Prediction of local scour around circular piles under waves using a novel artificial intelligence approach

Abstract

The scour phenomena around vertical piles in oceans and under waves may influence the structure stability. Therefore, accurately predicting the scour depth is an important task in the design of piles. Empirical approaches often do not provide the required accuracy compared with data mining methods for modeling such complex processes. The main objective of this study is to develop three data-driven methods, locally weighted linear regression (LWLR), support vector machine (SVR), and multivariate linear regression (MLR) to predict the scour depth around vertical piles due to waves in a sand bed. It is the first effort to develop the LWLR to predict scour depth around vertical piles. The models simulate the scour depth mainly based on Shields parameter, pile Reynolds number, grain Reynolds number, Keulegan–Carpenter number, and sediment number. 111 laboratory datasets, derived from several experimental studies, were used for the modeling. The results indicated that the LWLR provided highly accurate predictions of the scour depths around piles (R?=?0.939 and RMSE = 0.075). Overall, this study demonstrated that the LWLR can be used as a valuable tool to predict the wave-induced scour around piles.     

平原河网区域来水组成原理

对于一般树状分布河网，上一级河道总是汇入至下一级河道，位于河道下游断面的流量总是由其上游汇集而至。但对于平原河网地区，特别是人工控制建筑物众多，又受潮汐影响的地区(如太湖流域)，河网错综复杂，水流方向不定，要跟踪某个断面的水流去向，或某个河段的水体、断面流量是从哪里汇集而来的，非常困难。但这样的问题在生产实践中往往对其很感兴趣。例如从常熟枢纽引长江水流进入望虞河后，流向何处?河网各断面流量中或各河段水体中常熟枢纽引江水量占多少比重?对这些问题的研究可以估计常熟枢纽引江的效果和影响范围。因此，平原河网区域来水组成方法在生产实践中具有重要意义。重点介绍了平原河网区域来水组成原理及其在太湖流域的应用。     

显式完全平方守恒差分格式在近岸海流数值模拟中的应用

用显式完全平方守恒差分格式及其改进分解算法对南海月平均流和海面起伏进行了数值模拟，与隐式完全平方守恒差分格式相比，计算时间可省３—５倍，具有良好的时间效益，而且，其计算效果不比隐式完全平方守恒差分格式差。因此，显式完全平方守恒差分格式及其改进分解算法具有良好的实用价值。     

A critical analysis of processes governing the nutrient profiles in the ocean

We have theoretically considered the problem of interpretation of nutrient profiles in the upper ocean (100–2000m). We compare the experimental depth profiles of nonconservative tracers, both stable and radioactive, with solutions of one-dimensional steady state transport equations of increasing complexity including situations not encountered in the real oceans. Apart from gaining insight into the nutrient transport processes, this analysis is useful in offering a way to obtain operational estimates of depth dependent/independent eddy diffusivity and dissolution fluxes in the ocean. These parameters are essential for estimating new production, total production and burial of carbon in the sediments.     

城市小型河流水动力弥散和潜流交换过程

为研究城市小型河流中污染物的物理迁移过程规律,分析基流条件下流动水体与暂态存储区之间的滞留交互作用,采用溴化锂(LiBr)作为保守性示踪剂进行野外现场示踪试验,结合一维溶质运移存储模型(One-dimensional Transport with Inflow and Storage model, OTIS)定量解析潜流交换特性,估算纵向弥散系数(D)、潜流交换面积(A_s)、主河道断面面积(A)和潜流交换系数(α).模型度量指标D_aI值和均方根误差值结果表征参数模拟结果可靠性高,拟合效果理想.由泵入点O至下游1 300 m设置的A、B、C、D 4处监测点的模拟结果表明,水文参数D、A_s、A和α均随水文条件而变,OB河段(0~600 m)潜流交换能力较弱,主要以对流弥散过程为主;BD河段(600~1 300 m)具有较强的暂态存储能力,对溶质的滞留时间长;BC(600~1 000 m)和CD(1 000~1 300 m)河段交换系数分别为(3.42×10-6±0.65×10-6)s-1和(2.87×10-6±0.81×10-6 )s-1;河段BC存在2.2×10-5m3/(s·m)的侧向补给流量.4个河段对比发现,城市河流渠道化、河床沉积物贫瘠等特征导致潜流交换能力弱化.     

