4.6 Article

Application of Tree-Based Ensemble Models to Landslide Susceptibility Mapping: A Comparative Study

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Environmental Sciences

Comparative analysis of gradient boosting algorithms for landslide susceptibility mapping

Emrehan Kutlug Sahin

Summary: The aim of this study was to compare the prediction capabilities of four recent gradient boosting algorithms in modeling landslide susceptibility. The results showed that the CatBoost model had the highest prediction capability. Compared to other methods, the Random Forest method had lower prediction capability.

GEOCARTO INTERNATIONAL (2022)

Article Environmental Sciences

Landslide susceptibility mapping in three Upazilas of Rangamati hill district Bangladesh: application and comparison of GIS-based machine learning methods

Yasin Wahid Rabby et al.

Summary: This study evaluates and compares the performance of three machine learning models (KNN, RF, and XGBoost) for landslide susceptibility mapping in Rangamati District, Bangladesh, and finds that XGBoost has the best performance.

GEOCARTO INTERNATIONAL (2022)

Article Engineering, Geological

Landslide detection in the Himalayas using machine learning algorithms and U-Net

Sansar Raj Meena et al.

Summary: Event-based landslide inventories are crucial for understanding the causal relationship between triggering events and landslides, and for subsequent risk studies. This study explores the potential of U-Net and machine learning approaches for automated landslide detection in the Himalayas. The results suggest that the U-Net model performs slightly better than other methods in landslide detection.

LANDSLIDES (2022)

Article Computer Science, Interdisciplinary Applications

Methods for landslide detection based on lightweight YOLOv4 convolutional neural network

Bo Li et al.

Summary: This paper proposes a new algorithm for landslide detection in plateau environment using remote sensing data. The algorithm utilizes YOLOv4 framework and MobileNetv3 model to improve the efficiency and accuracy of landslide detection. The results show that the proposed model can significantly reduce the number of parameters while achieving high accuracy and detection speed.

EARTH SCIENCE INFORMATICS (2022)

Article Green & Sustainable Science & Technology

Landslide Susceptibility Mapping with Deep Learning Algorithms

Jules Maurice Habumugisha et al.

Summary: This study applied four deep learning algorithms to evaluate the possibility of landslides in Maoxian County, China. The results showed that landslide-prone areas were mostly located along the Minjiang River and in certain parts of the southeastern region. Slope, rainfall, and distance to faults were found to be the most influential factors affecting landslide occurrence. The DNN algorithm performed better than LSTM, CNN, and RNN in identifying landslides in Maoxian County.

SUSTAINABILITY (2022)

Article Environmental Sciences

Artificial neural network and sensitivity analysis in the landslide susceptibility mapping of Idukki district, India

Jesudasan Jacinth Jennifer et al.

Summary: The study developed two ANN models to generate landslide susceptibility maps, showing similar trends with the observed landslide locations in the region.

GEOCARTO INTERNATIONAL (2022)

Article Green & Sustainable Science & Technology

Regional Landslide Hazard Assessment Using Extreme Value Analysis and a Probabilistic Physically Based Approach

Hyuck-Jin Park et al.

Summary: Accurate assessment of landslide hazards is crucial for reducing casualties and damage. This study adopts a physically based approach with probabilistic analysis to estimate the spatial distribution of landslide probability, and proposes an indirect approach based on rainfall frequency to estimate temporal probability. Nonstationary characteristics of rainfall data are also considered.

SUSTAINABILITY (2022)

Article Multidisciplinary Sciences

Predictive Performances of Ensemble Machine Learning Algorithms in Landslide Susceptibility Mapping Using Random Forest, Extreme Gradient Boosting (XGBoost) and Natural Gradient Boosting (NGBoost)

Taskin Kavzoglu et al.

Summary: In this study, a novel ensemble learning method called NGBoost was proposed for landslide susceptibility modeling in Turkey. The predictive performance of NGBoost was compared to other ensemble learning methods, and the results showed that NGBoost had the highest predictive ability and outperformed other methods by approximately 6% in terms of overall accuracy.

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING (2022)

Article Engineering, Environmental

Landslide susceptibility mapping and rock slope stability assessment using frequency ratio and kinematic analysis in the mountains of Mgulat area, Northern Ethiopia

Gebremedhin Berhane et al.

