Toward the reliable prediction of reservoir landslide displacement using earthworm optimization algorithm-optimized support vector regression (EOA-SVR)

Liu, Zhiyang; Ma, Junwei; Xia, Ding; Jiang, Sheng; Ren, Zhiyuan; Tan, Chunhai; Lei, Dongze; Guo, Haixiang

doi:10.1007/s11069-023-06322-1

Cited by 21 publications

(4 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al [57] introduced an earthworm optimization algorithm-optimized support vector regression for the accurate prediction of reservoir landslide displacement. The proposed approach underwent evaluation and comparison with various metaheuristics, such as an artificial bee colony, biogeography-based optimization, a genetic algorithm, gray wolf optimization, particle swarm optimization, and a water cycle algorithm, through the Friedman and post hoc Nemenyi tests.…”

Section: Discussionmentioning

confidence: 99%

Modeling the Effects of Climate Change on the Current and Future Potential Distribution of Berberis vulgaris L. with Machine Learning

Sarikaya,

Uzun

2024

Sustainability

View full text Add to dashboard Cite

Species of the Berberis genus, which are widely distributed naturally throughout the world, are cultivated and used for various purposes such as food, medicinal applications, and manufacturing dyes. Model-based machine learning is a language for specifying models, allowing the definition of a model using concise code, and enabling the automatic creation of software that implements the specified model. Maximum entropy (MaxEnt 3.4.1) is an algorithm used to model the appropriate distribution of species across geographical regions and is based on the species distribution model that is frequently also used in modeling the current and future potential distribution areas of plant species. Therefore, this study was conducted to estimate the current and future potential distribution areas of Berberis vulgaris in Türkiye for the periods 2041–2060 and 2081–2100, according to the SSP2 4.5 and SSP5 8.5 scenarios based on the IPSL-CM6A-LR climate change model. For this purpose, the coordinates obtained in the WGS 84 coordinate system were marked using the 5 m high spatial resolution Google Satellite Hybrid base maps, which are readily available in the 3.10.4 QGIS program, the current version of QGIS (Quantum GIS). The CM6A-LR climate model, the latest version of the IPSL climate models, was used to predict the species’ future distribution area. The area showed a high correlation with the points representing B. vulgaris, which is generally distributed in the Mediterranean and the central and eastern Black Sea regions of Türkiye, and the very suitable areas encompassed 45,413.82 km2. However, when the SSP2 4.5 scenario was considered for the period 2041–2060, the areas very suitable for Berberis vulgaris comprised 59,120.05 km2, and in the SSP2 4.5 scenario, very suitable areas were found to encompass 56,730.46 km2 in the 2081–2100 period. Considering the SSP5 8.5 scenario for the period 2041–2060, the area most suitable for the B. vulgaris species is 66,670.39 km2. In the SSP5 8.5 scenario, very suitable areas were found to cover 20,108.29 km2 in the 2081–2100 period. Careful consideration of both the potential positive and negative impacts of climate change is essential, and these should be regarded as opportunities to implement appropriate adaptation strategies. The necessary conditions for the continued existence and sustainability of B. vulgaris—that is, areas with ecological niche potential—have been determined.

show abstract

Section: Discussionmentioning

confidence: 99%

Modeling the Effects of Climate Change on the Current and Future Potential Distribution of Berberis vulgaris L. with Machine Learning

Sarikaya,

Uzun

2024

Sustainability

View full text Add to dashboard Cite

show abstract

“…Numerous studies have shown that changes in reservoir water levels and precipitation are two critical factors influencing the stability of reservoir landslides [8][9][10][11][12][13]. Reservoir water and rainwater infiltrate into the landslide mass through soil and rock layers with different permeability characteristics, weakening the soil and rock mass parameters, altering the seepage field within the landslide, and subsequently affecting the stability of the landslide.…”

Section: Introductionmentioning

confidence: 99%

An Inversion Study of Reservoir Colluvial Landslide Permeability Coefficient by Combining Physical Model and Data-Driven Models

