Machine learning for pore-water pressure time-series prediction: Application of recurrent neural networks

Knowledge of pore-water pressure(PWP)variation is fundamental for slope stability.A precise prediction of PWP is difficult due to complex physical mechanisms and in situ natural variability.To explore the applicability and advantages of recurrent neural networks(RNNs)on PWP prediction,three variants of RNNs,i.e.,standard RNN,long short-term memory(LSTM)and gated recurrent unit(GRU)are adopted and compared with a traditional static artificial neural network(ANN),i.e.,multi-layer perceptron(MLP).Measurements of rainfall and PWP of representative piezometers from a fully instrumented natural slope in Hong Kong are used to establish the prediction models.The coefficient of determination(R^2)and root mean square error(RMSE)are used for model evaluations.The influence of input time series length on the model performance is investigated.The results reveal that MLP can provide acceptable performance but is not robust.The uncertainty bounds of RMSE of the MLP model range from 0.24 kPa to 1.12 k Pa for the selected two piezometers.The standard RNN can perform better but the robustness is slightly affected when there are significant time lags between PWP changes and rainfall.The GRU and LSTM models can provide more precise and robust predictions than the standard RNN.The effects of the hidden layer structure and the dropout technique are investigated.The single-layer GRU is accurate enough for PWP prediction,whereas a double-layer GRU brings extra time cost with little accuracy improvement.The dropout technique is essential to overfitting prevention and improvement of accuracy.     

多层城市冠层模式的建立及数值试验研究

为在城市气象数值模拟中更好地体现由城市发展引起的下垫面土地利用改变及人为活动对大气过程的影响,建立了基于建筑物三维分布的多层城市冠层模式,冠层内动力方程组考虑了建筑物冠层拖曳力的作用及雷诺应力的影响,通过引入建筑物宽度、间距以及垂直分布密度指数等建筑物形态特征参数,以更好地体现城市复杂地表对大气温度、湿度及动量方程的影响.同时,该模式分屋顶、4个侧壤及地面分别考虑辐射及能量平衡求解表面温度,计算各表面与大气的通量交换,并考虑辐射阴影效应、冠层内部各个面之间的可视因子、以及与冠层内建筑物密度指数、可视因子等相关的多重反射辐射导致的辐射截陷作用.模式的离线检验结果表明:(1)冠层模式计算风廓线与风洞实验测量数据吻合良好;(2)离线冠层模式能够模拟实际小区的风速、温度垂直廓线,并能够较好地体现小区内气温日变化.冠层模式与区域边界层模式耦合检验结果表明:(1)耦合模拟的近地面(2 m处)气温及地表温度的结果明显优于传统的水泥平板方案,尤其是在夜间,水泥平板方案与实测气温最大偏差4 K左右,耦合模拟方案为1-2 K;(2)耦合模拟方案考虑了建筑物对冠层之上的拖曳力影响以及建筑物形态结构对雷诺应力的影响,风速(10 m处)计算结果与观测值相差约在1 m/s,水泥平板方案偏差3 m/s左右.     

Evaluation of pile foundation response to lateral spreading

The effects of liquefaction on deep foundations are very damaging and costly, and they keep recurring in many earthquakes. The first part of the paper reviews the field experience of deep foundations affected by liquefaction during earthquakes in the last few decades, as well as the main lessons learned. The second part of the paper presents results of physical modeling of deep foundations in the presence of liquefaction conducted by the authors and others at the 100g-ton RPI centrifuge. In the last decade centrifuge modeling has been identified as a key tool to identify and quantify mechanisms, calibrate analyses and evaluate retrofitting strategies for pile foundations. Results are presented of centrifuge models of instrumented pile foundations subjected to lateral spreading, including single pile and pile groups, 2- and 3-layer soil profiles, mass and stiffening elements above ground to incorporate the effect of the superstructure, and evaluation of proposed retrofitting strategies. Interpretations of these centrifuge experiments and their relation to field observations and soil properties.     

Wave run-up on a fixed surface-piercing square column using multi-layer barrier

Steep or breaking waves may produce critical run-ups on a surface-piercing column, as represented by an unexpectedly high uprush, which has the potential of generating damaging localised wave-in-deck loads. Hence, to improve the air gap performance of offshore column-stabilised platforms, this paper proposes the mounting of an innovative multi-layer barrier on the column surface at a certain distance below the lower deck. Experiments were performed using a truncated square column to examine the performances of different versions of the barrier, namely, solid-plate, porous-plate, and intermittent-plate types, under four different focused waves. All the barrier types were found to obstruct and deflect uprush flow under storm conditions. However, the solid-plate type tended to experience considerable wave forces, with its impermeability also rendering the higher layers ineffective. The intermittent-plate type dissipated the uprush flow and decreased the wave impact, although it exhibited relatively strong flow disengaging, which decreased the efficiency under large wave run-ups. Conversely, the porous-plate type exhibited adequate performance, with a larger plate porosity and moderately high mounting elevation tending to improve the uprush obstruction performance and further decrease the wave slamming loads. A barrier with an appropriately designed plate porosity, number of layers, and mount elevation is expected to perform efficiently under severe sea states, providing protection for the lower deck against extreme wave run-ups.     

