Engineering
Liuxin Chen
- Lecturer
- liuxin.chen@jcu.edu.au
Mohamadreza Chalak Qazani
- Lecturer, Mechanical Engineering
- mohamadreza.chalakqazani@jcu.edu.au
Lewis Gooch
- Lecturer
- lewis.gooch@jcu.edu.au
Judy Yang
- Postdoctoral Research Fellow, Applied AI for Forestry Weed Detection and Mapping
- judy.yang@jcu.edu.au
Bouchra Senadji
- Head, Engineering
- bouchra.senadji@jcu.edu.au
Alzayat Saleh
- AIMS@JCU Postdoctoral Research Fellow, Marine Science Technology
- alzayat.saleh@jcu.edu.au
Anne Steinemann
- Adjunct Professor
- anne.steinemann@jcu.edu.au
Nico Adams
- Professor, Electronic Systems & IoT Engineering
- nico.adams@jcu.edu.au
Elsa Antunes
- Associate Professor, Mechanical Engineering
- elsa.antunes1@jcu.edu.au
Eric Wang
- Senior Lecturer, Electronic Systems and IoT Engineering
- eric.wang@jcu.edu.au
Sustainable assessment of nickel production residue as engineered landfill. (Old ID 27759)
Peter To
01 Sep 2022 - 31 Jan 2024
The residue left after leaching is a silica-rich sand material, which will be a washed, filtered and neutralised with magnesia, before being stockpiled on site for over 36 months. Numerous options for the end use of this leach residue have been investigated and were previously reported by JCU. These included re-use as a building product in bricks and as an engineered fill. The results favoured the material as a potential fill material and since these results were published numerous potential sites requiring fill in and around the Townville region have been identified. For this to be viable the mechanical and chemical properties of the material must be further investigated. If successful, the results of this test program should indicate eligibility for an End of Waste Code (EOWC).
Deployable Waste to Energy System (Old ID 27701)
Mohan Jacob
24 May 2022 - 31 Dec 2025
JCU has developed a customised microwave pyrolysis unit that can be used to conduct various experiments and control the pyrolysis conditions to convert different waste materials and generate by-products such as gas, oil and char. This project aims to develop a scale-up Deployable Waste to Energy processing unit that can process up to 50 kg of waste at a time. The project will be done in partnership with CUBIC, who will manage the project delivery.
Development of a Ground-Based AI Vision System for Fine-Scale Weed Detection in Tropical Reforestation
Tao Huang
09 Jan 2026 - 08 Jan 2027
Tropical reforestation initiatives face significant early-stage threats from fast-growing weed species that compete with young seedlings for sunlight, nutrients, and water. While drone-based monitoring provides valuable aerial perspectives, it often lacks the resolution needed to detect weeds growing in close proximity to seedlings or partially hidden by surrounding vegetation. To complement aerial detection, this project proposes the development of a ground-based computer vision system for fine-scale weed detection and growth dominance estimation, enabling precision weeding and decision support in reforestation programs. This first year of the TerraWeed project will focus on hardware setup, initial dataset creation, and the development of deep learning models for close-range classification and segmentation of weeds versus tree seedlings. This foundational work will provide a basis for deploying intelligent ground-based systems that support high-precision intervention in complex tropical environments.
Foundational Development of Drone-Based AI for Early Weed Detection in Tropical Reforestation
Tao Huang
01 Nov 2025 - 08 Jan 2027
Reforestation in tropical regions faces a major ecological and operational challenge: the rapid proliferation of aggressive weed species during the early growth stages of trees. These weeds often outcompete young seedlings for critical resources such as light, nutrients, and water, leading to high mortality rates and undermining the success of environmental restoration, carbon sequestration, and biodiversity initiatives. Current weed monitoring methods are manual, labor-intensive, and impractical for large-scale or remote reforestation projects. This project proposes to address this challenge by developing an AI-powered aerial monitoring system that uses drones to detect and map weed infestations in tropical reforestation zones. Year 1 will focus on establishing the technical foundation for this system, including sensor configuration, data collection protocols, dataset creation, and initial model development.
Airbag deployment test (Old ID 30048)
Mehdi Khatamifar
12 Jun 2023 - 31 Aug 2023
AEP Advance Engineering is planning to study airbag deployment in a car after modifications done on the car. This test will study an airbag deployment along the ceiling using high-speed camera at high frame per second rate of 5000. This study aims to investigate the deployment stages of the airbag and visually capture this process, so modifications applied on the car does not interfere with safety.
Vanadium Extraction and Processing Innovation Project’
Mahmood Sadat Noori
27 Feb 2026 - 30 Nov 2028
This project aims to advance the projects related to vanadium extraction and processing from the Toolebuc Formation in North Queensland and to develop capacity in North Queensland to assist with the emerging vanadium economy .
