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.     

EFFECTS OF FISH OIL,DHA OIL AND LECITIHIN IN MICROPARTICULATE DIETS ON STRESS TOLERANCE OF LARVAL GILTHEAD SEABREAM（SPARUS AURATA）

The effects of natural fish oil,DHA oil and soybean lecithin in microparticulate diets on stress tolerance of larval gilthead seabream(Sparus aurata)were investigated after 15 days feeding trials.The tolerance of larval gilthead seabream to various stress factors such as exposure to air(lack of dissolved oxygen),changes in water temperature(low)and salinity(high) were determined.This study showed that microparticulate diet with natural fish oil and soybean lecithin was the most effective for in-creasing the tolerance of larval gilthead seabream to various stresses,and that microparticulate diet with natural fish oil and palmitic acid(16:0)was more effective than microparticulate diet with DHA oil and soybean lecithin.     

THE POSITION AND ROLES OF PORTS AND RAILWAYS IN THE EURASIA LAND BRIDGE TRANSPORTATION IN NORTHEAST CHINA

This paper systematically analyzes and proves the favorable factors of utilizing the ports and the railways in Northeast China for the Asia-Europe land bridge transportation. It will be more beneficial to Dalian Port and HaDa (Harbin-Dalian) and Binzhou (Harbin-Manzhouli) railways in Northeast China to the Siberia railway in Russia than 1) to other ports and the corresponding railways in China, 2) to the Nakhodka Port in Russia and the corresponding railways and 3) to the Chongjin Port in North Korea and the corresponding railways. This paper also puts forward the reform measures to adopt the ports and the railways in the northeast region in China for the land bridge transportation and the problems in transportation policies and management systems.     

青海可可西里地区综合科学考察初报

本区至今还是综合科学考察的空白区。为查明基本情况,1989年夏以乘汽车路线考察方式穿行该区而作了预查,搜集了当地地质、地理、生物等基本资料。经考察发现,区内野生动物资源丰富,上新世以来火山活动普遍,湖泊众多,矿产资源可能有良好前景;所在区又为自然地域和地质构造的重要界线,对青藏高原研究具有重大科学价值。     

A numerical model for Type II supernovae — The collapse stage

We use the following numerical model for the collapse stage of a Type II supernova of 15 M_⊙. Our electron capture rate includes the effects of the inverse reaction and the neutron-proton mass difference. This decreases the electron density at the collapse stage and led to rather large values of the maximum inward velocity and of the corresponding mass (Umax = 3.06 × 10⁹cm/s, Mmax=0.76 M_⊙). These larger values are more favourable for the propagation of shock after the rebounce and the triggering-off of a Type-II supernova explosion. For neutrino transport, we use a leakage model and an equilibrium diffusion model, respectively, for the thin and thick stages and a grey atmosphere model to assess the effect of neutrino precipitation on the collapse. We found this effect to be small, the energy precipitation to be not more than 10^?5 the neutrino energy loss and the momentum precipitation not more than 10^?6 the gravitational acceleration.     

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…