NH3.10 | Exploring the Interplay: Quality of Landslide Inventories and reliability of Susceptibility and Hazard mapping
EDI
Exploring the Interplay: Quality of Landslide Inventories and reliability of Susceptibility and Hazard mapping
Convener: Roberto Sarro | Co-conveners: Michele Santangelo, Federica Fiorucci, Petra Jagodnik, Lorenzo Nava, Khamarrul Azahari Razak, Jhonatan Steven Rivera Rivera
Orals
| Fri, 19 Apr, 10:45–12:30 (CEST)
 
Room M2
Posters on site
| Attendance Fri, 19 Apr, 16:15–18:00 (CEST) | Display Fri, 19 Apr, 14:00–18:00
 
Hall X4
Posters virtual
| Attendance Fri, 19 Apr, 14:00–15:45 (CEST) | Display Fri, 19 Apr, 08:30–18:00
 
vHall X4
Orals |
Fri, 10:45
Fri, 16:15
Fri, 14:00
Landslide Inventory Maps (LIMs) are the basic tool for spatially representing landslides, forming the cornerstone for subsequent analyses in landslide research. Traditional methods of landslide mapping have historically relied on heuristic interpretation, resulting in varied accuracy, coverage, and timeliness. Their reliability is influenced by mapping errors arising from diverse techniques and base data. Recent research emphasizes geographic accuracy, thematic accuracy, and completeness/statistical representativeness as key factors defining the quality of LIMs.
Classification of susceptibility adds to the complexity of mapping efforts. Conventional methods often struggle with differences between the types of landslides due to variations in morphological and environmental factors. The integration of Machine Learning (ML) has revolutionized landslide mapping and modeling. ML's capacity to extract critical patterns from heterogeneous data sources enables precise classification of landslides, addressing challenges faced by conventional methods. Additionally, ML techniques offer a comprehensive view of the landscape and its dynamic changes and a comprehensive solution for assessing and mitigating landslide hazards by addressing challenges related to threshold determination, classification accuracy, and uncertainty evaluation.
We invite contributions addressing:
• Metrics for evaluating mapping accuracy, errors, and uncertainty.
• Statistical modelling of mapping errors and ML-based classification.
• Quality assessment methods for Landslide Inventory Maps.
• Impact of error propagation on susceptibility models, hazard assessment, and risk evaluation.
• Model inter-comparisons
• Relating LIMs quality to use limitations and decision-making at different land-management levels.

Session assets

Orals: Fri, 19 Apr | Room M2

Chairpersons: Roberto Sarro, Michele Santangelo, Petra Jagodnik
10:45–10:50
10:50–11:00
|
EGU24-17851
|
ECS
|
solicited
|
Virtual presentation
Badal Pokharel, Massimiliano Alvioli, and Samsung Lim

Evaluating landslide inventories is crucial and the first step in assessing the extent of landslide event damage. Despite the several studies in landslide inventory preparation and assessment, there is a lack of standardised criteria for measuring their quality and completeness. This study aims to introduce an integrated approach for analysing different event inventories prepared by different geomorphologists. We considered five landslide inventories prepared by various authors following the 2015 Gorkha earthquake in Nepal [1-5]. We prepared susceptibility maps using multiple realisations of logistic regression, with slope units of the areas as a spatial basic unit for the analysis [6]. The goal was to analyse their differences or similarities and comprehend the influence of using them to prepare landslide susceptibility maps [7].

The key questions we explored were: How can the quality and reliability of landslide inventories be evaluated? And what are the similarities or differences in the landslide susceptibility maps generated using inventories from different research teams for the same event? To this end, we utilised three evaluation criteria: (i) an error index to check the discrepancies between inventories, (ii) statistical analysis to examine the inconsistencies in predisposing factors and susceptibility map performance, (iii) geospatial analysis to evaluate differences among inventories and their corresponding.

The study highlighted differences in landslide inventories and attributed them to differences in data collection methods and subjective judgments. It emphasised the need to address subjectivity for more accurate and consistent landslide mapping. The results from statistical analysis showed substantial differences in the areal extent and overlapping degree between inventories. The geospatial analysis, such as hot spots and cluster/outlier analysis, highlighted the distinctive differences in spatial patterns of landslide susceptibility maps corresponding to different inventories. The suggested geospatial methods offer investigators a viewpoint for quantitatively analysing earthquake-triggered landslide inventories and related susceptibility maps.

References

[1] Zhang et al., Journal of Mountain Science (2016). https://doi.org/10.1007/s11629-016-4017-0

[2] Gnyawali et al., Springer International Publishing (2017). https://doi.org/10.1007/978-3-319-53485-5_10

[3] Roback et al., US Geological Survey Data Release (2017). https://doi.org/10.5066/F7DZ06F9,   

[4] Kargel et al., Science (2016). https://doi.org/10.1126/science.aac8353

[5] Pokharel and Thapa, Journal of Nepal Geological Society (2019). https://doi.org/10.3126/jngs.v59i0.24992

[6] Alvioli et al., Journal of Maps (2022). https://doi.org/10.1080/17445647.2022.2052768

[7] Pokharel et al., Scientific Reports (2021). https://doi.org/10.1038/s41598-021-00780-y

 

How to cite: Pokharel, B., Alvioli, M., and Lim, S.: Statistical and geospatial approaches to evaluate the quality of earthquake-triggered landslide inventories, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-17851, https://doi.org/10.5194/egusphere-egu24-17851, 2024.

11:00–11:10
|
EGU24-11385
|
On-site presentation
Matteo Berti, Alessandro Corsini, Marco Pizziolo, Simonelli Tommaso, Giuseppe Ciccarese, Vincenzo Critelli, Nicola Dal Seno, Cecilia Fabbiani, Mauro Generali, Elena Ioriatti, Francesco Lelli, Marco Mulas, Rodolfo Rani, Francesco Ronchetti, Michele Scaroni, Melissa Tondo, and Alessandro Zuccarini

Accurate and timely landslide inventory is crucial, particularly after large-scale disasters like earthquakes or heavy rainfalls. While remote sensing enhances mapping speed, accuracy is vital to avoid missing or falsely identifying landslides. Effective mapping depends on factors like immediate access to high-quality imagery and skilled surveyors for ground truth definition.

