Coastal Image Classification and Pattern Recognition: Tairua Beach, New Zealand

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”. Howev...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Bo Liu, Bin Yang, Sina Masoud-Ansari, Huina Wang, Mark Gahegan
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	coastal image convolutional neural networks beach state classification pattern recognition Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/38fde0fed4da436ea79965ced0f762ac
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:38fde0fed4da436ea79965ced0f762ac
record_format	dspace
spelling	oai:doaj.org-article:38fde0fed4da436ea79965ced0f762ac2021-11-11T19:17:40ZCoastal Image Classification and Pattern Recognition: Tairua Beach, New Zealand10.3390/s212173521424-8220https://doaj.org/article/38fde0fed4da436ea79965ced0f762ac2021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7352https://doaj.org/toc/1424-8220The 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. Additionally, 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 collected hourly coastal images and corresponding tidal data for more than 20 years (November 1998–August 2019). We classified the images into eight 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. We developed a classification model based on convolutional neural networks (CNN). After image pre-processing with data enhancement, we compared different CNN models. The improved ResNext obtained the best and most stable classification with <i>F1</i>-score of 90.41% and good generalization ability. The classification results of the whole dataset were transformed into time series data. MDLats algorithms were used to find frequent temporal patterns in morphology changes. Combining the pattern of coastal morphology change and the corresponding tidal data, we also analyzed the characteristics of beach morphology and the changes in morphodynamic states.Bo LiuBin YangSina Masoud-AnsariHuina WangMark GaheganMDPI AGarticlecoastal imageconvolutional neural networksbeach state classificationpattern recognitionChemical technologyTP1-1185ENSensors, Vol 21, Iss 7352, p 7352 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	coastal image convolutional neural networks beach state classification pattern recognition Chemical technology TP1-1185
spellingShingle	coastal image convolutional neural networks beach state classification pattern recognition Chemical technology TP1-1185 Bo Liu Bin Yang Sina Masoud-Ansari Huina Wang Mark Gahegan Coastal Image Classification and Pattern Recognition: Tairua Beach, New Zealand
description	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. Additionally, 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 collected hourly coastal images and corresponding tidal data for more than 20 years (November 1998–August 2019). We classified the images into eight 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. We developed a classification model based on convolutional neural networks (CNN). After image pre-processing with data enhancement, we compared different CNN models. The improved ResNext obtained the best and most stable classification with <i>F1</i>-score of 90.41% and good generalization ability. The classification results of the whole dataset were transformed into time series data. MDLats algorithms were used to find frequent temporal patterns in morphology changes. Combining the pattern of coastal morphology change and the corresponding tidal data, we also analyzed the characteristics of beach morphology and the changes in morphodynamic states.
format	article
author	Bo Liu Bin Yang Sina Masoud-Ansari Huina Wang Mark Gahegan
author_facet	Bo Liu Bin Yang Sina Masoud-Ansari Huina Wang Mark Gahegan
author_sort	Bo Liu
title	Coastal Image Classification and Pattern Recognition: Tairua Beach, New Zealand
title_short	Coastal Image Classification and Pattern Recognition: Tairua Beach, New Zealand
title_full	Coastal Image Classification and Pattern Recognition: Tairua Beach, New Zealand
title_fullStr	Coastal Image Classification and Pattern Recognition: Tairua Beach, New Zealand
title_full_unstemmed	Coastal Image Classification and Pattern Recognition: Tairua Beach, New Zealand
title_sort	coastal image classification and pattern recognition: tairua beach, new zealand
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/38fde0fed4da436ea79965ced0f762ac
work_keys_str_mv	AT boliu coastalimageclassificationandpatternrecognitiontairuabeachnewzealand AT binyang coastalimageclassificationandpatternrecognitiontairuabeachnewzealand AT sinamasoudansari coastalimageclassificationandpatternrecognitiontairuabeachnewzealand AT huinawang coastalimageclassificationandpatternrecognitiontairuabeachnewzealand AT markgahegan coastalimageclassificationandpatternrecognitiontairuabeachnewzealand
_version_	1718431577800704000

Coastal Image Classification and Pattern Recognition: Tairua Beach, New Zealand

Ejemplares similares