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.     

一种基于特征信息的车牌识别方法

根据中国车辆牌照本身的现有特征信息,提出一种车牌识别方法.采用全局动态阈值法进行二值化处理图像,牌照定位算法简单迅速,字符分割参考垂直投影间隔和字符的纵横比.实验结果表明,这种方法具有良好的环境适应性和鲁棒性.     

Porphyroblast inclusion-trail orientation data: eppure non son girate*!

Extensive examination of large numbers of spatially orientated thin sections of orientated samples from orogens of all ages around the world has demonstrated that porphyroblasts do not rotate relative to geographical coordinates during highly non-coaxial ductile deformation of the matrix subsequent to their growth. This has been demonstrated for all tectonic environments so far investigated. The work also has provided new insights and data on metamorphic, structural and tectonic processes including: (1) the intimate control of deformation partitioning on metamorphic reactions; (2) solutions to the lack of correlation between lineations that indicate the direction of movement within thrusts and shear zones, and relative plate motion; and (3) a possible technique for determining the direction of relative plate motion that caused orogenesis in ancient orogens.     

Anthropogenic trace metals in an ice core at Vestfonna,Svalbard, Norway

1　IntroductionAnicecoreobtainedfrom polarglaciersoricesheetsisoneofthemostimportantarchivestoreconstructpaleoclimaticandpaleoatmosphericcondition .Informationonpale o environmentcanbeextractedfromicecoresaschemicaland/orphysicalsignals.Amongthechemicalsignals,heavymetalsarenotedassignalsofterrestrialenvironmentalchangeandanthropogenicpollution (e.g .Murozumietal.1 969;NgandPatterson 1 981 ;Hongetal.1 994) .SinceconcentrationsofmostofthemetalsinpolarsnowincentralGreen landareatorbelowthepptl…     

The Latest Research Progress on El Nino

Cold water in the deep Pacific can be drawn up to the surface (or west warm water drifts eastwards ) because strong tide increases the mixing of seawater both in vertical and horizontal. In this way greenhouse effect is decreased or increased by means of absorbing (or releasing) CO2. Therefore, La Nina cold event (or El Nino warm event) may occur,which is caused by wanning - up or cooling - down air above the ocean. Volcanic action at sea bottom is also controlled by strong tide.     

青海省沙柳河南区有色金属矿成矿物质来源及矿床成矿模式探讨

本文简述了沙柳河南区有色金属矿床的基本特征。通过对成矿热液及成矿物质的来源与性质的研究,认为该矿床的成因类型为火山沉积—接触交代改造叠加型,进而探讨了该矿床的成矿模式。     

Ab initio infra-red spectra of iron-polycyclic aromatic hydrocarbon compounds: a model case

C₁₀H₆-Fe⁺ complexes were observed by Fourier transform mass spectrometry by Marty et al. (Chem. Phys. Lett. 256 (1996) 669). In this article, we present the infra-red (IR) spectra of the two isomers calculated by ab initio methods of quantum chemistry. In the past, the same approach has predicted successfully unexpected features of the IR spectra of polycyclic aromatic hydrocarbon (PAH) cations which were confirmed by measurements in matrices (J. Phys. Chem. 98 (1994) 9187). The C₁₀H₆-Fe⁺ systems are models for larger PAHs-Fe⁺ complexes, which are believed to play a key rôle in space chemistry.     

Accumulation of Zn,Cu and Cd by crabs and barnacles

The crab Carcinus maenas (L.) and the barnacle Elminius modestus Darwin were exposed to a range of dissolved concentrations of Zn, Cu and Cd for 21 days in artificial seawater. Accumulation of Zn and Cu by crabs has been interpreted in terms of the presence of a regulation mechanism to maintain constant body concentrations (83·2 ± 19·4 μg Zn g^?1 dry wt.; 39·8 ± 9·8 μg Cu g^?1 dry wt.) under varying external dissolved metal levels, until a threshold dissolved metal concentration (c. 400 μg Zn l^?1; c. 170 μg Cu l^?1) beyond which net accumulation of metal begins. Cadium appears to be accumulated by C. maenas at all exposures with no evidence for regulation of body cadmium concentrations. Exposure of E. modestus to Zn, Cu or Cd caused net accumulation of the respective metal in the bodies of the barnacles, with no evidence for regulation of body metal concentrations.