基于PSR-WSVM模型的边坡位移预测

为建立高精度的边坡位移预测模型，采用相空间重构（PSR）将边坡位移时间序列数据转换为多维数据，同时构造小波核函数改进的支持向量机模型，建立PSR-WSVM模型并应用于边坡位移预测。将PSR-WSVM模型预测结果与传统支持向量机（SVM）模型、小波支持向量机（WSVM）模型和基于相空间重构的支持向量机（PSR-SVM）模型预测结果进行对比，通过平均绝对误差（MAE）、平均绝对误差百分比（MAPE）和均方根误差（RMSE）3个精度评价指标验证PSR-WSVM模型的可行性。工程实例结果表明，PSR-WSVM模型预测结果的3个精度评价指标都优于另外3种模型，边坡位移预测的精度明显提升。     

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.     

P‐wave transmission across fractures with nonlinear deformational behaviour

Stress wave attenuation across fractured rock masses is a great concern of underground structure safety. When the wave amplitude is large, fractures experience nonlinear deformation during the wave propagation. This paper presents a study on normal transmission of P‐wave across parallel fractures with nonlinear deformational behaviour (static Barton–Bandis model). The results show that the magnitude of transmission coefficient is a function of incident wave amplitude, nondimensional fracture spacing and number of fractures. Two important indices of nondimensional fracture spacing are identified, and they divide the area of nondimensional fracture spacing into three parts (individual fracture area, transition area and small spacing area). In the different areas, the magnitude of transmission coefficient has different trends with nondimensional fracture spacing and number of fractures. In addition, the study reveals that under some circumstances, the magnitude of transmission coefficient increases with increasing number of fractures, and is larger than 1. Copyright © 2006 John Wiley & Sons, Ltd.     

Seasonal variations in prey selection by estuarine black-headed gulls (Larus ridibundus)

The number of black-headed gulls (Larus ridibundus) in the Clyde Estuary is large. In summer the average density has reached 1350 gulls km^?2 and in winter 180 gulls km^?2. This paper compares prey selection and feeding efficiency in gulls during summer and winter on tidal flats, and considers how seasonal differences may be adaptations to cope with seasonal changes in prey availability.Gross and net rates of energy intake were highest in summer because gulls captured more of the polychaete N. diversicolor than the amphipod C. volutator. In winter, gulls selected for C. volutator and therefore an energetically less profitable diet. Throughout the year gulls selected more C. volutator relative to N. diversicolor than expected on energetic grounds and so apparently did not maximize potential net rate of energy intake.Gulls used three techniques to capture prey and made most intensive use of the ‘crouch’ technique. Crouching gulls attained a much higher net rate of energy intake than ‘upright’ or ‘paddling’ gulls.A log-linear model showed that (a) season, water depth and gull density determined feeding technique and (b) feeding technique and season independently determined foraging success and prey selection. Thus gull density and water depth acted on prey selection through imposed variations in feeding technique.Reasons for gulls selecting energetically unprofitable C. volutator and for the use of several distinct feeding techniques are discussed.     

Generalized strain probing of constitutive models

Advanced material constitutive models are used to describe complex soil behaviour. These models are often used in the solution of boundary value problems under general loading conditions. Users and developers of constitutive models need to methodically investigate the represented soil response under a wide range of loading conditions. This paper presents a systematic procedure for probing constitutive models. A general incremental strain probe, 6D hyperspherical strain probe (HSP), is introduced to examine rate‐independent model response under all possible strain loading conditions. Two special cases of HSP, the true triaxial strain probe (TTSP) and the plane‐strain strain probe (PSSP), are used to generate 3‐D objects that represent model stress response to probing. The TTSP, PSSP and general HSP procedures are demonstrated using elasto‐plastic models. The objects resulting from the probing procedure readily highlight important model characteristics including anisotropy, yielding, hardening, softening and failure. The PSSP procedure is applied to a Neural Network (NN) based constitutive model. It shows that this probing is especially useful in understanding NN constitutive models, which do not contain explicit functions for yield surface, hardening, or anisotropy. Copyright © 2004 John Wiley & Sons, Ltd.     

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.     

A micromechanical finite element model for linear and damage‐coupled viscoelastic behaviour of asphalt mixture

This study presents a finite element (FE) micromechanical modelling approach for the simulation of linear and damage‐coupled viscoelastic behaviour of asphalt mixture. Asphalt mixture is a composite material of graded aggregates bound with mastic (asphalt and fine aggregates). The microstructural model of asphalt mixture incorporates an equivalent lattice network structure whereby intergranular load transfer is simulated through an effective asphalt mastic zone. The finite element model integrates the ABAQUS user material subroutine with continuum elements for the effective asphalt mastic and rigid body elements for each aggregate. A unified approach is proposed using Schapery non‐linear viscoelastic model for the rate‐independent and rate‐dependent damage behaviour. A finite element incremental algorithm with a recursive relationship for three‐dimensional (3D) linear and damage‐coupled viscoelastic behaviour is developed. This algorithm is used in a 3D user‐defined material model for the asphalt mastic to predict global linear and damage‐coupled viscoelastic behaviour of asphalt mixture. For linear viscoelastic study, the creep stiffnesses of mastic and asphalt mixture at different temperatures are measured in laboratory. A regression‐fitting method is employed to calibrate generalized Maxwell models with Prony series and generate master stiffness curves for mastic and asphalt mixture. A computational model is developed with image analysis of sectioned surface of a test specimen. The viscoelastic prediction of mixture creep stiffness with the calibrated mastic material parameters is compared with mixture master stiffness curve over a reduced time period. In regard to damage‐coupled viscoelastic behaviour, cyclic loading responses of linear and rate‐independent damage‐coupled viscoelastic materials are compared. Effects of particular microstructure parameters on the rate‐independent damage‐coupled viscoelastic behaviour are also investigated with finite element simulations of asphalt numerical samples. Further study describes loading rate effects on the asphalt viscoelastic properties and rate‐dependent damage behaviour. Copyright © 2006 John Wiley & Sons, Ltd.     

基于AGA的SVM需水预测模型研究

需水预测是一个由城市人口、工业水平、社会经济水平共同作用的多因素、多层次的复杂非线性系统.其结果将直接影响受区域水资源承载力约束的产业结构、布局形态等决策.作为一种集中参数预报方法,支持向量机方法具有对未来样本的较好的泛化性能,对于这类资料缺乏、系统结构尚欠清晰的问题可以取得较好的模拟和预测结果.基于此,本文将支持向量机方法引入需水预测领域,建立了需水预测支持向量机模型.同时,本文将加速遗传算法和支持向量机方法耦合起来,构造了支持向量机模型参数的自适应优化算法.模型在珠海市的应用实例表明:与简单遗传算法比较,AGA的模型参数寻优效率更高;与BP神经网络模型相比,SVM模型较好地解决了小样本、经验性等问题,并取得了较高的预测精度.