Spectral and Spatial Feature Integrated Ensemble Learning Method for Grading Urban River Network Water Quality

Urban river networks have the characteristics of medium and micro scales, complex water quality, rapid change, and time–space incoherence. Aiming to monitor the water quality accurately, it is necessary to extract suitable features and establish a universal inversion model for key water quality para...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiaoteng Zhou, Chun Liu, Akram Akbar, Yun Xue, Yuan Zhou
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	ensemble learning feature extraction UAV-borne remote sensing urban river network water quality grading Science Q
Acceso en línea:	https://doaj.org/article/167ef0c03c5041ce9f2057c8e7ba9322
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:167ef0c03c5041ce9f2057c8e7ba9322
record_format	dspace
spelling	oai:doaj.org-article:167ef0c03c5041ce9f2057c8e7ba93222021-11-25T18:54:35ZSpectral and Spatial Feature Integrated Ensemble Learning Method for Grading Urban River Network Water Quality10.3390/rs132245912072-4292https://doaj.org/article/167ef0c03c5041ce9f2057c8e7ba93222021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4591https://doaj.org/toc/2072-4292Urban river networks have the characteristics of medium and micro scales, complex water quality, rapid change, and time–space incoherence. Aiming to monitor the water quality accurately, it is necessary to extract suitable features and establish a universal inversion model for key water quality parameters. In this paper, we describe a spectral- and spatial-feature-integrated ensemble learning method for urban river network water quality grading. We proposed an in situ sampling method for urban river networks. Factor and correlation analyses were applied to extract the spectral features. Moreover, we analyzed the maximum allowed bandwidth for feature bands. We demonstrated that spatial features can improve the accuracy of water quality grading using kernel canonical correlation analysis (KCCA). Based on the spectral and spatial features, an ensemble learning model was established for total phosphorus (TP) and ammonia nitrogen (NH<sub>3</sub>-N). Both models were evaluated by means of fivefold validation. Furthermore, we proposed an unmanned aerial vehicle (UAV)-borne water quality multispectral remote sensing application process for urban river networks. Based on the process, we tested the model in practice. The experiment confirmed that our model can improve the grading accuracy by 30% compared to other machine learning models that use only spectral features. Our research can extend the application field of water quality remote sensing to complex urban river networks.Xiaoteng ZhouChun LiuAkram AkbarYun XueYuan ZhouMDPI AGarticleensemble learningfeature extractionUAV-borne remote sensingurban river networkwater quality gradingScienceQENRemote Sensing, Vol 13, Iss 4591, p 4591 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	ensemble learning feature extraction UAV-borne remote sensing urban river network water quality grading Science Q
spellingShingle	ensemble learning feature extraction UAV-borne remote sensing urban river network water quality grading Science Q Xiaoteng Zhou Chun Liu Akram Akbar Yun Xue Yuan Zhou Spectral and Spatial Feature Integrated Ensemble Learning Method for Grading Urban River Network Water Quality
description	Urban river networks have the characteristics of medium and micro scales, complex water quality, rapid change, and time–space incoherence. Aiming to monitor the water quality accurately, it is necessary to extract suitable features and establish a universal inversion model for key water quality parameters. In this paper, we describe a spectral- and spatial-feature-integrated ensemble learning method for urban river network water quality grading. We proposed an in situ sampling method for urban river networks. Factor and correlation analyses were applied to extract the spectral features. Moreover, we analyzed the maximum allowed bandwidth for feature bands. We demonstrated that spatial features can improve the accuracy of water quality grading using kernel canonical correlation analysis (KCCA). Based on the spectral and spatial features, an ensemble learning model was established for total phosphorus (TP) and ammonia nitrogen (NH<sub>3</sub>-N). Both models were evaluated by means of fivefold validation. Furthermore, we proposed an unmanned aerial vehicle (UAV)-borne water quality multispectral remote sensing application process for urban river networks. Based on the process, we tested the model in practice. The experiment confirmed that our model can improve the grading accuracy by 30% compared to other machine learning models that use only spectral features. Our research can extend the application field of water quality remote sensing to complex urban river networks.
format	article
author	Xiaoteng Zhou Chun Liu Akram Akbar Yun Xue Yuan Zhou
author_facet	Xiaoteng Zhou Chun Liu Akram Akbar Yun Xue Yuan Zhou
author_sort	Xiaoteng Zhou
title	Spectral and Spatial Feature Integrated Ensemble Learning Method for Grading Urban River Network Water Quality
title_short	Spectral and Spatial Feature Integrated Ensemble Learning Method for Grading Urban River Network Water Quality
title_full	Spectral and Spatial Feature Integrated Ensemble Learning Method for Grading Urban River Network Water Quality
title_fullStr	Spectral and Spatial Feature Integrated Ensemble Learning Method for Grading Urban River Network Water Quality
title_full_unstemmed	Spectral and Spatial Feature Integrated Ensemble Learning Method for Grading Urban River Network Water Quality
title_sort	spectral and spatial feature integrated ensemble learning method for grading urban river network water quality
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/167ef0c03c5041ce9f2057c8e7ba9322
work_keys_str_mv	AT xiaotengzhou spectralandspatialfeatureintegratedensemblelearningmethodforgradingurbanrivernetworkwaterquality AT chunliu spectralandspatialfeatureintegratedensemblelearningmethodforgradingurbanrivernetworkwaterquality AT akramakbar spectralandspatialfeatureintegratedensemblelearningmethodforgradingurbanrivernetworkwaterquality AT yunxue spectralandspatialfeatureintegratedensemblelearningmethodforgradingurbanrivernetworkwaterquality AT yuanzhou spectralandspatialfeatureintegratedensemblelearningmethodforgradingurbanrivernetworkwaterquality
_version_	1718410572427427840

Spectral and Spatial Feature Integrated Ensemble Learning Method for Grading Urban River Network Water Quality

Ejemplares similares