Binary Evolution Compared to Observed Algols

We present a grid of evolutionary tracks of 240 binaries with a B-type primary at birth and initial mass ratios: 0.4, 0.6 and 0.9. Conservative calculations are done for cases A and A/B RLOF. For pure RLOF B, conservative and liberal evolutionary sequences have both been computed. In order to compare statistically our computations with the observed distributions of orbital periods and mass ratios of Algols, we enlightened the Algol appearance in every evolutionary sequence. Conservative RLOF reproduces the observed distribution of orbital periods well, but it underestimates the observed mass ratios in the range q ε [0.4–1].     

面向分类的高光谱影像局部线性嵌入算法研究

局部线性嵌入算法(LLE)能很好保存数据点的局部性质,因此有很好的数据可视化效果,但它不是一种很好的面向分类的特征提取方法。因为它存在样本外点学习能力差和忽略了样本类别信息的缺点。对此,本文提出一种分类型局部线性嵌入算法。所提方法通过计算重构误差来判定样本类别,并引进平移向量和缩放因子对距离修正,显著提高类别可分性。在对高光谱影像进行分类的试验中验证了该方法的有效性。     

长时效的正压原始方程能量完全守恒(拟)谱模式

遵循误差反演补偿新计算原理,对正压原始方程传统气象全球拟谱模式方案进行了改造,构造了正压原始方程能量完全守恒全球拟增模式新计算方案,解决了正压原始方程的（非线性）计算稳定性问题和能量守恒整体性质保持问题,改进了相应正压原始方程传统气象全球拟谱模式方案的计算效能。新方案的数值试验表明：在计算实践上,新方案在解决能量守恒问题的同时,可解决（非线性）计算稳定性问题,并在一定条件下可解决非线性计算收敛性问题。进一步的比较数值试验还表明：在计算实践上,新方案具有在提高相应传统气象方案的计算精度,减少其计算量的同时,延长其计算时效,解决其中一类特定“气候漂移”问题方面的效用。本工作原理也适用于斜压原始方程情形。     

A Positivity-preserving Conservative Semi-Lagrangian Multi-moment Global Transport Model on the Cubed Sphere

A positivity-preserving conservative semi-Lagrangian transport model by multi-moment finite volume method has been developed on the cubed-sphere grid. Two kinds of moments(i.e., point values(PV moment) at cell interfaces and volume integrated average(VIA moment) value) are defined within a single cell. The PV moment is updated by a conventional semi-Lagrangian method, while the VIA moment is cast by the flux form formulation to assure the exact numerical conservation. Different from the spatial approximation used in the CSL2(conservative semi-Lagrangian scheme with second order polynomial function) scheme, a monotonic rational function which can effectively remove non-physical oscillations is reconstructed within a single cell by the PV moments and VIA moment. To achieve exactly positive-definite preserving, two kinds of corrections are made on the original conservative semi-Lagrangian with rational function(CSLR)scheme. The resulting scheme is inherently conservative, non-negative, and allows a Courant number larger than one.Moreover, the spatial reconstruction can be performed within a single cell, which is very efficient and economical for practical implementation. In addition, a dimension-splitting approach coupled with multi-moment finite volume scheme is adopted on cubed-sphere geometry, which benefitsthe implementation of the 1 D CSLR solver with large Courant number.The proposed model is evaluated by several widely used benchmark tests on cubed-sphere geometry. Numerical results show that the proposed transport model can effectively remove nonphysical oscillations and preserve the numerical nonnegativity, and it has the potential to transport the tracers accurately in a real atmospheric model.     

视觉皮层振荡神经网络在遥感影像分割中的应用

对于具有复杂场景的遥感影像,提出了基于各向异性扩散特征保持平滑的简化LEGION算法,弥补传统LEGION图像分割算法对噪声敏感的不足。对于多（高）光谱影像,则采用马氏距离计算光谱向量间的连接权得到扩展LEGION算法进行分割。实验结果表明,LEGION算法较传统的图像分割方法对单波段灰度遥感影像目标及其重要细节部分的分割效果更显著;扩展LEGION算法适用于多光谱遥感影像分割。