Study and verification on an improved comprehensive prediction model of landslide displacement

Bulletin of Engineering Geology and the Environment, Journal Year: 2024, Volume and Issue: 83(3)

Published: Feb. 29, 2024

Language: Английский

---

Application of machine learning in the assessment of landslide susceptibility: A case study of mountainous eastern Mediterranean region, Syria

Journal of King Saud University - Science, Journal Year: 2024, Volume and Issue: 36(5), P. 103174 - 103174

Published: March 20, 2024

Landslide is a considerable geomorphological risk in terrain systems worldwide. Advanced techniques present unique tool for predicting landslide susceptibility with unbiased and precise outputs. However, the application of this to analyze eastern Mediterranean landscape still not sufficiently understood. This study aimed assess implementation three machine learning (ML) algorithms, i.e., support vector (SVM), random forest (RF) extreme gradient boost (XGBoost), mapping mountainous area western Syria. In regard, 200 events were inventoried from historical data, aerial images conducted fieldworks. Sixteen triggering factors selected according literature geographical features (Monsoon period). The receiver operating characteristic (ROC) outcomes revealed that RF achieved better performance an under curve (AUC) 0.96, pursued by XGBoost SVM AUC 0.94 0.90, respectively. assessment presents essential understanding effective ML region Mediterranean. We emphasized, hence, algorithm has most robust prediction Moreover, outputs will provide local decision-makers insights produce regional management strategies landslide, especially after Syrian war phase.

Language: Английский

---

Sustainable Monitoring of Mining Activities: Decision-Making Model Using Spectral Indexes

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(2), P. 388 - 388

Published: Jan. 18, 2024

In response to the escalating demand for mineral resources and imperative sustainable management of natural assets, development effective methods monitoring mining excavations is essential. This study presents an innovative decision-making model that employs a suite spectral indices activities. The integration Combinational Build-up Index (CBI) with additional such as BRBA BAEI, alongside multitemporal analysis, enhances detection differentiation areas, ensuring greater stability reliability results, particularly when applied single datasets from Sentinel-2 satellite. research indicates average accuracy excavation (overall accuracy, OA) all test fields data approximately 72–74%, varying method employed. Utilizing CBI index often results in significant overestimation producer’s (PA) over user’s (UA), by about 10–14%. Conversely, introduction set three complementary achieves balance between PA UA, discrepancies 1–3%, narrows range result variations across different datasets. Furthermore, underscores limitations employing threshold values suggests adoption dedicated monthly thresholds diminish variability. These findings could have considerable implications advancement autonomous largely automated systems surveillance illegal excavations, providing predictable reliable methodology remote sensing applications environmental monitoring.

Language: Английский

---

Quantifying uncertainty in landslide susceptibility mapping due to sampling randomness

International Journal of Disaster Risk Reduction, Journal Year: 2024, Volume and Issue: 114, P. 104966 - 104966

Published: Nov. 1, 2024

Language: Английский

---

Displacement Prediction Method for Bank Landslide Based on SSA-VMD and LSTM Model

Mathematics, Journal Year: 2024, Volume and Issue: 12(7), P. 1001 - 1001

Published: March 27, 2024

Landslide displacement prediction is of great significance for the prevention and early warning slope hazards. In order to enhance extraction landslide historical monitoring signals, a method proposed based on decomposition data before prediction. Firstly, idea temporal addition, sparrow search algorithm (SSA) coupled with variational modal (VMD) used decompose total into trend item, periodic item random item; then, values subitems are fitted by using long short-term memory (LSTM) neural network, predicted cumulative obtained adding up three subsequences. Finally, measured Shuping taken as an example. Considering effects seasonal rainfall reservoir water level rise fall, this predicted, results other traditional models compared. The show that model SSA-VMD LSTM can predict more accurately capture characteristics which be reference

Language: Английский

---

Innovative approach for experimental investigation and monitoring and warning of the evolutionary patterns of dam body failure in earth dams

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 24, 2025

Language: Английский

---

Regression Model Selection for Life Expectancy Prediction: A Comparative Analysis of Imputation Techniques

Published: Feb. 21, 2024

This study carried out a comparative analysis of the mean, median, and mode imputations for NULL values in dataset. We used five different pre-processing techniques to create three distinct regression models, including tree-based models like decision trees random forests, as well linear support vector regression. allows us draw conclusions. The main objective this is compare these findings arrive at reasons behind output imputation techniques. model selection helps explain results. Using various qualitative measures, proposed method were tested verified lifetime prediction efficiency performance showed that forest achieved accuracy highest being 96.8%. These results emphasize importance forests comparison alternative methods innovatively life expectancy estimation.

Language: Английский

---

Research on the Application of Dynamic Process Correlation Based on Radar Data in Mine Slope Sliding Early Warning

Sensors, Journal Year: 2024, Volume and Issue: 24(15), P. 4976 - 4976

Published: July 31, 2024

With the gradual expansion of mining scale in open-pit coal mines, slope safety problems are increasingly diversified and complicated. In order to reduce potential loss caused by sliding major threat life property residents area, this study selected two areas Xinjiang as cases focused on relationship between phase noise deformation. The predicts specific time point analyzing dynamic history correlation tangent angle two. Firstly, series data micro-variation monitoring radar used obtain small deformation area differential InSAR (D-InSAR), is extracted from echo sequence data. Then, volume body calculated at each point, standard deviation accordingly. Finally, predicted combining ratio noise. results show that maximum rates bodies studied reach 10.1 mm/h 6.65 mm/h, respectively, volumes 2,619,521.74 mm

Language: Английский

---

A New Method for Landslide Failure-Time Prediction Based on Bayesian Optimized Saito Model and Machine Learning

Published: Jan. 1, 2024

The graphic method of Saito model based on monitoring curve landslide displacement is widely employed to predict the failure-time. setting calculation parameters are main influential factors prediction results, which mainly related geometric characteristics curve. However, in engineering practice, continuously implemented with data updated, and thus geometry will change time. Correspondingly, Optimal Calculation Parameters (OCPS) be changed, poses a great challenge that traditionally determined through manual analysis. Hence, considering dynamic background, Bayesian first proposed obtain OCPS different periods this study, where variation explored. Subsequently, four machine learning (ML) methods used learn explored OCPS, then predicted real-time curve, so as determine In comprehensive failure database compiled illustrate detail. verification results indicate optimized can produce precise values ML have satisfactory performance predicting determining Herein, XGBoost best among various models lowest value mean absolute error percentage

Language: Английский

---

Internal Stress Evolution in Thrust-Type Soil Landslides: Insights from Indoor Model Testing and Numerical Simulation

Geotechnical and Geological Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 12, 2024

Language: Английский

---