arXiv subjects

Luigi Lombardo

Publications and source records attributed to Luigi Lombardo.

14 recordsLinked to original sources

arXiv2025

Do Earthquakes Wake More Slopes Than They Calm?

Strong earthquakes can have a dual impact on the slow-moving landslide budget of a landscape by either triggering new actively deforming hillslopes or stabilizing existing ones. However, their regional-scale influence on hillslope processes remains poorly understood due to limited observational coverage and the masking effects of long-wavelength post-seismic signals. This knowledge gap constrains our ability to assess post-seismic landslide hazards, particularly since actively deforming hillslopes may evolve into rapid failures, especially under the influence of meteorological factors following a major earthquake. This study addresses this gap by analyzing slope instability across approximately 66,800sq.km of southeastern Türkiye in the aftermath of the February 6, 2023, Kahramanmaraş earthquake sequence. We used Sentinel-1 InSAR time series spanning three years before and one year after the earthquakes and applied a convolution-based filtering method to isolate localized surface deformation from broader tectonic signals. Given the challenge of validating deformation anomalies at a regional scale without in-situ measurements, we cross-checked these locations using high-resolution optical imagery and assigned confidence levels based on observable surface features indicative of slow-moving landslides. The resulting inventories were further enriched by expert-based assessments. Our results show that the total area affected by slow-moving landslides increased from 12.36sq.km to 159.38sq.km, reflecting a more than 12-fold rise. While a substantial number of slopes were newly activated (348), others became stabilized (28) or shifted to different deformation states (20). These findings highlight the complex response of hillslopes to seismic forcing and emphasize the importance of long-term monitoring to capture the full spectrum of earthquake-induced landslide behavior.

physics.geo-ph↗

arXiv2024

Towards physics-informed neural networks for landslide prediction

For decades, solutions to regional scale landslide prediction have mostly relied on data-driven models, by definition, disconnected from the physics of the failure mechanism. The success and spread of such tools came from the ability to exploit proxy variables rather than explicit geotechnical ones, as the latter are prohibitive to acquire over broad landscapes. Our work implements a Physics Informed Neural Network (PINN) approach, thereby adding to a standard data-driven architecture, an intermediate constraint to solve for the permanent deformation typical of Newmark slope stability methods. This translates into a neural network tasked with explicitly retrieving geotechnical parameters from common proxy variables and then minimize a loss function with respect to the available coseismic landside inventory. The results are very promising, because our model not only produces excellent predictive performance in the form of standard susceptibility output, but in the process, also generates maps of the expected geotechnical properties at a regional scale. Such architecture is therefore framed to tackle coseismic landslide prediction, something that, if confirmed in other studies, could open up towards PINN-based near-real-time predictions.

physics.geo-ph↗

arXiv2024

Statistics of extremes for natural hazards: landslides and earthquakes

In this chapter, we illustrate the use of split bulk-tail models and subasymptotic models motivated by extreme-value theory in the context of hazard assessment for earthquake-induced landslides. A spatial joint areal model is presented for modeling both landslides counts and landslide sizes, paying particular attention to extreme landslides, which are the most devastating ones.

stat.AP↗

arXiv2024

At the junction between deep learning and statistics of extremes: formalizing the landslide hazard definition

The most adopted definition of landslide hazard combines spatial information about landslide location (susceptibility), threat (intensity), and frequency (return period). Only the first two elements are usually considered and estimated when working over vast areas. Even then, separate models constitute the standard, with frequency being rarely investigated. Frequency and intensity are intertwined and depend on each other because larger events occur less frequently and vice versa. However, due to the lack of multi-temporal inventories and joint statistical models, modelling such properties via a unified hazard model has always been challenging and has yet to be attempted. Here, we develop a unified model to estimate landslide hazard at the slope unit level to address such gaps. We employed deep learning, combined with a model motivated by extreme-value theory to analyse an inventory of 30 years of observed rainfall-triggered landslides in Nepal and assess landslide hazard for multiple return periods. We also use our model to further explore landslide hazard for the same return periods under different climate change scenarios up to the end of the century. Our results show that the proposed model performs excellently and can be used to model landslide hazard in a unified manner. Geomorphologically, we find that under both climate change scenarios (SSP245 and SSP885), landslide hazard is likely to increase up to two times on average in the lower Himalayan regions while remaining the same in the middle Himalayan region whilst decreasing slightly in the upper Himalayan region areas.

