Landslides Analysis and Management: From Data Acquisition to Modelling and Monitoring II

Topic Information

Dear Colleagues,

Landslides, debris flows, rock falls, rock avalanches, and lahars are gravitational processes affecting different-sized areas and operate at different speeds depending on the geological and geomorphological context (tectonic setting, lithology, terrain morphology, hydrology and hydrogeology). They represent a dynamic response to a set of triggering factors mainly heavy rainfall, seismicity, volcanism, and human activities. The risk they represent for human life and economic activity is increasing due to the constantly increasing population, land-use changes, and climate change. Their socioeconomic repercussions include the cost to individuals, local communities, national services, and industry.

Different approaches are available to analyze landslide scenarios in order to assess, mitigate, and manage the related risks: laboratory and field investigations, susceptibility mapping, physical and numerical modelling, monitoring techniques, early warning system design, and so on. This Topic focuses on i) recent enhancements and trends in data acquisition technologies and landslide monitoring techniques, such as the use of UAVs (unmanned aerial vehicles) for tracking and monitoring the movements of landslides or WSN (wireless sensor network) applications for real-time monitoring purposes, SFM (structure-from-motion) photogrammetry applications, and so on; and ii) studies devoted to physical and numerical modelling of landslides aiming to explore recent advances and future challenges.

Contributions may cover a broad range of topics ranging from remote sensing applications and susceptibility mapping to physical and numerical modelling, utilization of sensor technology in landslide monitoring, the Internet of Things (IoT) for landslide monitoring, machine learning, and deep learning. Reviews of the state of the art on the mentioned topics are also encouraged, as well as case studies on landslide risk management.

We look forward to receiving your contributions.

Dr. Irene Manzella
Dr. Bouchra Haddad
Topic Editors

Keywords

Participating Journals

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
GeoHazards geohazards	-	2.6	2020	20.4 Days	CHF 1000
Remote Sensing remotesensing	4.2	8.3	2009	24.7 Days	CHF 2700
Sensors sensors	3.4	7.3	2001	16.8 Days	CHF 2600
Land land	3.2	4.9	2012	17.8 Days	CHF 2600

MDPI Topics is cooperating with Preprints.org and has built a direct connection between MDPI journals and Preprints.org. Authors are encouraged to enjoy the benefits by posting a preprint at Preprints.org prior to publication:

1. Immediately share your ideas ahead of publication and establish your research priority;
2. Protect your idea from being stolen with this time-stamped preprint article;
3. Enhance the exposure and impact of your research;
4. Receive feedback from your peers in advance;
5. Have it indexed in Web of Science (Preprint Citation Index), Google Scholar, Crossref, SHARE, PrePubMed, Scilit and Europe PMC.

Published Papers (5 papers)

Order results

Content type Publication Date

Result details

Normal Extended Compact

Journals

All GeoHazards Remote Sensing Sensors Land

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

Error

Oops... you haven't selected anything for export.

Ok

clear

20 pages, 15846 KiB  

Open AccessArticle

Modelling the Control of Groundwater on the Development of Colliery Spoil Tip Failures in Wales

by Lingfeng He, John Coggan, Patrick Foster, Tikondane Phiri and Matthew Eyre

Land 2024, 13(8), 1311; https://doi.org/10.3390/land13081311 - 19 Aug 2024

Viewed by 504

Abstract

Legacy colliery spoil tip failures pose a significant hazard that can result in harm to persons or damage to property and infrastructure. In this research, the 2020 Wattstown tip landslide caused by heavy rainfall was examined to investigate the likely mechanisms and developmental [...] Read more.

Legacy colliery spoil tip failures pose a significant hazard that can result in harm to persons or damage to property and infrastructure. In this research, the 2020 Wattstown tip landslide caused by heavy rainfall was examined to investigate the likely mechanisms and developmental factors contributing to colliery spoil tip failures in Welsh coalfields. To achieve this, an integrated method was proposed through the combination of remote sensing mapping, stability chart analysis, 2D limit equilibrium (LE) modelling, and 3D finite difference method (FDM) analysis. Various water table geometries were incorporated into these models to ascertain the specific groundwater condition that triggered the occurrence of the 2020 landslide. In addition, sensitivity analyses were carried out to assess the influence of the colliery spoil properties (i.e., cohesion, friction angle, and porosity) on the slope stability analysis. The results indicate that the landslide was characterised by a shallow rotational failure mode and spatially constrained by the critical water table and an underlying geological interface. In addition, the results also imply that the landslide was triggered by the rise of water table associated with heavy rainfall. Through sensitivity analysis, it was found that the properties of the colliery spoil played an important role in confining the extent of the landslide and controlling the process of its development. The findings underscore the detrimental effects of increased pore pressures, induced by heavy rainfall, on the stability of colliery tips, highlighting the urgent needs for local government to enhance water management strategies for this region. Full article

(This article belongs to the Topic Landslides Analysis and Management: From Data Acquisition to Modelling and Monitoring II)

