Deep learning methods for underground deformation time-series prediction

Enlin Ma; Mateusz Janiszewski; Masoud Torkan

doi:10.1201/9781003348030-334

Deep learning methods for underground deformation time-series prediction

Enlin Ma, Mateusz Janiszewski, Masoud Torkan

Chang'an University

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

91 Downloads (Pure)

Abstract

Prediction is a vague concept that is why we need to conceptualize it specifically for underground deformation time-series data. For this impending issue, this paper employs an advanced deep learning model Bi-LSTM-AM to address it. The results show its applicability for practical engineering. The proposed model is compared with other basic deep learning models including long short-term memory (LSTM), Bi-LSTM, gated recurrent units (GRU), and temporal convolutional networks (TCN). These models cover the most common three forms of deep learning for time-series prediction: recurrent neural networks (RNN) and convolutional neural networks (CNN). This research is supposed to benefit the underground deformation time-series prediction.

Original language	English
Title of host publication	Expanding Underground - Knowledge and Passion to Make a Positive Impact on the World- Proceedings of the ITA-AITES World Tunnel Congress, WTC 2023
Subtitle of host publication	Proceedings of the ITA-AITES World Tunnel Congress 2023 (WTC 2023), 12-18 May 2023, Athens, Greece
Editors	Georgios Anagnostou, Andreas Benardos, Vassilis P. Marinos
Place of Publication	London
Publisher	CRC Press
Pages	2775-2781
Number of pages	7
Edition	1st Edition
ISBN (Electronic)	978-1-003-34803-0
DOIs	https://doi.org/10.1201/9781003348030-334
Publication status	Published - 12 Apr 2023
MoE publication type	A4 Conference publication
Event	World Tunnel Congress - Athens, Greece Duration: 12 May 2023 → 18 May 2023

Conference

Conference	World Tunnel Congress
Abbreviated title	WTC
Country/Territory	Greece
City	Athens
Period	12/05/2023 → 18/05/2023

Keywords

underground engineering
time-series
deep learning
deformation prediction
machine learning

Access to Document

10.1201/9781003348030-334Licence: CC BY-NC-ND

10.1201_9781003348030-334_chapterpdfFinal published version, 1.99 MBLicence: CC BY-NC-ND

Cite this

Ma, E., Janiszewski, M., & Torkan, M. (2023). Deep learning methods for underground deformation time-series prediction. In G. Anagnostou, A. Benardos, & V. P. Marinos (Eds.), Expanding Underground - Knowledge and Passion to Make a Positive Impact on the World- Proceedings of the ITA-AITES World Tunnel Congress, WTC 2023: Proceedings of the ITA-AITES World Tunnel Congress 2023 (WTC 2023), 12-18 May 2023, Athens, Greece (1st Edition ed., pp. 2775-2781). CRC Press. https://doi.org/10.1201/9781003348030-334

Ma, Enlin ; Janiszewski, Mateusz ; Torkan, Masoud. / Deep learning methods for underground deformation time-series prediction. Expanding Underground - Knowledge and Passion to Make a Positive Impact on the World- Proceedings of the ITA-AITES World Tunnel Congress, WTC 2023: Proceedings of the ITA-AITES World Tunnel Congress 2023 (WTC 2023), 12-18 May 2023, Athens, Greece. editor / Georgios Anagnostou ; Andreas Benardos ; Vassilis P. Marinos. 1st Edition. ed. London : CRC Press, 2023. pp. 2775-2781

@inproceedings{36acf12658c14b3e8803a499bc4d9f08,

title = "Deep learning methods for underground deformation time-series prediction",

abstract = "Prediction is a vague concept that is why we need to conceptualize it specifically for underground deformation time-series data. For this impending issue, this paper employs an advanced deep learning model Bi-LSTM-AM to address it. The results show its applicability for practical engineering. The proposed model is compared with other basic deep learning models including long short-term memory (LSTM), Bi-LSTM, gated recurrent units (GRU), and temporal convolutional networks (TCN). These models cover the most common three forms of deep learning for time-series prediction: recurrent neural networks (RNN) and convolutional neural networks (CNN). This research is supposed to benefit the underground deformation time-series prediction.",

keywords = "underground engineering, time-series, deep learning, deformation prediction, machine learning",

author = "Enlin Ma and Mateusz Janiszewski and Masoud Torkan",

year = "2023",

month = apr,

day = "12",

doi = "10.1201/9781003348030-334",

language = "English",

pages = "2775--2781",

editor = "Georgios Anagnostou and Andreas Benardos and Marinos, {Vassilis P.}",

booktitle = "Expanding Underground - Knowledge and Passion to Make a Positive Impact on the World- Proceedings of the ITA-AITES World Tunnel Congress, WTC 2023",

publisher = "CRC Press",

address = "United States",

edition = "1st Edition",

note = "World Tunnel Congress, WTC ; Conference date: 12-05-2023 Through 18-05-2023",

