Civil engineering internships

Supervisor: Dr Jiaying Li

Eligibility: 

    -    This project is open to applications from students with broad background in engineering            and science discipline, , ideally with relevant skills in GIS and R or Python.

    -    WAM>75.  Students applying for projects within the School of Civil Engineering must have            completed at least 72 credit points at the time of application.

Project Description:

Chemical exposure serves as an important indicator of public health and wellbeing. In this project, we will link chemical contaminant data to population socioeconomics using QGIS or ArcGIS, and identify the drivers of changes. In this project, students will gain hands-on experience in data collection, data processing, GIS mapping, and multivariable analysis. The project will be conducted on-site, with desktop work using GIS software required. Students may be asked to produce a report or presentation summarizing their work at the end of the project. 

Requirement to be on campus: No

Supervisor: Dr Jiaying Li

Eligibility: This project is open to applications from students with a background in broad engineering and science discipline.  WAM>75.  Students applying for projects within the School of Civil Engineering must have completed at least 72 credit points at the time of application.

Project Description:

Emerging contaminants like pose an increasing threat to human and environmental health. Given their widespread presence in the environment, there is an urgent need for rapid, practical, and cost-effective methods to detect ECs in water environments. In this project, we will design and develop simple and inexpensive sensing methods for chemicals. In this project, students will gain hands-on experience in designing and developing novel sensors for detecting chemicals in water samples. The project will be conducted in the laboratory with chemical experiments and analysis required. Students may be asked to produce a report or presentation summarizing their work at the end of the project.

Requirement to be on campus: Yes *dependent on government’s health advice

Supervisor: A/Prof Yixiang Gan

Eligibility:

    -    Civil engineering degree with WAM>85, combined degree with computer science major is            highly recommended [Compulsory]

    -     Students applying for projects within the School of Civil Engineering must have            completed at least 72 credit points at the time of application.

    -     Basic background in soil mechanics (student should have learned CIVL2410, familiar with             porosity, solid deformability, etc.) [Compulsory]

    -    Strong data processing and algorithmic skills (student who have learned data structure            and algorithms, e.g. COMP2123, with HD result is highly recommended) [Compulsory]

    -    Previous experience in computer vision, especially with Meta’s SAM2/SAM3 models            [Preferred]

    -      Ability to explain code to project partners verbally and in writing, and to             adjust/refine/fine-tune AI models and construct/debug/optimize data-processing code             in line with project needs [Preferred]

    -      Previous research and publication experience [Preferred]

Project Description:

Geological storage of carbon dioxide (CO₂) and hydrogen (H₂) is a key strategy for reducing carbon emissions. Ensuring the safety and efficiency of subsurface gas storage requires improved understanding of gas migration within porous media. While most previous studies have focused on single injections in rigid porous media, far less attention has been given to cyclic injection regimes in deformable porous systems. This project will investigate gas migration, trapping, and deformation processes using a quasi-two-dimensional Hele-Shaw cell packed with soft hydrogel particles. This experimental platform will enable systematic investigation of the coupled interactions between multiphase flow, porous media deformation, and cyclic injection dynamics. Experimental videos will be analysed using Meta’s Segment Anything Model (SAM3) to extract quantitative information on gas distribution and migration patterns. The resulting data will be used to generate statistical analyses that advance the mechanistic understanding of gas transport in deformable porous systems.

Requirement to be on campus: No

Supervisor: Dr Faham Tahmasebinia

Eligibility: WAM>75.  Students applying for projects within the School of Civil Engineering must have completed at least 72 credit points at the time of application.

Project Description:

Implementing Artificial Intelligence (AI) techniques in the enhancement of steel moment frame structures signifies a groundbreaking shift in how these essential engineering systems are designed, analysed, and optimized. This review covers a broad array of AI strategies, such as machine learning algorithms, evolutionary algorithms, neural networks, and advanced optimization methods, which are utilized to tackle various challenges within the sector. The consolidation of these research findings underscores the interdisciplinary approach of AI in structural engineering, highlighting the integration of domain expertise with sophisticated computational methods. This comprehensive synthesis is a crucial resource for researchers, practitioners, and policymakers looking to grasp the cutting-edge developments in AI-enabled optimization of steel moment frame structures.

References: Mohsen Soori, Fooad Karimi Ghaleh Jough. Artificial Intelligent in Optimization of Steel Moment Frame Structures: A Review. International Journal of Structural and Construction Engineering, 2024.

Requirement to be on campus: No

Supervisor: Dr Faham Tahmasebinia

Eligibility: WAM>75.  Students applying for projects within the School of Civil Engineering must have completed at least 72 credit points at the time of application.

Project Description:

Artificial intelligence encompasses a range of techniques and fields, such as vision, perception, speech and dialogue, decision-making, planning, problem-solving, robotics, and other areas conducive to autonomous learning. This study focuses on exploring the potential of AI algorithms to enhance safety throughout different phases of the construction process. The research reviewed the scientific literature on applying artificial intelligence in construction and optimising these processes.

References: https://www.mdpi.com/1424-8220/23/21/8740

Requirement to be on campus: No