►▼ Show Figures

Figure 1

Figure 1
<p>Study area—Wattstown tip which is south of Wattstown in the county borough of Rhondda Cynon Taf, Wales, and displayed on ESRI world imagery.</p> Full article ">Figure 2
<p>Images of Wattstown standard tip. (<b>a</b>) A Google satellite image prior to the landslide (05/2020), (<b>b</b>) a Google satellite image after the landslide (07/2021), (<b>c</b>) delineation of the landslide boundary.</p> Full article ">Figure 3
<p>Daily rainfall located at the study area from November 2020 to December 2020 (Met Office Hadley Centre, 2023).</p> Full article ">Figure 4
<p>Remote-sensing mapping of the Wattstown standard tip prior to the 2020 landslide occurrence. (<b>a</b>) Hillshade map, (<b>b</b>) aspect map, and (<b>c</b>) slope angle map.</p> Full article ">Figure 5
<p>Methodology of this research, including the input part to collect data for landslide analysis, the methods part of different methods used for landslide analysis, the output part of the final results obtained using these methods, and the validation process using post-landslide satellite images.</p> Full article ">Figure 6
<p>Slope models for numerical analysis. (<b>a</b>) A 3D model and 9 monitoring points, (<b>b</b>) a satellite image showing the position of the 9 points, (<b>c</b>) a 2D model constructed along an N–S profile in the 3D model.</p> Full article ">Figure 7
<p>A representative Hoek and Bray circular failure chart to estimate the FS of a soil slope where the surface water is 8×H behind the toe of the slope.</p> Full article ">Figure 8
<p>FS values of the slope angle of 30° (grey line), 35° (red line), and 40° (blue line) in response to different groundwater conditions.</p> Full article ">Figure 9
<p>Results of 2D LE analysis based on the simplified Bishop method, showing FS estimation corresponding to the slip surface. (<b>a</b>) Dry slope, (<b>b</b>) partially saturated slope (regime_1).</p> Full article ">Figure 10
<p>FDM modelling result showing the total displacement of a dry slope (regime_1). (<b>a</b>) overview of the modelling result, (<b>b</b>) an N–S cross section of the total displacement contour.</p> Full article ">Figure 11
<p>The curves of total displacement at 9 monitoring points when the slope is in a dry condition.</p> Full article ">Figure 12
<p>FDM modelling result of a partially saturated slope (regime_1). (<b>a</b>) Contour of slope displacement and modelled displacement vectors of the unstable zone, (<b>b</b>) an N–S cross section of the slope displacement contour, (<b>c</b>) close-up image of the N–S cross section showing the geometry of the unstable zone and monitoring points P1, P6, and P8 on the slope.</p> Full article ">Figure 13
<p>The curves of total displacement at 9 monitoring points when the slope is in the regime_1 water condition.</p> Full article ">Figure 14
<p>The curves of total displacement at 9 monitoring points. (<b>a</b>) c = 0, (<b>b</b>) c = 20 kPa.</p> Full article ">Figure 15
<p>Results of sensitivity analysis associated with the cohesion of colliery spoil. (<b>a</b>) c = 0, (<b>b</b>) c = 20 kPa, (<b>c</b>) N–S cross section of the cohesionless modelling result, (<b>d</b>) N–S cross section of the 20 kPa modelling result.</p> Full article ">Figure 16
<p>The curves of total displacement at 9 monitoring points. (<b>a</b>) Φ = 32°, (<b>b</b>) Φ = 42°.</p> Full article ">Figure 17
<p>Results of sensitivity analysis associated with the friction angle of colliery spoil. (<b>a</b>) Φ = 32°, (<b>b</b>) Φ = 42°, (<b>c</b>) N–S cross section of the 32° friction angle modelling result, (<b>d</b>) N–S cross section of the 42° friction angle modelling result.</p> Full article ">Figure 18
<p>The curves of total displacement at 9 monitoring points. (<b>a</b>) φ = 10%, (<b>b</b>) φ = 30%.</p> Full article ">Figure 19
<p>Results of sensitivity analysis associated with the porosity of colliery spoil. (<b>a</b>) φ = 10%, (<b>b</b>) φ = 30%, (<b>c</b>) N–S cross section of the 10% porosity modelling result, (<b>d</b>) N–S cross section of the 30% porosity modelling result.</p> Full article ">Figure 20
<p>UKCP18 daily precipitation projection of a 5 km grid located in the study area from 1 July 2024 to 31 December 2028.</p> Full article ">

22 pages, 12234 KiB  

Open AccessArticle

Machine Learning-Driven Landslide Susceptibility Mapping in the Himalayan China–Pakistan Economic Corridor Region

by Mohib Ullah, Bingzhe Tang, Wenchao Huangfu, Dongdong Yang, Yingdong Wei and Haijun Qiu

Land 2024, 13(7), 1011; https://doi.org/10.3390/land13071011 - 8 Jul 2024

Viewed by 767

Abstract

The reliability of data-driven approaches in generating landslide susceptibility maps depends on data quality, analytical method selection, and sampling techniques. Selecting optimal datasets and determining the most effective analytical methods pose significant challenges. This study assesses the performance of seven machine learning classifiers [...] Read more.

