
Overview
Background
Dr Nikodem Rybak is a researcher specialising in advanced machine learning techniques that drive data-informed decision-making in complex and dynamic systems. His work spans multiple domains, including sustainable resource management, critical infrastructure resilience, and health, safety, and environmental risk assessment.
Dr Rybak's background combines expertise in developing transparent machine learning approaches with a strong focus on interpretability, enabling stakeholders to understand and trust the insights generated. His work leverages cutting-edge natural language processing methods to transform vast amounts of textual data into clear, actionable information. This approach fosters evidence-based strategies and supports effective governance, policy development, and organisational leadership.
Over the past decade, Dr Rybak has collaborated with industry partners, government agencies, and interdisciplinary research teams to address pressing challenges such as decarbonisation, resource allocation, and operational risk mitigation. By integrating robust predictive analytics, complex systems modelling, and innovative data visualisations, his research enables the uncovering of patterns, improvement of forecasting accuracy, and support of the sustainability of diverse systems.
Dr Rybak's work ultimately aims to empower decision-makers with tools that offer transparency, foster trust, and encourage responsible innovation. Through research on refinement of algorithms, methods, and applications, he strives to ensure that artificial intelligence serves as a reliable catalyst for positive social, economic, and environmental outcomes.
Availability
- Dr Nikodem Rybak is:
- Available for supervision
- Media expert
Fields of research
Qualifications
- Doctor of Philosophy, The University of Queensland
Research interests
-
Explainable Artificial Intelligence for Complex Systems
Research on machine learning methods that provide transparent and interpretable insights into complex systems, including social, economic, and environmental networks. The focus is on advancing explainable AI techniques to improve stakeholder trust, inform decision-making, and enhance the sustainability and resilience of real-world applications.
-
Natural Language Processing and Data-Driven Problem Solving
Development and refinement of NLP approaches enable effective extraction, understanding, and analysis of unstructured text data. This research aims to transform raw linguistic inputs into actionable insights, enhance predictive analytics, and support informed decisions across diverse domains such as health, safety, and decarbonisation efforts.
-
AI-Based Risk Management and Predictive Analytics
Integration of machine learning and modelling techniques to identify, quantify, and mitigate risks in industrial and environmental contexts. Through predictive analytics and scenario-based simulations, this work facilitates the anticipation of challenges, optimisation of resource allocation, and improvement of long-term strategic planning.
-
Advanced AI-Based Predictive Systems
Design and implementation of cutting-edge machine learning models to accurately forecast operational metrics, detect anomalies, and guide strategic decision-making processes. This research supports industries in optimising efficiency, maintaining robust supply chains, and driving sustainable growth through data-driven predictions and continuous improvement strategies.
Research impacts
Dr Rybak's research in explainable artificial intelligence and predictive analytics has a significant impact on various sectors by enhancing efficiency, safety, and sustainability. His development of transparent machine learning models allows organisations to identify potential risks early, allocate resources more effectively, and strengthen their resilience against unforeseen challenges.
Through partnerships with industry, government, and community stakeholders, Dr Rybak's research drives innovation that positively influences the broader economy and society. His efforts empower decision-makers to adopt evidence-based strategies that enhance productivity, and sustainability, ensuring that artificial intelligence serves as a force for good in real-world applications.
Works
Search Professor Nikodem Rybak’s works on UQ eSpace
2024
Journal Article
Exploring the impacts of automation in the mining industry: a systematic review using natural language processing
Codoceo-Contreras, Loreto, Rybak, Nikodem and Hassall, Maureen (2024). Exploring the impacts of automation in the mining industry: a systematic review using natural language processing. Mining Technology: Transactions of the Institutions of Mining and Metallurgy, 133 (3), 191-213. doi: 10.1177/25726668241270486
2024
Book Chapter
Artificial Intelligence Applications for Workplace Safety : An In-Depth Examination
Rybak, Nikodem and Hassall, Maureen (2024). Artificial Intelligence Applications for Workplace Safety : An In-Depth Examination. Encyclopedia of Information Science and Technology. (pp. 1-19) Hershey, PA United States: IGI Global. doi: 10.4018/978-1-6684-7366-5.ch085
2023
Other Outputs
Bowdens Silver - Research Review and Recommendations
Micklethwaite, Steven, Cook, Nicholas and Rybak, Nikodem (2023). Bowdens Silver - Research Review and Recommendations. Brisbane, Queensland: The University of Queensland, Sustainable Minerals Institute.