In May 2023, Italy's Emilia-Romagna region experienced a severe hydrogeological emergency, which triggered thousands of landslides. The landslide inventory, crucial for emergency management, faced challenges due to the high number of landslides. Initial efforts using Copernicus Emergency Management Service and national resources faced limitations in completeness and reliability. Ultimately, the official inventory was based on a detailed manual mapping from high-resolution aerial imagery.

This work presents the magnitude of the triggering event, the types of the landslides occurred with respect to the geological constraints and discusses the potential benefits and limitations of automated landslide mapping methods in such scenarios. Specifically, more than 50.000 landslides have so far been mapped over an area of around 1000 km2, which range from debris slides/avalanches to debris flows and rock block slides. The impact on infrastructures was significant especially on the road network. With respect to automatic mapping, two distinct techniques have been tested: the conventional NDVI (Normalized Difference Vegetation Index) method and the more sophisticated U-Net algorithm using different remote sensing images ranging in resolution from 10 to 0.2 m.

Results show that time-consuming creation of an extensive ground truth datasets is essential in order to evaluate the accuracy of automatic landslide mapping based on images of different resolution and quality, so to determine whether these methods can offer efficient alternatives to manual mapping in large-scale emergency situations.

How to cite: Berti, M., Corsini, A., Pizziolo, M., Tommaso, S., Ciccarese, G., Critelli, V., Dal Seno, N., Fabbiani, C., Generali, M., Ioriatti, E., Lelli, F., Mulas, M., Rani, R., Ronchetti, F., Scaroni, M., Tondo, M., and Zuccarini, A.: Landslide inventory following the May 2023 Romagna hydrometeorological event (Northern Italian Apennines): the unavoidable requirement for laborious manual mapping, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-11385, https://doi.org/10.5194/egusphere-egu24-11385, 2024.

11:10–11:20
|
EGU24-17066
|
Highlight
|
Virtual presentation
David Milledge, Dino Bellugi, and Alexander Densmore

Efforts to understand the controls on landslides rely heavily on manually mapped landslide inventories, but these are costly and time-consuming to collect, and their reproducibility is not typically well constrained. To test the performance of manual mapping we compare two or more manually mapped inventories of landslides triggered by five recent earthquakes: Kashmir in 2005, Aysén in 2007, Wenchuan in 2008, Haiti in 2010, and Gorkha in 2015. We find surprisingly poor agreement between these maps (at worst 8 % overlap and at best 30 %). This has implications both for how future models and/or classifiers are tested and for the interpretations that are based on these inventories. We then test the ability of a new automated landslide detection index (ALDI) to recover landslide locations. In more than 50% of cases, ALDI more skilfully reproduces landslide locations from one inventory (treated as the ground truth) than a second inventory for the same site based on ROC curve analysis. Finally we examine the spatial pattern of landslides identified in the different maps and the patterns of their agreement and disagreement to show that: 1) much of the disagreement appears to be due to georeferencing rather than landslide identification; and 2) the ALDI map, which is quick and easy to produce, can be used to identify georeferencing errors and thus post-process and improve manual maps.

How to cite: Milledge, D., Bellugi, D., and Densmore, A.: Manual Landslide Maps are Surprisingly Inaccurate but Automated Detection Could Help, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-17066, https://doi.org/10.5194/egusphere-egu24-17066, 2024.

11:20–11:30
|
EGU24-9020
|
ECS
|
Highlight
|
On-site presentation
 Lotte de Vugt, Shoujun Jia, Andreas Mayr, Barbara Schneider-Muntau, Thomas Zieher, Frank Perzl, Marc Adams, and Martin Rutzinger

For the development of accurate shallow landslide (translational debris and earth slides with a depth < 2 m) susceptibility assessments and further hazard or risk analyses, it is essential that complete and accurate landslide inventory data is available. Various methods are applied for the construction of shallow landslide inventories. However, it is known that the most used methods underreport landslides in forests, e.g. with visual interpretation of satellite/aerial imagery and manual mapping of landslides during field visits. To address this issue, several studies have instead used topographic Light Detection and Ranging (LiDAR) data to create their landslide inventories. These studies showed that landslides under forest cover can be mapped using topographic LiDAR, as LiDAR can penetrate the vegetation cover. The methods used in these studies can be divided into (1) methods using raster data derived from filtered LiDAR point-cloud data and (2) methods working directly on point-cloud datasets. The benefit of the raster-based methods is their computational speed and scalability, while point-cloud based methods are difficult to apply to larger areas, due to their high computational requirements, but have a greater measurement accuracy (e.g., landslide depth). This difference in accuracy is especially important for the mapping of shallow landslides, which often leave only limited traces in the landscape.

This study investigates how both methods can be combined to derive a semi-automatic workflow for mapping shallow landslides using LiDAR data that is accurate and scalable. The investigation focusses on mapping shallow landslides under forest, and on how the derived workflow for mapping landslides needs to be adapted to forested and non-forested areas. In a first step, potential landslide-prone areas are identified using the difference of pre- and post-event digital terrain models, an after-event digital terrain model and their related topographic derivatives such as the roughness coefficient and slope. In the next step, the identified areas are segmented and man-made topographic changes are removed, before they are further analyzed with a more accurate mapping technique using point-cloud data from the multiscale model-to-model cloud comparison (M3C2) algorithm. In addition to the M3C2 distances, the point-cloud based mapping will also make use of 3D shape features describing point location and orientation to increase the accuracy and robustness of the topographic change detection and estimation. The scalability of the workflow is tested by applying the workflow to several areas in the Tyrolean Alps (Austria).

First results, derived with a logistic regression model using the raster-based derivatives, show a distinct difference in the feature importance of the topographic derivatives when forested and non-forested areas are compared. In addition, the performance of the model also greatly benefits from a separate training in forested and non-forested areas, with an increase in the Area Under the Curve (AUC) value from 0.84 to 0.89 for, respectively, unseparated and separated training.