The reliability of data-driven approaches in generating landslide susceptibility maps depends on data quality, analytical method selection, and sampling techniques. Selecting optimal datasets and determining the most effective analytical methods pose significant challenges. This study assesses the performance of seven machine learning classifiers in the Himalayan region of the China–Pakistan Economic Corridor, utilizing statistical techniques and validation metrics. Thirteen geo-environmental variables were analyzed, including topographic (8), land cover (1), hydrological (1), geological (2), and meteorological (1) factors. These variables were evaluated for multicollinearity, feature importance, and their influence on landslide incidences. Our findings indicate that Support Vector Machines and Logistic Regression were highly effective, particularly near fault zones and roads, due to their effectiveness in handling complex, non-linear terrain interactions. Conversely, Random Forest and Logistic Regression demonstrated variability in their results. Each model distinctly identified landslide susceptibility zones ranging from very low to very high risk. Significant conditioning variables such as elevation, rainfall, lithology, slope, and land use were identified, reflecting the unique geomorphological conditions of the Himalayas. Further analysis using the Variance Inflation Factor and Pearson correlation coefficient showed minimal multicollinearity among the variables. Moreover, evaluations of Area Under the Receiver Operating Characteristic Curve (AUC-ROC) values confirmed the strong predictive capabilities of the models, with the Random Forest Classifier performing exceptionally well, achieving an AUC of 0.96 and an F-Score of 0.86. This study shows the importance of model selection based on dataset characteristics to enhance decision-making and strategy effectiveness. Full article

(This article belongs to the Topic Landslides Analysis and Management: From Data Acquisition to Modelling and Monitoring II)

►▼ Show Figures

Figure 1

Figure 1
<p>Study area and elevation map with highlighted landslide locations and major roads.</p> Full article ">Figure 2
<p>Field investigation maps depicting landslides in the study area, including (<b>a</b>) Study area map showing landslide polygons in red and elevation in grayscale. The red square indicates the specific region detailed in subfigures (<b>c</b>–<b>f</b>). (<b>b</b>) Detailed topographic map of the area within the red square in (<b>a</b>), showing the distribution of landslide polygons marked in red. The yellow lines in (<b>c</b>–<b>f</b>) delineate the boundaries of observed landslides. (<b>c</b>) Bara Khun area, (<b>d</b>) Shandur area, (<b>e</b>) Morkhun area, and (<b>f</b>) Astore area.</p> Full article ">Figure 3
<p>Workflow diagram illustrating the process of landslide susceptibility mapping. CART: Classification and Regression Trees, RFE: Recursive Feature Elimination, PCC: Pearson Correlation Coefficient, VIF: Variance Inflation Factor, TOL: Tolerance, WoE: Weight of Evidence, ROC curve: Receiver Operating Characteristic curve, AUC: Area Under the Curve, SVM: Support Vector Machine, RFC: Random Forest Classifier, LR: Logistic Regression, KNN: K-Nearest Neighbors, GBN: Gaussian Naive Bayes, GBDT: Gradient Boosting Decision Tree, CNN: Convolutional Neural Network.</p> Full article ">Figure 4
<p>Maps of conditioning factors in the study area: (<b>a</b>) aspect, (<b>b</b>) elevation, (<b>c</b>) slope, (<b>d</b>) terrain relief, (<b>e</b>) curvature, (<b>f</b>) valley depth, (<b>g</b>) active fault zones, (<b>h</b>) rainfall, (<b>i</b>) Land Use Land Cover (LULC), (<b>j</b>) Terrain Ruggedness Index (TRI), (<b>k</b>) Topographic Wetness Index (TWI), (<b>l</b>) road distance, (<b>m</b>) lithology. Additional Notes for (<b>m</b>) DS—Devonian Schist, C—Carboniferous Limestone, MPzV—Paleozoic Slate, Ch—Metamorphic Schist, E—Eocene Marl, D—Devonian Sandstone, gg—Igneous Metamorphic, J—Jurassic Limestone, Jd—Jurassic Dolomite, K—Cretaceous Sandstone, Kv—Cretaceous Volcanic, M—Mesozoic Sandstone, MPz—Paleozoic Sedimentary, Nh—Neogene Conglomerate, Nh-Z—Neogene Marble, O—Ordovician Limestone, P—Permian Limestone, Pd—Permian Dolostone, Pg—Permian Siliceous, Pt—Permian Quartzite, Pz—Paleozoic Metamorphic, Jx—Jurassic Metacarbonate, N—Neogene Sandstone, Q—Quaternary Sandstone, Qb—Quaternary Carbonate, Qh—Quaternary Mudstone, Qp—Pleistocene Gravel, Qpd—Quaternary Clastic, TK—Tertiary Cretaceous, TR—Triassic Sandstone, Tpm—Pliocene Calcareous, Tm—Miocene Marl, S—Silurian Limestone, T—Tertiary Carbonate, Td—Tertiary Dolostone, Te—Eocene Limestone.</p> Full article ">Figure 5
<p>Heat map of Pearson correlations for landslide variables, with red-to-blue grids showing high-to-low strength and labels representing r-values from Pearson correlations analysis, ranging from −1 to +1.</p> Full article ">Figure 6
<p>Illustrating factor–landslide relationships through the weight of evidence model. Each subplot is labeled with the corresponding factor name, including (<b>a</b>) active fault zone, (<b>b</b>) aspect, (<b>c</b>) curvature, (<b>d</b>) land use, (<b>e</b>) elevation, (<b>f</b>) rainfall, (<b>g</b>) road distance, (<b>h</b>) slope, (<b>i</b>) TRI (Topographic Ruggedness Index), (<b>j</b>) TWI (Topographic Wetness Index), (<b>k</b>) terrain relief, (<b>l</b>) valley depth, and (<b>m</b>) lithology. Land use classes are represented with their abbreviations: Artificial surfaces (AS), Barren (B), Cultivated Land (CL), Grassland (GL), Irrigated Cultivated Land (ICL), Sparse Vegetation (SV), Waterbody (WB), Dry Farmland (DFL/M), Lichens/Moss (LM), Shrub (S), Woodland (W), and Permanent Snow (PS).</p> Full article ">Figure 7
<p>Landslide covariate priority selection by CART and RFE models. (<b>a</b>) displays the priority of different covariates as determined by the CART (Classification and Regression Trees) model, quantifying each covariate’s importance in predicting landslide occurrence. The values on the radar chart reflect the normalized importance scores ranging from 0 to 0.18, with higher values indicating greater importance in the model. (<b>b</b>) illustrates the ranking of covariates by the RFE (Recursive Feature Elimination) method, where each covariate’s contribution to model accuracy is ranked from 0 to 12, with lower numbers representing higher priority.</p> Full article ">Figure 8
<p>Landslide susceptibility maps obtained using each model selection: (<b>a</b>) CNN, (<b>b</b>) GBDT, (<b>c</b>) GBN, (<b>d</b>) KNN, (<b>e</b>) LR, (<b>f</b>) RFC, (<b>g</b>) SVM.</p> Full article ">Figure 9
<p>Receiver Operating Characteristic (ROC) curves for various machine learning models evaluating landslide susceptibility.</p> Full article ">

