Comparing the prediction performance of a Deep Learning Neural Network model with conventional machine learning models in landslide susceptibility assessment

Bui, Dieu Tien; Tsangaratos, Paraskevas; Nguyen, Viet-Tien; Liem, Ngo Van; Trinh, Phan Trong

doi:10.1016/j.catena.2019.104426

Cited by 345 publications

(133 citation statements)

References 88 publications

Supporting

Mentioning

123

Contrasting

Unclassified

Order By: Relevance

“…This pondering is usually done according to criteria determined by experts and their knowledge of the study area. Other works have adopted other ways of applying this pondering based on the frequency ratio of events that a specific class has (Bui et al, 2020), which would be ideal when complete events report is available, which is not the case for Quito. For this research, part of the processing of the variables was normalization based on both weights and percentiles methods.…”

Section: Discussionmentioning

confidence: 99%

Landslide Susceptibility Mapping for Quito with Logistic Regression and Sensitivity Analysis

Puente-Sotomayor

Mustafà

Teller

2020

Preprint

View full text Add to dashboard Cite

The Andean region is one of the highest landslide-susceptible areas worldwide, while still limited attention has been devoted to the topic in this context in terms of research, risk reduction practice and urban policy. Given the collection of a few early datasets for landslides after a dozen years by the Andean city of Quito, this article aims to explore the predictive power of a binary logistic regression model (LOGIT) to test the provided data and multicriteria evaluation for landslide susceptibility in this urban area. Furthermore, two types of sensitivity analysis, the univariate and the MonteCarlo methods, were applied in order to suggest a better calibration of the LOGIT model. Amongst the ten variables included in the model for the context of Quito, which help to explain its landslide susceptibility, results showed that population and road density have relevant predicting power for high landslide susceptibility when adopting a weights-based data normalization for the model. This model was validated with a receiving operating characteristic of 0.79. Sensitivity analyses suggested calibrations of the model different from the referential one that would improve this metric up to 2%. The calibration process suggests further experimentation regarding other methods of normalization and a finer level of disaggregation of data. In terms of policy design, the LOGIT model coefficients values suggest the need of a deep analysis of the impacts that urban features such as population, road density, building footprint and floor area at a household scale have on the generation of landslide susceptibility in Andean cities like Quito.

show abstract

Section: Discussionmentioning

confidence: 99%

Landslide Susceptibility Mapping for Quito with Logistic Regression and Sensitivity Analysis

Puente-Sotomayor

Mustafà

Teller

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The hazard related to landslides at volcanoes is also significant. DNN models were proposed for landslide susceptibility assessment in Viet Nam, showing considerable better performance with respect to other ML methods such as MLP, SVM, DT and RF [156]. The use of DNN approach could be therefore an interesting approach for the landslide susceptibility mapping of active volcanoes.…”

Section: Applications Of Machine Learning To Other Volcanological Datamentioning

confidence: 99%

Machine Learning in Volcanology: A Review

Carniel¹,

Guzmán²

2021

Updates in Volcanology - Transdisciplinary Nature of Volcano Science

View full text Add to dashboard Cite

A volcano is a complex system, and the characterization of its state at any given time is not an easy task. Monitoring data can be used to estimate the probability of an unrest and/or an eruption episode. These can include seismic, magnetic, electromagnetic, deformation, infrasonic, thermal, geochemical data or, in an ideal situation, a combination of them. Merging data of different origins is a non-trivial task, and often even extracting few relevant and information-rich parameters from a homogeneous time series is already challenging. The key to the characterization of volcanic regimes is in fact a process of data reduction that should produce a relatively small vector of features. The next step is the interpretation of the resulting features, through the recognition of similar vectors and for example, their association to a given state of the volcano. This can lead in turn to highlight possible precursors of unrests and eruptions. This final step can benefit from the application of machine learning techniques, that are able to process big data in an efficient way. Other applications of machine learning in volcanology include the analysis and classification of geological, geochemical and petrological “static” data to infer for example, the possible source and mechanism of observed deposits, the analysis of satellite imagery to quickly classify vast regions difficult to investigate on the ground or, again, to detect changes that could indicate an unrest. Moreover, the use of machine learning is gaining importance in other areas of volcanology, not only for monitoring purposes but for differentiating particular geochemical patterns, stratigraphic issues, differentiating morphological patterns of volcanic edifices, or to assess spatial distribution of volcanoes. Machine learning is helpful in the discrimination of magmatic complexes, in distinguishing tectonic settings of volcanic rocks, in the evaluation of correlations of volcanic units, being particularly helpful in tephrochronology, etc. In this chapter we will review the relevant methods and results published in the last decades using machine learning in volcanology, both with respect to the choice of the optimal feature vectors and to their subsequent classification, taking into account both the unsupervised and the supervised approaches.

