An Earthquake Prediction System for Bangladesh Using Deep Long Short-Term Memory Architecture

Md Hasan Al Banna; Tapotosh Ghosh; Kazi Abu Taher; M. Shamim Kaiser; Mufti Mahmud

doi:10.1007/978-981-33-6081-5_41

An Earthquake Prediction System for Bangladesh Using Deep Long Short-Term Memory Architecture

Md Hasan Al Banna, Tapotosh Ghosh, Kazi Abu Taher, M. Shamim Kaiser^*, Mufti Mahmud

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Scopus citations

Abstract

Earthquake is a natural catastrophe, which is one of the most significant causes of structural and financial damage, along with the death of many humans. Prediction of the earthquake at least a month ahead of the event may diminish the death toll and financial loss. Bangladesh is in an active seismic region, where many earthquakes with small and medium magnitude occur almost every year. Several scientists have predicted that there is a good chance of an earthquake with startling energy shortly in this region. In this work, we have proposed a long short-term memory (LSTM)-based architecture for earthquake prediction in Bangladesh in the following month. After tuning hyperparameters, an architecture of 2 LSTM layers with 200 and 100 neurons, respectively, along with L1 and L2 regularization, was found to be the most efficient. The activation functions of the LSTM layers were tanh in the proposed architecture. The proposed LSTM architecture achieved a remarkable 70.67% accuracy with 64.78% sensitivity, 75.94% specificity in earthquake prediction for this region.

Original language	English
Title of host publication	Intelligent Systems - Proceedings of ICMIB 2020
Editors	Siba K. Udgata, Srinivas Sethi, Satish N. Srirama
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	465-476
Number of pages	12
ISBN (Print)	9789813360808
DOIs	https://doi.org/10.1007/978-981-33-6081-5_41
State	Published - 2021
Externally published	Yes
Event	1st International Conference on Machine Learning, Internet of Things and Big Data, ICMIB 2020 - Dhenkanal, India Duration: 19 Sep 2020 → 20 Sep 2020

Publication series

Name	Lecture Notes in Networks and Systems
Volume	185 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	1st International Conference on Machine Learning, Internet of Things and Big Data, ICMIB 2020
Country/Territory	India
City	Dhenkanal
Period	19/09/20 → 20/09/20

Bibliographical note

Publisher Copyright:
© 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Keywords

Earthquake
LSTM
Optimization
Prediction

ASJC Scopus subject areas

Control and Systems Engineering
Signal Processing
Computer Networks and Communications

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-981-33-6081-5_41

Cite this

Hasan Al Banna, M., Ghosh, T., Taher, K. A., Kaiser, M. S., & Mahmud, M. (2021). An Earthquake Prediction System for Bangladesh Using Deep Long Short-Term Memory Architecture. In S. K. Udgata, S. Sethi, & S. N. Srirama (Eds.), Intelligent Systems - Proceedings of ICMIB 2020 (pp. 465-476). (Lecture Notes in Networks and Systems; Vol. 185 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-33-6081-5_41

Hasan Al Banna, Md ; Ghosh, Tapotosh ; Taher, Kazi Abu et al. / An Earthquake Prediction System for Bangladesh Using Deep Long Short-Term Memory Architecture. Intelligent Systems - Proceedings of ICMIB 2020. editor / Siba K. Udgata ; Srinivas Sethi ; Satish N. Srirama. Springer Science and Business Media Deutschland GmbH, 2021. pp. 465-476 (Lecture Notes in Networks and Systems).

@inproceedings{24fec7c95dce4f02aa9ec77f08ec1c6c,

title = "An Earthquake Prediction System for Bangladesh Using Deep Long Short-Term Memory Architecture",

abstract = "Earthquake is a natural catastrophe, which is one of the most significant causes of structural and financial damage, along with the death of many humans. Prediction of the earthquake at least a month ahead of the event may diminish the death toll and financial loss. Bangladesh is in an active seismic region, where many earthquakes with small and medium magnitude occur almost every year. Several scientists have predicted that there is a good chance of an earthquake with startling energy shortly in this region. In this work, we have proposed a long short-term memory (LSTM)-based architecture for earthquake prediction in Bangladesh in the following month. After tuning hyperparameters, an architecture of 2 LSTM layers with 200 and 100 neurons, respectively, along with L1 and L2 regularization, was found to be the most efficient. The activation functions of the LSTM layers were tanh in the proposed architecture. The proposed LSTM architecture achieved a remarkable 70.67\% accuracy with 64.78\% sensitivity, 75.94\% specificity in earthquake prediction for this region.",

keywords = "Earthquake, LSTM, Optimization, Prediction",

author = "\{Hasan Al Banna\}, Md and Tapotosh Ghosh and Taher, \{Kazi Abu\} and Kaiser, \{M. Shamim\} and Mufti Mahmud",

note = "Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 1st International Conference on Machine Learning, Internet of Things and Big Data, ICMIB 2020 ; Conference date: 19-09-2020 Through 20-09-2020",