How to cite: de Vugt,  ., Jia, S., Mayr, A., Schneider-Muntau, B., Zieher, T., Perzl, F., Adams, M., and Rutzinger, M.: A scalable workflow for shallow landslide inventory construction based on multitemporal LiDAR data with the explicit inclusion of landslides in forests, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-9020, https://doi.org/10.5194/egusphere-egu24-9020, 2024.

11:30–11:40
|
EGU24-18951
|
ECS
|
Highlight
|
On-site presentation
Laura Waltersdorfer, Andrea Siposova, Matthias Schlögl, and Rudolf Mayer

Mountainous regions such as the Austrian Alps face a constant threat of natural hazards. Over time, this persistent danger has prompted a transition from heuristic hazard management strategies towards a more quantified risk culture. Since quantitative risk assessment heavily relies on understanding the occurrence frequency of the hazard processes under consideration, knowledge about past events and their characteristics becomes pivotal, thereby shaping the effectiveness and broader applicability of methodological workflows employed in this context.

We present challenges, and insights gleaned from the research project “gAia”, focusing on a data-driven susceptibility assessment for shallow landslides in Austria. The identified challenges mainly revolve around the quality of landslide inventories, which is influenced by factors like underreporting, inconsistent documentation, and lack of standardized data management practices. We thus recommend adopting FAIR (Findability, Accessibility, Interoperability, Reusability) principles and developing Data Management Plans to address these issues, and propose a general data management workflow:

  • Identify data sources and contents: Collect information about data sources and characteristics in a (machine-readable) DMP to obtain an overview of all data sources and most important characteristics (e.g. format, size, license, context, bias limitations). This should support the contextualization and ability to reuse this data.
  • Define processing activities: Explicitly define processing workflows to enhance reproducibility and transparency, using established standards such as Business Process Management (BPMN) or semantic web technologies to represent complex processes formally and make them more comparable and accessible to users.
  • Define (meta)-data and process activities trace templates: Provide metadata templates for datasets and trace processing activities to improve interoperability and reusability. Define domain-specific vocabularies and use concepts such as datasheets, model cards, ML experiment tracking and model registry tools as well as task orchestration platforms for data engineering pipelines to make results more traceable and reviewable. 
  • Monitoring processes for natural hazard event data: Implement processes to ensure adherence to quality metrics, with results published in machine-readable formats.

We detail the implementation of these steps using established concepts of traceability and provenance, and encourage to implement workflow tasks using common open source programming languages. In addition, we endorse the use of Git for version control and GitLab/GitHub as tools for facilitating collaboration and structuring technical tasks.

The benefits of the proposed data management strategies for enhancing quality and reliability of data as well as increasing overall transparency of processes are showcased in the gAia project. The project workflow, represented as a P-Plan, demonstrates the application of these strategies in different phases. Specifically, the importance of proper data management and adherence to FAIR principles for data-driven research and practical usability is highlighted using landslide inventories as a core example.

In summary, we provide insights into the complexities of geospatial data management in mountain hazard research and offer practical solutions to enhance the integrity and reliability of data for supporting effective risk assessment and disaster risk reduction.

gAia is funded through the KIRAS Security Research Program for Cooperative Research and Innovation Projects by the Austrian Research Promotion Agency (FFG) and the Federal Ministry of Finance, under grant agreement FO99988636910.

 

How to cite: Waltersdorfer, L., Siposova, A., Schlögl, M., and Mayer, R.: Adopting FAIR data management practices in mountain hazard research: Strategies for ensuring data quality for landslide susceptibility modeling, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-18951, https://doi.org/10.5194/egusphere-egu24-18951, 2024.

11:40–11:50
|
EGU24-4938
|
On-site presentation
Keh-Jian Shou

Due to the impact of climate change, the increasing frequency of extreme rainfall events, with concentrated rainfalls, commonly cause landslide hazard in the mountain areas of Taiwan. However, there are uncertainties for the predicted rainfall as well as the landslide susceptibility analysis.

This study employs machine learning approached, including the logistic regression method LR and deep learning method CNN, to analyze the landslide susceptibilities. Together with the predicted temporal rainfall, the predictive analysis of landslide susceptibility was performed in the adopted study area in Central Taiwan. The uncertainties within the rainfall prediction was firstly investigated before applied to the landslide susceptibility analysis. To assess the susceptibility of the landslides, logistic regression method LR and deep learning method CNN were applied. The results of predictive analysis, with the discussions on the accuracy and uncertainties, can be applied for a better landslide hazard management in the study area.

How to cite: Shou, K.-J.: On the Predictive Analysis of Landslide Susceptibility by ML Approached– for the Case in Taiwan, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-4938, https://doi.org/10.5194/egusphere-egu24-4938, 2024.

11:50–12:00
|
EGU24-19268
|
ECS
|
On-site presentation
Rajendran Shobha Ajin, Samuele Segoni, and Riccardo Fanti

A landslide susceptibility modelling has been carried out by applying two machine learning regression algorithms (SVR and CatBoost), and later two population-based optimization algorithms (metaheuristics) such as PSO and GWO were integrated to assess whether the integration improved the performance of the two regression algorithms. A total of 18 predisposing factors were selected for the study. After the multicollinearity assessment and feature selection applying the information gain (IG) method, four predisposing factors (three factors with collinearity issues and one irrelevant factor) were excluded. Hence, 14 predisposing factors were selected for the modelling. The landslide susceptibility maps were thus created by applying the CatBoost, CatBoost-PSO, CatBoost-GWO, SVR, SVR-PSO, and SVR-GWO models. The validation employing different techniques (MAE, MSE, RMSE, and R2) confirmed that the CatBoost model (MAE = 0.065 and 0.071, MSE = 0.027 and 0.032, RMSE = 0.165 and 0.180, and R2 = 0.890 and 0.869) is better than the SVR model (MAE = 0.179 and 0.181, MSE = 0.063 and 0.063, RMSE = 0.251 and 0.252, and R2 = 0.746 and 0.745). The integration of optimization algorithms improved the performance of these two regression models, and the GWO has the best performance when compared to the PSO algorithm. Also, CatBoost-GWO (AUC = 0.910) has the best performance, followed by CatBoost-PSO (AUC = 0.909), CatBoost (AUC = 0.899), SVR-GWO (AUC = 0.868), SVR-PSO (AUC = 0.858), and SVR (AUC = 0.840). The Friedman and Wilcoxon-signed rank tests confirmed that the models are significant. The feature importance assessment using the CatBoost confirmed elevation, slope, geomorphology, road, and soil bulk density as the top five important predisposing factors.

