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.     

Mobile Agent系统结构及其关键技术

Mobile Agent技术是一门新兴的技术,具有移动性、智能性和异步计算的特点,已成为计算机网络和分布式系统最具活力的发展方向.现对Mobile Agent的概念、系统结构及其关键技术进行了分析和探讨.     

Optimal Filtering Algorithm for Stochastic 2-D FMM Ⅱ with Multiplicative Noise

1　Introduction　Inrecentyearstherehasbeengrowingresearchin terestinthetwo dimensional (2 D )systemtheory .The 2 Dsystemsmayfindapplicationsinareassuchasmarineseismicdataprocessingandimageprocessing .Althoughmoreandmorevaluableresultshavebeengained ,mos…     

DISASTER ANALYSIS AND COUNTERMEASURES OF LAND SUBSIDENCE CAUSED BY COAL CUTTING IN CHINA

In recent years, many coal-producing countries have paid great attention to the land subsidence causedby coal cutting. In China, because of the dense population in coalfield areas, the land subsidence hazard is more seri-ous. After a brief analysis on the mechanism of land subsidence, this paper gives a comprehensive and systematical ac-count on all kinds of hazards caused by the land subsidence in China. The study shows that land subsidence has endan-gered land, buildings, traffic and communication lines, dykes and dams. It also causes damage to ecological and socialenvironment. In order to lessen the hazard of land subsidence, preventive measures should be taken to reduce the col-lapse amount, such as extraction with stowing, banded mining system, succession and coordination mining system, orhigh-pressure mudflow between rock strata. Measures of reinforcing or moving certain buildings should also be taken toreduce the destructive degree. In order to harness the subsidence land and bring them under control for fanning, mea-sures should be taken such as filling with spoil or fine breeze, excavating the deeper and covering the shallower land.     

Galileo系统及其在中国的应用

较详细地介绍了Galileo系统的全面体系结构、频率设计、服务内容及其广泛的应用范围，指出了它与GPS系统相比的优点，并对开发和增强Galileo系统在我国多层次、全方位的应用提出了建议。     

信号流图求解部分分式展开

含有多重极点的有理真分式展开为部分分式，不需要计算低阶导数。列出被求函数的各阶导数的关系式，画出各阶导数作为节点的信号流图。该图无环路，既直观表现出各高阶导数的相互关系及影响的单向性，也使求节点增益的梅森公式特别简便。该方法将求高阶导数问题简化为代数运算，特别适合于编制成计算机程序     

新疆塔中南坡奥陶系的地层缺失和沉积相变化

按照奥陶系内部6个组沉积的时间片段拟定塔中南坡不同区块存在不同程度的缺失。部分关键层段的牙形石和几丁虫组合特征证明一间房组和恰尔巴克组在塔中部分井区是存在的,但恰尔巴克组的分布范围最狭窄。总体上,塔中南坡隆起区地层缺失较多,古城墟隆起基本完整。据缺失状况和岩相展布,显示塔中南坡的沉积单元具有由东往西迁移的特征,且各时段迁移的距离与速度存在较大差异。     

鱼卡煤田大煤沟组高分辨率层序地层特征及聚煤规律

利用高分辨率层序地层学理论和技术方法,综合地震、测井、岩芯和煤质资料对柴达木盆地北缘鱼卡煤田中下侏罗统大煤沟组地层河湖三角洲沉积体系进行高分辨率层序地层学分析,从中识别出短期、中期、长期3个级别的基准面旋回层序,划分出向上"变深"非对称型、向上"变浅"非对称型及对称型3种短期基准面旋回基本结构类型。依据等时地层对比法则进行不同级次基准面旋回层序的联井对比,建立了大煤沟组的等时地层格架,在等时地层格架内进行了煤层对比,并在等时地层格架内分析了聚煤规律。     

Case history of controlling a landslide at Panluo open-pit mine in China

Controlling of landsides safely and economically is a great challenge to mine operators because landslides are major geological problems especially in open-pit mines. In this paper, a case history at Panluo open-pit mine is presented in detail to share the experiences and lessons with mine operators. Panluo open-pit mine is located in the southwestern Fujian province of China. It is the largest open-pit iron mine in the Fujian province and was planned in 1965 and is in full operation from 1978. In July 1990, an earthquake of magnitude 5.3 in Taiwan Strait and big rainstorms impacted the mine slope, causing tension cracks and rather large-scale failures, and forming a U-shaped landslide. Total potential volume was estimated to be up to 1.0 × 10⁶ m³. This directly threatened the mine production. In order to protect the mine production and the dwellers’ safety around, a dynamic comprehensive method was implemented including geotechnical investigations, in-situ testing and monitoring, stability analysis, and many mitigation and preventive measures. These measures slowed down the development and further occurrence of the landslide. The results showed that the landslides were still active, it was slowed with the control measures and moved rapidly with rainfall and mining down. However, no catastrophic accidents occurred and the pit mining was continued till it was closed at the elevation of 887 m in 2000. As a successful case of landslide control at an open-pit mine for 10 years, this paper reports the controlling measures in details. These experiences of landslide control may be beneficial to other similar mines for landslide control.     

Evolution of subcontinental lithospheric mantle beneath eastern China: Re–Os isotopic evidence from mantle xenoliths in Paleozoic kimberlites and Mesozoic basalts

The ages of subcontinental lithospheric mantle beneath the North China and South China cratons are less well-constrained than the overlying crust. We report Re–Os isotope systematics of mantle xenoliths entrained in Paleozoic kimberlites and Mesozoic basalts from eastern China. Peridotite xenoliths from the Fuxian and Mengyin Paleozoic diamondiferous kimberlites in the North China Craton give Archean Re depletion ages of 2.6–3.2 Ga and melt depletion ages of 2.9–3.4 Ga. No obvious differences in Re and Os abundances, Os isotopic ratios and model ages are observed between spinel-facies and garnet-facies peridotites from both kimberlite localities. The Re–Os isotopic data, together with the PGE concentrations, demonstrate that beneath the Archean continental crust of the eastern North China Craton, Archean lithospheric mantle of spinel- to diamond-facies existed without apparent compositional stratification during the Paleozoic. The Mesozoic and Cenozoic basalt-borne peridotite and pyroxenite xenoliths, on the other hand, show geochemical features indicating metasomatic enrichment, along with a large range of the Re–Os isotopic model ages from Proterozoic to Phanerozoic. These features indicate that lithospheric transformation or refertilization through melt-peridotite interaction could be the primary mechanism for compositional changes during the Phanerozoic, rather than delamination or thermal-mechanical erosion, despite the potential of these latter processes to play an important role for the loss of garnet-facies mantle. A fresh garnet lherzolite xenolith from the Yangtze Block has a Re depletion age of ∼1.04 Ga, much younger than overlying Archean crustal rocks but the same Re depletion ages as spinel lherzolite xenoliths from adjacent Mesozoic basalts, indicating Neoproterozoic resetting of the Re–Os system in the South China Craton.