当前位置: X-MOL 学术Front. Struct. Civ. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Dimensionality reduction and prediction of soil consolidation coefficient using random forest coupling with Relief algorithm
Frontiers of Structural and Civil Engineering ( IF 3 ) Pub Date : 2022-03-28 , DOI: 10.1007/s11709-022-0812-6
Hai-Bang Ly , Huong-Lan Thi Vu , Lanh Si Ho , Binh Thai Pham

The consolidation coefficient of soil (Cv) is a crucial parameter used for the design of structures leaned on soft soi. In general, the Cv is determined experimentally in the laboratory. However, the experimental tests are time-consuming as well as expensive. Therefore, researchers tried several ways to determine Cv via other simple soil parameters. In this study, we developed a hybrid model of Random Forest coupling with a Relief algorithm (RF-RL) to predict the Cv of soil. To conduct this study, a database of soil parameters collected from a case study region in Vietnam was used for modeling. The performance of the proposed models was assessed via statistical indicators, namely Coefficient of determination (R2), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). The proposal models were constructed with four sets of soil variables, including 6, 7, 8, and 13 inputs. The results revealed that all models performed well with a high performance (R2 > 0.980). Although the RF-RL model with 13 variables has the highest prediction accuracy (R2 = 0.9869), the difference compared with other models was negligible (i.e., R2 = 0.9824, 0.9850, 0.9825 for the cases with 6, 7, 8 inputs, respectively). Thus, it can be concluded that the hybrid model of RF-RL can be employed to predict Cv based on the basic soil parameters.



中文翻译:

随机森林耦合Relief算法降维及预测土壤固结系数

土体固结系数 ( C v ) 是软土倾斜结构设计中的关键参数。通常,C v是在实验室中通过实验确定的。然而,实验测试既费时又昂贵。因此,研究人员尝试了几种方法来通过其他简单的土壤参数来确定C v 。在这项研究中,我们开发了一个随机森林耦合的混合模型与一个 Relief 算法 (RF-RL) 来预测C v的土壤。为了进行这项研究,使用从越南一个案例研究区域收集的土壤参数数据库进行建模。所提出模型的性能通过统计指标进行评估,即确定系数 ( R 2 )、均方根误差 ( RMSE ) 和平均绝对误差 ( MAE )。建议模型由四组土壤变量构建,包括 6、7、8 和 13 个输入。结果表明,所有模型都表现良好,具有较高的性能(R 2 > 0.980)。尽管具有 13 个变量的 RF-RL 模型具有最高的预测精度(R 2 = 0.9869),但与其他模型相比差异可以忽略不计(即,对于分别有 6、7、8 个输入的情况,R 2 = 0.9824、0.9850、0.9825)。因此,可以得出结论,RF-RL 的混合模型可以用于基于基本土壤参数的C v预测。

更新日期:2022-03-28
down
wechat
bug