基于改进麻雀搜索算法-核极限学习机耦合算法的滑坡位移预测模型

传统的位移预测模型需要大量数据作为原始训练样本，一定程度上限制了预测模型的应用。为在有限的位移监测数据下进一步提高预测精度，针对金沙江沿岸某长期变形的滑坡体，采用麻雀搜索算法(sparrow search algorithm, SSA),结合核极限学习机算法(kernel-based extreme learning machine, KELM)算法，对滑坡的位移变化提出一种新的多变量位移预测方法，并与传统的支持向量机(support vector machine, SVM)进行对比，结果显示改进的SSA-KELM耦合滑坡预测模型比SVM模型预测精度更高，对金沙江沿岸地区的滑坡具有良好的位移预测效果。

A novel model for landslide displacement prediction using improved SSA-KELM algorithm

A large amount of data as original training samples is required for the traditional displacement prediction model, which limits the application of the prediction model to a certain extent. In order to further improve the prediction accuracy under the limited displacement monitoring data, a new multivariable displacement prediction method for landslide displacement is proposed in this paper, which combines the Sparrow Search Algorithm(SSA) with the Kernel-based Extreme Learning Machine(KELM), aiming at a long-term deformation landslide around the Jinsha river. Compared with the traditional Support Vector Machine (SVM), the results show that the novel model has higher prediction accuracy. It has a good prediction effect for landslide displacement along Jinsha River.