Yue,

Wang,

Wen

2024

Water

View full text Add to dashboard Cite

The saturated permeability coefficient (ks) is a key parameter for evaluating the seepage and stability of reservoir colluvial landslides. However, ks values obtained from traditional experimental methods are often characterized by large variations and low representativeness. As a result, there are significant deviations from actual observations when used in seepage field calculations for reservoir landslide analysis. This study proposes an intelligent inversion method that combines a physical model and a data-driven model for reservoir landslide ks based on actual groundwater level (GWL) monitoring data. This method combines Latin Hypercube Sampling (LHS), unsaturated flow finite element (FE) analysis, particle swarm optimization algorithm (PSO), and kernel extreme learning machine model (KELM). Taking the Hongyanzi landslide in Sichuan Province, China, as the research object, the GWL of the landslide under different ks was first obtained by LHS and transient seepage FE analysis. Then, a nonlinear functional relationship between ks and the landslide GWL was fitted based on the PSO-KELM model. Finally, the optimal landslide ks was obtained by minimizing the root-mean-squared error between the predicted and actual GWL using the PSO. A global sensitivity analysis was also conducted on the ks of different rock and soil layers to reveal their control rules on the calculation of landslide GWL. The research results demonstrate the feasibility of the proposed method and provide valuable information for similar landslides in practice.

show abstract

“…Therefore, incorporating a time series research technique based on deep learning into the prediction of landslide displacement can utilize the temporal correlation between data at different time points, comprehensively understand the evolution mechanism of deformation in landslides, and enhance the accuracy and dependability of forecasts. [22] proposed a reliable prediction of reservoir landslides based on an SVR model that responds to triggering factors. [23] proposed a landslide displacement dynamic prediction model based on singular Spectrum Analysis (SSA) and a stacked Long Short Term memory (SLSTM) network.…”

Section: Introductionmentioning

confidence: 99%

Study on Landslide Displacement Prediction Considering Inducement under Composite Model Optimization

Ye,

Liu,

Xie

et al. 2024

Electronics

View full text Add to dashboard Cite

The precise extraction of displacement time series for complex landslides poses significant challenges, and conventional landslide prediction models often overlook the deformation impacts of displacement triggers. To address this, we introduce a novel composite model tailored for predicting landslide displacement. This model employs Variational Mode Decomposition (VMD) to isolate each displacement component, with optimization achieved through the groupwise coupling algorithm. Subsequently, Grey correlation analysis (GRA) is applied to quantitatively assess the dynamic correlations between various triggering factors and landslide displacement. This analysis informs the construction of a feature set predicated on these correlation factors. Integrating the time-series VMD module into the standard Transformer architecture facilitates the prediction of landslide displacement. This integration allows for the extraction of critical time-evolution features associated with the displacement components. Ultimately, the predicted displacements are aggregated and reconstructed. We validate our model using the Bazimen landslide case study, analyzing displacement monitoring data from 1 January 2007, to 31 December 2012. The values of the root mean square error and the mean absolute percentage error were 1.86 and 4.85, respectively. This model offers a more nuanced understanding of the multifaceted causes and evolutionary dynamics underpinning landslide displacement and deformation, thereby markedly enhancing prediction accuracy.

show abstract

Toward the reliable prediction of reservoir landslide displacement using earthworm optimization algorithm-optimized support vector regression (EOA-SVR)

Cited by 21 publications

References 53 publications

Modeling the Effects of Climate Change on the Current and Future Potential Distribution of Berberis vulgaris L. with Machine Learning

Modeling the Effects of Climate Change on the Current and Future Potential Distribution of Berberis vulgaris L. with Machine Learning

An Inversion Study of Reservoir Colluvial Landslide Permeability Coefficient by Combining Physical Model and Data-Driven Models

Study on Landslide Displacement Prediction Considering Inducement under Composite Model Optimization

Contact Info

Product

Resources

About