Tony Boston

PhD Student
B.Sc. (Hons) (ANU), Grad. Dip. Computing Studies (UC)

Content navigation

About

Tony has more than 30 years experience in the development of integrated national information systems based on the aggregation of data from agencies across Australia. He has done this for a range of scientific and collections-based organisations, including geoscience and environment agencies, libraries, museums, herbaria, archives and galleries. Tony has an honours degree in Geology and a Graduate Diploma in Computer Science and extensive expertise in geographic information management including development of national and international data standards and systems for data collection, storage and management.

Tony's APS career included senior executive and director roles within the Department of the Environment, National Library of Australia and Bureau of Meteorology. At the Bureau, Tony was responsible for development of a national database of surface and groundwater information that underpins the Water Information Program and products such as the National Water Account and Australian Water Resource Assessments.

Affiliations

Research interests

Tony's research interests include use of earth observations data to monitor, estimate and predict water resources, land cover and environmental change as well as the application of machine learning techniques to data classification and interpretation.

Publications

Boston, T., Van Dijk, A., Thackway, R., 2024. U-Net Convolutional Neural Network for Mapping Natural Vegetation and Forest Types from Landsat Imagery in Southeastern Australia. J. Imaging 10, 143. https://doi.org/10.3390/jimaging10060143

Boston, T., Van Dijk, A., Thackway, R., 2023. Convolutional Neural Network Shows Greater Spatial and Temporal Stability in Multi-Annual Land Cover Mapping Than Pixel-Based Methods. Remote Sensing 15, 2132. https://doi.org/10.3390/rs15082132

Boston, T., Van Dijk, A., Larraondo, P.R., Thackway, R., 2022. Comparing CNNs and Random Forests for Landsat Image Segmentation Trained on a Large Proxy Land Cover Dataset. Remote Sensing 14, 3396. https://doi.org/10.3390/rs14143396

Boston, T., Van Dijk, A., 2019. Some experiments in automated identification of Australian plants using convolutional neural networks, in: Proceedings of the 23rd International Congress on Modelling and Simulation (MODSIM2019). Presented at the 23rd International Congress on Modelling and Simulation (MODSIM2019), Canberra, Australia. https://doi.org/10.36334/modsim.2019.A1.boston