A typical artificial neural network model-back-propagation model was presented for prediction on the soil liquefaction type based on the physical parameters of soils under earthquake.
本文根据人工神经网络的一典型模型—反向传播模型,以及地震荷载下的各项土的物理—力学参数,建立了土液化类型的神经网络数学模型。
It is feasible to predict soil infiltration capacities by routine physical parameters with stepwise regression models with multiple units.
采用多元逐步回归模型用常规土壤物理参数对土壤水分入渗模型参数进行预报是可行的。
A fitted relationship between the parameters and the soil texture was established, with which the model parameters of soil water retention curves can be predicted by the soil physical characteristic.
采用回归分析方法建立了参数与土壤物理特性间的函数关系,为采用土壤颗粒组成等土壤物理特性确定土壤水分特征曲线提供了指导。
应用推荐