Data-Efficient AI for Precision Weed Monitoring in Tropical Forests
Tao Huang
01 Mar 2026 - 31 Dec 2029
Reforestation plays a critical role in enhancing climate resilience, increasing carbon sequestration, and supporting ecosystem restoration in tropical regions. However, early-stage seedlings face a major threat from the rapid spread of aggressive weed species that compete for essential resources such as light, nutrients, and water. Traditional weed control approaches are labour-intensive, costly, and unsuitable for large or remote reforestation sites, making automated solutions highly desirable.
This PhD project aims to develop AI-driven computer vision systems for precise and efficient weed detection in tropical reforestation settings. Using aerial and ground imagery, the project will focus on building robust and accurate algorithms capable of operating under challenging environmental conditions. To reduce reliance on large annotated datasets, the research will explore data-efficient learning strategies, enabling scalable and cost-effective model development.
The system will be designed for deployment on drones and ground-based platforms, supporting real-time monitoring and decision-making in the field. By improving the accuracy and efficiency of weed detection, the project will help land managers target interventions more effectively, enhance seedling survival rates, and increase the overall success of reforestation programs. This work will contribute to advancing the application of AI and computer vision for environmental restoration, with strong pathways for real-world adoption and commercialisation through industry collaboration.
Feasibility of Vibration-Based Projectile Impact Localisation on Steel Targets
Tao Huang
02 Mar 2026 - 01 Mar 2027
This project will investigate whether vibration signals measured directly on steel shooting targets can be used to reliably determine the two-dimensional impact location of projectiles. The work focuses on the sensing and signal-processing components of impact localisation, while the overall system design, wireless communications, and firearm testing will be handled separately by TACRDLABS.
The core idea is to attach a small array of vibration sensors to the rear of a steel target and analyse the resulting waveforms when an impact occurs. Different sensor technologies will be considered, such as piezoelectric sensors, contact microphones, and knock sensors. The project will study how sensor type, mounting method (for example, adhesive versus bolt-on), and placement on the target influence signal quality, especially the earliest part of the vibration response that is most informative for localisation.
High-sample-rate vibration data from live firearm tests on steel targets will be collected and supplied by TACRDLABS. James Cook University will complement this with controlled mechanical impact experiments, such as hammer or pendulum strikes at known locations on instrumented targets. These datasets will be curated with associated metadata (sensor type, mounting method, target size, impact location, and impact type) to enable systematic analysis.
Using these datasets, the project will develop proof-of-concept signal processing methods and Python scripts to detect impacts, extract the earliest identifiable arrivals across multiple sensors, and estimate impact coordinates using time-difference-of-arrival style approaches. The analysis will examine how localisation performance depends on sensor layout, target size, and mounting method, and will explore strategies to improve robustness, such as increasing sensor count or applying appropriate filtering.
Performance will be quantified in terms of localisation error, timing precision requirements, and detection reliability under a range of realistic conditions. The findings will be synthesised into practical design rules and guidelines for sensor selection, coupling, and placement on steel targets, along with recommendations on timing and sampling requirements for future embedded implementations.
Overall, the project will deliver a focused feasibility assessment of vibration-based projectile impact localisation on steel targets, along with example algorithms and configuration guidelines that TACRDLABS can use in the design of an integrated smart target system for defence, law enforcement, and recreational shooting applications.
Microgrid Systems with Integrated Waste-to-Energy source for Forward-Deployed Defence Infrastructure
Yang Du
16 Mar 2026 - 16 Nov 2027
This project proposes the design and validation of a renewable, deployable microgrid that integrates various inputs such as waste-to-energy (W2E) systems, solar PV, batter and diesel generator. Designed for Defence operations in Northern Australia, the system will convert operational waste into usable energy (e.g., syngas or bio-oil) and provide reliable power for charging or storing energy in portable devices. It aims to enhance energy resilience, reduce reliance on fuel logistics, and support sustainable operations in remote or contested environments.
Generation Signalling Device (GSD) using AFLC signals
Bruce Belson
09 Mar 2026 - 25 Apr 2026
The proposed project involves the design and development of a prototype Generation Signalling Device (GSD) intended for use within Queensland electricity distribution networks operated by Ergon Energy and Energex.
Ergon and Energex manage grid stability by transmitting Audio Frequency Load Control (AFLC) ripple control signals superimposed on the mains supply to initiate load shedding and generation control. In solar photovoltaic systems, a GSD functions as an interface device that detects these AFLC signals and communicates corresponding shutdown or control commands to a connected inverter to assist in maintaining network balance. The project is being run under the aegis of the IoT stream of EE4500 2026 Block 2.
Start Date:
26 Mar 2026
Start Date:
23 Oct 2025
Start Date:
22 Oct 2025
Start Date:
25 Nov 2025
Start Date:
03 Sep 2025
Reseracher:
Stephanie Baker
(Senior Lecturer, Electronic Systems and Internet of Things Engineering)
Start Date:
01 Jan 2019
Start Date:
01 Jan 2022
Start Date:
01 Jan 2019