Research and Publications
TAIAO brings together a growing collection of research and publications that advance artificial intelligence for environmental science in Aotearoa New Zealand.
Here you’ll find accessible studies, reports, and insights across ecology, climate, biodiversity, and data science, alongside cutting‑edge work in machine learning, open‑source tools, and emerging methods. As TAIAO continues to grow as a national hub for environmental data science, our expanding community and research outputs reflect a shared commitment to open collaboration, data sovereignty, and supporting the future of environmental AI.
River: Machine Learning for streaming data
Introducing an adaptive machine‑learning approach that improves real‑time classification performance in continuously evolving, imbalanced data streams by ensuring rare but important events remain accurately recognised.
Adaptive random forests for evolving data stream classification
Adaptive Random Forests is a machine‑learning method designed to maintain high accuracy and adapt to concept drift in fast‑changing, real‑time data streams.
Machine learning for data streams: with practical examples in MOA
This book offers a practical and comprehensive guide to building adaptive machine‑learning systems for fast, continuous data streams, combining core theory with hands‑on examples using the MOA framework.
Leveraging Bagging for Evolving Data Streams
This research presents enhanced bagging techniques that improve accuracy, adaptability, and efficiency for machine‑learning models operating in fast, evolving data streams with frequent concept drift.
A survey on ensemble learning for data stream classification
A structured overview of ensemble learning methods for real‑time data‑stream classification, explaining how different techniques handle concept drift, limited resources, and evolving data to maintain accurate, adaptive performance.
Showcasing the TAIAO project: providing resources for machine learning from images of New Zealand's natural environment
A showcase of how the TAIAO project is building large, accessible image datasets and tools to advance machine‑learning research for recognising species and monitoring New Zealand’s natural environment.
The University of Waikato
University of Canterbury
The University of Auckland
Victoria University of Wellington
MetService
Beca
