PŪTAHI RANGAHAU/AUT RESEARCH CENTRE

Our themes

We conduct innovative artificial intelligence research to tackle real-world problems across various domains. Our team specialises in machine learning, natural language processing, computer vision and ethical AI systems, working closely with industry and community partners. We also focus on human-AI interaction and AI applications for healthcare, education and environmental sustainability. We're dedicated to creating culturally aware and responsible AI technologies that benefit society and make a positive impact on people's lives.

Our research groups

Medical Imaging AI

The Medical Imaging AI group at AUT focuses on developing advanced deep‐learning solutions to improve medical image interpretation, especially under challenging data conditions such as limited labels and heterogeneous multimodal inputs for applications in brain and clinical diagnostics.

Exploring cutting-edge machine learning approaches for healthcare imaging, including efficient training methods with limited data, multi-modal analysis combining diverse imaging techniques with clinical information, and robust adaptation across different medical devices and patient populations to enhance diagnostic accuracy and clinical deployment.

  • Label-efficient deep learning
    Few shot, meta learning, synthetic augmentation and test time adaptation for medical imaging.
  • Multimodal image analysis
    Cross-modality analysis of MRI, CT, fundus, histology and clinical metadata, especially for early disease detection.
  • Robust domain adaptation
    Handling distribution shifts across imaging devices or patient cohorts.

Core members: Catherine Shi, Yanbin Liu, Boris Bacic
Funding/fellowship: Google Cloud Research Credits 2023, Lambda Research Program 2025, DAAD AINet Fellowship (AInet Fellows 11/2024 - AI for Science)

Knowledge Engineering and Discovery Research Innovation

The AUT Knowledge Engineering and Discovery Research Institute (KEDRI) conducts world-leading research in the field of computational intelligence, neuroinformatics and bioinformatics, creating innovative applications of machine learning to advance human life and society. We develop novel information processing methods, technologies and their applications, and have produced extensive research output that is published in the field’s top ranking journals. At KEDRI, we work closely with a wide network of local and international partnerships and collaborators.

Visit KEDRI website

GeoEnviroSense

The group originated from the Geoinformatics Research Centre (GRC), established in 2009, where Dr Akbar Ghobakhlou was one of the founding members. The group develops methods that integrate satellite and drone imagery, computer vision, bioacoustics and IoT sensor networks for applications in biodiversity monitoring, precision agriculture, disaster risk reduction and environmental forecasting.

GES continues this trajectory, combining geospatial science with advances in artificial intelligence, machine learning and sensor innovation to address contemporary environmental challenges through rigorous academic inquiry.

GES research activities span:

  • Modelling and analysis of extreme weather events
  • Development of AI methods for plant disease detection
  • Design of bioacoustic and sensor-based systems for biodiversity monitoring
  • Application of computer vision and machine learning in precision agriculture

Through interdisciplinary collaboration and open scholarship, GES contributes to methodological innovation and deeper understanding of environmental systems at multiple scales.

  • AI for earth observation
    Development of deep learning and computer vision methods for analysing satellite, drone and aerial imagery to monitor land use, vegetation health and climate-related phenomena.
  • Edge AI & sensor networks
    Exploration of low-power, field-deployable IoT and sensor systems to enable continuous monitoring of ecological and environmental processes.
  • Environmental forecasting
    Application of time-series modelling and AI methods for forecasting climate extremes, air quality and ecological dynamics.
  • Precision agriculture
    Research into data-driven methods for sustainable farming, including micro-climate monitoring, sensor fusion and remote sensing, AI-based early detection of plant stress and disease to support targeted interventions.
  • Biodiversity and conservation science
    Use of bioacoustic monitoring, sensor technologies and AI to detect and track species, monitor invasive populations, and assess ecosystem health.

Core members: Akbar Ghobakhlou, Edmund Lai, Ajit Naranayan, Amin Barzegar
Affiliate members: Stéphane Mark, John Perrott, Martin Stommel

Ethics in AI

The Ethical AI Research Group at AUT is dedicated to advancing responsible and human-centred approaches to artificial intelligence. Our work focuses on fairness, transparency, accountability, privacy and the social impact of AI systems across diverse sectors. We collaborate across disciplines to critically examine how AI technologies are developed, deployed and governed. Through research, education and public engagement, we aim to ensure AI systems align with human values, promote equity, and support inclusive and sustainable innovation.

Core member: Parma Nand
Member: Hazel Abraham