Summary: The study generated a landslide susceptibility map (LSM) for Mgulat Mountain, identifying red sandstone and tillite lithologies, as well as slope steepness, as major conditioning factors for landslides. Five susceptibility classes were identified based on LSM results, providing important guidance for further land-use planning and mitigation of landslide risks. Detailed multidisciplinary investigations are recommended to consider cost-effective and technically sound mitigation measures.

BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT (2021)

Article Engineering, Environmental

Application and comparison of different ensemble learning machines combining with a novel sampling strategy for shallow landslide susceptibility mapping

Zhu Liang et al.

Summary: This study aims to evaluate and compare the performance of four models for landslide susceptibility modeling, with gradient boosting decision tree (GBDT) performing best in both training and validation datasets. The results indicate that GBDT is the most suitable model and can be further enhanced by combining with clustering analysis for improved sampling strategy of non-landslide points.

STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT (2021)

Article Geosciences, Multidisciplinary

The application of DInSAR and Bayesian statistics for the assessment of landslide susceptibility

Dimitris Kouhartsiouk et al.

Summary: The study conducted landslide susceptibility assessment in a southwestern region of Cyprus using a combination of differential interferometry and evidential statistics. The results classified active landslides and established a susceptibility model, with success and prediction rates calculated. Validation against existing landslide inventory showed a high agreement, indicating the methodology's effectiveness in providing updated landslide activity information.

NATURAL HAZARDS (2021)

Article Environmental Sciences

PS-InSAR-Based Validated Landslide Susceptibility Mapping along Karakorum Highway, Pakistan

Muhammad Afaq Hussain et al.

Summary: The research involved the comparison of XGBoost and RF models to analyze the association between causative parameters and landslides along the Karakorum Highway. A comprehensive landslide inventory and susceptibility mapping were conducted, with PS-InSAR technique used to investigate deformation movement in susceptible zones. The XGBoost method showed superior accuracy in creating a new LSM model for the area, which may assist in mitigating landslide disaster and ensuring safe operation of the highway.

REMOTE SENSING (2021)

Review Construction & Building Technology

A review on application of soft computing techniques for the rapid visual safety evaluation and damage classification of existing buildings

Ehsan Harirchian et al.

Summary: Assessing the seismic vulnerability of existing buildings is critical worldwide, with rapid urbanization and improper construction practices leading to unreliable building stock. Developing a rapid, reliable, and computationally easy method such as Rapid Visual Screening (RVS) is necessary, with Soft Computing (SC) techniques being widely used for their capabilities in targeting inherent imprecision in real-world phenomena.

JOURNAL OF BUILDING ENGINEERING (2021)

Article Geosciences, Multidisciplinary

Comparing classical statistic and machine learning models in landslide susceptibility mapping in Ardanuc (Artvin), Turkey

Halil Akinci et al.

Summary: This study compared the performance of machine learning models and traditional statistical methods in producing landslide susceptibility maps, with machine learning models showing higher success and prediction rates, especially with the RF model performing the best.

NATURAL HAZARDS (2021)

Article Environmental Sciences

Landslide and Wildfire Susceptibility Assessment in Southeast Asia Using Ensemble Machine Learning Methods

Qian He et al.

Summary: This study focused on landslide and wildfire susceptibility in Southeast Asia using ensemble machine learning algorithms. The results showed that Random Forest performed superiorly in modeling susceptibility, indicating its efficiency and accuracy in hazard assessment in the region.

REMOTE SENSING (2021)

Article Geosciences, Multidisciplinary

Uncertainty study of landslide susceptibility prediction considering the different attribute interval numbers of environmental factors and different data-based models

Faming Huang et al.

Summary: This study investigates the influences of different attribute interval numbers and data-based models on the accuracy of landslide susceptibility prediction. Results demonstrate that the prediction accuracy gradually increases with the increase in attribute interval numbers for a specific model, and the random forest model has the highest prediction accuracy as the attribute interval numbers increase.

CATENA (2021)

Article Environmental Sciences

Landslide Susceptibility Modeling: An Integrated Novel Method Based on Machine Learning Feature Transformation

Husam A. H. Al-Najjar et al.

