Landslide Susceptibility Prediction Based on Positive Unlabeled Learning Coupled With Adaptive Sampling

Many studies consider landslide susceptibility prediction as a binary classification problem when using machine learning methods, which requires both landslide and nonlandslide samples for modeling. Nevertheless, there are only landslide and unlabeled areas in the real world, and directly considerin...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhice Fang, Yi Wang, Ruiqing Niu, Ling Peng
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Adaptive sampling landslide susceptibility prediction (LSP) positive unlabeled (PU) learning sensitivity analysis uncertainty analysis Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
Acceso en línea:	https://doaj.org/article/64d4a45d731d4ee68fb6e1b2e3b9327b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:64d4a45d731d4ee68fb6e1b2e3b9327b
record_format	dspace
spelling	oai:doaj.org-article:64d4a45d731d4ee68fb6e1b2e3b9327b2021-11-25T00:00:12ZLandslide Susceptibility Prediction Based on Positive Unlabeled Learning Coupled With Adaptive Sampling2151-153510.1109/JSTARS.2021.3125741https://doaj.org/article/64d4a45d731d4ee68fb6e1b2e3b9327b2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9606594/https://doaj.org/toc/2151-1535Many studies consider landslide susceptibility prediction as a binary classification problem when using machine learning methods, which requires both landslide and nonlandslide samples for modeling. Nevertheless, there are only landslide and unlabeled areas in the real world, and directly considering unlabeled areas as nonlandslide areas may cause bias and incorrect label assignment. In this article, we present a positive unlabeled learning method coupled with adaptive sampling and random forest (AdaPU-RF) to predict landslide susceptibility in the Three Gorges Reservoir area, China. This method can make full use of the landslide and nonlandslide information contained in unlabeled areas. Experimental results show that the AdaPU-RF method achieves desirable predication outcomes in terms of accuracy analysis, sensitivity analysis, and uncertainty analysis. Overall, the application of AdaPU-RF provides a new perspective for landslide susceptibility prediction, and can be recommended for other areas with similar geo-environmental conditions.Zhice FangYi WangRuiqing NiuLing PengIEEEarticleAdaptive samplinglandslide susceptibility prediction (LSP)positive unlabeled (PU) learningsensitivity analysisuncertainty analysisOcean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 11581-11592 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Adaptive sampling landslide susceptibility prediction (LSP) positive unlabeled (PU) learning sensitivity analysis uncertainty analysis Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
spellingShingle	Adaptive sampling landslide susceptibility prediction (LSP) positive unlabeled (PU) learning sensitivity analysis uncertainty analysis Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 Zhice Fang Yi Wang Ruiqing Niu Ling Peng Landslide Susceptibility Prediction Based on Positive Unlabeled Learning Coupled With Adaptive Sampling
description	Many studies consider landslide susceptibility prediction as a binary classification problem when using machine learning methods, which requires both landslide and nonlandslide samples for modeling. Nevertheless, there are only landslide and unlabeled areas in the real world, and directly considering unlabeled areas as nonlandslide areas may cause bias and incorrect label assignment. In this article, we present a positive unlabeled learning method coupled with adaptive sampling and random forest (AdaPU-RF) to predict landslide susceptibility in the Three Gorges Reservoir area, China. This method can make full use of the landslide and nonlandslide information contained in unlabeled areas. Experimental results show that the AdaPU-RF method achieves desirable predication outcomes in terms of accuracy analysis, sensitivity analysis, and uncertainty analysis. Overall, the application of AdaPU-RF provides a new perspective for landslide susceptibility prediction, and can be recommended for other areas with similar geo-environmental conditions.
format	article
author	Zhice Fang Yi Wang Ruiqing Niu Ling Peng
author_facet	Zhice Fang Yi Wang Ruiqing Niu Ling Peng
author_sort	Zhice Fang
title	Landslide Susceptibility Prediction Based on Positive Unlabeled Learning Coupled With Adaptive Sampling
title_short	Landslide Susceptibility Prediction Based on Positive Unlabeled Learning Coupled With Adaptive Sampling
title_full	Landslide Susceptibility Prediction Based on Positive Unlabeled Learning Coupled With Adaptive Sampling
title_fullStr	Landslide Susceptibility Prediction Based on Positive Unlabeled Learning Coupled With Adaptive Sampling
title_full_unstemmed	Landslide Susceptibility Prediction Based on Positive Unlabeled Learning Coupled With Adaptive Sampling
title_sort	landslide susceptibility prediction based on positive unlabeled learning coupled with adaptive sampling
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/64d4a45d731d4ee68fb6e1b2e3b9327b
work_keys_str_mv	AT zhicefang landslidesusceptibilitypredictionbasedonpositiveunlabeledlearningcoupledwithadaptivesampling AT yiwang landslidesusceptibilitypredictionbasedonpositiveunlabeledlearningcoupledwithadaptivesampling AT ruiqingniu landslidesusceptibilitypredictionbasedonpositiveunlabeledlearningcoupledwithadaptivesampling AT lingpeng landslidesusceptibilitypredictionbasedonpositiveunlabeledlearningcoupledwithadaptivesampling
_version_	1718414697243344896

Landslide Susceptibility Prediction Based on Positive Unlabeled Learning Coupled With Adaptive Sampling

Ejemplares similares