Huang Lei, Qin Wei, Dai Guo-Liang, Zhu Ming-Xing, Liu Lei-Lei, Huang Ling-Jun, Yang Shan-Pian, Ge Miao-Miao
College of Architecture and Civil Engineering, Sanming University, Sanming, 365004, China.
College of Civil Engineering and Architecture, Wenzhou University, Wenzhou, 325035, China.
Sci Rep. 2024 Oct 19;14(1):24594. doi: 10.1038/s41598-024-75811-5.
Ground settlement prediction for highway subgrades is crucial in related engineering projects. When predicting the ground settlement, sparse sample data are often encountered in practice, which greatly affects the prediction accuracy. However, this has been seldom explored in previous studies. To resolve it, this paper proposes a regression Kriging (RK)-based method for ground settlement prediction with sparse data. Under the framework of RK, the stationarity of sample residual and trend structure are key factors for prediction accuracy. It is found that the use of Box-Cox transformation, which can help to achieve stationarity of sample residual, leads to significant increase of the prediction accuracy with sparse data. Specifically, the various evaluation metrics (i.e., root mean square error (RMSE), mean absolute error (MAE), mean arctangent absolute percent error (MAAPE) and scatter index (SCI)) are significantly decreased when the Box-Cox transformation is incorporated. In addition, the first-order polynomial trend structure is found to be more appropriate than those with higher orders for predicting settlements resulting from primary consolidation. Moreover, comparative study is conducted among the proposed RK method, classical prediction methods and back propagation neural network (BPNN). It is found that the evaluation metrics obtained by the RK method are significantly smaller than those obtained by the other methods, indicating its highest accuracy. By contrast, BPNN has the worst performance among the various methods, because the sparse data are inadequate to establish a satisfactory BPNN model.
公路路基的地面沉降预测在相关工程项目中至关重要。在预测地面沉降时，实际中常常会遇到稀疏样本数据，这极大地影响了预测精度。然而，以往的研究很少对此进行探讨。为了解决这一问题，本文提出了一种基于回归克里金（RK）的稀疏数据地面沉降预测方法。在RK框架下，样本残差的平稳性和趋势结构是影响预测精度的关键因素。研究发现，使用Box-Cox变换有助于实现样本残差的平稳性，能显著提高稀疏数据的预测精度。具体而言，当引入Box-Cox变换时，各种评估指标（即均方根误差（RMSE）、平均绝对误差（MAE）、平均反正切绝对百分比误差（MAAPE）和散射指数（SCI））都显著降低。此外，对于预测主固结引起的沉降，发现一阶多项式趋势结构比高阶趋势结构更合适。此外，还对所提出的RK方法、经典预测方法和反向传播神经网络（BPNN）进行了比较研究。结果发现，RK方法获得的评估指标明显小于其他方法获得的指标，表明其精度最高。相比之下，BPNN在各种方法中性能最差，因为稀疏数据不足以建立一个令人满意的BPNN模型。
