Scholarlink

<p>To tackle the difficulties of the point prediction in quantifying the reliability of landslide displacement prediction, a data-driven combination-interval prediction method (CIPM) based on copula and variational-mode-decomposition associated with kernel-based-extreme-learning-machine optimized by the whale optimization algorithm (VMD-WOA-KELM) is proposed in this paper. Firstly, the displacement is decomposed by VMD to three IMF components and a residual component of different fluctuation characteristics. The key impact factors of each IMF component are selected according to Copula model, and the corresponding WOA-KELM is established to conduct point prediction. Subsequently, the parametric method (PM) and non-parametric method (NPM) are used to estimate the prediction error probability density distribution (PDF) of each component, whose prediction interval (PI) under the 95% confidence level is also obtained. By means of the differential evolution algorithm (DE), a weighted combination model based on the PIs is built to construct the combination-interval (CI). Finally, the CIs of each component are added to generate the total PI. A comparative case study shows that the CIPM performs better in constructing landslide displacement PI with high performance.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Data-Driven Combination-Interval Prediction for Landslide Displacement Based on Copula and VMD-WOA-KELM Method

  • 期刊论文

  • 发表日期：

    2025年2月5日

查看全文
  • Longqi Li,
  • Yunhuang Yang,
  • Tianzhi Zhou,
  • Mengyun Wang

摘要

To tackle the difficulties of the point prediction in quantifying the reliability of landslide displacement prediction, a data-driven combination-interval prediction method (CIPM) based on copula and variational-mode-decomposition associated with kernel-based-extreme-learning-machine optimized by the whale optimization algorithm (VMD-WOA-KELM) is proposed in this paper. Firstly, the displacement is decomposed by VMD to three IMF components and a residual component of different fluctuation characteristics. The key impact factors of each IMF component are selected according to Copula model, and the corresponding WOA-KELM is established to conduct point prediction. Subsequently, the parametric method (PM) and non-parametric method (NPM) are used to estimate the prediction error probability density distribution (PDF) of each component, whose prediction interval (PI) under the 95% confidence level is also obtained. By means of the differential evolution algorithm (DE), a weighted combination model based on the PIs is built to construct the combination-interval (CI). Finally, the CIs of each component are added to generate the total PI. A comparative case study shows that the CIPM performs better in constructing landslide displacement PI with high performance.