How to cite: Ajin, R. S., Segoni, S., and Fanti, R.: Optimization of ML-based regression models applying metaheuristic algorithms to determine the landslide susceptibility, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-19268, https://doi.org/10.5194/egusphere-egu24-19268, 2024.

12:00–12:10
|
EGU24-10842
|
ECS
|
On-site presentation
Rodolfo Rani, Marco Sciarra, Stefano Rodani, and Matteo Berti

The integration of Machine Learning (ML) into susceptibility mapping and hazard modelling has unveiled complex relationships between landslide predisposing factors and occurrence. However, understanding the practical implications of landslide susceptibility results still crucial. One concern is the conventional treatment of landslide inventory data, where various landslide types are uniformly addressed during model training, proving unrealistic given diverse geological and geomorphological conditions for distinct landslide types. Moreover, each landslide type requires a unique mitigation strategy, and valuable information is lost when treating all landslides uniformly. Another challenge is how susceptibility models typically present probabilities, while practical applications demand clear categories to avoid underestimation or overestimation of risks.

This study explores the practical application of landslide susceptibility to linear infrastructure, specifically railway design. The investigation centres on two established models, comparing each other: firstly, the classical statistical-based method, Weight of Evidence (WoE); and secondly, a ML method, the Generalized Additive Model (GAM). WoE was chosen for its clarity, while GAM accommodates continuous variables, offering a nuanced understanding of non-linear relationships. The study area encompasses a new 22.11 km railway stretch in the central Marche Region, Italy. We assessed the susceptibility to five landslide types, as classified in the Italian Landslide Inventory (IFFI). The models (WoE and GAM) are applied using different landslide types as distinct training datasets, resulting in unique susceptibility maps for each type. Additionally, the study evaluates the models using the Area Under the Receiver Operating Characteristic (AUROC) curve, providing insights into their performance. The rockfall susceptibility map demonstrates high reliability (AUROC of 0.942 with WoE and 0.978 with GAM), while slide-type landslides show more modest but fairly good results (AUROC of 0.696 with WoE and 0.784 with GAM).

To provide a comprehensive understanding of the study area, overall landslide susceptibility was calculated, corresponding to the probability of failure for any type of landslide. The overall probability was obtained by implementing a complementary probability approach for landslide probability analysis. A method is then proposed to classify the sensitivity of landslide types by considering the difference in their influences, facilitating a clearer understanding of their contributions to the overall susceptibility assessment.

The second practical concern involves the accurate definition of hazard classes, pivotal due to its direct impact on risk management, decision-making, and overall infrastructure resilience. The study introduces a novel approach, using mode calculation to consolidate results from various reclassification methods. This strategic use of mode calculation ensures a reliable representation of hazard classes, addressing the limitations of individual methodologies.

The results underscore the importance of considering multiple models and methodologies to obtain a comprehensive perspective in decision-making processes. Importantly, the study highlights the use of both classical statistical methods, exemplified by WoE, and ML methods like GAM, showcasing the benefits of a diverse analytical approach in landslide risk assessment for linear infrastructure.

How to cite: Rani, R., Sciarra, M., Rodani, S., and Berti, M.: Toward Pragmatic Landslide Susceptibility Mapping for Railway Planning: A Comparative Analysis of Statistical and Machine Learning Methods - The Case Study of the Marche Region, Italy, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-10842, https://doi.org/10.5194/egusphere-egu24-10842, 2024.

12:10–12:20
|
EGU24-17519
|
ECS
|
Highlight
|
On-site presentation
Yaser Peiro, Luca Ciabatta, Evelina Volpe, and Elisabetta Cattoni

To mitigate the risk of landslides, building a model that can provide information on the spatial and temporal probabilities of landslides is essential yet challenging. Landslides are influenced by environmental factors, such as topography, geology, and mechanical properties of the soil, as well as triggering events like rainfall and earthquakes. This research leverages Random Forest algorithm for classification by creating multiple decision trees. Each tree is trained on a distinct, randomly selected subset of the dataset. The dataset includes specific static variables for each location, such as lithology, slope angle, aspect, curvature, and land use. Additionally, the study considers two dynamic variables for each location: high-resolution soil moisture data obtained from satellites to examine the impact of soil water content, and rainfall data.
By utilizing a unique rainfall-induced landslide database, which includes the location and time of landslide occurrences in the study area. The algorithm extracts the corresponding rainfall and soil moisture values preceding each landslide event and trains the model by adjusting both static and dynamic variables. The rainfall data is analyzed on two different time scales: short-term cumulative rainfall (1-72 hours before a landslide event) and medium-term cumulative rainfall (5-15 days before a landslide event). The outcomes are individual trees that determine the final class (landslide or non-landslide location) for each pixel based on the majority vote. The model's outputs, out-of-bag errors, and partial dependence plots provide insights into how each parameter influences the model's landslides predictions, and help to evaluate the impact of rainfall and soil saturation conditions on landslides occurrence both in space and in time.

How to cite: Peiro, Y., Ciabatta, L., Volpe, E., and Cattoni, E.: Spatiotemporal Modelling of Landslide Susceptibility Using Satellite Rainfall and Soil Moisture Products through Machine Learning Techniques, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-17519, https://doi.org/10.5194/egusphere-egu24-17519, 2024.

