Assessing the impact of climate change on landslide recurrence intervals in Nakhon Si Thammarat Province, Thailand, using CMIP6 climate models DOI Creative Commons
Thapthai Chaithong

Progress in Disaster Science, Год журнала: 2024, Номер 22, С. 100330 - 100330

Опубликована: Апрель 1, 2024

Climate variability and climate change may influence the frequency recurrence interval of landslides. Precipitation, as a main triggering factor landslides, be influenced by change. Changes in precipitation directly affect landslide intervals. Considering change, partial duration series method critical rainfall threshold are combined with simulated Phase 6 Coupled Model Intercomparison Project (CMIP6) general circulation models (GCMs) to predict changes future intervals Nakhon Si Thammarat Province, Thailand. The analytical results predicted over next 20 years (2023 2042). SSP1–2.6 SSP2–4.5 adopted socioeconomic development scenarios. According predictions, showed that return period occurrence will shorter than historical period; moreover, fluctuate greatly. DWR meteorological station shows most fluctuation for SSP1–2.6. In addition, Station experiences significant decrease approximately 35% under For SSP2–4.5, period. observed decline intervals, reduction 40%. Hence, landslides increase future. A comparison between revealed yielded lower periods.

Язык: Английский

On the use of explainable AI for susceptibility modeling: Examining the spatial pattern of SHAP values DOI Creative Commons
Nan Wang, Hongyan Zhang, Ashok Dahal

и другие.

Geoscience Frontiers, Год журнала: 2024, Номер 15(4), С. 101800 - 101800

Опубликована: Фев. 2, 2024

Hydro-morphological processes (HMP, any natural phenomenon contained within the spectrum defined between debris flows and flash floods) are globally occurring hazards which pose great threats to our society, leading fatalities economical losses. For this reason, understanding dynamics behind HMPs is needed aid in hazard risk assessment. In work, we take advantage of an explainable deep learning model extract global local interpretations HMP occurrences across whole Chinese territory. We use a neural network architecture interpret results through spatial pattern SHAP values. doing so, can understand prediction on hierarchical basis, looking at how predictor set controls overall susceptibility as well same level single mapping unit. Our accurately predicts with AUC values measured ten-fold cross-validation ranging 0.83 0.86. This predictive performance attests for excellent skill. The main difference respect traditional statistical tools that latter usually lead clear interpretation expense high performance, otherwise reached via machine/deep solutions, though interpretation. recent development AI key combine both strengths. explore combination context modeling. Specifically, demonstrate extent one enter new data-driven interpretation, supporting decision-making process disaster mitigation prevention actions.

Язык: Английский

Процитировано

25

Landslides in a changing world DOI Creative Commons
Irasema Alcántara-Ayala

Landslides, Год журнала: 2025, Номер unknown

Опубликована: Янв. 15, 2025

Abstract This article investigates the multifaceted dimensions to understand interrelatedness among global change drivers and their implications for landslide hazards disaster risk. Drawing on empirical research, it utilised a mixed-methods design; research combined diverse data sources experiential insights interdependencies bounded by local context scale. The findings underscore urgent need holistic approaches that consider complex of landslides as socio-natural change, emphasising importance collaboration, innovation, international cooperation in building resilience mitigating adverse effects risk systems societies. Furthermore, challenge reducing lies understanding addressing interplay between socio-environmental transformations geodynamic processes. escalating climate urban expansion, deforestation are anticipated magnify occurrence landslides, thereby posing significant risks human lives, infrastructure, ecosystems, livelihoods. However, most importantly, these further compounded environmental, social, economic, political, cultural, technological spheres associated with globalisation. systemic nature risk, particularly changing world, highlights interconnectedness different systems, resulting causality cascading impacts. These contribute broader discourse sustainability providing evidence supports integrated achieving long-term reduction based upon equitable sustainable use territories while integrating robust management strategies ensure resilient communities ecosystems.

Язык: Английский

Процитировано

3

Deciphering seasonal effects of triggering and preparatory precipitation for improved shallow landslide prediction using generalized additive mixed models DOI Creative Commons
Stefan Steger, Mateo Moreno, Alice Crespi

и другие.

