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.     

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.     

The Role of Aga Khan Rural Support Programme in Rural Development in the Karakorum, Hindu Kush ＆ Himalayan Region： Examples from the Northern Mountainous Belt of Pakistan

Pakistan is predominantly a mountainous country where rural development activities are characterised by inconsistency, politically motivated short-term projects without proper feedback. Since the inception of the country, the top-down approach has been followed, and the same development plans that were formulated for the plain areas have been extended to the mountains without any modification. In doing so, neither the participation of the local communities was cared for, nor the mountain specificities were considered in the planning process. Moreover, the representation of the local inhabitants was improper and contradictory to the facts. This biased approach has been one of the main causes for the failure of development projects carried out by different agencies of the Government. Contrary to the perception of the state authorities, the mountain communities proved to be more open to accept new approaches and demonstrated the capacity and capability of being a dependable development partner. In this paper, a detailed account of the Aga Khan Rural Support Programme （AKRSP） has been presented to assess and evaluate the approach followed by this non-governmental organisation （NGO）, and the response of the local inhabitants as collaborators in the development process. The achievements of the AKRSP from project planning, implementation and monitoring can be adopted as a model for rural development not only in the plains, but also in the mountainous areas of the developing countries in the world.     

Geometric Derivation of the Delaunay Variables and Geometric Phases

We derive the classical Delaunay variables by finding a suitable symmetry action of the three torus T³ on the phase space of the Kepler problem, computing its associated momentum map and using the geometry associated with this structure. A central feature in this derivation is the identification of the mean anomaly as the angle variable for a symplectic S ¹ action on the union of the non-degenerate elliptic Kepler orbits. This approach is geometrically more natural than traditional ones such as directly solving Hamilton–Jacobi equations, or employing the Lagrange bracket. As an application of the new derivation, we give a singularity free treatment of the averaged J ₂-dynamics (the effect of the bulge of the Earth) in the Cartesian coordinates by making use of the fact that the averaged J ₂-Hamiltonian is a collective Hamiltonian of the T³ momentum map. We also use this geometric structure to identify the drifts in satellite orbits due to the J ₂ effect as geometric phases.     

Spatial Variability of Rock Depth in Bangalore Using Geostatistical, Neural Network and Support Vector Machine Models

Geospatial technology is increasing in demand for many applications in geosciences. Spatial variability of the bed/hard rock is vital for many applications in geotechnical and earthquake engineering problems such as design of deep foundations, site amplification, ground response studies, liquefaction, microzonation etc. In this paper, reduced level of rock at Bangalore, India is arrived from the 652 boreholes data in the area covering 220 km². In the context of prediction of reduced level of rock in the subsurface of Bangalore and to study the spatial variability of the rock depth, Geostatistical model based on Ordinary Kriging technique, Artificial Neural Network (ANN) and Support Vector Machine (SVM) models have been developed. In Ordinary Kriging, the knowledge of the semi-variogram of the reduced level of rock from 652 points in Bangalore is used to predict the reduced level of rock at any point in the subsurface of the Bangalore, where field measurements are not available. A new type of cross-validation analysis developed proves the robustness of the Ordinary Kriging model. ANN model based on multi layer perceptrons (MLPs) that are trained with Levenberg–Marquardt backpropagation algorithm has been adopted to train the model with 90% of the data available. The SVM is a novel type of learning machine based on statistical learning theory, uses regression technique by introducing loss function has been used to predict the reduced level of rock from a large set of data. In this study, a comparative study of three numerical models to predict reduced level of rock has been presented and discussed.     

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.     

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.     

增氧机自动控制电路

介绍作者自行设计、研制的控制增氧机运行时间的自动控制电路及其原理．该电路采用ＣＭＯＳ集成芯片，结构简单、工作可靠，价格低，业经试验证实：各项性能指标均符合要求．     

Outer wave number spectrum and statistical distribution of apparent wave number vector

Based on the ray theory and Longuet-Higgins’s linear model of sea waves, the joint distribution of wave envelope and apparent wave number vector is established. From the joint distribution, we define a new concept, namely the outer wave number spectrum, to describe the outer characteristics of ocean waves. The analytical form of the outer wave number spectrum, the probability distributions of the apparent wave number vector and its components are then derived. The outer wave number spectrum is compared with the inner wave number spectrum for the average status of wind-wave development corresponding to a peakness factor P = 3. Discussions on the similarity and difference between the outer wave number spectrum and inner one are also presented in the paper.     

基于光谱和纹理的SVM矿化蚀变信息提取研究

针对传统矿化信息提取方法单一,利用光谱或纹理、信息量相对较少、需要大量样本的缺陷,利用基于光谱和纹理的支持向量机(SVM)原理,建立矿化信息提取模型.选择青海泽库县析界日地区作为典型研究区.首先提取研究区光谱和纹理信息,选取训练样本;然后求解最优超平面,进而确定决策函数;最后泛化推广识别其他待识别的样本.通过所提取的遥感蚀变异常信息与重砂异常点叠加分析,叠加基本吻合;从野外实地验证来看,均发现了不同程度的矿化现象,并指出了5个重点异常区.