National-scale data-driven rainfall induced landslide susceptibility mapping for China by accounting for incomplete landslide data

Lin, Qigen; Lima, Pedro; Steger, Stefan; Glade, Thomas; Jiang, Tong; Zhang, Jiahui; Liu, Tianxue; Wang, Ying

doi:10.1016/j.gsf.2021.101248

Cited by 89 publications

(53 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this reason, assuring inventory's best positional accuracy is extremely important. It is known that historical and accurate landslide inventories are virtually never available, especially when dealing with very large areas (Herrera et al 2018;Lima et al 2021;Lin et al 2021; van den Eeckhaut and Hervas 2014). However emerging landslide mapping techniques that enable, immediate and precise event-based cataloging or techniques allowing past landslide extraction from highresolution digital terrain models can positively contribute (Guzzetti et al 2012).…”

Section: Study Site Extent and Landslide Inventorymentioning

confidence: 99%

Literature review and bibliometric analysis on data-driven assessment of landslide susceptibility

et al. 2022

Self Cite

View full text Add to dashboard Cite

In recent decades, data-driven landslide susceptibility models (DdLSM), which are based on statistical or machine learning approaches, have become popular to estimate the relative spatial probability of landslide occurrence. The available literature is composed of a wealth of published studies and that has identified a large variety of challenges and innovations in this field. This review presents a comprehensive up-to-date overview focusing on the topic of DdLSM. This research begins with an introduction of the theoretical aspects of DdLSM research and is followed by an in-depth bibliometric analysis of 2585 publications. This analysis is based on the Web of Science, Clarivate Analytics database and provides insights into the transient characteristics and research trends within published spatial landslide assessments. Following the bibliometric analysis, a more detailed review of the most recent publications from 1985 to 2020 is given. A variety of different criteria are explored in detail, including research design, study area extent, inventory characteristics, classification algorithms, predictors utilized, and validation technique performed. This section, dealing with a quantitative-oriented review expands the time-frame of the review publication done by Reichenbach et al. in 2018 by also accounting for the four years, 2017–2020. The originality of this research is acknowledged by combining together: (a) a recap of important theoretical aspects of DdLSM; (b) a bibliometric analysis on the topic; (c) a quantitative-oriented review of relevant publications; and (d) a systematic summary of the findings, indicating important aspects and potential developments related to the DdLSM research topic. The results show that DdLSM are used within a wide range of applications with study area extents ranging from a few kilometers to national and even continental scales. In more than 70% of publications, a combination of the predictors, slope angle, aspect and geology are used. Simple classifiers, such as, logistic regression or approaches based on frequency ratio are still popular, despite the upcoming trend of applying machine learning algorithms. When analyzing validation techniques, 38% of the publications were not clear about the validation method used. Within the studies that included validation techniques, the AUROC was the most popular validation metric, being used accounting for 44% of the studies. Finally, it can be concluded that the application of new classification techniques is often cited as a main research scope, even though the most relevant innovation could also lie in tackling data-quality issues and research designs adaptations to fit the input data particularities in order to improve prediction quality.

show abstract

Section: Study Site Extent and Landslide Inventorymentioning

confidence: 99%

Literature review and bibliometric analysis on data-driven assessment of landslide susceptibility

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…This definition still results in more than six times more absence grid cells (N noLS > 25000) than landslide presence grid cells (N LS =3757). We therefore sample from the absence grid cells with a 1:1 ratio (N LS :N noLS ) as is commonly done, for example by Brenning (2005), Glade (2017), Nowicki Jessee et al (2018), Depicker et al (2020), Knevels et al (2020), Lin et al (2021) and Lucchese et al (2021). LSS models are subsequently constructed based on data from 7514 grid cells, as illustrated in Fig.…”

Section: Landslide Datamentioning

confidence: 99%

“…In this study, we create a statistical LSS model using MELR (Zuur, 2009), as previously also employed by , and at national scale by Lin et al (2021) and Lima et al (2021). Logistic regression is the most commonly used approach for statistical LSS mapping (Reichenbach et al, 2018), and is associated with strong generalizing capabilities (Brenning, 2005)a necessity when working at the global scale.…”

Section: Mixed Effects Logistic Regression (Melr) For Model Developmentmentioning

confidence: 99%

Estimating global landslide susceptibility and its uncertainty through ensemble modelling

