A spatial case-based reasoning method for regional landslide risk assessment

Zheng, Zhizhen; Chen, Jianhua; Xu, Kaihang; Xie, Huawei; Gan, Xianxia; Xu, He

doi:10.1016/j.jag.2021.102381

Cited by 15 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, they are more susceptible to injuries in collapse disasters and have a higher level of vulnerability. According to overall statistics on rural roads, it has been observed that the lower the road grade and technical standard, the more susceptible rural roads are to damage during disasters, compared to high-grade roads [39]. We measured the percentage of detached houses and bungalows in each township that are not surrounded by any other buildings.…”

Section: Vulnerabilitymentioning

confidence: 99%

“…However, when selecting the index system method, various scholars have enhanced their approaches from different perspectives. In order to examine the relationship between landslides and the surrounding environment, Zhao utilized the spatial case-based reasoning method to assess the risk of landslides in Lushan County [39]. In order to eliminate the error of subjective weighting, Gao utilized a weight-based generalized objective function to evaluate vulnerability.…”

Section: Comparison With Others' Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Risk Assessment of Landslide Collapse Disasters along National Highways Based on Information Quantity and Random Forest Coupling Methods: A Case Study of the G331 National Highway

Nie,

Lang,

Zhang

et al. 2023

IJGI

View full text Add to dashboard Cite

Based on the data from two field surveys in 2015 and 2022, this paper calculates the weight of values using the entropy weight method and the variation coefficient method, and evaluates risk using the information quantity method. The information quantities of four levels of criteria (hazards, exposure, vulnerability, emergency responses, and capability of recovery) were extracted and inputted into a random forest model. After optimizing the hyperparameters of the random forest using GridSearchCV, the risk assessment was performed again. Finally, the accuracy of the two evaluation results was verified using an ROC curve, and the model with the higher AUC value was selected to create a risk map. Compared with previous studies, this paper considers the factors of emergency responses and recovery capability, which makes the risk assessment more comprehensive. Our findings show that the evaluation results based on the coupling model are more accurate than the evaluation results of the information method, as the coupling model had an AUC value of 0.9329. After considering the indices of emergency responses and capability of recovery, the risk level of the highest-risk area in the study area decreased.

show abstract

Section: Vulnerabilitymentioning

confidence: 99%

Section: Comparison With Others' Studiesmentioning

confidence: 99%

Risk Assessment of Landslide Collapse Disasters along National Highways Based on Information Quantity and Random Forest Coupling Methods: A Case Study of the G331 National Highway

Nie,

Lang,

Zhang

et al. 2023

IJGI

View full text Add to dashboard Cite

show abstract

“…Qualitative models rely solely on expert judgment and involve direct mapping of the landscape to assess susceptibility against expert-defined factors (Aleotti andChowdhury 1999, Tanyu, Abbaspour et al 2021). Quantitative models mainly refer to statistical, machine learning (ML) or deep learning (DL) models, such as support vector machine (SVM) (Marjanović, Kovačević et al 2011), logistic regression (LR) (Sun, Xu et al 2021), random forests (RF) (Kim, Lee et al 2018), extreme gradient boosting (Xgboost) (Can, Kocaman et al 2021), convolutional neural network (CNN) (Wang, Fang et al 2019, Sameen, Pradhan et al 2020, Zhao, Chen et al 2021, and long short time memory (LSTM) (Fang, Wang et al 2021).…”

Section: Introductionmentioning

confidence: 99%

Selection of contributing factors for predicting landslide susceptibility using machine learning and deep learning models