CPR雷达探测北半球夏季多层云系结构统计特征分析

利用2007~2010年北半球夏季（6~8月）CloudSat卫星搭载的云廓线雷达（Cloud Profile Radar,CPR）探测结果对0°~60°N区域单层、双层和三层云系的水平分布、垂直结构特征及各云层云类组成、云水路径等物理量分布进行分析。云量的统计结果表明CPR探测的单层、双层和三层云系的云量分别为36.63%、8.26%和1.40%,云量的水平分布表明其高值区主要位于对流旺盛区域,且高值区的云层云顶高、厚度大,而低值区则多位于副热带高压区域。对不同云类的出现频率统计分析结果表明,单层云系中各云类的出现频率相近;多层云系的上层以卷云为主,下层以层积云为主。对比海陆差异发现洋面卷云和层积云的出现频率显著高于陆面,但高层云和高积云的出现频率低于陆面。云水路径分析表明,单层云系的冰水路径和液水路径均最大,而在多层云系中云层越高、厚度越大、冰水路径越大,液水路径则随着云层的降低增大。     

Analytical modeling of one-dimensional diffusion in layered systems with position-dependent diffusion coefficients

Diffusion in stratified porous media is common in the natural environment. The objective of this study is to develop analytical solutions for describing the diffusion in layered porous media with a position-dependent diffusion coefficient within each layer. The orthogonal expansion technique was used to solve a one-dimensional multi-layer diffusion equation in which the diffusion coefficient is expressed as a segmented linear function of positions in the porous media. The behavior of the solutions is illustrated using several examples of a three-layer system, with constant diffusion coefficient α₁ in layer 1 (0 < x < l₁), α₃ in layer 3(l₂ < x < l₃), and a linearly position-dependent diffusion coefficient α₁(1 + Δ(x − l₁)/(l₂ − l₁)) in the center layer (Δ = α₃/α₁ − 1). Because of the asymmetry of the layered system, the diffusion and related concentration distributions are also asymmetrical. For a given Δ value, the smaller the value of (l₂ − l₁)/l₃, the more significant the accumulation of concentration in the middle transition zone (l₁ < x < l₂), the sharper the change in the concentration profile of spatial distribution. Therefore, transition between two layers has significant effects on diffusion.     

多层等效源曲面磁异常转换方法

在磁异常数据处理中,利用等效源技术重构磁异常场具有较好的稳定性和较高的计算精度,因而被广泛应用.传统方法是采用设置在近地表的单层等效源拟合实测磁异常数据,尽管拟合精度很高,但向上延拓之后往往会出现较大的拟合误差,即可能存在磁异常信号的"泄漏",尤其在原始数据中存在背景场时更容易出现此种误差.本文提出一种多层等效源技术方案,应用分布于不同深度范围内的等效源模拟实测数据,减少了等效源参数设置的盲目性.理论模型试验表明,采用多层等效源方法重构的磁异常及其梯度与分量,较单层等效源方法具有更高精度,可以吸收更完整的实测磁异常信息.论文详细地讨论了如何优化多层等效源设置、等效源参数选择以及计算方法,通过二维和三维理论模型试验,验证了在复杂条件下多层等效源方法的可行性和适应性,并且将该方法应用于广西某地的实测磁异常数据转换之中,取得了较好的应用效果.     

Geospatial scenario based modelling of urban and agricultural intrusions in Ramsar wetland Deepor Beel in Northeast India using a multi-layer perceptron neural network

In recent decades, the world has experienced unprecedented urban growth which endangers the green environment in and around urban areas. In this work, an artificial neural network (ANN) based model is developed to predict future impacts of urban and agricultural expansion on the uplands of Deepor Beel, a Ramsar wetland in the city area of Guwahati, Assam, India, by 2025 and 2035 respectively. Simulations were carried out for three different transition rates as determined from the changes during 2001–2011, namely simple extrapolation, Markov Chain (MC), and system dynamic (SD) modelling, using projected population growth, which were further investigated based on three different zoning policies. The first zoning policy employed no restriction while the second conversion restriction zoning policy restricted urban-agricultural expansion in the Guwahati Municipal Development Authority (GMDA) proposed green belt, extending to a third zoning policy providing wetland restoration in the proposed green belt. The prediction maps were found to be greatly influenced by the transition rates and the allowed transitions from one class to another within each sub-model. The model outputs were compared with GMDA land demand as proposed for 2025 whereby the land demand as produced by MC was found to best match the projected demand. Regarding the conservation of Deepor Beel, the Landscape Development Intensity (LDI) Index revealed that wetland restoration zoning policies may reduce the impact of urban growth on a local scale, but none of the zoning policies was found to minimize the impact on a broader base. The results from this study may assist the planning and reviewing of land use allocation within Guwahati city to secure ecological sustainability of the wetlands.