A hybrid ensemble-based deep-learning framework for landslide susceptibility mapping

Lv, Liang; Chen, Tao; Dou, Jie

doi:10.1016/j.jag.2022.102713

Cited by 78 publications

(46 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The abovementioned studies provide the basis for a deeper understanding of geological disasters. However, most studies focused on single-type disasters such as debris flow (Chiou et al, 2015), landslides (Bai et al, 2010;Chen et al, 2017;Li et al, 2017;Deng et al, 2022;Lv et al, 2022), rockfall (Chiessi et al, 2010), flood hazard (Wang et al, 2015), etc., or adopted macro-regional scale investigations such as coastal areas (China) (Pan, 2016), Pearl River Delta (China) , urban agglomerations , and river basin (Chiou et al, 2015;Dong et al, 2021;Lv et al, 2022). Most micro-scale studies at the county level also lacked multi-type disaster investigations .…”

Section: Influencing Factors Of Geological Disastersmentioning

confidence: 99%

Spatial distribution and influencing factors of mountainous geological disasters in southwest China: A fine-scale multi-type assessment

Shu

Chen

Amani-Beni

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

Geological disasters have long been a constant threat to socioeconomic development and human life and property. Many studies focus on the occurred geological disasters and ignore the potential risk events. Fine-scale multi-type analysis of Potential Geological Disasters Spots (PGDSs) is a necessary but insufficiently explored research field in China’s mountainous areas. Taking Meigu County (Sichuan Province, Southwest China), a typical disaster-prone region, as the study area. Average nearest neighbor (ANN), standard deviational ellipse (SDE), kernel density estimation (KDE), and ordinary least squares (OLS) regression are used to assess the spatial distribution of potential geological disasters spots and their influencing factors. The findings show that: potential geological disasters spots have a significant spatial heterogeneity and exhibited a prominent clustering characteristic. They were distributed in an elevation range of 1,500–2000 m, which receives an average monthly rainfall of more than 240 mm, as well as in highly foliated (0.6 < Normalized Difference Vegetation Index (NDVI) < 0.8), west-facing (247.5–292.5°), and slopes of 10–20°. In addition, slope, aspect, population density, and rainfall were found as the main influencing factors. The results provide practical rural development measures with support for potential geological disasters spots avoidance and preparedness.

show abstract

Section: Influencing Factors Of Geological Disastersmentioning

confidence: 99%

Spatial distribution and influencing factors of mountainous geological disasters in southwest China: A fine-scale multi-type assessment

Shu

Chen

Amani-Beni

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…Therefore, early spatial prediction of landslides is desirable to avoid landslides and, as a result, damage 9 . There were 4862 landslides reported worldwide between 2004 and 2016, resulting in 55,997 deaths 10 . In this aspect, rigorous planning is required to reduce landslide hazard risk, loss, and slope instability mitigation 11 .…”

Section: Introductionmentioning

confidence: 99%

“…The strategies listed above have been utilized by researchers all across the world to predict landslides 37 , 41 , 56 – 58 . These data-driven or statistical models are built on simple principles that can outperform simple univariate and multivariate linear tasks 10 . Quantitative techniques for landslide prediction modeling have risen in prominence over the last two decades 15 .…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, hybrid machine learning algorithms have recently generated promising results in landslide prediction modeling 23 , 83 , 84 . The base model prediction performance is improved by using a hybrid technique 10 . Moreover, the hybrid models higher performance in predicting landslide revealed that the landslide modeling may be improved by factor optimization 85 .…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, the hybrid models higher performance in predicting landslide revealed that the landslide modeling may be improved by factor optimization 85 . Many studies have demonstrated the value of a hybrid strategy in landslide situations all over the world 10 , 82 , 83 , 86 . Due to regional geological and geomorphological causes, slope unsteadiness, including landslides, is a common problem in Uttarkashi, Uttarakhand 87 – 89 .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hybrid machine learning approach for landslide prediction, Uttarakhand, India