cs.LG↗

arXiv2024

Deep graphical regression for jointly moderate and extreme Australian wildfires

Recent wildfires in Australia have led to considerable economic loss and property destruction, and there is increasing concern that climate change may exacerbate their intensity, duration, and frequency. Hazard quantification for extreme wildfires is an important component of wildfire management, as it facilitates efficient resource distribution, adverse effect mitigation, and recovery efforts. However, although extreme wildfires are typically the most impactful, both small and moderate fires can still be devastating to local communities and ecosystems. Therefore, it is imperative to develop robust statistical methods to reliably model the full distribution of wildfire spread. We do so for a novel dataset of Australian wildfires from 1999 to 2019, and analyse monthly spread over areas approximately corresponding to Statistical Areas Level~1 and~2 (SA1/SA2) regions. Given the complex nature of wildfire ignition and spread, we exploit recent advances in statistical deep learning and extreme value theory to construct a parametric regression model using graph convolutional neural networks and the extended generalized Pareto distribution, which allows us to model wildfire spread observed on an irregular spatial domain. We highlight the efficacy of our newly proposed model and perform a wildfire hazard assessment for Australia and population-dense communities, namely Tasmania, Sydney, Melbourne, and Perth.

stat.AP↗

arXiv2022

Joint modeling of landslide counts and sizes using spatial marked point processes with sub-asymptotic mark distributions

To accurately quantify landslide hazard in a region of Turkey, we develop new marked point process models within a Bayesian hierarchical framework for the joint prediction of landslide counts and sizes. To accommodate for the dominant role of the few largest landslides in aggregated sizes, we leverage mark distributions with strong justification from extreme-value theory, thus bridging the two broad areas of statistics of extremes and marked point patterns. At the data level, we assume a Poisson distribution for landslide counts, while we compare different "sub-asymptotic" distributions for landslide sizes to flexibly model their upper and lower tails. At the latent level, Poisson intensities and the median of the size distribution vary spatially in terms of fixed and random effects, with shared spatial components capturing cross-correlation between landslide counts and sizes. We robustly model spatial dependence using intrinsic conditional autoregressive priors. Our novel models are fitted efficiently using a customized adaptive Markov chain Monte Carlo algorithm. We show that, for our dataset, sub-asymptotic mark distributions provide improved predictions of large landslide sizes compared to more traditional choices. To showcase the benefits of joint occurrence-size models and illustrate their usefulness for risk assessment, we map landslide hazard along major roads.

stat.ME↗

arXiv2020

Space-time clustering of flash floods in a changing climate (China, 1950-2015)

The persistence over space and time of flash flood disasters -- flash floods that have caused either economical or life losses, or both -- is a diagnostic measure of areas subjected to hydrological risk. The concept of persistence can be assessed via clustering analyses, performed here to analyse the national inventory of flash floods disasters in China occurred in the period 1950-2015. Specifically, we investigated the spatio-temporal pattern distribution of the flash floods and their clustering behavior by using both global and local methods: the first, based on the Ripley's K-function, and the second on scan statistics. As a result, we could visualize patterns of aggregated events, estimate the cluster duration and make assumptions about their evolution over time, also with respect precipitations trend. Due to the large spatial (the whole Chinese territory) and temporal scale of the dataset (66 years), we were able to capture whether certain clusters gather in specific locations and times, but also whether their magnitude tends to increase or decrease. Overall, the eastern regions in China are much more subjected to flash floods compared to the rest of the country. Detected clusters revealed that these phenomena predominantly occur between July and October, a period coinciding with the wet season in China. The number of detected clusters increases with time, but the associated duration drastically decreases in the recent period. This may indicate a change towards triggering mechanisms which are typical of short-duration extreme rainfall events. Finally, being flash floods directly linked to precipitation and their extreme realization, we indirectly assessed whether the magnitude of the trigger itself has also varied through space and time, enabling considerations in the context of climatic changes.

stat.AP↗

arXiv2020

High-resolution Bayesian mapping of landslide hazard with unobserved trigger event

Statistical models for landslide hazard enable mapping of risk factors and landslide occurrence intensity by using geomorphological covariates available at high spatial resolution. However, the spatial distribution of the triggering event (e.g., precipitation or earthquakes) is often not directly observed. In this paper, we develop Bayesian spatial hierarchical models for point patterns of landslide occurrences using different types of log-Gaussian Cox processes. Starting from a competitive baseline model that captures the unobserved precipitation trigger through a spatial random effect at slope unit resolution, we explore novel complex model structures that take clusters of events arising at small spatial scales into account, as well as nonlinear or spatially-varying covariate effects. For a 2009 event of around 4000 precipitation-triggered landslides in Sicily, Italy, we show how to fit our proposed models efficiently using the integrated nested Laplace approximation (INLA), and rigorously compare the performance of our models both from a statistical and applied perspective. In this context, we argue that model comparison should not be based on a single criterion, and that different models of various complexity may provide insights into complementary aspects of the same applied problem. In our application, our models are found to have mostly the same spatial predictive performance, implying that key to successful prediction is the inclusion of a slope-unit resolved random effect capturing the precipitation trigger. Interestingly, a parsimonious formulation of space-varying slope effects reflects a physical interpretation of the precipitation trigger: in subareas with weak trigger, the slope steepness is shown to be mostly irrelevant.