16 pages, 7776 KiB  

Open AccessArticle

Effect of Rockfall Spatial Representation on the Accuracy and Reliability of Susceptibility Models (The Case of the Haouz Dorsale Calcaire, Morocco)

by Youssef El Miloudi, Younes El Kharim, Ali Bounab and Rachid El Hamdouni

Land 2024, 13(2), 176; https://doi.org/10.3390/land13020176 - 2 Feb 2024

Cited by 1 | Viewed by 1041

Abstract

Rockfalls can cause loss of life and material damage. In Northern Morocco, rockfalls and rock avalanche-deposits are frequent, especially in the Dorsale Calcaire morpho-structural unit, which is mostly formed by Jurassic limestone and dolostone formations. In this study, we focus exclusively on its [...] Read more.

Rockfalls can cause loss of life and material damage. In Northern Morocco, rockfalls and rock avalanche-deposits are frequent, especially in the Dorsale Calcaire morpho-structural unit, which is mostly formed by Jurassic limestone and dolostone formations. In this study, we focus exclusively on its northern segment, conventionally known as “the Haouz subunit”. First, a rockfall inventory was conducted. Then, two datasets were prepared: one covering exclusively the source area and the other representing the entirety of the mass movements (source + propagation area). Two algorithms were then used to build rockfall susceptibility models (RSMs). The first one (Logistic Regression: LR) yielded the most unreliable results, where the RSM derived from the source area dataset significantly outperformed the one based on the entirety of the rockfall affected area, despite the lack of significant visual differences between both models. However, the RSMs produced using Artificial Neural Networks (ANNs) were more or less similar in terms of accuracy, despite the source area model being more conservative. This result is unexpected given the fact that previous studies proved the robustness of the LR algorithm and the sensitivity of ANN models. However, we believe that the non-linear correlation between the spatial distribution of the rockfall propagation area and that of the conditioning factors used to compute the models explains why modeling rockfalls in particular differs from other types of landslides. Full article

(This article belongs to the Topic Landslides Analysis and Management: From Data Acquisition to Modelling and Monitoring II)

