Journal of the Royal Society of New Zealand

17 papers13 directions
The Journal of the Royal Society of New Zealand is a multidisciplinary scientific publication that has increasingly featured machine learning and artificial intelligence research, with documented activity in these fields from 2019 through 2026. While the journal maintains a broad scientific scope, its contributions to the AI community are characterized by the application of computational techniques to ecological, environmental, and regional challenges. It serves as a venue for research that integrates advanced algorithms with practical scientific domains, particularly those relevant to the New Zealand context. Research published in the journal frequently explores deep learning and evolutionary machine learning. Specific applications include automatic species identification, seabird detection for fisheries protection, and health prediction for aquaculture using genetic programming. Other research directions involve instance segmentation for urban forestry and the debiasing of large language models. Prolific contributors to this venue include researchers such as Bing Xue, Mengjie Zhang, Bernhard Pfahringer, Eibe Frank, and Albert Bifet, many of whom are associated with developments in evolutionary computation and data mining. In the context of the machine learning community, the journal functions as a specialized outlet for applied AI research. It provides a platform for demonstrating how models like YOLOv8 and multispectral sensor configurations can be adapted for environmental monitoring and resource management. By hosting studies on buoyancy assessment in aquaculture and estuary health monitoring, the journal facilitates the intersection of data science with traditional biological and environmental research.

Papers by Year

2026 1
2025 3
2024 6
2023 2
2022 4
2019 1

Top Research Directions

Research directions most represented by papers from this venue.

Layer Wise Feature Over Specialization in Deep Networks 1
Reliable Model Selection with Small Validation Sets 1
Moving Beyond Binary Classification Frameworks 1
Efficient Single Stage Object Detection for Edge Hardware 1
Bridging the Dataset Diversity Gap for Environmental Generalization 1
Overcoming Spatial Context Neglect in Spectral Imaging 1
Evolutionary Optimization for Feature Subset Selection 1
Scaling Ecological Monitoring via Automated Computer Vision 1
Hyperparameter Optimization via Grid Search Cross Validation 1
Bridging the Domain Shift in Few Shot Learning 1
Spectral Band Selection for Hyperspectral Dimensionality Reduction 1
Regularizing Deep Networks in Low Data Regimes 1
Fine-Tuning Pre-Trained Models 1

Top Authors

AuthorPapers
Bing Xue10
Mengjie Zhang8
Bernhard Pfahringer3
Albert Bifet2
Gillian Dobbie1
Qi Chen1
Yanan Sun1
Yi Mei1

Impactful Papers

Papers from this venue that shaped research clusters.

Influential

Papers

TitleYear
Design of Cross‐Coupled Duplexers Based on Substrate Integrated Waveguide Hexagonal Resonators2026
Automatic species identification from images for Aotearoa2025
BuoyancyNet: a deep learning approach for assessing float buoyancy in mussel aquaculture2025
Deep learning‐based seabird detection in fisheries for seabird protection2025
Debiasing large language models: research opportunities*2024
Evolving multispectral sensor configurations using genetic programming for estuary health monitoring2024
Health prediction for king salmon via evolutionary machine learning with genetic programming2024
Hierarchical mussel farm reconstruction from video with object tracking2024
YOLOv8E: an efficient YOLOv8 method for instance segmentation of individual tree crowns in Wellington City, New Zealand2024
YOLOv8E: an efficient YOLOv8 method for instance segmentation of individual tree crowns in Wellington City, New Zealand2024
A new multi‐object tracking pipeline based on computer vision techniques for mussel farms2023
Artificial Intelligence in New Zealand: applications and innovation2023
A new artificial intelligent approach to buoy detection for mussel farming2022
Experiments in cross‐domain few‐shot learning for image classification2022
Lessons learned from developing a COVID‐19 algorithm governance framework in Aotearoa New Zealand2022
Showcasing the TAIAO project: providing resources for machine learning from images of New Zealand's natural environment2022
A survey on evolutionary machine learning2019