Combining a class-weighted algorithm and machine learning models in landslide susceptibility mapping: A case study of Wanzhou section of the Three Gorges Reservoir, China

Zhang, Huijuan; Song, Yingxu; Xu, Shiluo; He, Yakun; Li, Zhiwen; Yu, Xianyu; Liang, Yongqi; Wu, Weicheng; Wang, Yue

doi:10.1016/j.cageo.2021.104966

Cited by 61 publications

(24 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al [73] aim was to explore the implementation of a class-weighted algorithm with LGR and ensemble-based lightGBM and RF algorithm for landslide susceptibility mapping. The class-weighted method was used to handle imbalanced data issues of landslide and non-landslide samples.…”

Section: Author Year Ensemble Methodsmentioning

confidence: 99%

“…Liang et al [72] suggest the use of clustering analysis to improve the sampling of non-landslide locations. Zhang et al [73] explored an imbalanced dataset by using a class-weighted algorithm to solve class imbalance with landslide and non-landslide samples. The study addressed the disadvantage of SMOTE and its limitation with over-fitting.…”

Section: Datasets and Landslide Inventorymentioning

confidence: 99%

“…Several ensemble techniques were employed for landslide susceptibility studies. Some of the ensemble techniques used in different landslide studies include lightGBM [73] which is an ensemble algorithm based on DT. It belongs to the boosting ensemble technique family.…”

Section: Ensemble Techniquesmentioning

confidence: 99%

“…Microsoft introduced it as a new gradient boosting framework to overcome the limitations of GBDT in massive data. RF [57,72,73,76,123,130,131] is a basic ensemble ML model used in the generation of LSM and is considered a conventional technique because of its popularity in landslide susceptibility mapping. It belongs to the Boostrap aggregation family.…”

Section: Ensemble Techniquesmentioning

confidence: 99%

See 3 more Smart Citations

Landslide Susceptibility Mapping Using Machine Learning: A Literature Survey

et al. 2022

View full text Add to dashboard Cite

Landslide is a devastating natural disaster, causing loss of life and property. It is likely to occur more frequently due to increasing urbanization, deforestation, and climate change. Landslide susceptibility mapping is vital to safeguard life and property. This article surveys machine learning (ML) models used for landslide susceptibility mapping to understand the current trend by analyzing published articles based on the ML models, landslide causative factors (LCFs), study location, datasets, evaluation methods, and model performance. Existing literature considered in this comprehensive survey is systematically selected using the ROSES protocol. The trend indicates a growing interest in the field. The choice of LCFs depends on data availability and case study location; China is the most studied location, and area under the receiver operating characteristic curve (AUC) is considered the best evaluation metric. Many ML models have achieved an AUC value > 0.90, indicating high reliability of the susceptibility map generated. This paper also discusses the recently developed hybrid, ensemble, and deep learning (DL) models in landslide susceptibility mapping. Generally, hybrid, ensemble, and DL models outperform conventional ML models. Based on the survey, a few recommendations and future works which may help the new researchers in the field are also presented.

show abstract

Section: Author Year Ensemble Methodsmentioning

confidence: 99%

Section: Datasets and Landslide Inventorymentioning

confidence: 99%

Section: Ensemble Techniquesmentioning

confidence: 99%

Section: Ensemble Techniquesmentioning

confidence: 99%

See 2 more Smart Citations

Landslide Susceptibility Mapping Using Machine Learning: A Literature Survey

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The more accurate the landslide susceptibility map is, the more accurate the landslide hazard and risk maps are. Thanks to Geographical Information Systems, Remote Sensing, and science of statistics, landslide susceptibility approaches have diversified and evolved from the first examples to the present day (Brabb & Pampeyan, 1972;Carrara, 1977;Guzzetti et al, 2005;Zhang et al, 2022). Some of the approaches used in landslide susceptibility studies have come to the fore periodically.…”

Section: Extended Abstract Introductionmentioning

confidence: 99%

Kayma tipi heyelanların farklı duyarlılık modellerinde kombinasyonu: Sakarya Havzası Yukarı Çığırı örneği