►▼ Show Figures

Figure 1

Figure 1
<p>Geological map of the study area.</p> Full article ">Figure 2
<p>Examples of rockfall processes in the study area.</p> Full article ">Figure 3
<p>Methodology flowchart followed in this study.</p> Full article ">Figure 4
<p><b>A</b> (<b>a</b>)—Rockfall inventory map showing exclusively the source area. <b>B</b> (<b>b</b>)—Rockfall inventory map showing the entirety of the inventoried rockfalls.</p> Full article ">Figure 5
<p>Rockfall conditioning factors ((<b>A</b>): slope; (<b>B</b>): aspect; (<b>C</b>): curvature; (<b>D</b>): elevation; (<b>E</b>): rainfall; (<b>F</b>): distance to faults; (<b>G</b>): distance to roads; (<b>H</b>): distance to streams and (<b>I</b>): lithology).</p> Full article ">Figure 6
<p>Rockfall susceptibility maps were produced using logistic regression and artificial neural networks. ((<b>A</b>,<b>C</b>): RSM based on source area only; (<b>B</b>,<b>D</b>): inventory based on the entirety of the rockfalls).</p> Full article ">Figure 7
<p>Histogram of rockfall susceptibility categories. Histogram (<b>A</b>) shows logistic regression (LR) and histogram (<b>B</b>) shows the artificial neural network (ANN) using MLP approach. (S) is the designed source, and (S + PA) is the designed source + propagation area.</p> Full article ">Figure 8
<p>Importance degree of causative factors in MLP maps ((<b>A</b>) for the (S) ANN map and (<b>B</b>) for the (S + PA) ANN map).</p> Full article ">Figure 9
<p>ROC curves for the output RSMs: (<b>A</b>)—logistic regression (LR) curves: (S/PBA); (<b>B</b>)—multilayer perception (MLP) curves, with (S) being the designed source and (S/PBA) being the source + propagation area.</p> Full article ">

22 pages, 10665 KiB  

Open AccessArticle

Design and Implementation of a Prototype Seismogeodetic System for Tectonic Monitoring

by Javier Ramírez-Zelaya, Belén Rosado, Vanessa Jiménez, Jorge Gárate, Luis Miguel Peci, Amós de Gil, Alejandro Pérez-Peña and Manuel Berrocoso

Sensors 2023, 23(21), 8986; https://doi.org/10.3390/s23218986 - 5 Nov 2023

Viewed by 1562

Abstract

This manuscript describes the design, development, and implementation of a prototype system based on seismogeodetic techniques, consisting of a low-cost MEMS seismometer/accelerometer, a biaxial inclinometer, a multi-frequency GNSS receiver, and a meteorological sensor, installed at the Doñana Biological Station (Huelva, Spain) that transmits [...] Read more.

This manuscript describes the design, development, and implementation of a prototype system based on seismogeodetic techniques, consisting of a low-cost MEMS seismometer/accelerometer, a biaxial inclinometer, a multi-frequency GNSS receiver, and a meteorological sensor, installed at the Doñana Biological Station (Huelva, Spain) that transmits multiparameter data in real and/or deferred time to the control center at the University of Cadiz. The main objective of this system is to know, detect, and monitor the tectonic activity in the Gulf of Cadiz region and adjacent areas in which important seismic events occur produced by the interaction of the Eurasian and African plates, in addition to the ability to integrate into a regional early warning system (EWS) to minimize the consequences of dangerous geological phenomena. Full article

(This article belongs to the Topic Landslides Analysis and Management: From Data Acquisition to Modelling and Monitoring II)