Chen,

Fan

2023

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

Landslides are a common natural disaster that can cause casualties, property safety threats and economic losses. Therefore, it is important to understand or predict the probability of landslide occurrence at potentially risky sites. A commonly used means is to carry out a landslide susceptibility assessment based on a landslide inventory and a set of landslide contributing factors. This can be readily achieved using machine learning (ML) models such as logistic regression (LR), support vector machine (SVM), random forest (RF), extreme gradient boosting (Xgboost), or deep learning (DL) models such as convolutional neural network (CNN) and long short time memory (LSTM). As the input data for these models, landslide contributing factors have varying influences on landslide occurrence. Therefore, it is logically feasible to select more important contributing factors and eliminate less relevant ones, with the aim of increasing the prediction accuracy of these models. However, selecting more important factors is still a challenging task and there is no generally accepted method. Furthermore, the effects of factor selection using various methods on the prediction accuracy of ML and DL models are unclear. In this study, the impact of the selection of contributing factors on the accuracy of landslide susceptibility predictions using ML and DL models was investigated. Four methods for selecting contributing factors were considered for all the aforementioned ML and DL models, which included Information Gain Ratio (IGR), Recursive Feature Elimination (RFE), Particle Swarm Optimization (PSO), Least Absolute Shrinkage and Selection Operators (LASSO) and Harris Hawk Optimization (HHO). In addition, autoencoder-based factor selection methods for DL models were also investigated. To assess their performances, an exhaustive approach was adopted, testing all possible selection cases of contributing factors, the results of which served as the benchmark. The results confirmed that using more important contributing factors improved the prediction accuracy of the ML models considered. However, it was interesting to find that the selection of contributing factors using IGR and RFE reduced the predictive power of the DL models. For the DL models, using an autoencoder architecture improved their prediction performance. The study also found that the choice of factor selection methods was far more effective than the selection of contributing factors in improving the prediction accuracy of landslide susceptibility.

show abstract

“…Wang et al 22 introduced risk source identification and emergency classification and developed an emergency decision model based on scenario retrieval and case-based reasoning. By fully mining the spatial features, Zhao et al 23 proposed a novel spatial case-based reasoning method for landslide risk assessment.…”

Section: Introductionmentioning

confidence: 99%

A Pre-Generation of Emergency Reference Plan Model of Public Health Emergencies with Case-Based Reasoning

Ru¹,

Wen²,

Zhang³

2022

RMHP

View full text Add to dashboard Cite

Background and Purpose In the early 21st century, the coronavirus alone has ravaged the world three times. Public health emergencies have caused a tremendous negative impact on public health, daily life, and global economic development, for having the characteristics of complexity and great harm. To tackle these problems, a pre-generation of emergency reference plan model of public health emergencies is proposed to better deal with the outbreak and spread of public health events. Methods The method is divided into three stages. First, the modified SEIR model is used to predict the attribute values of the target case. Then, the similar case sets are extracted and filtered by calculating the similarity through the cross-efficiency evaluation method with the parallel system. Finally, the multi-stage emergency effect evaluation model is conducted so that the emergency plan with the best response effect at this stage can be made for reference. Results We collected 25 typical events of COVID-19 that occurred in 11 cities in China as historical case bases and target cases, respectively. The result of the experiment verified the feasibility and effectiveness of the proposed method. Conclusion This paper presents a new perspective on making a public health emergency plan, which could improve the decision-making accuracy and efficiency, maximize the emergency effect and save precious time for emergency response. This model can provide rapid decision supports for decision-making for public services such as government departments, centers for disease control, medical emergency centers and transport authorities, etc.

show abstract

A spatial case-based reasoning method for regional landslide risk assessment

Cited by 15 publications

References 43 publications

Risk Assessment of Landslide Collapse Disasters along National Highways Based on Information Quantity and Random Forest Coupling Methods: A Case Study of the G331 National Highway

Risk Assessment of Landslide Collapse Disasters along National Highways Based on Information Quantity and Random Forest Coupling Methods: A Case Study of the G331 National Highway

Selection of contributing factors for predicting landslide susceptibility using machine learning and deep learning models

A Pre-Generation of Emergency Reference Plan Model of Public Health Emergencies with Case-Based Reasoning

Contact Info

Product

Resources

About