CNN-Based Spectral Super-Resolution of Panchromatic Night-Time Light Imagery: City-Size-Associated Neighborhood Effects

Data on artificial night-time light (NTL), emitted from the areas, and captured by satellites, are available at a global scale in <i>panchromatic</i> format. In the meantime, data on <i>spectral</i> properties of NTL give more information for further analysis. Such data, howe...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Nataliya Rybnikova, Evgeny M. Mirkes, Alexander N. Gorban
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	night-time light (NTL) panchromatic red green blue (RGB) bands international space station (ISS) Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/9f9ab06a3a7243b5a724791a8e787ab2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9f9ab06a3a7243b5a724791a8e787ab2
record_format	dspace
spelling	oai:doaj.org-article:9f9ab06a3a7243b5a724791a8e787ab22021-11-25T18:58:18ZCNN-Based Spectral Super-Resolution of Panchromatic Night-Time Light Imagery: City-Size-Associated Neighborhood Effects10.3390/s212276621424-8220https://doaj.org/article/9f9ab06a3a7243b5a724791a8e787ab22021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7662https://doaj.org/toc/1424-8220Data on artificial night-time light (NTL), emitted from the areas, and captured by satellites, are available at a global scale in <i>panchromatic</i> format. In the meantime, data on <i>spectral</i> properties of NTL give more information for further analysis. Such data, however, are available locally or on a commercial basis only. In our recent work, we examined several machine learning techniques, such as linear regression, kernel regression, random forest, and elastic map models, to convert the panchromatic NTL images into colored ones. We compared red, green, and blue light levels for eight geographical areas all over the world with panchromatic light intensities and characteristics of built-up extent from spatially corresponding pixels and their nearest neighbors. In the meantime, information from more distant neighboring pixels might improve the predictive power of models. In the present study, we explore this neighborhood effect using convolutional neural networks (CNN). The main outcome of our analysis is that the neighborhood effect goes in line with the geographical extent of metropolitan areas under analysis: For smaller areas, optimal input image size is smaller than for bigger ones. At that, for relatively large cities, the optimal input image size tends to differ for different colors, being on average higher for red and lower for blue lights. Compared to other machine learning techniques, CNN models emerged comparable in terms of Pearson’s correlation but showed performed better in terms of WMSE, especially for testing datasets.Nataliya RybnikovaEvgeny M. MirkesAlexander N. GorbanMDPI AGarticlenight-time light (NTL)panchromaticredgreenblue (RGB) bandsinternational space station (ISS)Chemical technologyTP1-1185ENSensors, Vol 21, Iss 7662, p 7662 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	night-time light (NTL) panchromatic red green blue (RGB) bands international space station (ISS) Chemical technology TP1-1185
spellingShingle	night-time light (NTL) panchromatic red green blue (RGB) bands international space station (ISS) Chemical technology TP1-1185 Nataliya Rybnikova Evgeny M. Mirkes Alexander N. Gorban CNN-Based Spectral Super-Resolution of Panchromatic Night-Time Light Imagery: City-Size-Associated Neighborhood Effects
description	Data on artificial night-time light (NTL), emitted from the areas, and captured by satellites, are available at a global scale in <i>panchromatic</i> format. In the meantime, data on <i>spectral</i> properties of NTL give more information for further analysis. Such data, however, are available locally or on a commercial basis only. In our recent work, we examined several machine learning techniques, such as linear regression, kernel regression, random forest, and elastic map models, to convert the panchromatic NTL images into colored ones. We compared red, green, and blue light levels for eight geographical areas all over the world with panchromatic light intensities and characteristics of built-up extent from spatially corresponding pixels and their nearest neighbors. In the meantime, information from more distant neighboring pixels might improve the predictive power of models. In the present study, we explore this neighborhood effect using convolutional neural networks (CNN). The main outcome of our analysis is that the neighborhood effect goes in line with the geographical extent of metropolitan areas under analysis: For smaller areas, optimal input image size is smaller than for bigger ones. At that, for relatively large cities, the optimal input image size tends to differ for different colors, being on average higher for red and lower for blue lights. Compared to other machine learning techniques, CNN models emerged comparable in terms of Pearson’s correlation but showed performed better in terms of WMSE, especially for testing datasets.
format	article
author	Nataliya Rybnikova Evgeny M. Mirkes Alexander N. Gorban
author_facet	Nataliya Rybnikova Evgeny M. Mirkes Alexander N. Gorban
author_sort	Nataliya Rybnikova
title	CNN-Based Spectral Super-Resolution of Panchromatic Night-Time Light Imagery: City-Size-Associated Neighborhood Effects
title_short	CNN-Based Spectral Super-Resolution of Panchromatic Night-Time Light Imagery: City-Size-Associated Neighborhood Effects
title_full	CNN-Based Spectral Super-Resolution of Panchromatic Night-Time Light Imagery: City-Size-Associated Neighborhood Effects
title_fullStr	CNN-Based Spectral Super-Resolution of Panchromatic Night-Time Light Imagery: City-Size-Associated Neighborhood Effects
title_full_unstemmed	CNN-Based Spectral Super-Resolution of Panchromatic Night-Time Light Imagery: City-Size-Associated Neighborhood Effects
title_sort	cnn-based spectral super-resolution of panchromatic night-time light imagery: city-size-associated neighborhood effects
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/9f9ab06a3a7243b5a724791a8e787ab2
work_keys_str_mv	AT nataliyarybnikova cnnbasedspectralsuperresolutionofpanchromaticnighttimelightimagerycitysizeassociatedneighborhoodeffects AT evgenymmirkes cnnbasedspectralsuperresolutionofpanchromaticnighttimelightimagerycitysizeassociatedneighborhoodeffects AT alexanderngorban cnnbasedspectralsuperresolutionofpanchromaticnighttimelightimagerycitysizeassociatedneighborhoodeffects
_version_	1718410479511011328

CNN-Based Spectral Super-Resolution of Panchromatic Night-Time Light Imagery: City-Size-Associated Neighborhood Effects

Ejemplares similares