Developing constitutive models from EPR‐based self‐learning finite element analysis

A constitutive model that captures the material behavior under a wide range of loading conditions is essential for simulating complex boundary value problems. In recent years, some attempts have been made to develop constitutive models for finite element analysis using self‐learning simulation (SelfSim). Self‐learning simulation is an inverse analysis technique that extracts material behavior from some boundary measurements (eg, load and displacement). In the heart of the self‐learning framework is a neural network which is used to train and develop a constitutive model that represents the material behavior. It is generally known that neural networks suffer from a number of drawbacks. This paper utilizes evolutionary polynomial regression (EPR) in the framework of SelfSim within an automation process which is coded in Matlab environment. EPR is a hybrid data mining technique that uses a combination of a genetic algorithm and the least square method to search for mathematical equations to represent the behavior of a system. Two strategies of material modeling have been considered in the SelfSim‐based finite element analysis. These include a total stress‐strain strategy applied to analysis of a truss structure using synthetic measurement data and an incremental stress‐strain strategy applied to simulation of triaxial tests using experimental data. The results show that effective and accurate constitutive models can be developed from the proposed EPR‐based self‐learning finite element method. The EPR‐based self‐learning FEM can provide accurate predictions to engineering problems. The main advantages of using EPR over neural network are highlighted.     

A machine learning approach for predicting computational intensity and domain decomposition in parallel geoprocessing

ABSTRACT

High performance computing is required for fast geoprocessing of geospatial big data. Using spatial domains to represent computational intensity (CIT) and domain decomposition for parallelism are prominent strategies when designing parallel geoprocessing applications. Traditional domain decomposition is limited in evaluating the computational intensity, which often results in load imbalance and poor parallel performance. From the data science perspective, machine learning from Artificial Intelligence (AI) shows promise for better CIT evaluation. This paper proposes a machine learning approach for predicting computational intensity, followed by an optimized domain decomposition, which divides the spatial domain into balanced subdivisions based on the predicted CIT to achieve better parallel performance. The approach provides a reference framework on how various machine learning methods including feature selection and model training can be used in predicting computational intensity and optimizing parallel geoprocessing against different cases. Some comparative experiments between the approach and traditional methods were performed using the two cases, DEM generation from point clouds and spatial intersection on vector data. The results not only demonstrate the advantage of the approach, but also provide hints on how traditional GIS computation can be improved by the AI machine learning.     

Automatic Determination of Stellar Atmospheric Parameters Using Neural Networks and Instance-Based Machine Learning

In this article we show how machine learning methods can beeffectively applied to the problem of automatically predictingstellar atmospheric parameters from spectral information, a veryimportant problem in stellar astronomy. We apply feedforwardneural networks, Kohonen's self-organizing maps andlocally-weighted regression to predict the stellar atmosphericparameters effective temperature, surface gravity and metallicityfrom spectral indices. Our experimental results show that thethree methods are capable of predicting the parameters with verygood accuracy. Locally weighted regression gives slightly betterresults than the other methods using the original dataset asinput, while self-organizing maps outperform the other methods when significant amounts of noise are added. We also implemented a heterogeneous ensemble of predictors, combining the results given by the three algorithms. This ensemble yields better results than any of the three algorithms alone, using both the original and the noisy data.     

Prediction of Stellar Atmospheric Parameters using Instance-Based Machine Learning and Genetic Algorithms

In this article we present a method for the automated prediction of stellar atmospheric parameters from spectral indices. This method uses a genetic algorithm (GA) for the selection of relevant spectral indices and prototypical stars and predicts their properties, using the k-nearest neighbors method (KNN). We have applied the method to predict the effective temperature, surface gravity, metallicity, luminosity class and spectral class of stars from spectral indices. Our experimental results show that the feature selection performed by the genetic algorithm reduces the running time of KNN up to 92%, and the predictive accuracy error up to 35%. This revised version was published online in July 2006 with corrections to the Cover Date.     

