Time-Evolving Data Science / Artificial Intelligence for Advanced Open Environmental Science (TAIAO)
Led by the AI Institute, University of Waikato, TAIAO is a data science programme of $13 million (GST exclusive) over seven years, funded by the Ministry of Business, Innovation, and Employment (MBIE). It will advance the state-of-the-art in environmental data science by developing new machine learning methods for time series and data streams that are able to deal with large quantities of big data in real-time, which are tailored to deal with data collected on the New Zealand environment.
It will build a new open-source framework to implement machine learning on time series data, provide an open available repository with datasets to improve reproducibility in environmental data science, and build capability in fundamental and applied data science, accessible to all New Zealanders.
This programme is a collaboration between the Universities of Waikato, Auckland and Canterbury, Beca and MetService and includes world-leading data scientists, data engineers, and environmental scientists.
Lightmyography: Smart Wearable Solution for Control of Medical Devices
This research project aims to understand, refine, and optimise Lightmyography as a novel muscle-machine interface technology. Harnessing the unique properties of light to decode natural muscle movements will drive advancements in human-machine interfacing, redefining possibilities for individuals who rely on prosthetic and assistive devices.
This project has received Smart Ideas 2024 funding of $1 million over three years from MBIE and is led by the AI Institute. It brings together experts from the School of Computing & Mathematical Sciences and the School of Engineering at the University of Waikato, along with the Department of Mechanical Engineering at the University of Auckland. By collaborating across mechatronics, biomechatronics, robotics, and Māori perspectives, the project aims to shape a future where assistive technologies seamlessly integrate into the lives of end-users, enhancing autonomy, well-being, and overall quality of life.
Landslide Watch Aotearoa
The AI Institute is part of this five-year research programme, led by GNS Science, which was recently awarded $10.6 million through the MBIE 2024 Endeavour Research Programme fund.
Cyclone Gabrielle highlighted the growing vulnerability of homes, livelihoods, and wāhi tūpuna to landslides. This project focuses on detecting hazardous slopes and understanding the drivers of their movement, providing vital information for infrastructure development, community preparedness, and mitigation of landslide impacts before they occur.
The programme aims to transition from costly, reactive local monitoring to proactive, nationwide space-based observation. This approach will enable the identification of landslides, linking their movement to climate factors and characterising behaviour prior to causing damage.
Enhancing the ability to assess and forecast slow-moving landslides will support informed urban planning, improve community preparedness, and strengthen the economic resilience of New Zealand.
User friendly deep learning
The world, and particularly New Zealand, is experiencing a shortage of deep learning specialists, and it is unlikely that this will change soon: recent developments have shown that our modern, data-rich world consistently provides new opportunities for machine learning to increase productivity and yield better decision-making. The goal of this project is to enable domain experts to apply deep learning without involving a machine learning expert and without requiring any programming, while minimising the amount of data labeling required.
DeepWeather
The AI Institute is a partner in the DeepWeather project, led by Bodeker Scientific, which aims to make weather forecasting more accurate and affordable for Aotearoa New Zealand. With our economy heavily reliant on primary production, severe weather can cause significant economic, environmental, and social impacts.
DeepWeather applies artificial intelligence methods to develop a new way of generating weather forecasts, producing high-resolution forecasts at a fraction of current costs. A neural network (NN) will be trained to learn how to generate weather at hyperlocal scales (several 100m) given data from a lower resolution NWP model. While the initial training may be computationally expensive, once trained, the NN can be applied to any NWP forecast to fill in the missing detail inside each grid-cell, at negligible cost. This cost reduction means that we can generate higher resolution forecasts than are currently available, and process many more forecasts to produce probabilistic risk assessments of rare but highly damaging events.
AI Human Centric Security
The AI for Human-Centric Security is a Catalyst project funded by MBIE. The project is being led by Dr. Vimal Kumar, with teams from the University of Auckland and the University of Otago in NZ and Monash University, the University of Queensland, and Data61 in Australia. The project aims to use AI to aid human security experts in managing configuration in a diverse environment.
Entrepreneurial Universities - Real time analytics for Big Data
For most SMEs in New Zealand, the deployment of artificial intelligence solutions is hindered by two obstacles. First, one still needs access to significant processing power to build the networks. Second, the networks do not always converge on a good solution so significant expertise is needed to make them work.
This research programme focused on addressing two key questions:
- How can we make deployable machine learning technology available to the wider business and government communities in New Zealand so that they may benefit from the age of Big Data?
- Can we develop data streaming methods that scale to Big Data like large deep neural networks, but work well in all domains?