Landslide susceptibility mapping along the
Thimphu-Phuentsholing highway using machine learning

C 2022

Landslide susceptibility mapping along the Thimphu-Phuentsholing highway using machine learning

DAHAL, Manju Sara, Asheer CHHETRI, Hemant GHALLEY, Sangey PASANG, Moujhuri PATRA et. al.

Základní údaje

Originální název

Landslide susceptibility mapping along the Thimphu-Phuentsholing highway using machine learning

Autoři

DAHAL, Manju Sara, Asheer CHHETRI, Hemant GHALLEY, Sangey PASANG (64 Bhútán, domácí) a Moujhuri PATRA

Vydání

1. vyd. Cambridge, Computers in Earth and Environmental Sciences: Artificial Intelligence and Advanced Technologies in Hazards and Risk Management, od s. 601-617, 17 s. 2022

Nakladatel

Elsevier

Další údaje

Jazyk

angličtina

Typ výsledku

Kapitola resp. kapitoly v odborné knize

Obor

10500 1.5. Earth and related environmental sciences

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Odkazy

URL

Kód RIV

RIV/00216224:14310/22:00125019

Organizační jednotka

Přírodovědecká fakulta

ISBN

978-0-323-89861-4

DOI

http://dx.doi.org/10.1016/B978-0-323-89861-4.00038-5

Klíčová slova anglicky

Landslides; Thimphu-phuentsholing highway; Machine learning; Logistic regression; Random forest

Štítky

rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 11. 7. 2023 11:15, Mgr. Marie Šípková, DiS.

Anotace

V originále

In the Himalayan region, landslides are considered one of the most common natural disasters. The study area for this study is a 2 km buffer along the Thimphu-Phuentsholing highway in Bhutan, which is a part of Asian Highway 48. In this study, machine learning was adopted which allows relatively precise predictions to be made by providing accurate and reliable data. Of the numerous methods available for machine learning, two methods, i.e., random forest (RF) and logistic regression (LR) have been selected for this paper. Slope, aspect, geology, land cover, precipitation, distance from the drainage, distance from the road, TPI, TRI, Elevation, and surface roughness were the parameters selected for the study area. The two methods are validated and compared using the ROC and (AUC). The RF method performed slightly better than the LR method with an AUC of 0.91 and LR of 0.86.

Citovat

DAHAL, Manju Sara, Asheer CHHETRI, Hemant GHALLEY, Sangey PASANG a Moujhuri PATRA. Landslide susceptibility mapping along the Thimphu-Phuentsholing highway using machine learning. Online. In Pourghasemi, Hamid Reza. Computers in Earth and Environmental Sciences: Artificial Intelligence and Advanced Technologies in Hazards and Risk Management. 1. vyd. Cambridge: Elsevier, 2022, s. 601-617. ISBN 978-0-323-89861-4. Dostupné z: https://dx.doi.org/10.1016/B978-0-323-89861-4.00038-5.

@inbook{1798777,
   author = {Dahal, Manju Sara and Chhetri, Asheer and Ghalley, Hemant and Pasang, Sangey and Patra, Moujhuri},
   address = {Cambridge},
   booktitle = {Computers in Earth and Environmental Sciences: Artificial Intelligence and Advanced Technologies in Hazards and Risk Management},
   doi = {http://dx.doi.org/10.1016/B978-0-323-89861-4.00038-5},
   edition = {1},
   editor = {Pourghasemi, Hamid Reza},
   keywords = {Landslides; Thimphu-phuentsholing highway; Machine learning; Logistic regression; Random forest},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Cambridge},
   isbn = {978-0-323-89861-4},
   pages = {601-617},
   publisher = {Elsevier},
   title = {Landslide susceptibility mapping along the Thimphu-Phuentsholing highway using machine learning},
   url = {https://www.sciencedirect.com/science/article/pii/B9780323898614000385},
   year = {2022}
}

TY  - CHAP
ID  - 1798777
AU  - Dahal, Manju Sara - Chhetri, Asheer - Ghalley, Hemant - Pasang, Sangey - Patra, Moujhuri
PY  - 2022
TI  - Landslide susceptibility mapping along the Thimphu-Phuentsholing highway using machine learning
VL  - neuveden
PB  - Elsevier
CY  - Cambridge
SN  - 9780323898614
KW  - Landslides
KW  - Thimphu-phuentsholing highway
KW  - Machine learning
KW  - Logistic regression
KW  - Random forest
UR  - https://www.sciencedirect.com/science/article/pii/B9780323898614000385
N2  - In the Himalayan region, landslides are considered one of the most common natural disasters. The study area for this study is a 2 km buffer along the Thimphu-Phuentsholing highway in Bhutan, which is a part of Asian Highway 48. In this study, machine learning was adopted which allows relatively precise predictions to be made by providing accurate and reliable data. Of the numerous methods available for machine learning, two methods, i.e., random forest (RF) and logistic regression (LR) have been selected for this paper. Slope, aspect, geology, land cover, precipitation, distance from the drainage, distance from the road, TPI, TRI, Elevation, and surface roughness were the parameters selected for the study area. The two methods are validated and compared using the ROC and (AUC). The RF method performed slightly better than the LR method with an AUC of 0.91 and LR of 0.86.
ER  -

DAHAL, Manju Sara, Asheer CHHETRI, Hemant GHALLEY, Sangey PASANG a Moujhuri PATRA. Landslide susceptibility mapping along the Thimphu-Phuentsholing highway using machine learning. Online. In Pourghasemi, Hamid Reza. \textit{Computers in Earth and Environmental Sciences: Artificial Intelligence and Advanced Technologies in Hazards and Risk Management}. 1. vyd. Cambridge: Elsevier, 2022, s.~601-617. ISBN~978-0-323-89861-4. Dostupné z: https://dx.doi.org/10.1016/B978-0-323-89861-4.00038-5.

Podrobný výpis o publikaci