A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan)

Abstract Earthquakes and heavy rainfalls are the two leading causes of landslides around the world. Since they often occur across large areas, landslide detection requires rapid and reliable automatic detection approaches. Currently, deep learning (DL) approaches, especially different convolutional...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Omid Ghorbanzadeh, Alessandro Crivellari, Pedram Ghamisi, Hejar Shahabi, Thomas Blaschke
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/ed41ca3c6abe431c9ad297276161f66d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ed41ca3c6abe431c9ad297276161f66d
record_format	dspace
spelling	oai:doaj.org-article:ed41ca3c6abe431c9ad297276161f66d2021-12-02T18:30:57ZA comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan)10.1038/s41598-021-94190-92045-2322https://doaj.org/article/ed41ca3c6abe431c9ad297276161f66d2021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-94190-9https://doaj.org/toc/2045-2322Abstract Earthquakes and heavy rainfalls are the two leading causes of landslides around the world. Since they often occur across large areas, landslide detection requires rapid and reliable automatic detection approaches. Currently, deep learning (DL) approaches, especially different convolutional neural network and fully convolutional network (FCN) algorithms, are reliably achieving cutting-edge accuracies in automatic landslide detection. However, these successful applications of various DL approaches have thus far been based on very high resolution satellite images (e.g., GeoEye and WorldView), making it easier to achieve such high detection performances. In this study, we use freely available Sentinel-2 data and ALOS digital elevation model to investigate the application of two well-known FCN algorithms, namely the U-Net and residual U-Net (or so-called ResU-Net), for landslide detection. To our knowledge, this is the first application of FCN for landslide detection only from freely available data. We adapt the algorithms to the specific aim of landslide detection, then train and test with data from three different case study areas located in Western Taitung County (Taiwan), Shuzheng Valley (China), and Eastern Iburi (Japan). We characterize three different window size sample patches to train the algorithms. Our results also contain a comprehensive transferability assessment achieved through different training and testing scenarios in the three case studies. The highest f1-score value of 73.32% was obtained by ResU-Net, trained with a dataset from Japan, and tested on China’s holdout testing area using the sample patch size of 64 × 64 pixels.Omid GhorbanzadehAlessandro CrivellariPedram GhamisiHejar ShahabiThomas BlaschkeNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-20 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Omid Ghorbanzadeh Alessandro Crivellari Pedram Ghamisi Hejar Shahabi Thomas Blaschke A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan)
description	Abstract Earthquakes and heavy rainfalls are the two leading causes of landslides around the world. Since they often occur across large areas, landslide detection requires rapid and reliable automatic detection approaches. Currently, deep learning (DL) approaches, especially different convolutional neural network and fully convolutional network (FCN) algorithms, are reliably achieving cutting-edge accuracies in automatic landslide detection. However, these successful applications of various DL approaches have thus far been based on very high resolution satellite images (e.g., GeoEye and WorldView), making it easier to achieve such high detection performances. In this study, we use freely available Sentinel-2 data and ALOS digital elevation model to investigate the application of two well-known FCN algorithms, namely the U-Net and residual U-Net (or so-called ResU-Net), for landslide detection. To our knowledge, this is the first application of FCN for landslide detection only from freely available data. We adapt the algorithms to the specific aim of landslide detection, then train and test with data from three different case study areas located in Western Taitung County (Taiwan), Shuzheng Valley (China), and Eastern Iburi (Japan). We characterize three different window size sample patches to train the algorithms. Our results also contain a comprehensive transferability assessment achieved through different training and testing scenarios in the three case studies. The highest f1-score value of 73.32% was obtained by ResU-Net, trained with a dataset from Japan, and tested on China’s holdout testing area using the sample patch size of 64 × 64 pixels.
format	article
author	Omid Ghorbanzadeh Alessandro Crivellari Pedram Ghamisi Hejar Shahabi Thomas Blaschke
author_facet	Omid Ghorbanzadeh Alessandro Crivellari Pedram Ghamisi Hejar Shahabi Thomas Blaschke
author_sort	Omid Ghorbanzadeh
title	A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan)
title_short	A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan)
title_full	A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan)
title_fullStr	A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan)
title_full_unstemmed	A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan)
title_sort	comprehensive transferability evaluation of u-net and resu-net for landslide detection from sentinel-2 data (case study areas from taiwan, china, and japan)
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/ed41ca3c6abe431c9ad297276161f66d
work_keys_str_mv	AT omidghorbanzadeh acomprehensivetransferabilityevaluationofunetandresunetforlandslidedetectionfromsentinel2datacasestudyareasfromtaiwanchinaandjapan AT alessandrocrivellari acomprehensivetransferabilityevaluationofunetandresunetforlandslidedetectionfromsentinel2datacasestudyareasfromtaiwanchinaandjapan AT pedramghamisi acomprehensivetransferabilityevaluationofunetandresunetforlandslidedetectionfromsentinel2datacasestudyareasfromtaiwanchinaandjapan AT hejarshahabi acomprehensivetransferabilityevaluationofunetandresunetforlandslidedetectionfromsentinel2datacasestudyareasfromtaiwanchinaandjapan AT thomasblaschke acomprehensivetransferabilityevaluationofunetandresunetforlandslidedetectionfromsentinel2datacasestudyareasfromtaiwanchinaandjapan AT omidghorbanzadeh comprehensivetransferabilityevaluationofunetandresunetforlandslidedetectionfromsentinel2datacasestudyareasfromtaiwanchinaandjapan AT alessandrocrivellari comprehensivetransferabilityevaluationofunetandresunetforlandslidedetectionfromsentinel2datacasestudyareasfromtaiwanchinaandjapan AT pedramghamisi comprehensivetransferabilityevaluationofunetandresunetforlandslidedetectionfromsentinel2datacasestudyareasfromtaiwanchinaandjapan AT hejarshahabi comprehensivetransferabilityevaluationofunetandresunetforlandslidedetectionfromsentinel2datacasestudyareasfromtaiwanchinaandjapan AT thomasblaschke comprehensivetransferabilityevaluationofunetandresunetforlandslidedetectionfromsentinel2datacasestudyareasfromtaiwanchinaandjapan
_version_	1718378014621827072

A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data (case study areas from Taiwan, China, and Japan)

Ejemplares similares