Cargando…

Land-Use and Land-Cover Classification in Semi-Arid Areas from Medium-Resolution Remote-Sensing Imagery: A Deep Learning Approach

Detailed Land-Use and Land-Cover (LULC) information is of pivotal importance in, e.g., urban/rural planning, disaster management, and climate change adaptation. Recently, Deep Learning (DL) has emerged as a paradigm shift for LULC classification. To date, little research has focused on using DL meth...

Descripción completa

Detalles Bibliográficos
Autores principales: Ali, Kamran, Johnson, Brian A.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9695710/
https://www.ncbi.nlm.nih.gov/pubmed/36433346
http://dx.doi.org/10.3390/s22228750
_version_ 1784838130518458368
author Ali, Kamran
Johnson, Brian A.
author_facet Ali, Kamran
Johnson, Brian A.
author_sort Ali, Kamran
collection PubMed
description Detailed Land-Use and Land-Cover (LULC) information is of pivotal importance in, e.g., urban/rural planning, disaster management, and climate change adaptation. Recently, Deep Learning (DL) has emerged as a paradigm shift for LULC classification. To date, little research has focused on using DL methods for LULC mapping in semi-arid regions, and none that we are aware of have compared the use of different Sentinel-2 image band combinations for mapping LULC in semi-arid landscapes with deep Convolutional Neural Network (CNN) models. Sentinel-2 multispectral image bands have varying spatial resolutions, and there is often high spectral similarity of different LULC features in semi-arid regions; therefore, selection of suitable Sentinel-2 bands could be an important factor for LULC mapping in these areas. Our study contributes to the remote sensing literature by testing different Sentinel-2 bands, as well as the transferability of well-optimized CNNs, for semi-arid LULC classification in semi-arid regions. We first trained a CNN model in one semi-arid study site (Gujranwala city, Gujranwala Saddar and Wazirabadtownships, Pakistan), and then applied the pre-trained model to map LULC in two additional semi-arid study sites (Lahore and Faisalabad city, Pakistan). Two different composite images were compared: (i) a four-band composite with 10 m spatial resolution image bands (Near-Infrared (NIR), green, blue, and red bands), and (ii) a ten-band composite made by adding two Short Wave Infrared (SWIR) bands and four vegetation red-edge bands to the four-band composite. Experimental results corroborate the validity of the proposed CNN architecture. Notably, the four-band CNN model has shown robustness in semi-arid regions, where spatially and spectrally confusing land-covers are present.
format Online
Article
Text
id pubmed-9695710
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96957102022-11-26 Land-Use and Land-Cover Classification in Semi-Arid Areas from Medium-Resolution Remote-Sensing Imagery: A Deep Learning Approach Ali, Kamran Johnson, Brian A. Sensors (Basel) Article Detailed Land-Use and Land-Cover (LULC) information is of pivotal importance in, e.g., urban/rural planning, disaster management, and climate change adaptation. Recently, Deep Learning (DL) has emerged as a paradigm shift for LULC classification. To date, little research has focused on using DL methods for LULC mapping in semi-arid regions, and none that we are aware of have compared the use of different Sentinel-2 image band combinations for mapping LULC in semi-arid landscapes with deep Convolutional Neural Network (CNN) models. Sentinel-2 multispectral image bands have varying spatial resolutions, and there is often high spectral similarity of different LULC features in semi-arid regions; therefore, selection of suitable Sentinel-2 bands could be an important factor for LULC mapping in these areas. Our study contributes to the remote sensing literature by testing different Sentinel-2 bands, as well as the transferability of well-optimized CNNs, for semi-arid LULC classification in semi-arid regions. We first trained a CNN model in one semi-arid study site (Gujranwala city, Gujranwala Saddar and Wazirabadtownships, Pakistan), and then applied the pre-trained model to map LULC in two additional semi-arid study sites (Lahore and Faisalabad city, Pakistan). Two different composite images were compared: (i) a four-band composite with 10 m spatial resolution image bands (Near-Infrared (NIR), green, blue, and red bands), and (ii) a ten-band composite made by adding two Short Wave Infrared (SWIR) bands and four vegetation red-edge bands to the four-band composite. Experimental results corroborate the validity of the proposed CNN architecture. Notably, the four-band CNN model has shown robustness in semi-arid regions, where spatially and spectrally confusing land-covers are present. MDPI 2022-11-12 /pmc/articles/PMC9695710/ /pubmed/36433346 http://dx.doi.org/10.3390/s22228750 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ali, Kamran
Johnson, Brian A.
Land-Use and Land-Cover Classification in Semi-Arid Areas from Medium-Resolution Remote-Sensing Imagery: A Deep Learning Approach
title Land-Use and Land-Cover Classification in Semi-Arid Areas from Medium-Resolution Remote-Sensing Imagery: A Deep Learning Approach
title_full Land-Use and Land-Cover Classification in Semi-Arid Areas from Medium-Resolution Remote-Sensing Imagery: A Deep Learning Approach
title_fullStr Land-Use and Land-Cover Classification in Semi-Arid Areas from Medium-Resolution Remote-Sensing Imagery: A Deep Learning Approach
title_full_unstemmed Land-Use and Land-Cover Classification in Semi-Arid Areas from Medium-Resolution Remote-Sensing Imagery: A Deep Learning Approach
title_short Land-Use and Land-Cover Classification in Semi-Arid Areas from Medium-Resolution Remote-Sensing Imagery: A Deep Learning Approach
title_sort land-use and land-cover classification in semi-arid areas from medium-resolution remote-sensing imagery: a deep learning approach
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9695710/
https://www.ncbi.nlm.nih.gov/pubmed/36433346
http://dx.doi.org/10.3390/s22228750
work_keys_str_mv AT alikamran landuseandlandcoverclassificationinsemiaridareasfrommediumresolutionremotesensingimageryadeeplearningapproach
AT johnsonbriana landuseandlandcoverclassificationinsemiaridareasfrommediumresolutionremotesensingimageryadeeplearningapproach