►▼ Show Figures

Figure 1

Figure 1
<p>Instrumentation located in the Doñana National Park, Huelva, Spain: (<b>A</b>) the prototype seismogeodetic system, (<b>B</b>) metal tripod that supports the Leica Geodetic (AR10) antenna, Leica GNSS receiver, and weather sensor, (<b>C</b>) box containing the GNSS receiver and main communication switch, (<b>D</b>) Vaisala weather sensor (WXT520), (<b>E</b>) concrete chamber located 1m away from the tripod, (<b>F</b>) Leica GR30 GNSS receiver, (<b>G</b>) contents of the concrete chamber: Seismometer, Inclinometer, communications connectors, power supply connectors, and desiccant bags that prevent humidity, (<b>H</b>) GNSS receiver UBX–M8030, (<b>I</b>) Raspberry Shake 4D Seismometer/Accelerometer, (<b>J</b>) Biaxial Digital Tilt Logger DTL202B, and (<b>K</b>) Vaisala weather sensor, owned by AEMET.</p> Full article ">Figure 2
<p>Network diagram and hardware components of the prototype seismogeodetic system (communications, sensors, servers, virtual machines, NAS, mirror backup, etc.); it is divided into three parts: Prototype Seismogeodetic (Doñana Station), UCA–HUB, and Control Center (LAGC). Initially, the prototype, and the UCA–HUB are interconnected by the VPN service provided by the CSIC, facilitating data transmission over the Internet to the management and control center, which has a Citrix XenServer virtual infrastructure with virtual machines that have services and applications dedicated to the automatic acquisition, processing, visualization, and filtering of data produced.</p> Full article ">Figure 3
<p>Structure of the components involved in the implementation of the prototype; it is divided into two groups and three subgroups that show the components of hardware, services, communications, and virtual infrastructure of the control center (LAGC–UCA), and Doñana Station, as well as the virtual machines that contain the acquisition, processing, and filtering modules.</p> Full article ">Figure 4
<p>Results (E, N, U) of the DONA station time series; the GNSS processing was performed with the BERNESE 5.2 software using ITRF14. This figure shows the time series with the linear fit and the CATS filter, as well as the velocities per component.</p> Full article ">Figure 5
<p>Results (E, N, U) of the DONA station time series; the GNSS processing was performed with the BERNESE 5.2 software using ITRF14. In addition, Kalman and Wavelets filters were applied.</p> Full article ">Figure 6
<p>Seismogram with a simulation of a seismic event (EHZ, ENE, ENN, and ENZ components) to know the resolution of Raspberry Shake RS4D seismometer/accelerometer and check the quality of the generated data.</p> Full article ">Figure 7
<p>Seismic events display on SEISAN 12.0 software for seismic analysis. (<b>A</b>) Seismogram of the earthquake that occurred at 22:03:49 on 1 January 2022, recorded on Z channel of the RS4D seismometer with a filter of 2–15 Hz. (<b>B</b>) Unfiltered seismogram of the same event with the waves phases P and S, and coda selected. (<b>C</b>) Signal amplification, and impulsive arrival of the P-wave and arrival of the S-wave.</p> Full article ">Figure 8
<p>Map showing the geodynamic context, seismic activity (2015–2022), and main faults of the southern region of the Iberian Peninsula and North Africa. The most important faults are Gorringe Bank Region, Gulf of Cadiz (GC), Azores–Gibraltar Fault, Saint Vincent Cape (SVCP), Alboran Sea, Betic Mountain Ranges, Eastern Betic Shear Zone (EBSZ), Trans-Alboran Shear Zone (TASZ), Horseshoe Abyssal Plain (HAP), Horseshoe fault (HF), São Vicente Canyon (SVC), Guadalquivir Bank (GVB), and Marquês de Pombal Fault Block (MPFB). In addition, clusters A, B, C, and D are shown, which reflect the concentration and distribution of the seismic epicenters.</p> Full article ">Figure 9
<p>Map showing the location of the 4.4 Mw earthquake that occurred on 1 January 2022 in the Gulf of Cadiz (Lat: 36.3276, Lon: −7.6271, depth: 6 km) recorded by the RS4D seismometer/accelerometer. We also show seismic events of different magnitudes that occurred between 2005 and 2022 in the Gulf of Cadiz and adjacent areas (data taken from the public seismic catalog of IGN), the location of the Seismogeodesic System in the Doñana Biological Station, Huelva, Spain, the Control Center (LAGC–UCA), and the focal mechanism produced by the studied earthquake (A).</p> Full article ">Figure 10
<p>Seismogram (<b>A</b>) and spectrogram (<b>B</b>) of the earthquake that occurred on 1 January 2022 at 22:03:49 registered by the RS4D seismometer/accelerometer integrated in the prototype. In this seismic signal, a low signal-to-noise ratio was found in certain periods of time, which allowed the use of a first filter of 0.5 Hz to 10 Hz and a later one of 2 Hz to 8 Hz.</p> Full article ">Figure 11
<p>East, North, and Vertical components of the GNSS-GPS time series (1 Hz sample rate) for the position of the GR30 GNSS receiver seconds after the magnitude 4.4 Mw earthquake of 1 January 2022, with epicenter about 130 km southwest of Doñana, Huelva, Spain. A small change in the trend is shown 45 s (approximately) after the event occurred; this corresponds to the arrival of the seismic wave.</p> Full article ">Figure 12
<p>Inclinometry results (30 s sample rate) where the displacement produced in both sensors (Tilt 1, Tilt2) is observed and that corresponds to the arrival of the seismic wave of the 4.4 Mw earthquake that occurred on 1 January 2022 in the gulf of Cadiz.</p> Full article ">Figure 13
<p>Accelerographic signals from the ALMT (Almonte) station corresponding to the 5.4 Mw earthquake that occurred on 14 August 2022 in the Gulf of Cadiz.</p> Full article ">Figure 14
<p>Accelerographic signals from the LEPE station corresponding to the 5.4 Mw earthquake that occurred on 14 August 2022 in the Gulf of Cadiz.</p> Full article ">

37 pages, 24846 KiB  

Open AccessArticle

Landslide Susceptibility Mapping Based on Interpretable Machine Learning from the Perspective of Geomorphological Differentiation

by Deliang Sun, Danlu Chen, Jialan Zhang, Changlin Mi, Qingyu Gu and Haijia Wen

Land 2023, 12(5), 1018; https://doi.org/10.3390/land12051018 - 5 May 2023

Cited by 27 | Viewed by 4361

Abstract

(1) Background: The aim of this paper was to study landslide susceptibility mapping based on interpretable machine learning from the perspective of topography differentiation. (2) Methods: This paper selects three counties (Chengkou, Wushan and Wuxi counties) in northeastern Chongqing, delineated as the corrosion [...] Read more.

