Increasing irrigation-triggered landslide activity caused by intensive farming in deserts on three continents

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2024, Номер 134, С. 104242 - 104242

Опубликована: Окт. 23, 2024

Язык: Английский

---

Do post-failure landslides become stable?

CATENA, Год журнала: 2025, Номер 249, С. 108699 - 108699

Опубликована: Янв. 5, 2025

---

Integrated Machine Learning Approaches for Landslide Susceptibility Mapping Along the Pakistan–China Karakoram Highway

Land, Год журнала: 2025, Номер 14(1), С. 172 - 172

Опубликована: Янв. 15, 2025

The effectiveness of data-driven landslide susceptibility mapping relies on data integrity and advanced geospatial analysis; however, selecting the most suitable method identifying key regional factors remains a challenging task. To address this, this study assessed performance six machine learning models, including Convolutional Neural Networks (CNNs), Random Forest (RF), Categorical Boosting (CatBoost), their CNN-based hybrid models (CNN+RF CNN+CatBoost), Stacking Ensemble (SE) combining CNN, RF, CatBoost in along Karakoram Highway northern Pakistan. Twelve were examined, categorized into Topography/Geomorphology, Land Cover/Vegetation, Geology, Hydrology, Anthropogenic Influence. A detailed inventory 272 occurrences was compiled to train models. proposed stacking ensemble improve modeling, with achieving an AUC 0.91. Hybrid modeling enhances accuracy, CNN–RF boosting RF’s from 0.85 0.89 CNN–CatBoost increasing CatBoost’s 0.87 0.90. Chi-square (χ2) values (9.8–21.2) p-values (<0.005) confirm statistical significance across This identifies approximately 20.70% area as high very risk, SE model excelling detecting high-risk zones. Key influencing showed slight variations while multicollinearity among variables remained minimal. approach reduces uncertainties, prediction supports decision-makers implementing effective mitigation strategies.

Язык: Английский

---

Landslide susceptibility assessment using information quantity and machine learning integrated models: a case study of Sichuan province, southwestern China

Earth Science Informatics, Год журнала: 2025, Номер 18(2)

Опубликована: Янв. 18, 2025

Язык: Английский

---

A robust index was extracted to assess the prolonged changes in debris flow activity after a high magnitude earthquake

CATENA, Год журнала: 2025, Номер 250, С. 108733 - 108733

Опубликована: Янв. 18, 2025

Язык: Английский

---

A cooperative search algorithm-based flood forecasting framework: application across diverse Chinese catchments

Frontiers in Earth Science, Год журнала: 2025, Номер 13

Опубликована: Фев. 11, 2025

Flood forecasting is crucial for disaster mitigation, particularly in regions prone to flash floods. This study introduces a novel flood framework by coupling the Geomorphological Instantaneous Unit Hydrograph (GIUH) with Xinanjiang model and optimizing parameters using Cooperation Search Algorithm (CSA). Applied across six diverse Chinese catchments, significantly improved computational efficiency accuracy. Key findings demonstrate that: 1) CSA achieved high Nash-Sutcliffe Efficiency (NSE &gt;0.9) only 16 optimization trials on average, outperforming SCE-UA algorithms; 2) The performed exceptionally data-sparse regions, achieving NSE values &gt;0.9 even minimal datasets; 3) Enhanced runoff routing via GIUH enabled accurate simulation of extreme rainfall events. These results highlight framework’s potential operational management globally. Future research will expand validation datasets explore applications varied hydrological climatic conditions.

Язык: Английский

---

Predicting the Dynamic of Debris Flow Based on Viscoplastic Theory and Support Vector Regression

Water, Год журнала: 2025, Номер 17(1), С. 120 - 120

Опубликована: Янв. 4, 2025

The prediction of debris flows is essential for safeguarding infrastructure and minimizing the economic losses associated with hazards. Traditional empirical theoretical models, while providing foundational insights, often struggle to capture complex nonlinear behaviors inherent in flows. This study aims enhance flow by integrating modeling data-driven approaches. We model as a viscoplastic fluid, employing Herschel–Bulkley rheological describe its behavior. By combining kinematic wave lubrication theory, we develop comprehensive framework that encapsulates mechanical physics identifies key governing parameters. Numerical solutions this are utilized generate an extensive training dataset, which subsequently used train support vector regression (SVR) model. SVR targets slide depth velocity upon impact, using explanatory variables including yield stress, material density, source area length, slope length. demonstrates high predictive accuracy, achieving coefficients determination R2 0.956 0.911 at impact. Additionally, relative residuals σ primarily distributed within range −0.05 0.05 both These results indicate proposed hybrid not only incorporates fundamental physical mechanisms but also significantly enhances performance through optimization. underscores critical advantage merging models machine learning techniques, offering robust tool improved risk assessment, can inform development more effective early warning systems mitigation measures.

Язык: Английский

---

Backward erosion piping mechanism in dike foundations with and without landside blanket layers: numerical simulation of size effects

Frontiers in Earth Science, Год журнала: 2025, Номер 12

Опубликована: Янв. 8, 2025

Introduction This study investigates the backward erosion piping mechanism and its dependency on model size through both experiments numerical simulations. The objective is to understand how different dimensions affect hydraulic gradients behavior in dike systems. Methods Numerical simulations were performed using finite element method (FEM), where foundation was modeled 3D seepage flow simulated under various gradients. Physical also conducted small-scale models verify results effects of size. Results Discussion show that dikes without blanket layers, increase steadily as channel develops, leading upstream failure. In contrast, with a layer exhibit stabilizing effect: gradient initially decreases before increasing, self-healing phenomenon halts further progression. reveals effect—indicated by gradients—diminishes larger becomes negligible beyond certain threshold. Additionally, interaction between width depth significantly influences progression piping. These findings offer valuable insights for designing more resilient systems improving flood protection strategies.

Язык: Английский

---

Flash flood simulation based on distributed hydrological model in future scenarios

Frontiers in Earth Science, Год журнала: 2025, Номер 12

Опубликована: Янв. 14, 2025

Extreme rainfall events are frequent, particularly in economically underdeveloped hilly areas, where conventional hydrological models struggle to accurately simulate the formation of flash floods. Therefore, this study focuses on Daxi River Basin Guangdong Province. First, CMIP6 precipitation data is utilized analyze future variations interannual and monthly scales. Compared baseline period, annual increases under all three scenarios. Next, design storms with a return period greater than 2 years allocated into patterns. By combining accumulated soil moisture content, different distributed applied calculate corresponding flood discharges for events. The results indicate that: 1) Precipitation SSP5-8.5 scenario generally higher SSP1-2.6 SSP2-4.5 scenarios, showing mildest increase. 2) peak simulated by CREST model relatively low, at 235.4 m³/s, fewer covered, which significantly lower simulation accuracy CNFF model. 3) has low probability experiencing disasters exceeding 10-year from 2026 2070. above research will provide important references disaster prevention similar basins.

Язык: Английский

---

Increasing landslide deformation and activity in a changing local environment: a case study of Zhouqu County in the Bailong River Basin

Bulletin of Engineering Geology and the Environment, Год журнала: 2025, Номер 84(2)

Опубликована: Фев. 1, 2025

Язык: Английский

---