Coastal image classification and analysis based on convolutional neural networks and pattern recognition

Dr Bo Liu1,2, Bin Yang2, Professor Giovanni Coco1, Huina  Wang2, Sina Masoud-Ansari1, Professor Mark  Gahegan1

1Univ. Of Auckland, Auckland, New Zealand
2Beijing University of Technology, Beijing , China

The study of coastal processes is critical for the protection and development of beach amenities, infrastructure and properties. Many studies of beach evolution rely on data collected using remote sensing and show that beach evolution can be characterized by a finite number of “beach states”. However, due to practical constraints, long-term data displaying all beach states are rare. Also, when the dataset is available, the accuracy of the classification is not entirely objective since it depends on the operator. To address this problem, we have collected hourly coastal images and corresponding tidal data for more than 20 years (Nov. 1998-Aug. 2019). We classified the coastal images into 8 categories according to the classic beach state classification, defined as 1)reflective, 2)incident  scaled  bar, 3) non-rhythmic,  attached  bar, 4)attached rhythmic  bar, 5)offshore  rhythmic  bar, 6)non-rhythmic,  3-D  bar, 7)infragravity  scaled  2-D  bar, 8)dissipative. Classification models are usually based on convolutional neural networks. After image pre-processing with data enhancement, we have compared Densenet, Resnet, Resnext and improved Resnext models. The improved Resnext obtained the best and most stable classification with an accuracy of 94.58% and good generalization ability. The classification results of the whole dataset are transformed into time series data. FP-Growth and MDLats algorithms are used to find frequent patterns and motifs which represent the pattern of coastal morphology changes within a certain period of time. Combining the pattern of coastal morphology change and the corresponding tidal data, we also analysed the characteristics of beach morphology and the changes in morphological dynamics states.


Biography:

Bo Liu is a visiting scholar at School of Computer Science, the University of Auckland, and an associate professor of School of Software Engineering, Beijing University of Technology. She received Ph.D. degree from the Department of Automation, Tsinghua University. She once worked in NEC Laboratory China as a researcher and at the University of Chicago and Argonne National Laboratory as a Research Professional. She joined Beijing University of Technology in 2015 as an associate professor. Her research interests include big data, data mining, machine learning, cloud computing, scientific workflow and Semantic Web. She has authored over 100 articles and inventions.

Expanding the knowledge base of WA’s marine environment by improving the Environmental Impact Assessment process and leveraging Australia’s eResearch infrastructure investment.

Mr Gordon Motherwell2, Mr Chris  Gentle3,4, Mr Peter Brenton5, Mr Luke Edwards1,3

1Pawsey Supercomputing Centre, Perth, Australia
2Department of Water and Environmental Regulation, Perth, Australia
3Western Australian Marine Science Institution, Perth, Australia
4Western Australian Biodiversity Science Institute, Perth, Australia
5Atlas of Living Australia, Canberra, Australia

Until recently, Environmental Impact Assessment (EIA) practice was to use environmental information submitted with a proposal for the purpose of that proposal’s assessment only. The actual data was not submitted. As part of Digital Environmental Impact Assessment effort, centralising the collection and access to this data gathered and used for regulatory processes will reduce future approval and project delays and reduce effort, uncertainty and risk.

The Index of Marine Surveys for Assessments (IMSA) is a Department of Water and Environmental Regulation (the department) project, implemented in partnership with the Western Australian Marine Science Institution (WAMSI). IMSA is the first platform of its kind to deliver systematic capture and sharing of marine data taken as part of an EIA. With an estimated $50 million spent annually undertaking marine surveys for EIAs in WA, IMSA was developed to centralise this data and make it publicly available. IMSA provides access to marine surveyed reports, metadata and map layers through the department’s BioCollect online portal (provided by Atlas of Living Australia), as well as processed data products and raw data packages (hosted at the Pawsey Supercomputing Centre).

This talk will showcase “eResearch in Action” by describing how Government and private industry can work together to bring many benefits to the community.  IMSA was able to be implemented quickly by re-using existing NCRIS supported eResearch infrastructure and will enable future opportunities to better understand and manage the marine environment.


Biography:

Luke undertakes various outreach, engagement, support and training activities to drive uptake of Pawsey services.  He also currently works as the Data Manager for WAMSI (Western Australian Marine Science Institution) and Facility Manager for ASDAF (Australian Space Data Analysis Facility).

http://orcid.org/0000-0001-8590-3361

Recent Comments

    Categories

    About the conference

    eResearch Australasia provides opportunities for delegates to engage, connect, and share their ideas and exemplars concerning new information centric research capabilities, and how information and communication technologies help researchers to collaborate, collect, manage, share, process, analyse, store, find, understand and re-use information.

    Conference Managers

    Please contact the team at Conference Design with any questions regarding the conference.

    © 2018 - 2020 Conference Design Pty Ltd