stat.ME↗

arXiv2020

From scenario-based seismic hazard to scenario-based landslide hazard: fast-forwarding to the future via statistical simulations

Ground motion scenarios exists for most of the seismically active areas around the globe. They essentially correspond to shaking level maps at given earthquake return times which are used as reference for the likely areas under threat from future ground displacements. Being landslides in seismically actively regions closely controlled by the ground motion, one would expect that landslide susceptibility maps should change as the ground motion patterns change in space and time. However, so far, statistically-based landslide susceptibility assessments have primarily been used as time-invariant.In other words, the vast majority of the statistical models does not include the temporal effect of the main trigger in future landslide scenarios. In this work, we present an approach aimed at filling this gap, bridging current practices in the seismological community to those in the geomorphological and statistical ones. More specifically, we select an earthquake-induced landslide inventory corresponding to the 1994 Northridge earthquake and build a Bayesian Generalized Additive Model of the binomial family, featuring common morphometric and thematic covariates as well as the Peak Ground Acceleration generated by the Northridge earthquake. Once each model component has been estimated, we have run 1000 simulations for each of the 217 possible ground motion scenarios for the study area. From each batch of 1000 simulations, we have estimated the mean and 95\% Credible Interval to represent the mean susceptibility pattern under a specific earthquake scenario, together with its uncertainty level. Because each earthquake scenario has a specific return time, our simulations allow to incorporate the temporal dimension into any susceptibility model, therefore driving the results toward the definition of landslide hazard.

stat.AP↗

arXiv2020

From scenario-based seismic hazard to scenario-based landslide hazard: rewinding to the past via statistical simulations

The vast majority of landslide susceptibility studies assumes the slope instability process to be time-invariant under the definition that "the past and present are keys to the future". This assumption may generally be valid. However, the trigger, be it a rainfall or an earthquake event, clearly varies over time. And yet, the temporal component of the trigger is rarely included in landslide susceptibility studies and only confined to hazard assessment. In this work, we investigate a population of landslides triggered in response to the 2017 Jiuzhaigou earthquake ($M_w = 6.5$) including the associated ground motion in the analyses, these being carried out at the Slope Unit (SU) level. We do this by implementing a Bayesian version of a Generalized Additive Model and assuming that the slope instability across the SUs in the study area behaves according to a Bernoulli probability distribution. This procedure would generally produce a susceptibility map reflecting the spatial pattern of the specific trigger and therefore of limited use for land use planning. However, we implement this first analytical step to reliably estimate the ground motion effect, and its distribution, on unstable SUs. We then assume the effect of the ground motion to be time-invariant, enabling statistical simulations for any ground motion scenario that occurred in the area from 1933 to 2017. As a result, we obtain the full spectrum of potential susceptibility patterns over the last century and compress this information into a susceptibility model/map representative of all the possible ground motion patterns since 1933. This backward statistical simulations can also be further exploited in the opposite direction where, by accounting for scenario-based ground motion, one can also use it in a forward direction to estimate future unstable slopes.

stat.AP↗

arXiv2019

Space-Time Landslide Predictive Modelling

Landslides are nearly ubiquitous phenomena and pose severe threats to people, properties, and the environment. Investigators have for long attempted to estimate landslide hazard to determine where, when, and how destructive landslides are expected to be in an area. This information is useful to design landslide mitigation strategies, and to reduce landslide risk and societal and economic losses. In the geomorphology literature, most attempts at predicting the occurrence of populations of landslides rely on the observation that landslides are the result of multiple interacting, conditioning and triggering factors. Here, we propose a novel Bayesian modelling framework for the prediction of space-time landslide occurrences of the slide type caused by weather triggers. We consider log-Gaussian cox processes, assuming that individual landslides stem from a point process described by an unknown intensity function. We tested our prediction framework in the Collazzone area, Umbria, Central Italy, for which a detailed multi-temporal landslide inventory spanning 1941-2014 is available together with lithological and bedding data. We tested five models of increasing complexity. Our most complex model includes fixed effects and latent spatio-temporal effects, thus largely fulfilling the common definition of landslide hazard in the literature. We quantified the spatio-temporal predictive skill of our model and found that it performed better than simpler alternatives. We then developed a novel classification strategy and prepared an intensity-susceptibility landslide map, providing more information than traditional susceptibility zonations for land planning and management. We expect our novel approach to lead to better projections of future landslides, and to improve our collective understanding of the evolution of landscapes dominated by mass-wasting processes under geophysical and weather triggers.

