一种多神经网络加权组合的滑坡位移组合预测模型

A Combined Prediction Model of Landslide Displacement with Weighted Combination of Multiple Neural Networks

ES评分 0

DOI 10.14075/j.jgg.2025.03.086
刊名
Journal of Geodesy and Geodynamics
年,卷(期) 2026, 46(2)
作者
作者单位

1 长安大学地质工程与测绘学院, 西安, 710054;
2 西部矿产资源与地质工程教育部重点实验室, 西安, 710054

摘要
结合支持向量回归(SVR)、反向传播神经网络(BPNN)和线性回归神经网络(LRNN)三种机器学习模型, 构建一种多神经网络加权组合的滑坡位移组合预测模型。该组合模型构建过程主要由单一模型预测和多神经网络加权两部分组成, 模型并不着重于当前预测点之前所有历史时刻的预测误差, 而更关注当前预测点的邻近时段, 根据实测数据利用最小二乘法计算赋予当前预测点最优的单一类预测模型的权重系数, 再基于此权重系数对单一类预测模型当前预测点的预测结果进行加权求和, 最终获得高精度预测结果。通过对我国典型黄土滑坡域甘肃黑方台党川滑坡体北斗/GNSS实测数据对比测试表明, 相较于单一类型预测模型、简单平均组合预测模型及多神经网络切换预测模型, 本文组合预测模型具有更高的预测精度, 具有较好的推广应用价值。
Abstract
A multi-neural-network weighted ensemble model for landslide displacement prediction is constructed by integrating three machine learning models: support vector regression (SVR), back propagation neural network (BPNN), and linear regression neural network (LRNN). The model development process primarily consists of two components: individual model prediction and multi-neural-network weighting. Instead of emphasizing prediction errors from all historical moments preceding the current prediction point, this ensemble model focuses on the proximity period around the current prediction point. Optimal weight coefficients for individual prediction models are calculated using the least squares method based on observed data, followed by weighted summation of predictions from individual models at the current point using these weights, ultimately achieving high-precision forecasting results. Comparative tests conducted on Beidou/GNSS monitoring data from the Dangchuan landslide mass at Heifangtai in Gansu province—a typical loess landslide area in China—demonstrate that this proposed ensemble model exhibits superior prediction accuracy compared to single-model approaches, simple averaging ensemble models, and multi-neural-network switching models. The proposed methodology shows significant potential for practical applications in landslide displacement prediction.
关键词
滑坡; 位移预测; 神经网络; 最小二乘; 加权组合
KeyWord
landslide; displacement prediction; neural network; least squares; weighted summation
基金项目
页码 139-147
  • 参考文献
  • 相关文献
  • 引用本文

瞿伟, 杜易泽, 徐荣堂, 李久元, 边子策. 一种多神经网络加权组合的滑坡位移组合预测模型 [J]. 大地测量与地球动力学. 2026; 46; (2). 139 - 147.

  • 文献评论

相关学者

相关机构