12:20–12:30
|
EGU24-16687
|
ECS
|
Highlight
|
Virtual presentation
Aadityan Sridharan, Remya Ajai A.S, and Sundararaman Gopalan

Landslide risk assessment is ineludible for communities in mountainous regions of the world. Life and habitat loss plague these communities due to rapid mass movements. Cloud burst conditions and strong earthquake tremors trigger thousands of landslides that can run amuck in the terrain. One way to assess the risk is by field investigations. Vast areas cannot be covered on foot and other limitations such as a lack of accessible roads. The next viable alternative is aerial photography and unmanned aerial vehicles (UAV). The range and accuracy of the deployed drones and aircraft also limit this method of earth observation. Overcoming these limitations, optical satellite images give us information for a vast area and can observe the surface daily, which is only limited by cloud cover. These satellites have advanced to give highly accurate images with a resolution of 3m/pixel.

Remote sensing image processing techniques are used to generate automated inventory of landslides. Most of the current algorithms use segmentation algorithms to map the landslide polygons but do not include the urban settlements that are vulnerable to these mass movements. Planet lab images (3m/pixel) and Google earth images (0.2m/pixel) can be acquired at a daily temporal scale. These images can be further processed to identify the scars caused by the landslides and the outlines of urban settlements. Sridharan et al 2020 and 2022 have looked at discrete wavelet transforms (DWT) and deep learning algorithms for assessing the proximity of these landslide scars to urban settlements.

In this work, we extend these algorithms with high-resolution satellite images and identify the risk caused by landslides to communities. We collected images for landslides from various parts of the world that are observed to be active and added them as one class of training dataset. From the urban settlements that are in steep terrain, we collect a second set of images as another training class. More than 3000 images are used for training and validation with a 70:30 train-test split. The models are then tested by classifying a set of images that contain both classes to assess their potential in identifying landslide risk to communities. Classic Support vector machine is used as a classifier after extracting features by DWT. Traditional deep learning algorithms such as AlexNET and ResNET are trained and tested on the satellite images. We observe both DWT and Deep learning algorithms  have good overall accuracy in extracting features and validating them while there are some accuracy differences in identifying the risk in mixed images that have both the classes. The models are rated based on the confusion matrix and AUC-ROC. While various DWT give an accuracy in range of 90 – 96%, the deep learning models have a range of 95 – 98%.

How to cite: Sridharan, A., Ajai A.S, R., and Gopalan, S.: The Use of Wavelet Transforms and Deep learning algorithms to identify risk caused by landslides from multitemporal satellite images, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-16687, https://doi.org/10.5194/egusphere-egu24-16687, 2024.

Posters on site: Fri, 19 Apr, 16:15–18:00 | Hall X4

Display time: Fri, 19 Apr, 14:00–Fri, 19 Apr, 18:00
Chairpersons: Federica Fiorucci, Lorenzo Nava, Jhonatan Steven Rivera Rivera
X4.52
|
EGU24-8385
|
ECS
Landslides along the Engineering Corridors in the Northeastern Margin of the Qinghai-Tibet Plateau: Comprehensive Inventory and Distribution Patterns
(withdrawn after no-show)
Jing Zhang, Renmao Yuan, and Jie Chen
X4.53
|
EGU24-10760
|
ECS
|
Ikram Zangana, Rainer Bell, Lucian Drăguţ, and Lothar Schrott

For assessing landslide susceptibility and hazard reliable landslide inventories are essential. Historic landslides might indicate periods of increased landslide activity compared to more recent decades. However, landslide features might have diminished over time especially due to human impact. Often features of historic landslides are well preserved under forest providing a valuable source for preparing or completing landslide inventories, but mapping them is challenging.

Analyzing Light Detection and Ranging (LiDAR) and its derivatives have become powerful tools in landslide research, particularly in the identification and mapping of landslides. In contrast to the expert-based analysis of LiDAR derivatives, there is a limited number of studies employing object-based approaches to (semi)automatically mapping landslides from LiDAR data. This study focuses on the use of Geographic Object-Based Image Analysis (GEOBIA) based solely on LiDAR derivatives (1 m resolution) to conduct inventory mapping of forest-covered landslides within a middle mountainous region in Germany.

The study centers on Jena and its surrounding areas in Germany, covering an approximate area of 150 km². As part of the Thuringia basin, the study area is dominated by two major geological formations. The Muschelkalk  (limestone) covers the majority of the upper parts of the slopes and the plateau areas. It is underlain by the Buntsandstein  (marls, claystone and sandstone). Large landslides are historic and covered by forest. The methodology incorporates an inventory map for the purposes of module training and validation. LiDAR derivatives, encompassing slope, plan curvature, Terrain Roughness Index (TRI), Terrain Position Index (TPI), and differential openness, are systematically applied across diverse scales to identify landslide scarps and bodies within distinct window sizes. This systematic approach is further complemented by multi-resolution segmentation at multiple levels, support vector machine (SVM), rule-based classification, GEOBIA-based refinements, and a rigorous accuracy assessment. Collectively, these components establish a comprehensive framework for the progression of landslide detection and mapping methodologies.

The results reveal that the proposed approach achieved an 80% detection rate compared to the expert-based inventory. Nevertheless, continuous efforts are being made to reduce the occurrence of false positive detections. While the module demonstrates proficiency in identifying and mapping historical forest-covered landslides, its current functionality is limited to recognizing and mapping large and medium-sized landslides [area > 0,5 ha]. The transferability of this module should be evaluated in other regions. We anticipate that globally landslides with clear geomorphological signatures in high-resolution Digital Terrain Models (DTMs) can be identified using this approach.

How to cite: Zangana, I., Bell, R., Drăguţ, L., and Schrott, L.: Geographic Object-Based Image Analysis (GEOBIA) for inventory mapping of forest-covered landslides: a case study in Jena, Germany, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-10760, https://doi.org/10.5194/egusphere-egu24-10760, 2024.

