Exploring the uncertainty of landslide susceptibility assessment caused by the number of non–landslides

CATENA, Год журнала: 2023, Номер 227, С. 107109 - 107109

Опубликована: Март 28, 2023

Язык: Английский

---

Swarm optimization based heterogeneous machine learning techniques for enhanced landslide susceptibility assessment with comprehensive uncertainty quantification

Earth Science Informatics, Год журнала: 2025, Номер 18(1)

Опубликована: Янв. 1, 2025

Язык: Английский

---

Effect of hydrogeochemical behavior on groundwater resources in Holocene aquifers of moribund Ganges Delta, India: Infusing data-driven algorithms

Environmental Pollution, Год журнала: 2022, Номер 314, С. 120203 - 120203

Опубликована: Сен. 20, 2022

Язык: Английский

---

Novel evolutionary-optimized neural network for predicting landslide susceptibility

Environment Development and Sustainability, Год журнала: 2023, Номер 26(7), С. 17687 - 17719

Опубликована: Май 19, 2023

Язык: Английский

---

Assessment of environmental geological disaster susceptibility under a multimodel comparison to aid in the sustainable development of the regional economy

Environmental Science and Pollution Research, Год журнала: 2022, Номер 30(3), С. 6573 - 6591

Опубликована: Авг. 24, 2022

Язык: Английский

---

Combination four different ensemble algorithms with the generalized linear model (GLM) for predicting forest fire susceptibility

Geomatics Natural Hazards and Risk, Год журнала: 2023, Номер 14(1)

Опубликована: Май 9, 2023

In this study, the generalized linear model (GLM) and four ensemble methods (partial least squares (PLS), boosting, bagging, Bayesian) were applied to predict forest fire hazard in Chalus Rood watershed Mazandaran Province, Iran. Data from 108 historical events collected through field surveys as basis of analysis. About 70% data used for training models, while remaining 30% was testing. A total 14 environmental, climatic, vegetation variables input features models probability. After conducting a multicollinearity test on independent variables, GLM modeling. The efficiency evaluated using receiver operating characteristic (ROC) curve parameters. Results validation process, based area under ROC (AUC), showed that GLM, PLS-GLM, boosted-GLM, Bagging-GLM, Bayesian-GLM had efficiencies 0.79, 0.75, 0.81, 0.84, 0.85, respectively. results indicated all methods, except PLS algorithm, improved performance modeling hazards watershed, with Bayesian algorithm being most efficient method among them.

Язык: Английский

---

GIS-based modeling of landslide susceptibility zonation by integrating the frequency ratio and objective–subjective weighting approach: a case study in a tropical monsoon climate region

Frontiers in Environmental Science, Год журнала: 2023, Номер 11

Опубликована: Май 30, 2023

Accurate detection of landslide spatial patterns is vital in susceptibility, hazard, and risk disaster mapping. Geographic Information System (GIS)-based quantitative approaches provide a rigorous procedure for gaining deep insight into natural anthropogenic landslides from different scales. This study aims to implement comprehensive solution retrieving the susceptibility index. For that purpose, inventory was performed tropical monsoon climate region, with magnitude elevation spanning −65 m 1,900 above sea, considering 15 fundamental causative factors belonging groups topography, hydrology, geology, land cover conditions activities, weather. The frequency ratio (FR) implemented rank subclasses each factor. factor weight estimation, were applied, including subjective-based analytic hierarchy process (AHP), objective-based Shannon entropy (SE), synergy both methods (AHP–SE), built on these two approaches. Out 271 identified locations, 70% (196 points) used training remaining 30% (71 applied validation. results showed integrated AHP–SE outperformed individual approaches, area under receiver operating characteristic curve (AUC) reaching 0.876, following SE (AUC = 0.848) AHP 0.818). In approach, pattern monsoons confirmed as most crucial landslide-predisposing research contributes novel discussion by integrating knowledge-based consultation statistical data analysis accurate geospatial data, incorporating significant explanatory toward reliable landslide-prone zonation over space time dimensions.

Язык: Английский

---

Deep learning approaches for landslide information recognition: Current scenario and opportunities

Journal of Earth System Science, Год журнала: 2024, Номер 133(2)

Опубликована: Апрель 25, 2024

Язык: Английский

---

Landslide susceptibility zonation mapping using geospatial technologies and multi criteria evaluation techniques in the upper Didessa sub-basin, Southwest Ethiopia

Geology Ecology and Landscapes, Год журнала: 2024, Номер unknown, С. 1 - 15

Опубликована: Авг. 28, 2024

Landslides have a profound impact on landscape geology, resulting in extensive devastation and loss of human lives. Mapping landslide susceptibility is crucial for effective land use planning mountainous country like Ethiopia. This study was conducted the upper Didessa sub-basin, southwestern parts Ethiopia using Geographic Information System (GIS) multi criteria evaluation (MCE) technique. employed blend primary data, encompassing field surveys interviews with experts, as well secondary data derived from diverse source, such remote sensing digital soil maps, geological maps. A total eleven critical factors were to assess triggers landslides. These include slope, aspect, drainage density, topographic wetness index (TWI), stream power (SPI), ruggedness (TRI), hypsometric integral, lithology, cover (LULC), texture, distance roads. The analytical hierarchy process (AHP) method used determine significance each indicator through pairwise comparison matrix. area categorized into different zones based landslides, namely very high, moderate, low, low. Results revealed that cultivated had highest likelihood experiencing nine incidents out 25, followed by built-up areas seven Conversely, dense forests, sparse grazing experienced lower Out 11 contributing 24% surveyed region deemed moderate susceptibility, 12% 6% falling categories high respectively. findings this research provide important information policymakers develop efficient measures preventing reducing risks

Язык: Английский

---

Mudslide susceptibility assessment based on a two-channel residual network

Geomatics Natural Hazards and Risk, Год журнала: 2024, Номер 15(1)

Опубликована: Март 1, 2024

In response to the challenges posed by rugged terrain in Yunnan, hindering large-scale mudslide screening efforts, this article introduces a dual-channel Convolutional Neural Network (CNN) constructed using elevation data from historical mudslide-prone valleys (Digital Elevation Model, DEM) and remote sensing imagery. The network is designed facilitate comprehensive assessment of potential hazards gullies, serving as crucial tool for early disaster warning. model initially employs an enhanced residual structure extract fundamental features both types data. Subsequently, it leverages SE module deep separable emphasize importance relevant expedite convergence. Finally, classifies gullies under evaluation based on their similarity where mudslides have previously occurred. Experimental results demonstrate model's robust performance assessing mudflow-prone achieving impressive precision rate up 81.10% recall 82.76%. When applied evaluate hazard across entirety Nujiang Prefecture, predicts that 87.80% locations are at extremely high risk. These findings underscore viability utilizing image-based gully feature analysis levels gullies.

Язык: Английский

---