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.     

Determination of the regional deformation rates of Shanghai and Kashima VLBI stations based on ITRF97

The vertical deformation rates (VDRs) and horizontal deformation rates (HDRs) of Shanghai VLBI station in China and Kashima and Kashima34 VLBI stations in Japan were re-analysed using the baseline length change rates from Shanghai to 13 global VLBI stations, and from Kashima to 27 stations and from Kashima34 to 12 stations, based on the NASA VLBI global solution glb1123 (Ma, 1999). The velocity vectors of the global VLBI stations were referred to the ITRF97 reference frame, and the Eulerian vectors of different models of plate motion were used for comparative solutions. The VDR of Shanghai station is estimated to be −1.91±0.56 mm/yr, and those of Kashima and Kashima34 stations, −3.72±0.74mm/yr and −8.81±0.84mm/yr, respectively. The difference between the last two was verified by further analysis. Similar estimates were also made for the Kokee, Kauai and MK_VLBA VLBI stations in mid-Pacific.     

利用自回归模型检测地球极移重力效应

同时采用4个台站的国际超导重力仪长期连续重力观测资料和国际地球自转服务中心提供的同步地球自转参数，研究了极移引起的地球重力场变化特征。利用自回归模型估计了各序列的功率谱密度和积谱密度，结果表明极移导致的重力效应的主要能量集中在Chandler摆动和周年项附近，叠积后实际重力观测与极移重力信号理论值之间的差异分别为0．4％和3．9％，说明超导重力仪可有效监测极移导致的重力变化。     

SOME IMPORTANT CHARACTERISTICS OFSURFACE ALBEDO OF CHINA IN RECENT YEARS

Sdsealbedoisdefinedasaratioofreflectivesolarradiationtototalacradiation,whichcanindicatetheaborptionandreflectivecapabilityofthe~hforsolarradiation.Itisan~tfactortoinfluencethes~radiationbalance,espeiallyfortheformationandvariationoflocalndcroclirnate.Generally,theactualdatafromo~tionalstationSforrebationareedintheanalysisofsolacealal.HOwever,therepresentativenessOfthedateisIratedduetothescarcityofobservationalstationandunevendistributionofs~condition.Afterthe1960s,theanalysisfors~ealbedoise…     

A multi‐level parallelized substructuring‐frontal solution for coupled thermo/hydro/mechanical problems in unsaturated soil

This paper proposes a multi‐level parallelized substructuring–frontal combined algorithm for the analysis of the problem of thermo/hydraulic/mechanical behaviour of unsaturated soil. Temperature, displacement, pore water pressure and pore air pressure are treated as the primary variables in a non‐linear analysis. Details are given firstly of the substructuring–frontal combined approach. The incorporation of the algorithm in a multi‐level parallel strategy is then discussed. The parallel processing can thus be carried out at different substructural levels. The method thus developed impacts, in a positive way, on both computer storage requirement and execution time. Copyright © 2003 John Wiley & Sons, Ltd.     

Multistep matched-field inversion for broad-band data from ASIAEX2001

This paper discusses the results of geoacoustic inversion carried out using explosive charge data from the Asian Seas International Acoustic Experiment (ASIAEX) East China Sea (ECS) Experiment. A multifrequency incoherent matched-field inversion processor and a genetic algorithm (GA) are used for the inversion. A multistep matched field inversion approach is presented, which makes use of the varying sensitivities of wave fields at various frequencies to reduce the inversion problem into a sequence of smaller inversions with fewer unknowns to estimate at each stage. Different parameters are estimated using data at different frequencies according to their sensitivities. Inversion results for different areas in the ECS region are summarized and compared with core data.     

四川石棉独立碲矿床蚀变岩的地质地球化学研究

四川石棉大水沟独立碲矿床堪称世界首例，其矿体两侧的围岩蚀变较窄，且蚀变带与矿脉及未蚀变岩呈清楚而截然的接触关系。主要围岩蚀变为白云石化、白（绢）云母化、云英岩化及电气石化等。这些蚀变作用分别发生于１７７．７～１６５．１Ｍａ和９１．７１～８０．１９Ｍａ。蚀变作用过程中ＳｉＯ２大量析出，Ａｌ２Ｏ３、ＴｉＯ２、ＣａＯ、ＭｇＯ、Ｋ２Ｏ、Ｈ２Ｏ、ＣＯ２、Ｆｅ２Ｏ３、ＭｎＯ则有不同程度地带入。与此同时，ＲＥＥ在此过程中包集体迁出，Ｔｅ、Ｂｉ、ＡＳ等元素的含量则决定于蚀变作用及其强度，而与原岩无关。     

Models of CN and C2 comae for comet Tago-Sato-Kosaka and comet bennett

Based on the CN and C₂ comae isophotes for two comets (1961 IX and 1970 16) given by Rahe et al. and the relevant theory of physical chemistry, we have deduced the distributions of the CN and C₂ modecules in the coma, their scale heights and mean lifetimes. The results favour the viewpoint that HCN is the parent of CN, and that C₂H₂ is the parent of C₂.     

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 …