Mapping of earthquake hotspot and coldspot zones for identifying potential landslide hotspot areas in the Himalayan region

Bulletin of Engineering Geology and the Environment, Год журнала: 2022, Номер 81(7)

Опубликована: Июнь 4, 2022

Язык: Английский

---

Application of Bagging, Boosting and Stacking Ensemble and EasyEnsemble Methods for Landslide Susceptibility Mapping in the Three Gorges Reservoir Area of China

International Journal of Environmental Research and Public Health, Год журнала: 2023, Номер 20(6), С. 4977 - 4977

Опубликована: Март 11, 2023

Since the impoundment of Three Gorges Reservoir area in 2003, potential risks geological disasters reservoir have increased significantly, among which hidden dangers landslides are particularly prominent. To reduce casualties and damage, efficient precise landslide susceptibility evaluation methods important. Multiple ensemble models been used to evaluate upper part Badong County landslides. In this study, EasyEnsemble technology was solve imbalance between nonlandslide sample data. The extracted factors were input into three bagging, boosting, stacking for training, mapping (LSM) drawn. According importance analysis, important affecting occurrence altitude, terrain surface texture (TST), distance residences, rivers land use. influences different grid sizes on results compared, a larger found lead overfitting prediction results. Therefore, 30 m selected as unit. accuracy, under curve (AUC), recall rate, test set precision, kappa coefficient multi-grained cascade forest (gcForest) model with method 0.958, 0.991, 0.965, 0.946, 0.91, respectively, significantly better than values produced by other models.

Язык: Английский

---

Survey: Rainfall Prediction Precipitation, Review of Statistical Methods

WSEAS TRANSACTIONS ON SYSTEMS, Год журнала: 2024, Номер 23, С. 47 - 59

Опубликована: Янв. 8, 2024

Rainfall precipitation prediction is the process of using various models and data sources to predict amount timing precipitation, such as rain or snow, in a particular location. This an important because it can help us prepare for severe weather events, floods, droughts, hurricanes, well plan our daily activities. Processing rainfall typically involves several steps, which may vary depending on specific set research question. Here general overview steps involved: (1) Collecting data: be collected methods, including gauges, radar, satellite imagery. The obtained from public sources, government agencies institutions. (2) Quality control: Before data, it's check errors inconsistencies. involve identifying missing incomplete outliers, inconsistencies measurement units. control performed manually automated software. (3) Pre-processing: Once has been quality controlled, need pre-processed analysis. aggregating temporal spatial resolution, daily, monthly, annual averages, converting format. (4) Analysis: processed used types analysis, trend frequency These analyses identify patterns, changes, relationships data. (5) Visualization: Finally, results analysis visualized graphs, maps, other visualizations communicate findings. Overall, processing requires careful attention detail clear understanding question sources.

Язык: Английский

---

Landslide susceptibility modeling in a complex mountainous region of Sikkim Himalaya using new hybrid data mining approach

Geocarto International, Год журнала: 2021, Номер 37(25), С. 9021 - 9046

Опубликована: Ноя. 24, 2021

Landslide is recognized as one of the greatest threats in complex mountainous regions Sikkim Himalaya. Therefore, landslide susceptibility modeling (LSMs) has become an ideal tool for managing disasters. Keeping this fact view, researchers always try to develop optimal models better performance LSMs. Thus, present research study proposed a novel ensemble approach Alternating Decision Tree (ADTree) and Quantum-Particle Swamp Optimization (QPSO) algorithm stand-alone ADTree, QPSO Random Forest LSMs Rangpo River Basin, India. A total 342 historical datasets with 14 appropriate causative factors were used The robustness was appraised via receiver operating characteristics others statistical indices. Results indicated that QPSO-ADTree model outperformed other models. Overall, can be applied promising precise several globe.

Язык: Английский

---

Application of novel deep boosting framework-based earthquake induced landslide hazards prediction approach in Sikkim Himalaya

Geocarto International, Год журнала: 2022, Номер 37(26), С. 12509 - 12535

Опубликована: Апрель 20, 2022

A major earthquake (6.9 Moment magnitude) occurred in the Sikkim and Darjeeling areas of Indian Himalaya as well adjacent Nepal on 18th September 2011, triggering a large number landslides. total 188 landslide locations were extracted order to create inventory map (LIM). The earthquake-induced susceptibility maps (LSMs) created using an Artificial Neural Network (ANN) model three novel deep learning approaches (DLAs), namely Deep Boosting (DB), Learning (DLNN), Tree (DLT), training points 22 conditioning factors. LSMs validated several statistical indices results showed optimal accuracy for all models, where DB yielding highest prediction rate curve (PRC) 98.5%. This is followed by DLT (97%), DLNN (96%), ANN (91%). demonstrate maximum efficacy proposed LSM.

Язык: Английский

---