Landslide Susceptibility Assessment Using the Analytic Hierarchy Process (AHP): A Case Study of a Construction Site for Photovoltaic Power Generation in Yunxian County, Southwest China

Sustainability, Journal Year: 2023, Volume and Issue: 15(6), P. 5281 - 5281

Published: March 16, 2023

China is actively promoting the construction of clean energy to reach its objective achieving carbon neutrality. However, engineering constructions in mountainous regions are susceptible landslide disasters. Therefore, assessment disaster susceptibility indispensable for prevention and risk management projects. In this context, present study involved conducting a field survey at 42 points selected planned site region. According geological geographical conditions region, existing regulation, influencing factors landslides, was performed based on 11 impact factors, namely, slope, slope aspect, curvature, relative relief, NDVI, road, river, fault, lithology, density points, land-use type. Next, their respective influences, these were further divided into subfactors according AHP, weights each factor subfactor calculated. The GIS tools employed linear combination calculation interval division, accordingly, zone map constructed. ROC curve adopted test partition evaluation results, AUC value determined be 0.845, which indicated high accuracy results.

Language: Английский

---

Comparison of natural breaks method and frequency ratio dividing attribute intervals for landslide susceptibility mapping

Bulletin of Engineering Geology and the Environment, Journal Year: 2023, Volume and Issue: 82(10)

Published: Sept. 19, 2023

Language: Английский

---

Analysis of Geological Hazard Susceptibility of Landslides in Muli County Based on Random Forest Algorithm

Sustainability, Journal Year: 2023, Volume and Issue: 15(5), P. 4328 - 4328

Published: Feb. 28, 2023

Landslides seriously threaten human life and property. The rapid accurate prediction of landslide geological hazard susceptibility is the key to disaster prevention mitigation. Traditional evaluation methods have disadvantages in terms factor classification subjective weight determination. Based on this, this paper uses a random forest model built using Python language predict Muli County western Sichuan outputs accuracy. results show that (1) three most important factors are elevation, distance from road, average annual rainfall, sum their weights 67.54%; (2) model’s performance good, with ACC = 99.43%, precision 99.3%, recall 99.48%, F1 99.39%; (3) development zoning basically same. Therefore, can effectively accurately evaluate regional susceptibility. However, there some limitations: information statistical table incomplete; demanding requirements training concentration relating definition non-landslide point sets, range should be delineated according field surveys.

Language: Английский

---

Influences of non-landslide sampling strategies on landslide susceptibility mapping: a case of Tianshui city, Northwest of China

Bulletin of Engineering Geology and the Environment, Journal Year: 2025, Volume and Issue: 84(3)

Published: Feb. 11, 2025

Language: Английский

---

Hybrid machine learning approach for landslide prediction, Uttarakhand, India

Scientific Reports, Journal Year: 2022, Volume and Issue: 12(1)

Published: Nov. 22, 2022

Abstract Natural disasters always have a damaging effect on our way of life. Landslides cause serious damage to both human and natural resources around the world. In this paper, prediction accuracy five hybrid models for landslide occurrence in Uttarkashi, Uttarakhand (India) was evaluated compared. approach, Rough Set theory coupled with different namely Bayesian Network (HBNRS), Backpropagation Neural (HBPNNRS), Bagging (HBRS), XGBoost (HXGBRS), Random Forest (HRFRS) were taken into account. The database development prepared using fifteen conditioning factors that had 373 181 non-landslide locations then randomly divided training testing ratio 75%:25%. appropriateness predictability these assessed multi-collinearity test least absolute shrinkage selection operator approach. accuracy, sensitivity, specificity, precision, F-Measures, area under curve (AUC)-receiver operating characteristics curve, used evaluate compare performance individual created models. findings indicate constructed model HXGBRS (AUC = 0.937, Precision 0.946, F1-score 0.926 Accuracy 89.92%) is most accurate predicting landslides when compared other (HBPNNRS, HBNRS, HBRS, HRFRS). Importantly, fusion performed rough set method, capability each improved. Simultaneously, proposed shows superior stability can effectively avoid overfitting. After core modules developed, user-friendly platform designed as an integrated GIS environment dynamic maps effective large prone areas. Users predict probability selected region by changing values factors. approach could be beneficial impact slopes tracking along national routes.