}

Ma, E, Janiszewski, M & Torkan, M 2023, Deep learning methods for underground deformation time-series prediction. in G Anagnostou, A Benardos & VP Marinos (eds), Expanding Underground - Knowledge and Passion to Make a Positive Impact on the World- Proceedings of the ITA-AITES World Tunnel Congress, WTC 2023: Proceedings of the ITA-AITES World Tunnel Congress 2023 (WTC 2023), 12-18 May 2023, Athens, Greece. 1st Edition edn, CRC Press, London, pp. 2775-2781, World Tunnel Congress, Athens, Greece, 12/05/2023. https://doi.org/10.1201/9781003348030-334

Deep learning methods for underground deformation time-series prediction. / Ma, Enlin; Janiszewski, Mateusz ; Torkan, Masoud.
Expanding Underground - Knowledge and Passion to Make a Positive Impact on the World- Proceedings of the ITA-AITES World Tunnel Congress, WTC 2023: Proceedings of the ITA-AITES World Tunnel Congress 2023 (WTC 2023), 12-18 May 2023, Athens, Greece. ed. / Georgios Anagnostou; Andreas Benardos; Vassilis P. Marinos. 1st Edition. ed. London: CRC Press, 2023. p. 2775-2781.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Deep learning methods for underground deformation time-series prediction

AU - Ma, Enlin

AU - Janiszewski, Mateusz

AU - Torkan, Masoud

PY - 2023/4/12

Y1 - 2023/4/12

N2 - Prediction is a vague concept that is why we need to conceptualize it specifically for underground deformation time-series data. For this impending issue, this paper employs an advanced deep learning model Bi-LSTM-AM to address it. The results show its applicability for practical engineering. The proposed model is compared with other basic deep learning models including long short-term memory (LSTM), Bi-LSTM, gated recurrent units (GRU), and temporal convolutional networks (TCN). These models cover the most common three forms of deep learning for time-series prediction: recurrent neural networks (RNN) and convolutional neural networks (CNN). This research is supposed to benefit the underground deformation time-series prediction.

AB - Prediction is a vague concept that is why we need to conceptualize it specifically for underground deformation time-series data. For this impending issue, this paper employs an advanced deep learning model Bi-LSTM-AM to address it. The results show its applicability for practical engineering. The proposed model is compared with other basic deep learning models including long short-term memory (LSTM), Bi-LSTM, gated recurrent units (GRU), and temporal convolutional networks (TCN). These models cover the most common three forms of deep learning for time-series prediction: recurrent neural networks (RNN) and convolutional neural networks (CNN). This research is supposed to benefit the underground deformation time-series prediction.

KW - underground engineering

KW - time-series

KW - deep learning

KW - deformation prediction

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=85160335368&partnerID=8YFLogxK

U2 - 10.1201/9781003348030-334

DO - 10.1201/9781003348030-334

M3 - Conference article in proceedings

SP - 2775

EP - 2781

BT - Expanding Underground - Knowledge and Passion to Make a Positive Impact on the World- Proceedings of the ITA-AITES World Tunnel Congress, WTC 2023

A2 - Anagnostou, Georgios

A2 - Benardos, Andreas

A2 - Marinos, Vassilis P.

PB - CRC Press

CY - London

T2 - World Tunnel Congress

Y2 - 12 May 2023 through 18 May 2023

ER -

Ma E, Janiszewski M , Torkan M. Deep learning methods for underground deformation time-series prediction. In Anagnostou G, Benardos A, Marinos VP, editors, Expanding Underground - Knowledge and Passion to Make a Positive Impact on the World- Proceedings of the ITA-AITES World Tunnel Congress, WTC 2023: Proceedings of the ITA-AITES World Tunnel Congress 2023 (WTC 2023), 12-18 May 2023, Athens, Greece. 1st Edition ed. London: CRC Press. 2023. p. 2775-2781 doi: 10.1201/9781003348030-334

Deep learning methods for underground deformation time-series prediction

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this