康孟羽, 朱月琴, 陈晨, 邵葆蓉, 王涛. 2022: 基于多元非线性回归和BP神经网络的滑坡滑动距离预测模型研究. 地质通报, 41(12): 2281-2289. DOI: 10.12097/j.issn.1671-2552.2022.12.017
    引用本文: 康孟羽, 朱月琴, 陈晨, 邵葆蓉, 王涛. 2022: 基于多元非线性回归和BP神经网络的滑坡滑动距离预测模型研究. 地质通报, 41(12): 2281-2289. DOI: 10.12097/j.issn.1671-2552.2022.12.017
    KANG Mengyu, ZHU Yueqin, CHEN Chen, SHAO Baorong, WANG Tao. 2022: Research on landslide sliding distance prediction model based on multiple nonlinear regression and BP neural network. Geological Bulletin of China, 41(12): 2281-2289. DOI: 10.12097/j.issn.1671-2552.2022.12.017
    Citation: KANG Mengyu, ZHU Yueqin, CHEN Chen, SHAO Baorong, WANG Tao. 2022: Research on landslide sliding distance prediction model based on multiple nonlinear regression and BP neural network. Geological Bulletin of China, 41(12): 2281-2289. DOI: 10.12097/j.issn.1671-2552.2022.12.017

    基于多元非线性回归和BP神经网络的滑坡滑动距离预测模型研究

    Research on landslide sliding distance prediction model based on multiple nonlinear regression and BP neural network

    • 摘要: 滑坡灾害严重威胁着人类的生命财产安全, 对土地资源造成了一定影响。滑坡滑动距离直接表明了滑坡的冲击、堆积范围大小, 是估算滑坡受灾面积、评估滑坡潜在风险的重要参数, 也是滑坡防灾减灾工作中需要重点关注的指标。为了更准确高效地预测滑坡危害范围, 分别采用多元非线性回归和BP神经网络2种模型对影响滑坡滑动距离的因子进行了评估和建模, 并对天水地区的滑坡实例进行研究。研究结果表明, 2种模型均可用于滑坡滑动距离的预测。相较而言, BP神经网络的预测结果与实际情况有更高的拟合度, 准确性更高。

       

      Abstract: Landslide disasters seriously threaten the safety of human life and property and have a certain impact on land resources. The landslide sliding distance directly indicates the impact and accumulation range size of landslides, which is an important parameter for estimating the affected area of landslides and assessing the potential risk of landslides and is also an indicator that needs to be focused on in landslide prevention and mitigation work. In order to predict the landslide hazard range more accurately and efficiently, this paper uses the theories of multivariate nonlinear regression and BP neural network to estimate the sliding distance of the landslide, respectively. And to study examples of landslides in the Tianshui region, the results show that both models can be used to predict landslide. Compared with the actual results, the BP neural network has a higher degree of fit and accuracy.

       

    /

    返回文章
    返回