X4.54
|
EGU24-15157
Michele Santangelo, Francesca Ardizzone, Francesco Bucci, Mauro Cardinali, and Federica Fiorucci

The quality of a landslide inventory depends on its accuracy and the type and certainty of information shown on the map. Defining the accuracy of a landslide inventory is not straightforward, and there are no standards. Accuracy depends on the completeness of the map and the geographic and thematic correctness of the information displayed on the map.

In this study, an expert, semi-quantitative evaluation approach was developed to assess mapping errors and consequently determine the quality of a geomorphological historical landslide inventory map for a 2,000 km2 area in the Southern Italian Apennines (Daunia, Puglia region) prepared through aerial photo-interpretation.

Quality control aims to quantify parameters, even in terms of binary choices. Whenever involving expert estimates, the assessment was carried out through a reference grid to limit inconsistencies. Furthermore, the expert evaluations were carried out by a team of evaluators working collegially, and who had not previously worked simultaneously on the same areas.

The general approach involves a systematic evaluation within 5 sample areas covering a total of 202 km2 deemed a choice enabling the identification of areas that are sufficiently extensive (i.e., 10% of the total area and 20% of the total number of landslides) and adequately represent the diverse morphological and litho-structural characteristics of the study area. The assumption of representativeness of these areas forms the basis for extrapolating error data to the entire investigated area.

Geographic accuracy gauges the degree of correspondence between morphological and photographic evidence of landslides and their portrayal on the map. This correspondence was decomposed in terms of position, shape, and size and was evaluated, for each landslide portrayed in the 5 sites, at the declared scale of the final map (1:5,000). Each component was considered acceptable if at least 2/3 of the landslide was mapped correctly, and the overall accuracy satisfactory if at least two components were sufficient.

To assess the completeness of the inventory, the authors of the map were preliminarily asked to state the minimum size of landslides consistently mapped (ACM) in the inventory. Then, within the sample areas, the ratio between the number of landslides exceeding ACM and not represented in the map and the number of the landslides mapped expresses the degree of completeness of the inventory for the declared ACM.

To evaluate the thematic accuracy, a percentage score was assigned representing the proportion of landslides with specific thematic errors within the inventory, considering the correct classification (type and relative age) of each landslide represented in the map and compared to its photographic and morphological evidence.

Considering the absence of qualitative standards in the scientific literature for landslide inventory maps, and, consequently, the lack of evaluative standards for the accuracy of such cartographic products, this work can be considered an attempt to define a procedure to evaluate the informative content of landslide inventory maps.

How to cite: Santangelo, M., Ardizzone, F., Bucci, F., Cardinali, M., and Fiorucci, F.: An expert semi-quantitative evaluation approach to measure the quality of landslide inventories, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-15157, https://doi.org/10.5194/egusphere-egu24-15157, 2024.

X4.55
|
EGU24-15211
|
ECS
|
Highlight
Petra Jagodnik

The analysis of surface topography by using LiDAR (Light Detection and Ranging) technology proved to be effective in landslide inventory mapping during the last two decades. Among the leading methods is the visual interpretation of LiDAR Digital Terrain Model (DTM) derivatives, applied for the mapping of different landslide types along diverse environments. Landslides are usually first being searched for by interpreting the hillshade map, while the landslide delineation is commonly followed by interpretation of the slope and the contour line maps. Several studies have also demonstrated the curvature map and the topographic roughness map to be effective tools in landslide detection and mapping. However, the landslide features topography can be poorly or even barely observable on the hillshade map, so a certain amount of landslides may be omitted from the final inventory if other derivatives are not visually inspected in detail. Hence, the thematic accuracy of a landslide inventory map depends on the geomorphic expression of landslides on the hillshade map, while the geographical accuracy depends on the adopted mapping procedure and the type of derivatives used for landslide delineation. Despite the overall usefulness of the visual interpretation of LiDAR DTM derivatives in landslide studies, the effectiveness of particular LiDAR DTM derivatives for the identification and precise delineation of individual landslide features has not been tested yet. 

This study quantitatively ranks the airborne LiDAR datasets derived from the 1-m DTM, used for the production of the geomorphological landslide inventory map of the Vinodol Valley (65 km2) in Croatia, according to their effectiveness for identification and precise delineation of particular landslide features. Landslides are mapped by one and the same expert, by interpreting a total of nine DTM derivatives. Six steps were carried out in this study: (i) the creation of the landslide dataset, which consisted of 394 small debris slides; (ii) the classification of landslides according to their geomorphic expression on the hillshade map, distinguishing four classes; (iii) the grading of the each DTM derivative for its effectiveness in precise delineation of particular landslide feature (i.e., crown, right flank, left flank, foot, toe), by assigning the grade of 0, 1, or 2 to each map; (iv) the statistical analysis of a total of 15,760 grades using the Friedman test; (v) the ranking of DTM derivatives in total of eight ranks based on the post-hoc analysis; and (vi) the classification of the DTM derivatives according to their effectiveness in mapping small landslides, considering the geomorphic expression of a landslide on the hillshade map. Finally, two categories of LiDAR DTM derivatives are proposed: (i) the main LiDAR DTM derivative, i.e. the most effective one for the precise delineation of particular landslide feature of particular geomorphic expression on the hillshade map; and (ii) the secondary LiDAR DTM derivative, which is still considered to be effective for the precise delineation of particular landslide feature of particular geomorphic expression on the hillshade map, but should be visually interpreted coupled with other secondary map(s), or with the main DTM derivative.

How to cite: Jagodnik, P.: Evaluating the potential of visual interpretation of airborne LiDAR datasets for the identification and mapping of small landslides, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-15211, https://doi.org/10.5194/egusphere-egu24-15211, 2024.