Natural hazards and earth system sciences, Год журнала: 2023, Номер 23(4), С. 1483 - 1506

Опубликована: Апрель 21, 2023

Abstract. The increasing availability of long-term observational data can lead to the development innovative modelling approaches determine landslide triggering conditions at a regional scale, opening new avenues for prediction and early warning. This research blends strengths existing with capabilities generalized additive mixed models (GAMMs) develop an interpretable approach that identifies seasonally dynamic precipitation shallow landslides. model builds upon 21-year record landslides in South Tyrol (Italy) separates induced from did not. accounts effects acting four temporal scales: short-term “triggering” precipitation, medium-term “preparatory” seasonal effects, across-year variability. It provides relative probability scores were used establish thresholds optimal performance terms hit false-alarm rates, as well additional related user-defined scores. GAMM shows high predictive indicates more is required induce summer than winter/spring, which presumably be attributed mainly vegetation temperature effects. discussion illustrates why quality input data, study design, transparency are crucial using advanced data-driven techniques.

Язык: Английский

Процитировано

30

The influence of spatial patterns in rainfall on shallow landslides DOI Creative Commons
Hugh G. Smith, Andrew Neverman, Harley Betts

и другие.

Geomorphology, Год журнала: 2023, Номер 437, С. 108795 - 108795

Опубликована: Июнь 16, 2023

Understanding how rainfall events influence the pattern and magnitude of landslide response is an important research focus from geomorphological hazard planning perspectives. Few studies quantitatively relate spatial patterns in landslides, largely due to difficulties acquiring inventories data on for individual storm events. However, increasing availability frequent, high-resolution satellite imagery weather radar overcoming these impediments. Here, we aim a) identify which factors most susceptibility shallow landslides at event scale b) assess density varies relation rainfall. We combine spanning study areas located across upper North Island New Zealand with estimates different explanatory variables using a logistic regression model. found land cover slope exert largest ahead intra-event intensities pre-event accumulations. Of variables, maximum 12-h normalised by 10-y recurrence interval intensity 10-d accumulation mean annual had susceptibility. Forest reduced sensitivity variations slope, rainfall, rock type, contrast pasture. observed 3.5-fold increase once was ≥25 % above pastoral weak sedimentary rocks. This threshold consistent late century under highest levels projected warming Zealand, suggests that could be significantly amplified climate change. Our demonstrates insights gained combining better understand influencing

Язык: Английский

Процитировано

25

Modeling landslide susceptibility based on convolutional neural network coupling with metaheuristic optimization algorithms DOI Creative Commons
Zhuo Chen, Danqing Song

International Journal of Digital Earth, Год журнала: 2023, Номер 16(1), С. 3384 - 3416

Опубликована: Авг. 23, 2023

Landslides are one of the most common geological hazards worldwide, especially in Sichuan Province (Southwest China). The current study's main purposes to explore potential applications convolutional neural networks (CNN) hybrid ensemble metaheuristic optimization algorithms, namely beluga whale (BWO) and coati algorithm (COA), for landslide susceptibility mapping (China). For this aim, fourteen conditioning factors were compiled a spatial database. effectiveness development predictive model was quantified using linear support vector machine model. receiver operating characteristic (ROC) curve (AUC), root mean square error, six statistical indices used test compare three resultant models. training dataset, AUC values CNN-COA, CNN-BWO CNN models 0.946, 0.937 0.855, respectively. In terms validation CNN-COA exhibited higher value 0.919, while 0.906 0.805, results indicate that model, followed by offers best overall performance analysis.

Язык: Английский

Процитировано

24

Adopting the margin of stability for space–time landslide prediction – A data-driven approach for generating spatial dynamic thresholds DOI Creative Commons
Stefan Steger, Mateo Moreno, Alice Crespi

и другие.

Geoscience Frontiers, Год журнала: 2024, Номер 15(5), С. 101822 - 101822

Опубликована: Март 13, 2024

Shallow landslide initiation typically results from an interplay of dynamic triggering and preparatory conditions along with static predisposition factors. While data-driven methods for assessing susceptibility or establishing rainfall-triggering thresholds are prevalent, integrating spatio-temporal information large-area prediction remains a challenge. The main aim this research is to generate spatial model that operates at daily scale explicitly counteracts potential errors in the available data. Unlike previous studies focusing on space–time modelling, it places strong emphasis reducing propagation data into modelling results, while ensuring interpretable outcomes. It introduces also other noteworthy innovations, such as visualizing final predictions linked true positive rates false alarm by using animations highlighting its application hindcasting scenario-building. initial step involves creation spatio-temporally representative sample presence absence observations study area South Tyrol, Italy (7400 km2) within well-investigated terrain. Model setup entails controls operate various temporal scales through binomial Generalized Additive Mixed Model. relationships then interpreted based variable importance partial effect plots, predictive performance evaluated cross-validation techniques. Optimal user-defined probability cutpoints used establish quantitative reflect both, rate (correctly predicted landslides) (precipitation periods misclassified landslide-inducing conditions). resulting maps directly visualize threshold exceedance. demonstrates high revealing geomorphologically plausible patterns largely consistent current process knowledge. Notably, shows generally drier hillslopes exhibit greater sensitivity certain precipitation events than regions adapted wetter conditions. practical applicability approach demonstrated scenario-building context. In currently evolving field we recommend error handling, interpretability, geomorphic plausibility, rather allocating excessive resources algorithm case comparisons.

Язык: Английский

Процитировано

15

Assessing the impact of climate change on rainfall-triggered landslides: a case study in California DOI Creative Commons
Shabnam J. Semnani, Yi Han, C. Bonfils

и другие.

Landslides, Год журнала: 2025, Номер unknown

Опубликована: Янв. 8, 2025

Язык: Английский

Процитировано

1

An enhanced rainfall-induced landslide catalogue in Italy DOI Creative Commons
Maria Teresa Brunetti, Stefano Luigi Gariano, Massimo Melillo

и другие.

Scientific Data, Год журнала: 2025, Номер 12(1)

Опубликована: Фев. 5, 2025

Язык: Английский

Процитировано

1

Potential impacts of future climate on the spatio-temporal variability of landslide susceptibility in Iran using machine learning algorithms and CMIP6 climate-change scenarios DOI
Saeid Janizadeh, Sayed M. Bateni, Changhyun Jun

и другие.

Gondwana Research, Год журнала: 2023, Номер 124, С. 1 - 17

Опубликована: Май 19, 2023

Язык: Английский

Процитировано

21

Active thickness estimation and failure simulation of translational landslide using multi-orbit InSAR observations: A case study of the Xiongba landslide DOI Creative Commons
Wu Zhu, Luyao Yang,

Yiqing Cheng

и другие.

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2024, Номер 129, С. 103801 - 103801

Опубликована: Март 29, 2024

The active thickness of the translational landslides plays a pivotal role in evaluating its hazards and simulating instability. Existing techniques have difficulties estimating accurate due to limitations observation conditions imaging geometry, leading deviations failure simulations. To overcome these challenges, this study proposes an enhanced method that utilizes multi-orbit Interferometric Synthetic Aperture Radar (InSAR) observations estimate subsequently conduct more instability involves integrating InSAR parameters with spatial geometry landslide establish slope coordinate system. This system enables projection one-dimensional Line Of Sight (LOS) displacements onto three-dimensional landslide. Subsequently, is estimated by combining mass conservation method. Finally, incorporated into geological model construction simulate dynamic movement was applied Xiongba Gongga County, Tibet Autonomous Region, China. results show deformation mainly concentrated at forefront, maximum rates 4.7 m/a, 2.3 1.24 m/a. encompasses area around 5.33 square kilometers, varies from 0 106.59 m. displacement distance reaches 1469.76 m, peak velocity 60.37 m/s. proposed provides scientific support for assessing, analyzing, preventing disasters.

Язык: Английский

Процитировано

9