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.     

Application of micropolar plasticity to post failure analysis in geomechanics

A micropolar elastoplastic model for soils is formulated and a series of finite element analyses are employed to demonstrate the use of a micropolar continuum in overcoming the numerical difficulties encountered in application of finite element method in standard Cauchy–Boltzmann continuum. Three examples of failure analysis involving a deep excavation, shallow foundation, and a retaining wall are presented. In all these cases, it is observed that the length scale introduced in the polar continuum regularizes the incremental boundary value problem and allows the numerical simulation to be continued until a clear collapse mechanism is achieved. The issue of grain size effect is also discussed. Copyright © 2004 John Wiley & Sons, Ltd.     

An explicit representation of steady state response of a beam on an elastic foundation to moving harmonic line loads

A closed‐form deflection response of a beam rest is presented in this paper using the integral transform method. The theory of linear partial differential equations is used to represent the deflection of beam subjected to a moving harmonic line load in integration form. The solution is finally carried out using the inverse Fourier transform. To evaluate the integration analytically, poles of the integrand are identified with the help of algebraic equation theory. Residue theorem is then utilized to represent the integration as a contour integral in the complex plane. Closed‐form deflections and numerical results are provided for different combinations of load frequency and velocity. Copyright © 2002 John Wiley & Sons, Ltd.     

THE CHARACTERISTIC OF MARINE ENVIRONMENT IN LINGDINGYANG ESTUARY

1 HYDROLOGIC FEATURES Lingdingyang Estuary, located at the middle south of Guangdong Province, is a bell-shaped estuary with a north-south direction. Its area is about 2100km2. The north of Qi′ao Island and Inner-Lingding Island, and the south of Humen are grouped as Neilingdingyang Estuary, having an area of 1041km2. Affected by topography, runoff and tide, its dynamic condition is very complicated. Different water areas have different hydrologic features. The topography under …     

基于统一强度理论的地基临界荷载公式

基于统一强度理论,按照临界荷载公式的推导方法,得到地基临界荷载的统一解公式。Mohr-Coulomb强度理论计算的结果为其特例。把计算结果与《建筑地基基础设计规范》中的结果进行了对比分析,认为当不同程度地考虑中间主应力σ2的影响时,可以有效地发挥地基的强度潜能。并通过实例计算了统一强度理论参数b取不同值时地基承载力特征值,并进行了对比分析。     

REVIEWS OF GEOGRAPHIC SOFTWARE

Reviews of geographic software in this article: DEMO-GRAPHICS: WORLD POPULATIONS AND PROJECTIONS. ESP GAUSS. CEMODEL S. Damus LIMDEP. William H. Greene MICROSTAT 4.1 OTIS PCIPS. (Personal Computer Image Processing System) . H.J. Meyers and R. Bernstein. REGRESSION ANALYSIS OF TIME SERIES (RATS) SPSS/PC+ URBAN DATA MANAGEMENT SOFTWARE (UDMS)     

The influence of macrophyte growth,typical of eutrophic conditions,on river flow velocities and turbulence production

The influence of emergent and submerged macrophytes on flow velocity and turbulence production is demonstrated in a 140 m reach of the River Blackwater in Farnborough, Hampshire, UK. Macrophyte growth occurs in patches and is dominated by Sparganium erectum and Sparganium emersum. In May 2001, patches of S. erectum were already established and occupied 18% of the channel area. The flow adjusted to these (predominantly lateral) patches by being channelled through a narrower cross‐section. The measured velocity profiles showed a logarithmic form, with deviations attributable to topographic control. The channel bed was the main source of turbulence. In September 2001, in‐stream macrophytes occupied 27% of the channel, and overhanging bank vegetation affected 32% of the area. Overall flow resistance, described by Manning's n, showed a threefold increase that could be attributed to the growth of S. emersum in the middle of the channel. Velocity profiles showed different characteristic forms depending on their position relative to plant stems and leaves. The overall velocity field had a three‐dimensional structure. Turbulence intensities were generally higher and turbulence profiles tended to mirror the velocity profiles. Evidence for the generation of coherent eddies was provided by ratios of the root mean square velocities. Spectral analysis identified deviations from the Kolmogorov ?5/3 power law and provided statistical evidence for a spectral short‐cut, indicative of additional turbulence production. This was most marked for the submerged vegetation and, in some instances, the overhanging bank vegetation. The long strap‐like leaves of S. emersum being aligned approximately parallel to the flow and the highly variable velocity field created by the patch arrangement of macrophytes suggest that the dominant mechanism for turbulence production is vortex shedding along shear zones. Wake production around individual stems of S. emersum close to the bed may also be important locally. Copyright © 2006 John Wiley & Sons, Ltd.     

Application of stress release models to historical earthquakes from North China

Univariate and multivariate stress release models are fitted to historical earthquake data from North China. It is shown that a better fit is obtained by treating separately the Eastern part of the region, including the North China Plain and Bohai Sea, and the Western part of the region, including the Ordos Plateau and its Eastern boundary. Further improvement is obtained by fitting the large events (M7.6) and smaller events in the Western region by different stress release models. The comparisons are made by computing the likelihoods of the fitted models and discounting the number of parameters used by Akaike's AIC criterion. The models are used to develop long-term risk scenarios for the East and West regions.     

1990年12月14日台湾强震的预报判据

本文运用福建省沿海气象要素的异常变化,作台湾省的中、短期地震预报,取得了成功的效果。采用长乐历年各月14时最低气压的距平值,作台湾省未来4～7个月内出现强震的预报依据,并采用热异常进行短临跟踪。当秋冬季节连续4d 长乐、福州、台北的气温均比广州累计高出10℃时,预报未来1～5d 台湾省出现7级强震。又根据近百年来台湾发生的强震,统计其活动季节,得到近20年来7级地震发生的时间,绝大部分在9～12月。     

Rain-Flow and Reverse Rain-Flow Counting Method for the Compilation of Fatigue Load Spectrum

The rain-flow counting method is widely used to compile the fatigue load spectrum. The second stage counting of the rain-flow method is a troublesome process. In order to overcome this drawback, the rain-flow and reverse rain-flow counting method is proposed in this paper. In this counting method, the rule for counting of the rain-flow method is modified, so that the sequence of load-time need not be adjusted. This is a valid and useful method to count cycles and compile the load spectrum and it can be widely used in ocean engineering.