civil Engineering, Sharif University of Technology, in the year of 2015. My research output is recognised by close to 50 technical publications including scholarly articles, several book chapters, and conference papers. I have secured substantial research funding as a Chief Investigator (CI) through the most prestigious national schemes offered by the Australian Research Council (ARC). In total, I have managed more than $6M funding due to more than 10 projects within 7 years of work experience at UNSW. One of the primary areas of my research has been the hydro-mechanical coupling processes in saturated/unsaturated porous formations. This involves the development of physical models as well as advanced computational frameworks in relation to the hydraulic fracturing treatments in neat, fractured and/or layered domains. This has been in lines with my role as a Chief Investigator (CI) in our Discovery Project with Australian Research Council (ARC) entitled, "Non-differentiable Energy Minimisation For Modelling Fractured Porous Media" In more recent years, I have been investigating the application of deep learning in the study of complex mechanical response of geo-infrastructures by means of the Physics-Informed Neural Networks (PINNs). As a Chief Investigator (CI) in the Research Hub on Resilient and Intelligent Infrastructure Systems (RIIS), I lead "Subtheme 3.2: Physics informed artificial intelligence, machine learning and explanation". The project in particular aims to sustainability, serviceability, resilience, planning, decision making, and safe operations. I contributes to the hub in discovery, inversion, and data processing with the purpose of health monitoring of the infrastructures across Australia in partnership with 25 industry partners, which is a key to sustainability in engineering design and practice. UNSW page: https://www.unsw.edu.au/staff/mohammad-vahab Google Scholar Profile: https://scholar.google.com/citations?hl=en&user=lVI_ZacAAAAJ&view_op=list_works&sortby=pubdate
Key Responsibilities • Teaching undergraduate and postgraduate courses in geotechnical engineering, with an emphasis on practical design, numerical modelling, and real-world civil engineering applications. • Conducting research in geotechnical engineering, computational geomechanics, advanced numerical modelling, and data-driven methods for infrastructure and mining engineering. • Supporting the development of geotechnical engineering at CQUniversity through curriculum development, research growth, laboratory capability, and industry engagement. • Developing collaborative research initiatives with industry, government, and academic partners to address emerging challenges in geotechnical and civil engineering. • Supervising undergraduate and postgraduate research students in computational mechanics, physics-informed AI and related areas. • Contributing to academic leadership, professional engagement, and service within the School of Engineering and Technology.
Key Responsibilities • Concrete Structures: Design and review of residential, infrastructure, commercial projects. In the majority of projects, I have used ETABS to develop the structural model. Meanwhile, I have used ABAQUS and Strand7 to conduct advanced numerical analysis in lines with the requirements of the project. • Soil-Structure Interaction (SSI): At TTW, a frequent task is determining the springs associated with pads and piles. By reviewing geotech reports, particularly borehole logs, I have calculated the upper and lower bound spring stiffness for various projects. I have also assisted in determining pile design actions from the analysis for design checks. • Specialist Engineering Assessment (SEA): Critical underground assets require protective measures. The advance team has conducted many SEAs for Sydney Water and Sydney Metro assets, involving a wide range of structures - from masonry and unreinforced concrete to reinforced concrete sections. • 2D/3D Modelling (FEA): I have extensive experience in modelling geotechnical engineering modelling for: - Retaining walls - Tunnels - Pad footings - Culverts - Piles - Pipes - Excavations
Key Responsibilities • Collaborating with industry partners of RIIS to define requirements and delivery milestones for R & D projects. • Leading the "theme 3: modelling, simulations, and prognostics" team, overseeing predictive modelling, simulation, performance assessment, physics-informed artificial intelligence, machine learning, and explanation. • Conducting fundamental and novel research on the use of physics-informed machine learning in geotechnical engineering. • Staffing and managing a team of R & D members, providing direct leadership and guidance. • Planning and tracking projects, creating key milestones and performance indicators to ensure successful project delivery. • Securing funding from sponsors to support ongoing research and development efforts. • Organising and leading workshops to reach decisions on delivery options and other key technical issues. • Providing high level project reports to industry partners, working groups, executive committee. • Engaging with media and presenting at conferences and engineering communities to promote RIIS's R & D efforts. Key Achievements • Successfully secured $5m funding from the ARC as a Chief Investigator, in collaboration with 20 leading industries in Australia, including Ports Australia, Southeast Water, Azure Mining Technology, Rockfield Technologies, and BHP, among others. • Employed and led a team of 10 researchers to pursue one of five main themes of the project. • Authored and submitted multiple comprehensive reports and scholarly articles on the application of physics-informed neural networks in the areas of elasticity, foundation design, pile-soil interaction, and fracture mechanics.
Key Responsibilities • Conducting cutting-edge research in the field of geotechnical engineering, with a focus on the development and application of advanced computational frameworks. • Contributing to the development of new research initiatives that align with the School's research priorities and strategic goals. • Collaborating with industry partners to identify and address the research needs of the geotechnical engineering industry. • Identifying and securing funding from a variety of sources, including the ARC, industry partners, and other funding bodies. • Supervising and mentoring postgraduate students to ensure timely and high-quality completion of their research projects. Key Achievements • Secured a total of close to $6m funding as a Chief Investigator in collaboration with ARC, leading international industry partners, and local government bodies, such as Hexagon, State Asphalt, PSM, OPEC System, and Roads and Maritime Services. • Further advancing the state-of-the-art in dynamic fracturing by extension of a MATLAB/Julia code for explicit dynamic fracture analysis in geomaterials using energy minimization in the context of discontinuous Galerkin (DG). • Implemented XFEM/phase-field models for fractured porous media and constitutive modelling in commercial software, such as COMSOL and FLAC, to meet the research needs of industry partners and the wider geotechnical engineering community. • Successfully supervised 20 master's projects using Flac2D, Flac3D, and Plaxis 2D in collaboration with the leading industry partners of the school, ensuring timely and high-quality completion of research projects in Tunnelling, Slope Stability, Piles. • Managed and led a team of 5 research and development staff, providing mentorship and guidance to support the development of their research skills and professional growth.
Key Responsibilities • Identified and extracted characteristic features that can differentiate normal I/O patterns with anomalies. • Developed and trained machine learning models based on those features to be able to detect anomalies. Key Achievements • Developed an efficient Python code for a Flexible I/O (FIO) generator, incorporating pre-assigned compression/entropy. • Customized file size distribution for generated files to closely match the best real-world practice.