year = "2021",

doi = "10.1007/978-981-33-6081-5\_41",

language = "English",

isbn = "9789813360808",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "465--476",

editor = "Udgata, \{Siba K.\} and Srinivas Sethi and Srirama, \{Satish N.\}",

booktitle = "Intelligent Systems - Proceedings of ICMIB 2020",

address = "Germany",

}

Hasan Al Banna, M, Ghosh, T, Taher, KA, Kaiser, MS & Mahmud, M 2021, An Earthquake Prediction System for Bangladesh Using Deep Long Short-Term Memory Architecture. in SK Udgata, S Sethi & SN Srirama (eds), Intelligent Systems - Proceedings of ICMIB 2020. Lecture Notes in Networks and Systems, vol. 185 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 465-476, 1st International Conference on Machine Learning, Internet of Things and Big Data, ICMIB 2020, Dhenkanal, India, 19/09/20. https://doi.org/10.1007/978-981-33-6081-5_41

An Earthquake Prediction System for Bangladesh Using Deep Long Short-Term Memory Architecture. / Hasan Al Banna, Md; Ghosh, Tapotosh; Taher, Kazi Abu et al.
Intelligent Systems - Proceedings of ICMIB 2020. ed. / Siba K. Udgata; Srinivas Sethi; Satish N. Srirama. Springer Science and Business Media Deutschland GmbH, 2021. p. 465-476 (Lecture Notes in Networks and Systems; Vol. 185 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An Earthquake Prediction System for Bangladesh Using Deep Long Short-Term Memory Architecture

AU - Hasan Al Banna, Md

AU - Ghosh, Tapotosh

AU - Taher, Kazi Abu

AU - Kaiser, M. Shamim

AU - Mahmud, Mufti

PY - 2021

Y1 - 2021

N2 - Earthquake is a natural catastrophe, which is one of the most significant causes of structural and financial damage, along with the death of many humans. Prediction of the earthquake at least a month ahead of the event may diminish the death toll and financial loss. Bangladesh is in an active seismic region, where many earthquakes with small and medium magnitude occur almost every year. Several scientists have predicted that there is a good chance of an earthquake with startling energy shortly in this region. In this work, we have proposed a long short-term memory (LSTM)-based architecture for earthquake prediction in Bangladesh in the following month. After tuning hyperparameters, an architecture of 2 LSTM layers with 200 and 100 neurons, respectively, along with L1 and L2 regularization, was found to be the most efficient. The activation functions of the LSTM layers were tanh in the proposed architecture. The proposed LSTM architecture achieved a remarkable 70.67% accuracy with 64.78% sensitivity, 75.94% specificity in earthquake prediction for this region.

AB - Earthquake is a natural catastrophe, which is one of the most significant causes of structural and financial damage, along with the death of many humans. Prediction of the earthquake at least a month ahead of the event may diminish the death toll and financial loss. Bangladesh is in an active seismic region, where many earthquakes with small and medium magnitude occur almost every year. Several scientists have predicted that there is a good chance of an earthquake with startling energy shortly in this region. In this work, we have proposed a long short-term memory (LSTM)-based architecture for earthquake prediction in Bangladesh in the following month. After tuning hyperparameters, an architecture of 2 LSTM layers with 200 and 100 neurons, respectively, along with L1 and L2 regularization, was found to be the most efficient. The activation functions of the LSTM layers were tanh in the proposed architecture. The proposed LSTM architecture achieved a remarkable 70.67% accuracy with 64.78% sensitivity, 75.94% specificity in earthquake prediction for this region.

KW - Earthquake

KW - LSTM

KW - Optimization

KW - Prediction

UR - https://www.scopus.com/pages/publications/85105908911

U2 - 10.1007/978-981-33-6081-5_41

DO - 10.1007/978-981-33-6081-5_41

M3 - Conference contribution

AN - SCOPUS:85105908911

SN - 9789813360808

T3 - Lecture Notes in Networks and Systems

SP - 465

EP - 476

BT - Intelligent Systems - Proceedings of ICMIB 2020

A2 - Udgata, Siba K.

A2 - Sethi, Srinivas

A2 - Srirama, Satish N.

PB - Springer Science and Business Media Deutschland GmbH

T2 - 1st International Conference on Machine Learning, Internet of Things and Big Data, ICMIB 2020

Y2 - 19 September 2020 through 20 September 2020

ER -

Hasan Al Banna M, Ghosh T, Taher KA, Kaiser MS, Mahmud M. An Earthquake Prediction System for Bangladesh Using Deep Long Short-Term Memory Architecture. In Udgata SK, Sethi S, Srirama SN, editors, Intelligent Systems - Proceedings of ICMIB 2020. Springer Science and Business Media Deutschland GmbH. 2021. p. 465-476. (Lecture Notes in Networks and Systems). doi: 10.1007/978-981-33-6081-5_41

An Earthquake Prediction System for Bangladesh Using Deep Long Short-Term Memory Architecture

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Fingerprint

Cite this