Earthquake-triggered landslide susceptibility in Italy by means of Artificial Neural Network

Amato, Gabriele; Fiorucci, Matteo; Martino, Salvatore; Lombardo, Luigi; Palombi, Lorenzo

doi:10.31223/x59w39

Cited by 6 publications

(2 citation statements)

References 107 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another way to elaborate on model performance is to look at confusion plots (see, Amato et al, 2021), where the model accuracy is decoupled for presence and absence data. These are shown in Figure 6, for both RTS and ALD, as well as for the results obtained from the fit, RCV and SCV.…”

Section: Susceptibility Modeling Performancementioning

confidence: 99%

Assessing multi-hazard susceptibility to cryospheric hazards: lesson learnt from an Alaskan example

Elia¹,

Castellaro²,

Dahal³

et al. 2023

Preprint

View full text Add to dashboard Cite

Classifying a given landscape on the basis of its susceptibility to surface processes is a standard procedure in low to mid-latitudes. Conversely, these procedures have hardly been explored in periglacial regions, primarily because of the limited presence of human settlements and, therefore, the little need for risk assessment. However, global warming is radically changing this situation and will change it even more in the future. For this reason, understanding the spatial and spatiotemporal dynamics of geomorphological processes in peri-arctic environments can be crucial to make informed decisions in such unstable environments and shed light on what changes may follow at lower latitudes. For this reason, here we explored the use of data-driven models capable of recognizing locations prone to develop retrogressive thaw slumps (RTSs) and/or active layer detachments (ALDs). These are cryospheric hazards induced by permafrost degradation, and their development can negatively affect human settlements or infrastructure, change the sediment budget dynamics and release greenhouse gases. Specifically, we test a binomial Generalized Additive Modeling structure to estimate the probability of RST and ALD occurrences in the North sector of the Alaskan territory. The results we obtain show that our binary classifiers can accurately recognize locations prone to RTS and ALD, in a number of goodness-of-fit (AUC_RTS = 0.83; AUC_ALD = 0.86), random cross-validation (mean AUC_RTS = 0.82; mean AUC_ALD = 0.86), and spatial cross-validation (mean AUC_RTS = 0.74; mean AUC_ALD = 0.80) routines.Overall, our analytical protocol has been implemented to build an open-source tool scripted in Python as part of an interactive Jupyter notebook where all the operational steps are automatized for anyone to replicate the same experiment. Our protocol allows one to access cloud-stored information, pre-process it, and download it locally to be integrated for spatial predictive purposes. Data and codes can be accessed at this GitHub repository: https://github.com/zincoblenda/CryoS

show abstract

Section: Susceptibility Modeling Performancementioning

confidence: 99%

Assessing multi-hazard susceptibility to cryospheric hazards: lesson learnt from an Alaskan example

Elia¹,

Castellaro²,

Dahal³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…point 1a) ensures that the simulations will include all of the potential sources that could develop into rockfalls and whose runout could concern the railway network (this work does not attempt to account for any anthropogenic mass displacements in the vicinities of the railway track). We favor SU as suitable mapping units for the description of landslide phenomena (Alvioli et al, 2016;Camilo et al, 2017;Schlögel et al, 2018;Bornaetxea et al, 2018;Tanyaş et al, 2019a,b;Jacobs et al, 2020;Amato et al, 2020;Chen et al, 2020;Li and Lan, 2020). More specifically, we adopted SUs instead of a geometric buffer around the track, because rockfall trajectories initiated in a given SU will be bounded within the SU, with reasonable confidence.…”

Section: Identification Of Rockfall Source Areasmentioning

confidence: 99%

Rockfall susceptibility and network-ranked susceptibility along the Italian railway

Alvioli,

Santangelo,

Fiorucci

et al. 2021

Preprint

View full text Add to dashboard Cite

Rockfalls pose a substantial threat to ground transportation, due to their rapidity, destructive potential and high probability of occurrence on steep topographies, often found along roads and railway routes. Various factors can trigger rockfalls, including intense rainfall and seismic activity, and diverse phenomena affect their probability of occurrence. Approaches for the assessment of rockfall susceptibility range from purely phenomenological methods and statistical methods, suitable for modeling large areas, to purely deterministic ones, usually easier to use in local analyses. A common requirement is the need to locate potential detachment points, often found uphill on cliffs, and the subsequent assessment of the runout areas of rockfalls stemming from such points.Here, we apply a physically based model for the calculation of rockfall trajectories along the whole Italian railway network, within a corridor of total length of about 17,000 km and varying width. We propose a data-driven method for the location of rockfall source points based on expert mapping of potential source areas on sample representative locations. Using empirical distributions of gridded slope values in source areas mapped by experts, we derived probabilistic maps of rockfall sources in the proximity of the railway network, regardless of a particular trigger.Source areas act as starting points of simulated trajectories, within the three-dimensional model STONE. The program provides a pixel-by-pixel trajectory count, which we classify into a susceptibility map. We obtained the map analyzing the railway track as a collection of segments, for which we provide segment-wise rockfall susceptibility.Eventually, we considered an equivalent graph representation of the network, which helps classifying the segments both on the basis of rockfall susceptibility and the role of each segment in the network, resulting in a network-ranked susceptibility.

show abstract

On the prediction of landslide occurrences and sizes via Hierarchical Neural Networks

Aguilera

Lombardo

Tanyaş

et al. 2022

Stoch Environ Res Risk Assess

Self Cite

View full text Add to dashboard Cite

For more than three decades, the part of the geoscientific community studying landslides through data-driven models has focused on estimating where landslides may occur across a given landscape. This concept is widely known as landslide susceptibility. And, it has seen a vast improvement from old bivariate statistical techniques to modern deep learning routines. Despite all these advancements, no spatially-explicit data-driven model is currently capable of also predicting how large landslides may be once they trigger in a specific study area. In this work, we exploit a model architecture that has already found a number of applications in landslide susceptibility. Specifically, we opt for the use of Neural Networks. But, instead of focusing exclusively on where landslides may occur, we extend this paradigm to also spatially predict classes of landslide sizes. As a result, we keep the traditional binary classification paradigm but we make use of it to complement the susceptibility estimates with a crucial information for landslide hazard assessment. We will refer to this model as Hierarchical Neural Network (HNN) throughout the manuscript. To test this analytical protocol, we use the Nepalese area where the Gorkha earthquake induced tens of thousands of landslides on the 25th of April 2015. The results we obtain are quite promising. The component of our HNN that estimates the susceptibility outperforms a binomial Generalized Linear Model (GLM) baseline we used as benchmark. We did this for a GLM represents the most common classifier in the landslide literature. Most importantly, our HNN also suitably performed across the entire procedure. As a result, the landslide-area-class prediction returned not just a single susceptibility map, as per tradition. But, it also produced several informative maps on the expected landslide size classes. Our vision is for administrations to consult these suite of model outputs and maps to better assess the risk to local communities and infrastructure. And, to promote the diffusion of our HNN, we are sharing the data and codes in a githubsec repository in the hope that we would stimulate others to replicate similar analyses.

show abstract

Earthquake-triggered landslide susceptibility in Italy by means of Artificial Neural Network

Cited by 6 publications

References 107 publications

Assessing multi-hazard susceptibility to cryospheric hazards: lesson learnt from an Alaskan example

Assessing multi-hazard susceptibility to cryospheric hazards: lesson learnt from an Alaskan example

Rockfall susceptibility and network-ranked susceptibility along the Italian railway

On the prediction of landslide occurrences and sizes via Hierarchical Neural Networks

Contact Info

Product

Resources

About