Kainthura

Sharma

2022

Sci Rep

View full text Add to dashboard Cite

Natural disasters always have a damaging effect on our way of life. Landslides cause serious damage to both human and natural resources around the world. In this paper, the prediction accuracy of five hybrid models for landslide occurrence in the Uttarkashi, Uttarakhand (India) was evaluated and compared. In this approach, the Rough Set theory coupled with five different models namely Bayesian Network (HBNRS), Backpropagation Neural Network (HBPNNRS), Bagging (HBRS), XGBoost (HXGBRS), and Random Forest (HRFRS) were taken into account. The database for the models development was prepared using fifteen conditioning factors that had 373 landslide and 181 non-landslide locations that were then randomly divided into training and testing locations with a ratio of 75%:25%. The appropriateness and predictability of these conditioning factors were assessed using the multi-collinearity test and the least absolute shrinkage and selection operator approach. The accuracy, sensitivity, specificity, precision, and F-Measures, and the area under the curve (AUC)-receiver operating characteristics curve, were used to evaluate and compare the performance of the individual and hybrid created models. The findings indicate that the constructed hybrid model HXGBRS (AUC = 0.937, Precision = 0.946, F1-score = 0.926 and Accuracy = 89.92%) is the most accurate model for predicting landslides when compared to other models (HBPNNRS, HBNRS, HBRS, and HRFRS). Importantly, when the fusion is performed with the rough set method, the prediction capability of each model is improved. Simultaneously, the HXGBRS model proposed shows superior stability and can effectively avoid overfitting. After the core modules were developed, the user-friendly platform was designed as an integrated GIS environment using dynamic maps for effective landslide prediction in large prone areas. Users can predict the probability of landslide occurrence for selected region by changing the values of a conditioning factors. The created approach could be beneficial for predicting the impact of landslides on slopes and tracking landslides along national routes.

show abstract

Landslide risk assessment and management using hybrid machine learning‐based empirical models

Yang,

Jiang,

Arabameri

et al. 2023

Geological Journal

View full text Add to dashboard Cite

Landslides are a prevalent geologic phenomenon that substantially threatens human life and infrastructure, resulting in considerable loss and destruction. The practice of landslide susceptibility mapping is crucial for the mitigation of risks connected with this natural disaster. This work aims at investigating the influence of varying sample sizes on the precision of landslide susceptibility modelling using a case study conducted in the Alamout basin, Iran. The researchers used a machine learning methodology based on tree algorithms to construct a model for predicting the likelihood of landslides. Additionally, they adopted a multi‐scenario strategy to address the inherent uncertainty associated with the input data. The integration of the naive Bayes tree (NBTree), random forest (RF), logistic model tree (LMT) and J48 algorithms was performed. The modelling process included using 20 predictive parameters across four distinct scenarios. Four models, labelled S1, S2, S3 and S4, were used in this study. These models utilized 25%, 50%, 75% and 100% of the available inventory data. The research presented in this study is distinguished by using a tree‐based methodology for landslide susceptibility modelling and incorporating a multi‐scenario strategy to address the inherent uncertainty associated with the input data. The findings indicated that the augmentation of the sample size improved the precision of the models. The efficacy of using a multi‐scenario strategy in enhancing the dependability of the model is also underscored. Among the 20 input elements used in the modelling process, it was seen that slope angle accounted for the highest relative significance, constituting 25.60% of the overall influence. Following more closely, distance to fault contributed significantly, with a relative importance of 23.40%. Additionally, rainfall and elevation exhibited notable contributions, with relative volumes of 7.91% and 5.50%, respectively. All four landslide models showed adequate learning and forecasting ability throughout the training and testing phases. During the testing phase, the true skill score (TSS) values exhibited a range of 0.631–0.804, while the area under the receiver operating characteristic curve values showed a range of 0.745–0.921. The susceptibility maps indicated that a significant portion of the region exhibits moderate to very high susceptibility zones, with the northern and eastern sectors displaying greater landslide values than the western region. The model's performance showed improvement from S1 to S4 in both the training and testing phases. The performance of the models exhibited the following trend: in scenario 1, the RF model outperformed the J48, LMT and NBTree models; in scenario 2, the RF model surpassed the NBTree and LMT models, while being on par with the J48 model; in scenarios 3 and 4, the RF model showed superior performance compared to the NBTree, J48 and LMT models. Therefore, the RF model proved to be the most effective among the models evaluated. The findings derived from this research have the potential to serve as valuable references for the purposes of land‐use planning and catastrophe risk management.

show abstract

A hybrid ensemble-based deep-learning framework for landslide susceptibility mapping

Cited by 78 publications

References 74 publications

Spatial distribution and influencing factors of mountainous geological disasters in southwest China: A fine-scale multi-type assessment

Spatial distribution and influencing factors of mountainous geological disasters in southwest China: A fine-scale multi-type assessment

Hybrid machine learning approach for landslide prediction, Uttarakhand, India

Landslide risk assessment and management using hybrid machine learning‐based empirical models

Contact Info

Product

Resources

About