Water deep mapping from HJ-1B satellite data by a deep network model in the sea area of Pearl River Estuary, China

Remote sensing (RS) water depth inversion is an important technology and the method of water depth measurement. Taking the waters around the islands outside the Pearl River Estuary as an example, five optical RS depth inversion algorithms were introduced. Then, five water depth inversion models were...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhao Xiaoning, Wang Daqing, Xu Haoli, Shi Yue, Deng Zhengdong, Ding Zhibin, Liu Zhixin, Xu Xingang, Lu Zhao, Wang Guangyuan, Cheng Zijian
Formato:	article
Lenguaje:	EN
Publicado:	De Gruyter 2021
Materias:	rs hj-1b water depth inversion deep learning Geology QE1-996.5
Acceso en línea:	https://doaj.org/article/37b39c4ab9414fe2b9abd99e780a0c61
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:37b39c4ab9414fe2b9abd99e780a0c61
record_format	dspace
spelling	oai:doaj.org-article:37b39c4ab9414fe2b9abd99e780a0c612021-12-05T14:10:49ZWater deep mapping from HJ-1B satellite data by a deep network model in the sea area of Pearl River Estuary, China2391-544710.1515/geo-2020-0267https://doaj.org/article/37b39c4ab9414fe2b9abd99e780a0c612021-07-01T00:00:00Zhttps://doi.org/10.1515/geo-2020-0267https://doaj.org/toc/2391-5447Remote sensing (RS) water depth inversion is an important technology and the method of water depth measurement. Taking the waters around the islands outside the Pearl River Estuary as an example, five optical RS depth inversion algorithms were introduced. Then, five water depth inversion models were trained through the HJ-1B satellite RS image and the measured water depth data. The results show that the mean absolute error (MAE) of the deep learning model was the smallest (2.350 m), and that the distribution of predicted water depth points was closest to the actual value. Deep learning has been widely used in RS image classification and recognition and shows its advantages. Therefore, the deep learning model was applied to extract the depth of the shallow water. Meanwhile, the obtained inversion effect map is closest to the actual contour map. The water depth inversion performance of back propagation neural network model is better than that of the radial basis function (RBF) neural network model. Besides, the inversion accuracy of the RBF neural network may be affected due to the small amount of data and the improper number of hidden neurons. The results show broad application prospects of machine learning algorithms in RS water depth inversion. Also, this study provided data support for model optimization, training, and parameter setting.Zhao XiaoningWang DaqingXu HaoliShi YueDeng ZhengdongDing ZhibinLiu ZhixinXu XingangLu ZhaoWang GuangyuanCheng ZijianDe Gruyterarticlershj-1bwater depth inversiondeep learningGeologyQE1-996.5ENOpen Geosciences, Vol 13, Iss 1, Pp 782-795 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	rs hj-1b water depth inversion deep learning Geology QE1-996.5
spellingShingle	rs hj-1b water depth inversion deep learning Geology QE1-996.5 Zhao Xiaoning Wang Daqing Xu Haoli Shi Yue Deng Zhengdong Ding Zhibin Liu Zhixin Xu Xingang Lu Zhao Wang Guangyuan Cheng Zijian Water deep mapping from HJ-1B satellite data by a deep network model in the sea area of Pearl River Estuary, China
description	Remote sensing (RS) water depth inversion is an important technology and the method of water depth measurement. Taking the waters around the islands outside the Pearl River Estuary as an example, five optical RS depth inversion algorithms were introduced. Then, five water depth inversion models were trained through the HJ-1B satellite RS image and the measured water depth data. The results show that the mean absolute error (MAE) of the deep learning model was the smallest (2.350 m), and that the distribution of predicted water depth points was closest to the actual value. Deep learning has been widely used in RS image classification and recognition and shows its advantages. Therefore, the deep learning model was applied to extract the depth of the shallow water. Meanwhile, the obtained inversion effect map is closest to the actual contour map. The water depth inversion performance of back propagation neural network model is better than that of the radial basis function (RBF) neural network model. Besides, the inversion accuracy of the RBF neural network may be affected due to the small amount of data and the improper number of hidden neurons. The results show broad application prospects of machine learning algorithms in RS water depth inversion. Also, this study provided data support for model optimization, training, and parameter setting.
format	article
author	Zhao Xiaoning Wang Daqing Xu Haoli Shi Yue Deng Zhengdong Ding Zhibin Liu Zhixin Xu Xingang Lu Zhao Wang Guangyuan Cheng Zijian
author_facet	Zhao Xiaoning Wang Daqing Xu Haoli Shi Yue Deng Zhengdong Ding Zhibin Liu Zhixin Xu Xingang Lu Zhao Wang Guangyuan Cheng Zijian
author_sort	Zhao Xiaoning
title	Water deep mapping from HJ-1B satellite data by a deep network model in the sea area of Pearl River Estuary, China
title_short	Water deep mapping from HJ-1B satellite data by a deep network model in the sea area of Pearl River Estuary, China
title_full	Water deep mapping from HJ-1B satellite data by a deep network model in the sea area of Pearl River Estuary, China
title_fullStr	Water deep mapping from HJ-1B satellite data by a deep network model in the sea area of Pearl River Estuary, China
title_full_unstemmed	Water deep mapping from HJ-1B satellite data by a deep network model in the sea area of Pearl River Estuary, China
title_sort	water deep mapping from hj-1b satellite data by a deep network model in the sea area of pearl river estuary, china
publisher	De Gruyter
publishDate	2021
url	https://doaj.org/article/37b39c4ab9414fe2b9abd99e780a0c61
work_keys_str_mv	AT zhaoxiaoning waterdeepmappingfromhj1bsatellitedatabyadeepnetworkmodelintheseaareaofpearlriverestuarychina AT wangdaqing waterdeepmappingfromhj1bsatellitedatabyadeepnetworkmodelintheseaareaofpearlriverestuarychina AT xuhaoli waterdeepmappingfromhj1bsatellitedatabyadeepnetworkmodelintheseaareaofpearlriverestuarychina AT shiyue waterdeepmappingfromhj1bsatellitedatabyadeepnetworkmodelintheseaareaofpearlriverestuarychina AT dengzhengdong waterdeepmappingfromhj1bsatellitedatabyadeepnetworkmodelintheseaareaofpearlriverestuarychina AT dingzhibin waterdeepmappingfromhj1bsatellitedatabyadeepnetworkmodelintheseaareaofpearlriverestuarychina AT liuzhixin waterdeepmappingfromhj1bsatellitedatabyadeepnetworkmodelintheseaareaofpearlriverestuarychina AT xuxingang waterdeepmappingfromhj1bsatellitedatabyadeepnetworkmodelintheseaareaofpearlriverestuarychina AT luzhao waterdeepmappingfromhj1bsatellitedatabyadeepnetworkmodelintheseaareaofpearlriverestuarychina AT wangguangyuan waterdeepmappingfromhj1bsatellitedatabyadeepnetworkmodelintheseaareaofpearlriverestuarychina AT chengzijian waterdeepmappingfromhj1bsatellitedatabyadeepnetworkmodelintheseaareaofpearlriverestuarychina
_version_	1718371714848522240

Water deep mapping from HJ-1B satellite data by a deep network model in the sea area of Pearl River Estuary, China

Ejemplares similares