show abstract

“…Regardless of the technique (pixel/object-based), several classification algorithms exist and can be applied separately or jointly (e.g., Support Vector Machine algorithm-SVM in Van Den Eeckhaut et al 2012; Random Forest-RF algorithm in Stumpf and Kerle 2011a, both in Li et al 2015). Both techniques have been used in a wide range of remote-sensing applications including landslide detection and susceptibility mapping (Ballabio and Sterlacchini 2012;Catani et al 2013;Achour and Pourghasemi 2019;Arabameri et al 2019;Bui et al 2020;Fang et al 2020). For a good integration of the Fig.…”

Section: From Conventional Classification Algorithms To Artificial Nementioning

confidence: 99%

“…(Yang and Chen 2010;Song et al 2012;Yang et al 2013;Behling et al 2014;Moosavi et al 2014;Achour and Pourghasemi 2019;Arabameri et al 2019;Ghorbanzadeh et al 2019;Wang et al 2019;Bui et al 2020;Du et al 2020;Fang et al 2020;Hong et al 2015;Hu et al 2020;Huang et al 2020).…”

unclassified

Remote Sensing for Assessing Landslides and Associated Hazards

et al. 2020

View full text Add to dashboard Cite

Multi-platform remote sensing using space-, airborne and ground-based sensors has become essential tools for landslide assessment and disaster-risk prevention. Over the last 30 years, the multiplicity of Earth Observation satellites mission ensures uninterrupted optical and radar imagery archives. With the popularization of Unmanned Aerial Vehicles, free optical and radar imagery with high revisiting time, ground and aerial possibilities to perform high-resolution 3D point clouds and derived digital elevation models, it can make it difficult to choose the appropriate method for risk assessment. The aim of this paper is to review the mainstream remote-sensing methods commonly employed for landslide assessment, as well as processing. The purpose is to understand how remote-sensing techniques can be useful for landslide hazard detection and monitoring taking into consideration several constraints such as field location or costs of surveys. First we focus on the suitability of terrestrial, aerial and spaceborne systems that have been widely used for landslide assessment to underline their benefits and drawbacks for data acquisition, processing and interpretation. Several examples of application are presented such as Interferometry Synthetic Aperture Radar (InSAR), lasergrammetry, Terrestrial Optical Photogrammetry. Some of these techniques are unsuitable for slow moving landslides, others limited to large areas and others to local investigations. It can be complicated to select the most appropriate system. Today, the key for understanding landslides is the complementarity of methods and the automation of the data processing. All the mentioned approaches can be coupled (from field monitoring to satellite images analysis) to improve risk management, and the real challenge is to improve automatic solution for landslide recognition and monitoring for the implementation of near real-time emergency systems.

show abstract

Comparing the prediction performance of a Deep Learning Neural Network model with conventional machine learning models in landslide susceptibility assessment

Cited by 345 publications

References 88 publications

Landslide Susceptibility Mapping for Quito with Logistic Regression and Sensitivity Analysis

Landslide Susceptibility Mapping for Quito with Logistic Regression and Sensitivity Analysis

Machine Learning in Volcanology: A Review

Remote Sensing for Assessing Landslides and Associated Hazards

Contact Info

Product

Resources

About