A machine learning approach for predicting computational intensity and domain decomposition in parallel geoprocessing     

Peng Yue  Fan Gao  Boyi Shangguan  Zheren Yan 《International journal of geographical information science》2020,34(11):2243-2274

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.  相似文献   

针铁矿对湖泊草、藻来源可溶有机质的非均质吸附     

章奇  居琪  李健欣  曹驰程  江和龙  张晖 《湖泊科学》2020,32(4):1041-1049

为探究富营养化湖泊中自生源可溶有机质(DOM)在泥水界面的吸附行为,以马来眼子菜(Potamogeton malaianus)和铜绿微囊藻(Microcystis aeruginosa)释放的DOM为代表,考察针铁矿对草、藻源DOM中不同组分的吸附特征.三维荧光平行因子分析表明类富里酸组分C1和类胡敏酸组分C4的含量很低,而类蛋白物质(类酪氨酸组分C2和类色氨酸组分C3)分别占草、藻源DOM荧光组成的70%和93%. 2种DOM均可被针铁矿吸附,吸附过程符合伪一级动力学.通过等温线拟合发现针铁矿吸附藻源DOM的非线性更强,饱和吸附量(23.77 mg/g)高于草源DOM(19.10 mg/g).特别地,类蛋白组分呈现非线性吸附,而类腐殖物质的吸附近似线性,且针铁矿对于DOM各荧光组分的吸附量顺序为:C3C2 C4 C1,此非均质吸附特征与DOM组分的初始含量、分子大小、芳香性及有效吸附位点有关.红外光谱证实氨基、羧基和羟基是吸附过程中的重要官能团.因此,草、藻源DOM显著改变了针铁矿表面的有机物质组成,影响湖泊沉积物的生物地球化学行为.  相似文献   

多层构造油藏纵向细分计算单元对储量参数及结果的影响     

颜冠山  刘宗宾  宋洪亮  韩雪芳  王欣然 《地质与资源》2020,29(4):342-350

为满足油田中后期精细开发及后续调整挖潜的需要，亟需进行更精细的储量研究，其中最重要的一环就是纵向细分计算单元.对于多层构造油藏，纵向细分主要根据油层组内隔夹层分布特征、小层物性特征，细分到以小层或者分布特征和物性相近且纵向上连续分布的小层组合为计算单元.根据纵向细分计算单元前后储量参数选值的理论推导，结合储层的沉积展布特征，认为含油面积范围内无储层尖灭时，仅平面油层厚度差异较大的油藏平均有效厚度变小.含油面积范围内储层尖灭时，正常三角洲沉积储层的油藏各参数一般都变小；而辫状河三角洲沉积储层的油藏一般平均有效厚度变小，平均有效孔隙度和平均含油饱和度变大.这一结论可以有效指导储量评估过程中纵向细分计算单元方案划分，为同类油田的精细储量研究提供技术支撑.  相似文献   

New formulae for capacity energy-based assessment of liquefaction triggering     

Yasaman Jafariavval 《Marine Georesources & Geotechnology》2020,38(2):214-222

Abstract

Liquefaction of loose saturated soil deposits is a hazardous type of ground failure occurring under earthquake excitations. Therefore, an accurate estimation of liquefaction potential is extremely important in geotechnical engineering. In the current study, a new model is proposed which estimates the level of strain energy needed for liquefaction initiation. A compiled database containing cyclic tests gathered from previously published works was used to develop new models to predict liquefaction potential. M5′ algorithm was used to find the best correlation between parameters. It was shown that not only the derived formulas are acceptably accurate but also they feature a very simple structure in comparison with available formulas in the literature. The proposed equations are accurate, physically sound and uncomplicated. Furthermore, safety factors were given for different levels of risk, which can be useful for engineering practice. In addition, the influence of different predictors on the liquefaction potential was evaluated and also the significance of input variables was assessed via sensitivity analysis. Finally, a new model was introduced for preliminary estimation of liquefaction potential.  相似文献   

Parallelization of the flow-path network model using a particle-set strategy     

Fangli Zhang 《International journal of geographical information science》2019,33(10):1984-2010

