
Geoscience Frontiers, Год журнала: 2024, Номер unknown, С. 101999 - 101999
Опубликована: Дек. 1, 2024
Язык: Английский
Geoscience Frontiers, Год журнала: 2024, Номер unknown, С. 101999 - 101999
Опубликована: Дек. 1, 2024
Язык: Английский
Geological Journal, Год журнала: 2025, Номер 60(5), С. 1184 - 1201
Опубликована: Фев. 19, 2025
ABSTRACT Creating accurate and effective Landslide Susceptibility (LS) maps can aid disaster prevention mitigation efforts provide sufficient public safety. The primary aim of this study is to develop an LS map for the Garo Hills region in Meghalaya, India, using weight evidence (WoE), frequency ratio (FR), Shannon entropy (SE) methods. A comprehensive landslide inventory catalogued 98 events from 2000 2023 analysis, nine key geographical environmental parameters were prepared. Conducted multicollinearity correlation analysis identify mitigate collinearity issues between factors. model's performance was analysed through area under curve (AUC) value receiver operating characteristic (ROC) curves three recent landslides. results showed that FR method achieved highest accuracy, with successive rate (SRC) AUC predictive (PRC) values 0.860 0.940, respectively, classified susceptibility at sites as high, moderate, low. WoE effectively identified landslides site high very zones, achieving SRC PRC 0.844 0.915, respectively. SE robust predicting landslide‐prone areas, comparable other methods (0.913), though its (0.771) lower. Developed revealed zones account approximately 10% 3% area, predominantly near roads, steep slopes, higher elevations. information valuable civilians government authorities involved hazard monitoring management.
Язык: Английский
Процитировано
1Journal of Rock Mechanics and Geotechnical Engineering, Год журнала: 2024, Номер unknown
Опубликована: Сен. 1, 2024
Язык: Английский
Процитировано
8Geoscience Frontiers, Год журнала: 2025, Номер unknown, С. 102081 - 102081
Опубликована: Май 1, 2025
Язык: Английский
Процитировано
0Ecological Indicators, Год журнала: 2024, Номер 170, С. 113002 - 113002
Опубликована: Дек. 17, 2024
Язык: Английский
Процитировано
3Sustainability, Год журнала: 2025, Номер 17(8), С. 3291 - 3291
Опубликована: Апрель 8, 2025
With global population growth and accelerated technological innovation, human activities have expanded, leading to worsening ecological degradation more frequent disasters, particularly in vulnerable underdeveloped mountainous areas. Western Sichuan, predominantly consisting of cities, has unique geographical conditions that not only hinder socioeconomic development but also create an environment conducive disaster occurrence. This study, therefore, investigates the resilience cities western Sichuan. Using support vector machine (SVM), this study predicts geo-disaster risks. Shapley values from cooperative game theory are employed optimize three evaluation methods, TOPSIS, Grey Relational Analysis (GRA), Rank Sum Ratio (RSR), calculate social values. Finally, determined by integrating risk with resilience. Kernel density estimation GeoDetector then used analyze The findings reveal (1) is generally improving, a gradual decrease number low resilience, though overall level remains low; (2) disparities among evident, showing “east-high, west-low” distribution, primarily due eastern region’s proximity developed it received; (3) proliferation information technology tourism key drivers development, while exacerbate risks; (4) enhancement dependent on interaction multiple driving factors than any single factor. aligned United Nations Sustainable Development Goals (SDG3, SDG4, SDG8, SDG9, SDG11, SDG15), offers recommendations for provides theoretical policy formulation cities.
Язык: Английский
Процитировано
0Algorithms, Год журнала: 2025, Номер 18(5), С. 258 - 258
Опубликована: Апрель 29, 2025
Landslides are hazardous events that occur mainly in mountainous areas and cause substantial losses of various kinds worldwide; therefore, it is important to investigate them. In this study, a specific Machine Learning (ML) method was further analyzed due the good results obtained previous stage research. The algorithm implemented Extreme Gradient Boosting (XGBoost), which used evaluate susceptibility landslides recorded city Cuenca (Ecuador) its surroundings, generating respective Landslide Susceptibility Maps (LSM). For model implementation, landslide inventory updated 2019 several sets from 15 available conditioning factors were considered, applying two different methods random point sampling. Additionally, hyperparameter tuning process XGBoost has been employed order optimize predictive computational performance each model. validated using AUC-ROC, F-Score degree coincidence adjustment at high very levels, showing capacity most cases. best with set six previously determined, as produced values validation metrics (AUC = 0.83; 0.73) levels above 90%. Wilcoxon text led establishing significant differences between methods. These show need perform analyses data determine appropriate ones.
Язык: Английский
Процитировано
0International Journal of Digital Earth, Год журнала: 2024, Номер 17(1)
Опубликована: Окт. 1, 2024
Язык: Английский
Процитировано
2Advances in Space Research, Год журнала: 2024, Номер 74(11), С. 5489 - 5513
Опубликована: Авг. 22, 2024
Язык: Английский
Процитировано
1Earth Science Informatics, Год журнала: 2024, Номер unknown
Опубликована: Авг. 31, 2024
Язык: Английский
Процитировано
1Earth Science Informatics, Год журнала: 2024, Номер 18(1)
Опубликована: Дек. 26, 2024
Язык: Английский
Процитировано
1