Language: Английский

---

Influence of anthropogenic activities on landslide susceptibility: A case study in Solan district, Himachal Pradesh, India

Journal of Mountain Science, Journal Year: 2023, Volume and Issue: 20(2), P. 429 - 447

Published: Feb. 1, 2023

Language: Английский

---

Spatial Prediction of Landslide Susceptibility Using Logistic Regression (LR), Functional Trees (FTs), and Random Subspace Functional Trees (RSFTs) for Pengyang County, China

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(20), P. 4952 - 4952

Published: Oct. 13, 2023

Landslides pose significant and serious geological threat disasters worldwide, threatening human lives property; China is particularly susceptible to these disasters. This paper focuses on Pengyang County, which situated in the Ningxia Hui Autonomous Region of China, an area prone landslides. study investigated application machine learning techniques for analyzing landslide susceptibility. To construct validate model, we initially compiled a inventory comprising 972 historical landslides equivalent number non-landslide sites (Data sourced from County Department Natural Resources). ensure impartial evaluation, both datasets were randomly divided into two sets using 70/30 ratio. Next, extracted 15 conditioning factors, including slope angle, elevation, profile curvature, plan aspect, TWI (topographic wetness index), TPI position distance roads rivers, NDVI (normalized difference vegetation rainfall, land use, lithology, SPI (stream power STI (sediment transport spatial database. Subsequently, correlation analysis between factors occurrences was conducted certainty factor (CF) method. Three models established by employing logistic regression (LR), functional trees (FTs), random subspace (RSFTs) algorithms. The susceptibility map categorized five levels: very low, medium, high, high Finally, predictive capability three algorithms assessed under receiver operating characteristic curve (AUC). better prediction, higher AUC value. results indicate that all are practical, with only minor discrepancies accuracy. integrated model (RSFT) displayed highest performance, achieving value 0.844 training dataset 0.837 validation dataset. followed LR (0.811 0.814 dataset) FT (0.776 0.760 dataset). proposed methods resulting can assist researchers local authorities making informed decisions future geohazard prevention mitigation. Furthermore, they will prove valuable be useful other regions similar characteristics features.

Language: Английский

---

Evaluating causative factors for landslide susceptibility along the Imphal-Jiribam railway corridor in the North-Eastern part of India using a GIS-based statistical approach

Environmental Science and Pollution Research, Journal Year: 2023, Volume and Issue: 31(41), P. 53767 - 53784

Published: Aug. 11, 2023

Language: Английский

---

Rule-based fuzzy inference system for landslide susceptibility mapping along national highway 7 in Garhwal Himalayas, India

Quaternary Science Advances, Journal Year: 2023, Volume and Issue: 11, P. 100093 - 100093

Published: June 17, 2023

The Mountainous terrain is experiencing rapid development in a bewildering manner, which makes it more susceptible to landslides. Management and mitigation of landslide hazard begin with its mapping by integrating numerous methods Geographic Information System (GIS) tools. However, difficult produce reliable susceptibility maps (LSM) due their complex nature. Therefore, the present study investigates applicability Mamdani's fuzzy inference system (FIS) LSM Himalayan India. It compared commonly used frequency ratio (FR) information value method (IVM) approaches. Several causative factors were extracted prepare thematic layers, including slope, aspect, curvature, solar radiance, SPI, TWI, rainfall, soil depth NDVI. Landslide inventory was also created using google earth images previously published work. accuracy estimates for FR, IVM FIS performed based on ROC curves. found provide an 77.7%, followed (72%) FR (71%) LSM. current prototype further studies Garhwal Himalayas similar terrains, vigorous techniques theory. outcomes this work propose that expert's knowledge-based can accurate such terrain. Planners concerned authorities use results management mitigation.

Language: Английский

---

Spatial prediction of the geological hazard vulnerability of mountain road network using machine learning algorithms

Geomatics Natural Hazards and Risk, Journal Year: 2023, Volume and Issue: 14(1)

Published: Jan. 25, 2023

The current assessment index of the geological hazard vulnerability for mountain road network is relatively simple, and methods used are subjective, complex, inefficient. This study proposes a prediction model incorporating machine learning algorithms. First, based on quantification characteristics local rescue forces, an objective reasonable index-based system was constructed by combining population, economic, material factors. Second, FAHP AHP-TOPSIS were applied development models to carry out preliminary different types. Third, results as sample set build using SVM, RF, BPNN Finally, five-fold cross-validation statistical parameter accuracy analysis conducted determine most with highest mapping network. indicated that RF algorithm demonstrated robustness.

Language: Английский

---