Summary: This study examined the effectiveness of six feature transformations in landslide susceptibility modeling, with the use of Ohe-X transformation significantly improving model performance. A case study in the landslide-prone area in Cameron Highlands, Malaysia was conducted to test this novel approach.

REMOTE SENSING (2021)

Article Geosciences, Multidisciplinary

Application of Bayesian Hyperparameter Optimized Random Forest and XGBoost Model for Landslide Susceptibility Mapping

Shibao Wang et al.

Summary: Bayesian hyperparameter optimization was used to improve the prediction performance of random forest and extreme gradient boosting decision tree models for landslide susceptibility mapping. The results showed that the random forest model had higher predictive ability than the extreme gradient boosting decision tree model after optimization.

FRONTIERS IN EARTH SCIENCE (2021)

Article Geosciences, Multidisciplinary

A comparison among fuzzy multi-criteria decision making, bivariate, multivariate and machine learning models in landslide susceptibility mapping

Quoc Bao Pham et al.

Summary: This study analyzed the landslide susceptibility in the Kysuca river basin in Slovakia using various models, with RFC model proving to be the most accurate. Additionally, the FDEMATEL-ANP model demonstrated better prediction capability compared to multivariate LR, machine learning NBC, and deep learning XGBoost models.

GEOMATICS NATURAL HAZARDS & RISK (2021)

Article Geosciences, Multidisciplinary

Artificial neural network ensembles applied to the mapping of landslide susceptibility

L. Bragagnolo et al.

CATENA (2020)

Article Environmental Sciences

Landslide susceptibility zoning in a catchment of Zagros Mountains using fuzzy logic and GIS

Siamak Baharvand et al.

ENVIRONMENTAL EARTH SCIENCES (2020)

Review Geosciences, Multidisciplinary

Machine learning methods for landslide susceptibility studies: A comparative overview of algorithm performance

Abdelaziz Merghadi et al.

EARTH-SCIENCE REVIEWS (2020)

Article Computer Science, Interdisciplinary Applications

Building a landslide hazard indicator with machine learning and land surface models

T. A. Stanley et al.

ENVIRONMENTAL MODELLING & SOFTWARE (2020)

Article Computer Science, Information Systems

Rainfall-Induced Shallow Landslide Susceptibility Mapping at Two Adjacent Catchments Using Advanced Machine Learning Algorithms

Ananta Man Singh Pradhan et al.

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION (2020)

Article Computer Science, Interdisciplinary Applications

Formation lithology classification using scalable gradient boosted decision trees

Vikrant A. Dev et al.

COMPUTERS & CHEMICAL ENGINEERING (2019)

Article Environmental Sciences

Debris Flow Susceptibility Mapping Using Machine-Learning Techniques in Shigatse Area, China

Yonghong Zhang et al.

REMOTE SENSING (2019)

Article Geosciences, Multidisciplinary

Prediction of the landslide susceptibility: Which algorithm, which precision?

Hamid Reza Pourghasemi et al.

CATENA (2018)

Review Geosciences, Multidisciplinary

A review of statistically-based landslide susceptibility models

Paola Reichenbach et al.

EARTH-SCIENCE REVIEWS (2018)

Article Computer Science, Interdisciplinary Applications

Evaluating machine learning and statistical prediction techniques for landslide susceptibility modeling

J. N. Goetz et al.

COMPUTERS & GEOSCIENCES (2015)

Article Geosciences, Multidisciplinary

Machine Learning Feature Selection Methods for Landslide Susceptibility Mapping

Natan Micheletti et al.

MATHEMATICAL GEOSCIENCES (2014)

Article Computer Science, Interdisciplinary Applications

Application of the analytical hierarchy process (AHP) for landslide susceptibility mapping: A case study from the Tinau watershed, west Nepal

P. Kayastha et al.

COMPUTERS & GEOSCIENCES (2013)

Article Computer Science, Artificial Intelligence

Random forests

L Breiman

MACHINE LEARNING (2001)

Article Statistics & Probability

Greedy function approximation: A gradient boosting machine

JH Friedman

ANNALS OF STATISTICS (2001)