(1) Background: The aim of this paper was to study landslide susceptibility mapping based on interpretable machine learning from the perspective of topography differentiation. (2) Methods: This paper selects three counties (Chengkou, Wushan and Wuxi counties) in northeastern Chongqing, delineated as the corrosion layered high and middle mountain region (Zone I), and three counties (Wulong, Pengshui and Shizhu counties) in southeastern Chongqing, delineated as the middle mountainous region of strong karst gorges (Zone II), as the study area. This study used a Bayesian optimization algorithm to optimize the parameters of the LightGBM and XGBoost models and construct evaluation models for each of the two regions. The model with high accuracy was selected according to the accuracy of the evaluation indicators in order to establish the landslide susceptibility mapping. The SHAP algorithm was then used to explore the landslide formation mechanisms of different landforms from both a global and local perspective. (3) Results: The AUC values for the test set in the LightGBM mode for Zones I and II are 0.8525 and 0.8859, respectively, and those for the test set in the XGBoost model are 0.8214 and 0.8375, respectively. This shows that LightGBM has a high prediction accuracy with regard to both landforms. Under the two different landform types, the elevation, land use, incision depth, distance from road and the average annual rainfall were the common dominant factors contributing most to decision making at both sites; the distance from a fault and the distance from the river have different degrees of influence under different landform types. (4) Conclusions: the optimized LightGBM-SHAP model is suitable for the analysis of landslide susceptibility in two types of landscapes, namely the corrosion layered high and middle mountain region, and the middle mountainous region of strong karst gorges, and can be used to explore the internal decision-making mechanism of the model at both the global and local levels, which makes the landslide susceptibility prediction results more realistic and transparent. This is beneficial to the selection of a landslide susceptibility index system and the early prevention and control of landslide hazards, and can provide a reference for the prediction of potential landslide hazard-prone areas and interpretable machine learning research. Full article

(This article belongs to the Topic Landslides Analysis and Management: From Data Acquisition to Modelling and Monitoring II)