Felsberg

Poesen

Bechtold

et al. 2021

Preprint

View full text Add to dashboard Cite

Abstract. This study assesses global landslide susceptibility (LSS) at the coarse 36-km spatial resolution of global satellite soil moisture observations, to prepare for a subsequent combination of a global LSS map with dynamic soil moisture estimates for landslide modelling. Global LSS estimation intrinsically contains uncertainty, arising from errors in the underlying data, the spatial mismatch between landslide events and predictor information, and large-scale model generalizations. For a reliable uncertainty assessment, this study combines methods from the landslide community with common practices in meteorological modelling to create an ensemble of global LSS maps. The predictive LSS models are obtained from a mixed effects logistic regression, associating hydrologically triggered landslide data from the Global Landslide Catalog (GLC) with predictor variables from the Catchment land surface modeling system (incl. input parameters of soil (hydrological) properties and resulting climatological statistics of water budget estimates), geomorphological and lithological data. Road network density is introduced as a random effect to mitigate potential landslide inventory bias. We use a blocked random cross validation to assess the model uncertainty that propagates into the LSS maps. To account for other uncertainty sources, such as input uncertainty, we also perturb the predictor variables and obtain an ensemble of LSS maps. The perturbations are optimized so that the total predicted uncertainty fits the observed discrepancy between the ensemble average LSS and the landslide presence or absence from the GLC. We find that the most reliable total uncertainty estimates are obtained through the inclusion of a topography-dependent perturbation between 15 % and 20 % to the predictor variables. The areas with the largest LSS uncertainty coincide with moderate ensemble average LSS. The spatial patterns of the average LSS agree well with previous global studies and yield areas under the Receiver Operation Characteristic between 0.63 and 0.9 for independent regional to continental landslide inventories.

show abstract

“…Landslide susceptibility assessment (LSA) is a key component of the landslide risk evaluation. There are many related studies that assess the susceptibility or risk of landslides on a national scale, such as China [6,7], Portugal [8], Iran [9], and New Zealand [10], and even on a global scale [11,12]. For national scale LSAs, these studies use conventional models such as logistic regression (LR), random forest (RF), etc., and even incorporate local policy orientations and considerations of the physical vulnerability of buildings.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Tree-Structured Parzen Estimator Optimization in Three Typical Neural Network Models for Landslide Susceptibility Assessment

Rong

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Landslides pose a constant threat to the lives and property of mountain people and may also cause geomorphological destruction such as soil and water loss, vegetation destruction, and land cover change. Landslide susceptibility assessment (LSA) is a key component of landslide risk evaluation. There are many related studies, but few analyses and comparisons of models for optimization. This paper aims to introduce the Tree-structured Parzen Estimator (TPE) algorithm for hyperparameter optimization of three typical neural network models for LSA in Shuicheng County, China, as an example, and to compare the differences of predictive ability among the models in order to achieve higher application performance. First, 17 influencing factors of landslide multiple data sources were selected for spatial prediction, hybrid ensemble oversampling and undersampling techniques were used to address the imbalanced sample and small sample size problem, and the samples were randomly divided into a training set and validation set. Second, deep neural network (DNN), recurrent neural network (RNN), and convolutional neural network (CNN) models were adopted to predict the regional landslides susceptibility, and the TPE algorithm was used to optimize the hyperparameters respectively to improve the assessment capacity. Finally, to compare the differences and optimization effects of these models, several objective measures were applied for validation. The results show that the high-susceptibility regions mostly distributed in bands along fault zones, where the lithology is mostly claystone, sandstone, and basalt. The DNN, RNN, and CNN models all perform well in LSA, especially the RNN model. The TPE optimization significantly improves the accuracy of the DNN and CNN (3.92% and 1.52%, respectively), but does not improve the performance of the RNN. In summary, our proposed RNN model and TPE-optimized DNN and CNN model have robust predictive capability for landslide susceptibility in the study area and can also be applied to other areas containing similar geological conditions.

show abstract

National-scale data-driven rainfall induced landslide susceptibility mapping for China by accounting for incomplete landslide data

Cited by 89 publications

References 70 publications

Literature review and bibliometric analysis on data-driven assessment of landslide susceptibility

Literature review and bibliometric analysis on data-driven assessment of landslide susceptibility

Estimating global landslide susceptibility and its uncertainty through ensemble modelling

Comparison of Tree-Structured Parzen Estimator Optimization in Three Typical Neural Network Models for Landslide Susceptibility Assessment

Contact Info

Product

Resources

About