CİHANGİR

2022

Türk Coğrafya Dergisi

View full text Add to dashboard Cite

Heyelan duyarlılık haritaları heyelanın mekânsal tahmini için önem arz etmektedir. Bu nedenleheyelan duyarlılık modellerinin doğruluğu tehlike ve risk çalışmaları için temel oluşturmaktadır.Bir bölgede heyelanın tüm tipleri için tek bir model oluşturulması duyarlılığın başarısını etkilemektedir.Heyelanların her bir tipi, farklı mekanizma ve materyalde gerçekleştiği için heyelanıdenetleyen hazırlayıcı koşullar da değişmektedir. Bu yüzden duyarlılık modellerinin tek bir heyelantipine göre oluşturulması daha iyi sonuçlar vermektedir. Bu nedenle çalışmanın amacı, tekbir heyelan ana mekanizmasına bağlı moloz ve toprak kayması tipine göre duyarlılık haritalarınınnitel ve yarı nicel yaklaşımlarda nasıl sonuçlar verdiğini ortaya koymaktır. Bu amaç doğrultusundaSakarya havzasının yukarı çığırında bulunan çalışma alanı için, Varnes (1978) sınıflamasınagöre moloz ve toprak kayması tipindeki heyelanlar için Frekans Oran, Analitik Hiyerarşi Süreci,Ağırlıklandırılmış Çakıştırma, Modifiye AHP ve CBS Matris Model yaklaşımları ile duyarlılık modellerioluşturulmuştur. Model sonuçlarına bağlı duyarlılık oluşturulurken heyelanın yamacıntamamını etkileyeceğinden çalışma alanı yamaç ünitelerine bölünerek çalışılmıştır. Beş modelsonucuna göre ROC eğrisinin altında kalan sonuçlar 0,79 ile 0,92 arasında değişmektedir. Budurum modellerin çok iyi sonuçlar verdiğini ve çalışma sahasının heyelan duyarlılığı açısındaniyi temsil edildiğini göstermektedir. Sonuçlara göre heyelanın en yüksek ve en düşük olabileceğialanlar tüm modelde ortak alanlara karşılık gelmektedir. Çalışmada sonuç olarak ana heyelantipine göre oluşturulan modellerin yüksek sonuçlar verdiği ortaya çıkmıştır. Bu sonuçlar, tümmodelin tek bir modelde birleştirilmesinde kolaylık sağlamıştır. Böylece tüm modelden tek birmodel çıktısı elde eden çalışma, heyelan tehlike ve risk çalışmalarının iyileştirilmesine katkı sağlamaktadır.

show abstract

A comparative study of regional landslide susceptibility mapping with multiple machine learning models

Wang,

Liu

et al. 2023

Geological Journal

View full text Add to dashboard Cite

The purpose of this study is to utilize three machine learning models—random forest, logistic regression and extreme gradient boosting—to assess the landslide susceptibility of Wushan County and compare the predictive performance of each algorithm. To achieve this, the database was randomly divided into training (80%) and testing (20%) datasets. We considered the impact of soil thickness, which has rarely been explored in previous research. A spatial database of 19 conditioning factors related to the occurrence of a landslide was constructed to develop the landslide susceptibility maps. Thereafter, three models were estimated and compared using metrics such as accuracy, recall, F1 score and area under the receiver operating characteristic curve (AUC). The results show that the random forest model with the testing dataset has higher accuracy (0.848), F1 score (0.740) and AUC (0.904) values. Soil thickness is found to play a significant role in the occurrence of a landslide. The quantitative analysis of landslide susceptibility maps indicates the superiority of the random forest model. Finally, the outcomes of the random forest model incorporating multicollinearity analysis and factor selection were thoroughly discussed. In conclusion, the random forest is the recommended algorithm for evaluating landslide susceptibility to aid in disaster management in Wushan County.

show abstract

Combining a class-weighted algorithm and machine learning models in landslide susceptibility mapping: A case study of Wanzhou section of the Three Gorges Reservoir, China

Cited by 61 publications

References 42 publications

Landslide Susceptibility Mapping Using Machine Learning: A Literature Survey

Landslide Susceptibility Mapping Using Machine Learning: A Literature Survey

Kayma tipi heyelanların farklı duyarlılık modellerinde kombinasyonu: Sakarya Havzası Yukarı Çığırı örneği

A comparative study of regional landslide susceptibility mapping with multiple machine learning models

Contact Info

Product

Resources

About