使用水块混合层模式模拟上层海洋的季节变化

使用块体混合层模式对一个固定海洋观测站所测的上层海洋之物理特性进行了模拟，结果发现了难以重复观测到的许多物理特征。文章提出了水块混合层模式，着重模拟了扩展湾流体系（ＥＧＳＳ）中的一个水块，在它被海流从佛罗里达海峡（２４°Ｎ，８０°Ｗ）带到挪威海（６８°Ｎ，１０°Ｅ）的过程中，其物理特性（其中包括温度、盐度、混合层深度和夹卷速度）随时间的变化。模拟结果较好地再现了所观测的物理特性的演化。     

水下智能潜器的神经网络运动控制

本文介绍一种基于神经网络的水下智能潜器的运动控制方法，该方法通过在线学习，融控制与滤波为一体。计算机仿真与水池实验验证表明，该方法的控制与滤波性能良好，对环境的学习与适应能力强。该方法事实上可用于一般动力系统的控制。     

流形上的空间密度聚类算法研究

研究流形上的聚类分析，针对基于密度的空间聚类引入了流形概念，提出1种基于流形的密度聚类算法，该方法将流形的概念与聚类相结合，可以适用于样本为复杂分布的聚类。文中通过实例证明此算法的有效性。     

The shedding of mesoscale anticyclonic eddies from the Alaskan Stream and westward transport of warm water

The south-flowing waters of the Kamchatka and Oyashio Currents and west-flowing waters of the Alaskan Stream are key components of the western sub-Arctic Pacific circulation. We use CTD data, Argo buoys, WOCE surface drifters, and satellite-derived sea-level observations to investigate the structure and interannual changes in this system that arise from interactions among anticyclonic eddies and the mean flow. Variability in the temperature of the upstream Oyashio and Kamchatka Currents is evident by warming in mesothermal layer in 1994–2005 compared to 1990–1991. A major fraction of the water in these currents is derived directly from the Alaskan Stream. The stream also sheds large anticyclonic (Aleutian) eddies, averaging approximately 300 km in diameter with a volume transport significant in comparison with that of the Kamchatka Current itself. These eddies enclose pools of relatively warm and saline water whose temperature is typically 4 °C warmer and salinity is 0.4 greater than that of cold-core Kamchatka eddies in the same density range. Aleutian eddies drift at approximately 1.2 km d⁻¹ and retain their distinctive warm and salty characteristics for at least 2 years. Selected westward pathways during 1990–2004 are identified. If the shorter northern route is followed, Aleutian eddies remain close to the stream and persist sufficiently long to carry warm and saline water directly to the Kamchatka Current. This was observed during 1994–1997 with substantial warming of the waters in the Kamchatka Current and upstream Oyashio. If the eddies take a more southern route they detach from the stream but can still contribute significant quantities of warm and saline water to the upstream Oyashio, as in 2004–2005. However, the eddies following this southern route may dissipate before reaching the western boundary current region.     

Baroclinic Buoyancy-Inertia Joint Stability Parameter

At present, the barotropic buoyant stability parameter has been derived from a vertical virtual displacement of a water parcel. The barotropic inertial stability parameter in the eccentrically cyclogeostrophic, basic current field was derived in 2003 from a horizontal cross-stream virtual displacement of a parcel. By expressing acceleration of a parcel due to a virtual displacement, which is arbitrarily sloping within a vertical section across the basic current, in terms of natural coordinates, we derived the vertical component of baroclinic buoyant stability parameter B ₂ ², the horizontal component of baroclinic inertial stability parameter I ₂ ², the baroclinic joint stability parameter J ², its buoyant component B ² and its inertial component I ². B ² is far greater than I ₂ ², and when neglecting relative vorticity except for vertical shear, a downward convex curve of J ² plotted against the slope of a virtual displacement follows a trend of B ² curve. If a parcel displaces along a horizontal surface or an isopycnal surface, however, B ² vanishes, and J ² becomes equal to I ². Actual parcel is apt to displace not only along the bottom slope, but also along the sea surface and an isopycnal interfacial surface, which is approximately equivalent to an isentropic surface, preferred by lateral mixing and exchange of momentum. Such actual displacement makes B ² vanishing, and grants I ² an important role. The present analysis of I ² examining effects due to curvature and horizontal and vertical shear vorticities are useful in deepening our understanding of baroclinic instability in actual oceanic streams.