2023
Book Chapter
Machine learning-enhanced text mining as a support tool for research on climate change : theoretical and technical considerations
Rybak, Nikodem and Hassall, Maureen (2023). Machine learning-enhanced text mining as a support tool for research on climate change : theoretical and technical considerations. 5G, artificial intelligence, and next generation internet of things. (pp. 86-122) edited by Patricia Ordóñez de Pablos and Xi Zhang. Hershey, PA, United States: IGI Global. doi: 10.4018/978-1-6684-8634-4.ch004
2022
Journal Article
What can machine learning teach us about Australian climate risk disclosures?
Harker, Callan, Hassall, Maureen, Lant, Paul, Rybak, Nikodem and Dargusch, Paul (2022). What can machine learning teach us about Australian climate risk disclosures?. Sustainability, 14 (16) 10000, 10000. doi: 10.3390/su141610000
2022
Book Chapter
Machine learning enhanced decision-making: applications of Industry 4.0
Rybak, Nikodem and Hassall, Maureen (2022). Machine learning enhanced decision-making: applications of Industry 4.0. Handbook of smart materials, technologies, and devices. (pp. 477-517) edited by Chaudhery Mustansar Hussain and Paolo Di Sia. Cham, Switzerland: Springer International Publishing. doi: 10.1007/978-3-030-84205-5_20
2021
Conference Publication
Deep learning unsupervised text-based detection of anomalies in U.S. Chemical Safety and Hazard Investigation Board reports
Rybak, Nikodem and Hassall, Maureen (2021). Deep learning unsupervised text-based detection of anomalies in U.S. Chemical Safety and Hazard Investigation Board reports. International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), Mauritius, Mauritius, 7-8 October 2021. Piscataway, NJ United States: IEEE. doi: 10.1109/iceccme52200.2021.9590834
2021
Journal Article
Tracking conflict and emotions with a computational qualitative discourse analytic support approach
Rybak, Nikodem and Angus, Daniel J. (2021). Tracking conflict and emotions with a computational qualitative discourse analytic support approach. PLoS ONE, 16 (5 May) e0251186, 1-29. doi: 10.1371/journal.pone.0251186
2020
Other Outputs
Technical considerations for the application of deep learning methods for multimodal emotion recognition
Rybak, Nikodem (2020). Technical considerations for the application of deep learning methods for multimodal emotion recognition. PhD Thesis, School of Information Technology and Electrical Engineering, The University of Queensland. doi: 10.14264/bf3427d
2017
Conference Publication
New real-time methods for operator situational awareness retrieval and higher process safety in the control room
Rybak, Nikodem, Hassall, Maureen, Parsa, Kourosh and Angus, Daniel J. (2017). New real-time methods for operator situational awareness retrieval and higher process safety in the control room. 3rd Annual IEEE International Symposium on Systems Engineering, ISSE 2017, Vienna, Austria, October 11-13, 2017. Piscataway, NJ United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/SysEng.2017.8088300
2016
Conference Publication
Hand in hand: tools and techniques for understanding children's touch with a social robot
Hensby, Kristyn, Wiles, Janet, Boden, Marie, Heath, Scott, Nielsen, Mark, Pounds, Paul, Riddell, Joshua, Rogers, Kristopher, Rybak, Nikodem, Slaughter, Virginia, Smith, Michael, Taufatofua, Jonathon, Worthy, Peter and Weigel, Jason (2016). Hand in hand: tools and techniques for understanding children's touch with a social robot. 11th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2016, Christchurch, New Zealand, 7-10 March 2016. Piscataway, NJ, United States: IEEE Computer Society. doi: 10.1109/HRI.2016.7451794
2016
Conference Publication
Social cardboard: pretotyping a social ethnodroid in the wild
Wiles, Janet, Worthy, Peter, Hensby, Kristyn, Boden, Marie, Heath, Scott, Pounds, Paul, Rybak, Nikodem, Smith, Michael, Taufotofua, Jonathon and Weigel, Jason (2016). Social cardboard: pretotyping a social ethnodroid in the wild. 11th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2016, Christchurch, New Zealand, 7-10 March 2016. Piscataway, NJ, United States: IEEE. doi: 10.1109/HRI.2016.7451841
Supervision
Availability
- Dr Nikodem Rybak is:
- Available for supervision
Before you email them, read our advice on how to contact a supervisor.
Media
Enquiries
Contact Dr Nikodem Rybak directly for media enquiries about:
- Climate & Energy System Modeling with AI
- Cutting-Edge AI for Behavioral Modeling
- Data-Driven Decision Making
- Explainable AI & Responsible Innovation
- Interdisciplinary AI Research & Applications
- Machine Learning for Complex Systems
- Natural Language Processing (NLP) Solutions
- Risk Management through Predictive Analytics
- Sustainable & Ethical AI Approaches
- Transparency & Interpretability in AI
Need help?
For help with finding experts, story ideas and media enquiries, contact our Media team: