Susceptibility modeling of hydro-morphological processes considered river topology

Geo-spatial Information Science, Год журнала: 2025, Номер unknown, С. 1 - 20

Опубликована: Янв. 17, 2025

Hydro-Morphological Processes (HMP, any natural phenomenon contained within the spectrum defined between debris flows and flash floods) are most likely to occur in small catchments, especially buffer zones along or near rivers. Rivers transfer matter energy hydrographic units, thus potentially affecting occurrence of HMPs nearby catchments. To date, previous HMP susceptibility studies based on data-driven modeling lacked taking into account these interactions In this work, we fully considered role played by river topology developed a Topology-based model (Topo-HMPSM) emulate catchments predict for Yangtze River Basin during 1985–2015. Results confirmed that our proposed outperforms four selected baseline models with best F1-score (mean = 0.744, 0.756) relatively lower uncertainties. A graph-based deep neural network improves predictive interpretability using embedding learning techniques. This work attempts set standard incorporating models. Our findings highlight importance predicting support better informed hazard mitigation strategies.

Язык: Английский

---

Functional Regression for Space‐Time Prediction of Precipitation‐Induced Shallow Landslides in South Tyrol, Italy

Journal of Geophysical Research Earth Surface, Год журнала: 2025, Номер 130(4)

Опубликована: Апрель 1, 2025

Abstract Landslides are geomorphic hazards in mountainous terrains across the globe, driven by a complex interplay of static and dynamic controls. Data‐driven approaches have been employed to assess landslide occurrence at regional scales analyzing spatial aspects time‐varying conditions separately. However, joint assessment landslides space time remains challenging. This study aims predict precipitation‐induced shallow within Italian province South Tyrol (7,400 km 2 ). We introduce functional predictor framework where precipitation is represented as continuous series, contrast conventional that treat scalar predictor. Using hourly data past occurrences from 2012 2021, we implemented generalized additive model derive statistical relationships between occurrence, various factors, preceding evaluated resulting predictions through several cross‐validation routines, yielding performance scores frequently exceeding 0.90. To demonstrate predictive capabilities, performed hindcast for storm event Passeier Valley on 4–5 August 2016, capturing observed locations illustrating evolution predicted probabilities. Compared standard early warning approaches, this eliminates need predefine fixed windows aggregation while inherently accounting lagged effects. By integrating controls, research advances prediction large areas, addressing seasonal effects underlying limitations.

Язык: Английский

---

Landslide-induced vulnerability of road networks in Lahaul and Spiti, India: a geospatial study

Bulletin of Engineering Geology and the Environment, Год журнала: 2025, Номер 84(6)

Опубликована: Май 24, 2025

Язык: Английский

---

Space-time modeling of cascading hazards: Chaining wildfires, rainfall and landslide events through machine learning

CATENA, Год журнала: 2024, Номер 246, С. 108452 - 108452

Опубликована: Окт. 8, 2024

Язык: Английский

---