Temporal detection of sharp landslide deformation with ensemble-based LSTM-RNNs and Hurst exponent

The sharp slope deformation which often contains seasonal patterns is the major source of the landslide hazard with respect to the local community, which it is a serious geological environment problem. In this paper, a long short-term memory-based deep learning framework has been proposed to model t...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Huajin Li, Qiang Xu, Yusen He, Xuanmei Fan, He Yang, Songlin Li
Formato:	article
Lenguaje:	EN
Publicado:	Taylor & Francis Group 2021
Materias:	sharp landslide deformation deep learning nested cross-validation elastic net hurst exponent Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350 Risk in industry. Risk management HD61
Acceso en línea:	https://doaj.org/article/c578abac1dae4e7f94f5086c17b5ccc0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c578abac1dae4e7f94f5086c17b5ccc0
record_format	dspace
spelling	oai:doaj.org-article:c578abac1dae4e7f94f5086c17b5ccc02021-11-04T15:00:42ZTemporal detection of sharp landslide deformation with ensemble-based LSTM-RNNs and Hurst exponent1947-57051947-571310.1080/19475705.2021.1994474https://doaj.org/article/c578abac1dae4e7f94f5086c17b5ccc02021-01-01T00:00:00Zhttp://dx.doi.org/10.1080/19475705.2021.1994474https://doaj.org/toc/1947-5705https://doaj.org/toc/1947-5713The sharp slope deformation which often contains seasonal patterns is the major source of the landslide hazard with respect to the local community, which it is a serious geological environment problem. In this paper, a long short-term memory-based deep learning framework has been proposed to model the deformation behaviors especially the sharp deformation of the landslide. First, the Box–Cox transformation is applied to normalize the dataset that includes time-series deformation, precipitation, and reservoir water level. Then, an elastic net (EN)-based ensemble of long short-term memory recurrent neural networks (LSTM-RNNs) is applied to forecast landslide deformation by using month forward-chaining nested cross-validation. This method is performed on the time-series data as our training strategy. Last, the Hurst exponent is formulated to identify incoming sharp deformation. The computational results demonstrated that this approach can accurately identify future sharp deformation. The Hurst exponent illustrates the abnormal patterns in the prediction errors which indicate sharp deformation. As a result, the proposed framework would assist the on-site risk analysis and decision-making process for geological engineers to prevent the landslide hazard in the future.Huajin LiQiang XuYusen HeXuanmei FanHe YangSonglin LiTaylor & Francis Grouparticlesharp landslide deformationdeep learningnested cross-validationelastic nethurst exponentEnvironmental technology. Sanitary engineeringTD1-1066Environmental sciencesGE1-350Risk in industry. Risk managementHD61ENGeomatics, Natural Hazards & Risk, Vol 12, Iss 1, Pp 3089-3113 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	sharp landslide deformation deep learning nested cross-validation elastic net hurst exponent Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350 Risk in industry. Risk management HD61
spellingShingle	sharp landslide deformation deep learning nested cross-validation elastic net hurst exponent Environmental technology. Sanitary engineering TD1-1066 Environmental sciences GE1-350 Risk in industry. Risk management HD61 Huajin Li Qiang Xu Yusen He Xuanmei Fan He Yang Songlin Li Temporal detection of sharp landslide deformation with ensemble-based LSTM-RNNs and Hurst exponent
description	The sharp slope deformation which often contains seasonal patterns is the major source of the landslide hazard with respect to the local community, which it is a serious geological environment problem. In this paper, a long short-term memory-based deep learning framework has been proposed to model the deformation behaviors especially the sharp deformation of the landslide. First, the Box–Cox transformation is applied to normalize the dataset that includes time-series deformation, precipitation, and reservoir water level. Then, an elastic net (EN)-based ensemble of long short-term memory recurrent neural networks (LSTM-RNNs) is applied to forecast landslide deformation by using month forward-chaining nested cross-validation. This method is performed on the time-series data as our training strategy. Last, the Hurst exponent is formulated to identify incoming sharp deformation. The computational results demonstrated that this approach can accurately identify future sharp deformation. The Hurst exponent illustrates the abnormal patterns in the prediction errors which indicate sharp deformation. As a result, the proposed framework would assist the on-site risk analysis and decision-making process for geological engineers to prevent the landslide hazard in the future.
format	article
author	Huajin Li Qiang Xu Yusen He Xuanmei Fan He Yang Songlin Li
author_facet	Huajin Li Qiang Xu Yusen He Xuanmei Fan He Yang Songlin Li
author_sort	Huajin Li
title	Temporal detection of sharp landslide deformation with ensemble-based LSTM-RNNs and Hurst exponent
title_short	Temporal detection of sharp landslide deformation with ensemble-based LSTM-RNNs and Hurst exponent
title_full	Temporal detection of sharp landslide deformation with ensemble-based LSTM-RNNs and Hurst exponent
title_fullStr	Temporal detection of sharp landslide deformation with ensemble-based LSTM-RNNs and Hurst exponent
title_full_unstemmed	Temporal detection of sharp landslide deformation with ensemble-based LSTM-RNNs and Hurst exponent
title_sort	temporal detection of sharp landslide deformation with ensemble-based lstm-rnns and hurst exponent
publisher	Taylor & Francis Group
publishDate	2021
url	https://doaj.org/article/c578abac1dae4e7f94f5086c17b5ccc0
work_keys_str_mv	AT huajinli temporaldetectionofsharplandslidedeformationwithensemblebasedlstmrnnsandhurstexponent AT qiangxu temporaldetectionofsharplandslidedeformationwithensemblebasedlstmrnnsandhurstexponent AT yusenhe temporaldetectionofsharplandslidedeformationwithensemblebasedlstmrnnsandhurstexponent AT xuanmeifan temporaldetectionofsharplandslidedeformationwithensemblebasedlstmrnnsandhurstexponent AT heyang temporaldetectionofsharplandslidedeformationwithensemblebasedlstmrnnsandhurstexponent AT songlinli temporaldetectionofsharplandslidedeformationwithensemblebasedlstmrnnsandhurstexponent
_version_	1718444797279076352

Temporal detection of sharp landslide deformation with ensemble-based LSTM-RNNs and Hurst exponent

Ejemplares similares