X4.56
|
EGU24-3526
Paul Höhn, Konrad Heidler, Robert Behling, and Xiao Xiang Zhu

Landslides, with their devastating impact on communities and infrastructure, present a pressing challenge for accurate and timely detection. Effective monitoring is therefore essential, not only to understand the process of landslides, but also to provide comprehensive risk assessments for future planning and to mitigate the consequences of such events. In addition, timely mapping of these hazardous events is essential to gain an overview and coordinate rescue efforts, while also addressing the geoscientific component of how these processes evolve over space and time, including potential acceleration due to climate change. To address this critical need, our study presents a large-scale, multi-temporal dataset that uniquely combines time-series data from the Sentinel-1 and Sentinel-2 satellites to improve landslide monitoring. Our initiative aims to create a globally standardized dataset that will overcome the challenges of transferring existing algorithms and facilitate the development of more effective models. This innovative and still growing dataset, which already includes over 7500 landslides from 16 global regions, offers a unique opportunity to advance machine learning methods for landslide detection. Using time-series analysis of Sentinel-1 radar data, we have successfully identified the onset and end dates of landslide events. Complementing this, Sentinel-2 optical data analyzed by NDVI change provide detailed land cover information critical for accurate landslide labelling. Our methodological approach is rigorously validated by manual expert review to ensure the reliability and accuracy of our results. By incorporating temporal context and combining the cloud-penetrating capabilities of Sentinel-1 with the rich multispectral resolution of Sentinel-2, this research represents a significant advance in the use of satellite data for landslide monitoring and serves as an invaluable resource for both the remote sensing and machine learning communities. It supports both object-based landslide identification and granular pixel-level analysis through semantic segmentation, extending its versatility for various environmental research applications. In our initial benchmarks, we evaluated existing state-of-the-art models such as UNet3D, U-TAE, TSViT and U-ConvLSTM to better understand their individual advantages for landslide monitoring. This process highlights the potential of our dataset to provide a reliable benchmark for future developments in landslide detection research.

How to cite: Höhn, P., Heidler, K., Behling, R., and Zhu, X. X.: Sen12Landslides: A Multi-modal, Large-scale, Multi-temporal Benchmark Dataset for satellite-based Landslide Monitoring, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-3526, https://doi.org/10.5194/egusphere-egu24-3526, 2024.

X4.57
|
EGU24-18374
|
Highlight
Zhan Cheng, michel Jaboyedoff, and wenping gong

Landslides represent one of the most pervasive and detrimental geohazards worldwide. Precise detection of potential landslides is imperative for effective landslide risk management. While the utilization of Unmanned Aerial Vehicles (UAVs) has seen a recent surge in landslide evaluation, the majority of contemporary UAV image-based identifications predominantly depend on visual inspections. This study introduces a sophisticated image analysis framework tailored for landslide identification in UAV-captured imagery. This framework not only discerns landslide boundaries but also detects ground surface fractures. Employing an object-oriented image analysis approach, potential landslide boundaries within UAV images are identified. Concurrently, an automated model, refined through a deep transfer learning methodology, recognizes ground surface fractures in these images. Subsequent to this, a fusion of identified landslide boundaries and ground fractures is achieved through Boolean operations, facilitating nuanced landslide detection within UAV imagery. To underscore the proficiency of our proposed framework, we selected the Heifangtai Terrace in Gansu, China, as a case study. The resultant identifications are cross-referenced with field survey data to confirm the validity.

How to cite: Cheng, Z., Jaboyedoff, M., and gong, W.: Landslide Identification in UAV Images Through Recognition of Landslide Boundaries and Ground Surface Cracks, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-18374, https://doi.org/10.5194/egusphere-egu24-18374, 2024.

X4.58
|
EGU24-16693
Txomin Bornaetxea, Ivan Marchesini, Michele Santangelo, Alessandro Mondini, and Federica Fiorucci

Landslide inventories form the backbone of numerous natural hazard studies, providing essential data for assessing susceptibility, hazard, and risk. However, the accuracy and comprehensiveness of these inventories are influenced by various factors, including the visibility of the terrain from observation points. This study delves into the critical relationship between terrain visibility and the quality of field-based landslide inventories, with a focus on the implications for hazard analysis.
Traditionally, the visibility of a territory has been an overlooked factor, often assumed to be uniform across inventories. However, our research, leveraging the r.survey tool in conjunction with digital elevation models, reveals that the density of landslide information is strongly correlated with visibility. In areas of high visibility, field-based inventories exhibit a higher density of landslide reports, whereas regions with poor visibility are often underrepresented. Conversely, inventories derived from satellite imagery, while consistent, may also lack detailed information, particularly regarding smaller landslides in potentially visible zones, such as areas near roads.
The introduction of r.survey, a GRASS GIS plugin, has allowed for an effective visibility assessments. It not only calculates the visibility from various observation points but also incorporates the concept of solid angles to account for the size and orientation of observed objects. This innovative approach enables the development of a 'Size-specific Effective Surveyed Area' (SsESA), refining our understanding of the actual terrain covered during field surveys.
Furthermore, our ongoing empirical studies aim to establish a minimum solid angle threshold to determine the visibility of landslides, crucial for improving the accuracy of landslide inventories. Such insights are invaluable for statistical modeling, as biases in inventory data directly influence hazard assessments. By enhancing our understanding of visibility-related biases, we can refine inventory methodologies, ensuring more robust and accurate landslide susceptibility models.
In conclusion, terrain visibility significantly impacts the quality and comprehensiveness of field-based landslide inventories. Through the continued development and application of tools like r.survey, we can mitigate visibility-related biases, fostering more reliable hazard assessments and better-informed mitigation strategies.

How to cite: Bornaetxea, T., Marchesini, I., Santangelo, M., Mondini, A., and Fiorucci, F.: Impact of Terrain Visibility on Field-Based Landslide Inventories and the Role of r.survey, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-16693, https://doi.org/10.5194/egusphere-egu24-16693, 2024.