stat.AP↗

arXiv2018

Geostatistical modeling to capture seismic-shaking patterns from earthquake-induced landslides

In this paper, we investigate earthquake-induced landslides using a geostatistical model that includes a latent spatial effect (LSE). The LSE represents the spatially structured residuals in the data, which are complementary to the information carried by the covariates. To determine whether the LSE can capture the residual signal from a given trigger, we test whether the LSE is able to capture the pattern of seismic shaking caused by an earthquake from the distribution of seismically induced landslides, without prior knowledge of the earthquake being included in the statistical model. We assess the landslide intensity, i.e., the expected number of landslide activations per mapping unit, for the area in which landslides triggered by the Wenchuan (M 7.9, May 12, 2008) and Lushan (M 6.6, April 20, 2013) earthquakes overlap. We chose an area of overlapping landslides in order to test our method on landslide inventories located in the near and far fields of the earthquake. We generated three different models for each earthquake-induced landslide scenario: i) seismic parameters only (as a proxy for the trigger); ii) the LSE only; and iii) both seismic parameters and the LSE. The three configurations share the same set of morphometric covariates. This allowed us to study the pattern in the LSE and assess whether it adequately approximated the effects of seismic wave propagation. Moreover, it allowed us to check whether the LSE captured effects that are not explained by the shaking levels, such as topographic amplification. Our results show that the LSE reproduced the shaking patterns in space for both earthquakes with a level of spatial detail even greater than the seismic parameters. In addition, the models including the LSE perform better than conventional models featuring seismic parameters only.

stat.AP↗

arXiv2017

Modeling soil organic carbon with Quantile Regression: Dissecting predictors' effects on carbon stocks

Soil Organic Carbon (SOC) estimation is crucial to manage both natural and anthropic ecosystems and has recently been put under the magnifying glass after the Paris agreement 2016 due to its relationship with greenhouse gas. Statistical applications have dominated the SOC stock mapping at regional scale so far. However, the community has hardly ever attempted to implement Quantile Regression (QR) to spatially predict the SOC distribution. In this contribution, we test QR to estimate SOC stock (0-30 $cm$ depth) in the agricultural areas of a highly variable semi-arid region (Sicily, Italy, around 25,000 $km2$) by using topographic and remotely sensed predictors. We also compare the results with those from available SOC stock measurement. The QR models produced robust performances and allowed to recognize dominant effects among the predictors with respect to the considered quantile. This information, currently lacking, suggests that QR can discern predictor influences on SOC stock at specific sub-domains of each predictors. In this work, the predictive map generated at the median shows lower errors than those of the Joint Research Centre and International Soil Reference, and Information Centre benchmarks. The results suggest the use of QR as a comprehensive and effective method to map SOC using legacy data in agro-ecosystems. The R code scripted in this study for QR is included.

stat.AP↗

arXiv2017

Point process-based modeling of multiple debris flow landslides using INLA: an application to the 2009 Messina disaster

We develop a stochastic modeling approach based on spatial point processes of log-Gaussian Cox type for a collection of around 5000 landslide events provoked by a precipitation trigger in Sicily, Italy. Through the embedding into a hierarchical Bayesian estimation framework, we can use the Integrated Nested Laplace Approximation methodology to make inference and obtain the posterior estimates. Several mapping units are useful to partition a given study area in landslide prediction studies. These units hierarchically subdivide the geographic space from the highest grid-based resolution to the stronger morphodynamic-oriented slope units. Here we integrate both mapping units into a single hierarchical model, by treating the landslide triggering locations as a random point pattern. This approach diverges fundamentally from the unanimously used presence-absence structure for areal units since we focus on modeling the expected landslide count jointly within the two mapping units. Predicting this landslide intensity provides more detailed and complete information as compared to the classically used susceptibility mapping approach based on relative probabilities. To illustrate the model's versatility, we compute absolute probability maps of landslide occurrences and check its predictive power over space. While the landslide community typically produces spatial predictive models for landslides only in the sense that covariates are spatially distributed, no actual spatial dependence has been explicitly integrated so far for landslide susceptibility. Our novel approach features a spatial latent effect defined at the slope unit level, allowing us to assess the spatial influence that remains unexplained by the covariates in the model.

stat.AP↗