As a Ministry of Business, Innovation and Employment (MBIE) supported initiative, TAIAO is committed to promoting and facilitating the adoption of artificial intelligence (AI) and automation technologies in New Zealand's environmental sector.
The newsletter will keep you informed about the latest advancements in this field, stories of successful implementation of these technologies, and upcoming events. Thank you for joining us on this journey to create a more sustainable future for our planet!
In this newsletter, you will find information on:
To keep you up to date between newsletters, follow our new LinkedIn and Twitter accounts below:
Researchers around the world are studying the impacts of rising sea level and have created a report to support vulnerable communities. However, there is a need for Aotearoa New Zealand to have a unique report due to its tectonic activity.
Because New Zealand is on a tectonic plate, our land is continuously moving vertically up and down. So the impacts of rising sea levels in 100 years’ time could be quite different for some of our communities compared to those around the world.
So TAIAO is supporting a program called "Our Changing Coasts", a five-year MBIE-funded programme, that aims to forecast sea levels and the resulting coastal landscape changes over the next century. Read more about the programme and how TAIAO is supporting it here.
AI and Data Science Associate Professor Yun Sing Koh, Ben Halstead and the team of researchers were awarded for their work on probabilistic framework (PF) methods at the Data Science and Advanced Analytics conference.
PFs are essential for accurate and efficient machine learning systems, but they face challenges when there is a concept drift. Professor Koh found that existing PFs only reviewed past data inputs when current information was considered irrelevant. This created inaccuracies when a concept drift occurred, and new models needed to be retrained.
To address this issue, Professor Koh and her team created a new PF method called SELeCT that continuously reads past and present data to ensure their predictions are accurate. Read more about Professor Koh’s research and new PF model here.
Each newsletter we will spotlight some of the hardworking members of TAIAO. From sharing their career journey and achievements, we will give you a bit of insight into the team and how they’ve gotten to where they are now.
Meet Dr Varvara Vetrova, an early-career researcher with Ph.D. from Waikato University. Varvara co-led an MBIE-funded Endevaour grant BioSecure-ID from 2016 to 2019. This grant provided foundations for the current Aotearoa species classifier. She received the Worsley early career research award from the NZ Statistical Association in 2019. She is currently focused on using her expertise in applied statistics, machine learning, and deep learning to make advancements in the environmental and biomedical domains.
Varvara's research interests also include developing new methods for spatiotemporal forecasting, particularly for extreme climate events, and applications of deep neural networks for fine-grained recognition.
Meet Dr Phil Mourot, a senior data scientist with over 25 years of experience in natural hazards and early warning system systems. With a PhD in geophysics from France, Phil specialises in developing new methods and tools to predict natural disasters. He has extensive field experience, from analysing the Mont Blanc glaciers in the French Alps to monitoring the Merapi volcano in Indonesia. Phil moved to Aotearoa in 2015 and is now a Senior Advisor at the Waikato Regional Council and advocates resilience to reduce disaster risk and support climate adaptation.
Phil joined the TAIAO team in 2021 from the University of Waikato. His research focuses on predicting the impact of floods using deep learning and improving emergency management during a crisis. Phil is involved in numerous advisory groups and national projects, such as the AI Researcher Association of NZ (he holds the Secretary position) and QuakeCORE IP4.
Creating digital trees to stop biosecurity threats in their tracks sounds like something from science fiction, but for Paul Benden, it’s all in a day’s work.
The University of Canterbury Masters student is currently six months into developing a computer model that uses regular photo updates to create digital twins of trees. The long-term aim is a system that compares the digital twin models to the regular photos it receives and generates an alert if the tree is not growing healthily. Read more about his work here.
TAIAO provides an open source community platform for Environmental Data Science and AI. In the platform, you can discuss the notebooks and datasets found on TAIAO and get to know other contributors. Click here to sign up.