X4.59
|
EGU24-16674
|
ECS
New Landslide Inventory and Assessment in Malaysia: A Geological and Geomorphological Modelling Approach 
(withdrawn after no-show)
Mohamad Faruq Syahmi Md Aripin, Muhammad Afiq Ariff Mohd Hellmy, Zakaria Mohamad, Khamarrul Azahari Razak, Nornajiha Nasruddin, Ahmad Daniel Razali, Mohd Khairudin Muhamed, Zafrul Fazry Mohd Fauzi, and Abd Rasid Jaapar
X4.60
|
EGU24-17080
|
ECS
Analysis of Rainfall-induced Multiple-Occurrence Regional LandslideEvents (MORLEs) in the Philippines
(withdrawn)
Ma. Malyn Tumonong
X4.61
|
EGU24-18897
|
ECS
Thomas Kreuzer, Christian Büdel, Peter Priesmeier, Alexander Fekete, and Birgit Terhorst

Tehran, the bustling capital of Iran, is internationally recognized as one of the urban areas most susceptible to natural hazards. Among the various threats, landslides constitute a significant danger to infrastructure, buildings and the inhabitants. The general exposure to hazards initiated the creation of multiple landslide susceptibility maps, especially for the mountainous terrain north of the city. These maps are pivotal for urban planning and disaster mitigation efforts.

Despite the high relevance of hazard and susceptibility maps in the study area, a systematic comparison of these susceptibility maps has not been undertaken so far, mainly due to the lack of accessible data. Primarily available maps exist in the form of published images, precluding detailed, pixel-level analyses that could reveal insights into their relative accuracy and effectiveness.

Addressing the data accessibility challenge, the current study introduces an innovative approach for extracting quantitative information from all published maps in the area of interest. The applied method leverages a modified k-means clustering algorithm, traditionally limited by its sensitivity to initial cluster centres and less suited for colour quantization. However, our proposed approach showcases reliability when applied to thematic maps characterized by monochromatic colour schemes.

Our research undertook a detailed comparison of 14 landslide susceptibility maps, all intersecting the northern area of Tehran, and encompassing various scales. The comparative analysis proved a significant discordance between the published maps. It can be observed that map performance is predominantly influenced by factors such as data resolution, methodological approaches, and parameter selection, rather than by the sheer number of parameters. Through this comparative assessment, we have identified critical parameters that greatly influence landslide susceptibility predictions.

A striking conclusion of the present study is the absence of a singularly superior methodology amongst the numerous scientific approaches assessed. Although all methods are established and reputable within the scientific community, our results demonstrate that they yield clear discrepancies when applied to the context of Tehran's landscape. In the context of landslide hazard evaluation, susceptibility mapping constitutes the foundational element within our Integrated Disaster Risk Management (IDRM) framework. Consequently, our findings highlight significant challenges concerning the practical implementation of these maps.

In conclusion, the present study points to complex problems of creating accurate landslide susceptibility maps and identified significant discrepancies that can arise from methodological variations. These findings demonstrate the urgent need for further research to deepen our understanding of landslide susceptibility mapping. It is mandatory that future studies continue to refine these techniques to enhance their predictive power, reduce uncertainties, and, ultimately, support the resilience of urban areas and societies. This is one of the main tasks in the project: “Geovisual analysis, evaluation and monitoring of geohazards and their related landforms” as part of the BMBF INCREASE research program (Förder-Nr. 01DK20101H).

How to cite: Kreuzer, T., Büdel, C., Priesmeier, P., Fekete, A., and Terhorst, B.: Comparative Assessment of Landslide Susceptibility Maps in the Alborz Mountain range by Tehran: Methodologies and Challenges, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-18897, https://doi.org/10.5194/egusphere-egu24-18897, 2024.

X4.62
|
EGU24-11501
|
ECS
Machine Learning Algorithms for Landslide Susceptibility Mapping applied on Portofino Promontory (Italy)
(withdrawn)
Giulia Mazzaccaro, Stefania Magrì, Monica Solimano, Pietro De Stefanis, Anna Palla, Francesco Faccini, and Ilaria Gnecco

Posters virtual: Fri, 19 Apr, 14:00–15:45 | vHall X4

Display time: Fri, 19 Apr, 08:30–Fri, 19 Apr, 18:00
Chairpersons: Federica Fiorucci, Khamarrul Azahari Razak, Lorenzo Nava
vX4.10
|
EGU24-19369
|
ECS
Siti Nuha Amisyah Sappe, Rabieahtul Abu Bakar, Khamarrul Azahari Razak, Zakaria Mohamad, Abdul Aziz Ab Rahman, Mohamad Abd Manap, and Tajul Anuar Jamaluddin

Genting Highland is predominantly the mode of landslides, especially prevalent during and post monsoon seasons. Globally, landslides encapsulates the widespread hydro-geological disaster elucidating their causes, risks, and impacts on infrastructure and human life. Attributed  from Malaysia natural undulated terrain, torrential rainfall, expanding urbanization contributed to the increasing landslide occurrences. Laying the groundwork for a more efficient landslide mapping over a vast area underscores the imperative need of Artificial Intelligence (AI). Landslide mapping to-date transitions from conventional delineation to employing U-Net, a deep learning architecture, to automate and expedite the process of identifying landslides from remote sensing data towards the emphasizes on rapid landslide mapping. This study is to create detailed landslide inventory maps by mapping new and old landslide footprint for Genting Highlands, with U-Net Deep Learning as a pivotal tool. Entail a systematic process, to identify landslide structures according to predefined categories, using high-resolution satellite imagery to train the U-Net model, and ultimately producing validated landslide maps for the region. The stages for integrating U-Net Deep Learning with geospatial analysis include data acquisition, pre-processing, DL training, analysis, and the final output of landslide mapping. Spot-7 imagery as input to the U-Net and  landslide semantic shapes that consist of crown, transportation body and foot, whereby pixel by pixel are classified when introduced. The anticipated results, showcasing the validity and precision of the model's landslide automated delineation on other imageries. Verification involves the comparison between U-Net's projected landslides to a manually delineated landslide inventory for Genting Highlands. Hence, this research provide precise and efficient tools for identifying and forecasting landslides in landslide-prone areas. 

How to cite: Sappe, S. N. A., Abu Bakar, R., Razak, K. A., Mohamad, Z., Ab Rahman, A. A., Abd Manap, M., and Jamaluddin, T. A.: U-Net Deep Learning for Geospatial Landslide Inventory Mapping in Genting Highlands, Malaysia, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-19369, https://doi.org/10.5194/egusphere-egu24-19369, 2024.