►▼ Show Figures

Figure 1

Figure 1
<p>Landform zoning map.</p> Full article ">Figure 2
<p>(<b>a</b>) The percentage plot of landform types of Zone I; (<b>b</b>) The percentage plot of landform types of Zone II.</p> Full article ">Figure 3
<p>Location of the research area (the left is Zone II and the right is Zone I).</p> Full article ">Figure 4
<p>Historical landslide event data feature partition statistics.</p> Full article ">Figure 5
<p>Theme layer of partial landslide conditioning factors in Zone I. (<b>a</b>) curvature; (<b>b</b>) elevation; (<b>c</b>) distance from faults; (<b>d</b>) slope; (<b>e</b>) POI; (<b>f</b>) perennial mean rainfall; (<b>g</b>) distance from river; (<b>h</b>) distance from roads; (<b>i</b>) surface cutting depth; (<b>j</b>) lithology; (<b>k</b>) aspect; (<b>l</b>) land use; (<b>m</b>) NDVI; (<b>n</b>) relief; (<b>o</b>) TRI; and (<b>p</b>) TWI.</p> Full article ">Figure 5 Cont.
<p>Theme layer of partial landslide conditioning factors in Zone I. (<b>a</b>) curvature; (<b>b</b>) elevation; (<b>c</b>) distance from faults; (<b>d</b>) slope; (<b>e</b>) POI; (<b>f</b>) perennial mean rainfall; (<b>g</b>) distance from river; (<b>h</b>) distance from roads; (<b>i</b>) surface cutting depth; (<b>j</b>) lithology; (<b>k</b>) aspect; (<b>l</b>) land use; (<b>m</b>) NDVI; (<b>n</b>) relief; (<b>o</b>) TRI; and (<b>p</b>) TWI.</p> Full article ">Figure 5 Cont.
<p>Theme layer of partial landslide conditioning factors in Zone I. (<b>a</b>) curvature; (<b>b</b>) elevation; (<b>c</b>) distance from faults; (<b>d</b>) slope; (<b>e</b>) POI; (<b>f</b>) perennial mean rainfall; (<b>g</b>) distance from river; (<b>h</b>) distance from roads; (<b>i</b>) surface cutting depth; (<b>j</b>) lithology; (<b>k</b>) aspect; (<b>l</b>) land use; (<b>m</b>) NDVI; (<b>n</b>) relief; (<b>o</b>) TRI; and (<b>p</b>) TWI.</p> Full article ">Figure 5 Cont.
<p>Theme layer of partial landslide conditioning factors in Zone I. (<b>a</b>) curvature; (<b>b</b>) elevation; (<b>c</b>) distance from faults; (<b>d</b>) slope; (<b>e</b>) POI; (<b>f</b>) perennial mean rainfall; (<b>g</b>) distance from river; (<b>h</b>) distance from roads; (<b>i</b>) surface cutting depth; (<b>j</b>) lithology; (<b>k</b>) aspect; (<b>l</b>) land use; (<b>m</b>) NDVI; (<b>n</b>) relief; (<b>o</b>) TRI; and (<b>p</b>) TWI.</p> Full article ">Figure 6
<p>Theme layer of partial landslide conditioning factors in Zone II. (<b>a</b>) curvature; (<b>b</b>) elevation; (<b>c</b>) distance from faults; (<b>d</b>) slope; (<b>e</b>) POI; (<b>f</b>) perennial mean rainfall; (<b>g</b>) distance from river; (<b>h</b>) distance from roads; (<b>i</b>) surface cutting depth; (<b>j</b>) lithology; (<b>k</b>) aspect; (<b>l</b>) land use; (<b>m</b>) NDVI; (<b>n</b>) relief; (<b>o</b>) TRI; and (<b>p</b>) TWI.</p> Full article ">Figure 6 Cont.
<p>Theme layer of partial landslide conditioning factors in Zone II. (<b>a</b>) curvature; (<b>b</b>) elevation; (<b>c</b>) distance from faults; (<b>d</b>) slope; (<b>e</b>) POI; (<b>f</b>) perennial mean rainfall; (<b>g</b>) distance from river; (<b>h</b>) distance from roads; (<b>i</b>) surface cutting depth; (<b>j</b>) lithology; (<b>k</b>) aspect; (<b>l</b>) land use; (<b>m</b>) NDVI; (<b>n</b>) relief; (<b>o</b>) TRI; and (<b>p</b>) TWI.</p> Full article ">Figure 6 Cont.
<p>Theme layer of partial landslide conditioning factors in Zone II. (<b>a</b>) curvature; (<b>b</b>) elevation; (<b>c</b>) distance from faults; (<b>d</b>) slope; (<b>e</b>) POI; (<b>f</b>) perennial mean rainfall; (<b>g</b>) distance from river; (<b>h</b>) distance from roads; (<b>i</b>) surface cutting depth; (<b>j</b>) lithology; (<b>k</b>) aspect; (<b>l</b>) land use; (<b>m</b>) NDVI; (<b>n</b>) relief; (<b>o</b>) TRI; and (<b>p</b>) TWI.</p> Full article ">Figure 7
<p>Research flow chart.</p> Full article ">Figure 8
<p>Model ROC curves of XGBoost (<b>a</b>) and LightGBM (<b>b</b>).</p> Full article ">Figure 9
<p>Model ROC curves of XGBoost (<b>a</b>) and LightGBM (<b>b</b>).</p> Full article ">Figure 10
<p>Landslide susceptibility zoning map ((<b>a</b>) is the result of Zone I, (<b>b</b>) is the result of Zone II).</p> Full article ">Figure 11
<p>Factor importance ranking diagram based on LightGBM model ((<b>a</b>) for Zone I, (<b>b</b>) for Zone II).</p> Full article ">Figure 12
<p>SHAP summary plot ((<b>a</b>) for Zone I, (<b>b</b>) for Zone II).</p> Full article ">Figure 13
<p>Single-factor dependence plot for Zone I. (<b>a</b>) Elevation; (<b>b</b>) distance from river; (<b>c</b>) distance from roads; (<b>d</b>) surface cutting depth; (<b>e</b>) land use; (<b>f</b>) perennial mean rainfall.</p> Full article ">Figure 13 Cont.
<p>Single-factor dependence plot for Zone I. (<b>a</b>) Elevation; (<b>b</b>) distance from river; (<b>c</b>) distance from roads; (<b>d</b>) surface cutting depth; (<b>e</b>) land use; (<b>f</b>) perennial mean rainfall.</p> Full article ">Figure 14
<p>Single-factor dependence plot for Zone II. (<b>a</b>) Elevation; (<b>b</b>) perennial mean rainfall; (<b>c</b>) distance from roads; (<b>d</b>) land use; (<b>e</b>) distance from faults; (<b>f</b>) surface cutting depth.</p> Full article ">Figure 14 Cont.
<p>Single-factor dependence plot for Zone II. (<b>a</b>) Elevation; (<b>b</b>) perennial mean rainfall; (<b>c</b>) distance from roads; (<b>d</b>) land use; (<b>e</b>) distance from faults; (<b>f</b>) surface cutting depth.</p> Full article ">Figure 15
<p>Two cases waterfall plots (<b>a</b>) Jinjiling landslide, (<b>b</b>) Jiweishan landslide.</p> Full article ">

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

 

Error

Oops... you haven't selected anything for export.

Ok

clear

Displaying articles 1-5