AUTHOR=Jiang Song , Liu Hongsheng , Lian Minjie , Lu Caiwu , Zhang Sai , Li Jinyuan , Li PengCheng 

TITLE=Rock slope displacement prediction based on multi-source information fusion and SSA-DELM model

JOURNAL=Frontiers in Environmental Science

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/environmental-science/articles/10.3389/fenvs.2022.982069

DOI=10.3389/fenvs.2022.982069

ISSN=2296-665X

ABSTRACT=Aiming at the utilization of multi-source heterogeneous data information cross fusion in the application of complex rock slope collapse, landslide, and other engineering disaster analysis, monitoring, and forecasting, the research proposes a new method combining variable selection, sparrow search algorithm, and deep extreme learning machine.A displacement prediction method based on a fusion of multi-source heterogeneous monitoring data for rock slopes. This method uses Pearson correlation analysis and grey correlation analysis to screen the influencing factor variables that affect landslide deformation and uses the filtered influencing factor variables as the input variables of DELM model to avoid the influence of random input weights and random thresholds of DELM model. SSA algorithm optimizes the parameters of the model, obtains the optimal parameter combination of the model, and further improves the prediction accuracy of the fusion model. The model is verified by using the landslide data of a Cement Mine in Fengxiang District, Baoji City, Shaanxi Province. The results show that the data fusion algorithm based on variable selection and SSA-DELM are suitable for landslide displacement prediction of multi-source heterogeneous monitoring data. Compared with the traditional machine learning methods SVM, ELM and DELM, this model has higher prediction accuracy.