High-performance simulation of flow dynamics remains a major challenge in the use of physical-based, fully distributed hydrologic models. Parallel computing has been widely used to overcome efficiency limitation by partitioning a basin into sub-basins and executing calculations among multiple processors. However, existing partition-based parallelization strategies are still hampered by the dependency between inter-connected sub-basins. This study proposed a particle-set strategy to parallelize the flow-path network (FPN) model for achieving higher performance in the simulation of flow dynamics. The FPN model replaced the hydrological calculations on sub-basins with the movements of water packages along the upstream and downstream flow paths. Unlike previous partition-based task decomposition approaches, the proposed particle-set strategy decomposes the computational workload by randomly allocating runoff particles to concurrent computing processors. Simulation experiments of the flow routing process were undertaken to validate the developed particle-set FPN model. The outcomes of hourly outlet discharges were compared with field gauged records, and up to 128 computing processors were tested to explore its speedup capability in parallel computing. The experimental results showed that the proposed framework can achieve similar prediction accuracy and parallel efficiency to that of the Triangulated Irregular Network (TIN)-based Real-Time Integrated Basin Simulator (tRIBS).  相似文献   

基于并行计算的海洋平台谱分析疲劳筛选技术研究     

李洛东  刘成名  梁园华 《海洋工程》2018,36(5):56-64

为了得到海洋平台疲劳失效风险最大的焊接区域,提出了以有限元网格单元应力为基础的谱分析筛选方法,并开发了程序。程序采用并行计算架构,单次完成数万个单元的累积损伤度/疲劳寿命计算,并通过有限元软件以云图方式显示疲劳寿命。采用该程序计算双浮筒半潜式平台的疲劳寿命。结果表明,该型平台疲劳失效风险较高的区域为立柱与上壳体下浮体连接对角线转角区域、浮筒中纵舱壁与立柱连接区域。并行计算方法的引入,大大缩减疲劳损伤度计算的分析时间,采用22核心的CPU,时间缩短为原来的1/18.5,17小时完成全平台外壳单元谱分析计算。  相似文献   

基于GPU加速的Boussinesq类波浪传播变形数值模型     

孙家文  朱桐  房克照  刘忠波 《海洋工程》2020,38(2):111-119

Boussinesq波浪模型是一类相位解析模型,在时域内求解需要较高的空间和时间分辨率以保证计算精度。为提高计算效率,有必要针对该类模型开展并行算法的研究。与传统的中央处理器(CPU)相比,图形处理器(GPU)有大量的运算器,可显著提高计算效率。基于统一计算设备架构CUDA C语言和图形处理器,实现了Boussinesq模型的并行运算。将本模型的计算结果同CPU数值模拟结果和解析解相比较,发现得到的结果基本一致。同时也比较了CPU端与GPU端的计算效率,结果表明,GPU数值模型的计算效率有明显提升,并且伴随数值网格的增多,提升效果更为明显。  相似文献   

结合云计算与大数据的出租房消防安全监管GIS     

徐刚  杨立博  裴政皓  陈杰 《测绘通报》2019,(8):121-124,157

我国城镇化进程和经济发展效果卓著，但消防建设规划与城市扩张发展之间并不协调。虽然现有研究已经运用GIS技术到消防安全监管当中，但依然存在信息联动性不强，可视化程度低的问题。为此，本文基于地理信息系统技术对城市开发区内地理信息数据、多源多时态遥感及航空影像、巡查数据、出租房数据等进行有效整合完善，以建立时空地理信息大数据。笔者利用虚拟化、云计算等技术建立出租房消防安全动态监管平台。此平台为管理部门提供了基于地理信息的决策支持，提升了出租房管理的高效性和科学性。系统的建成和应用对我国的出租房管理信息化工作的开展具有重要意义。  相似文献   

Boussinesq相位解析的海岸水动力学数学模型研究进展     

张尧  谢欣  陶爱峰  王岗  陈新平  郑金海 《海洋通报》2018,(5):481-493

由于在平衡计算效率和精度上具有优势,Boussinesq相位解析数学模型研究不断取得突破,已成为波浪和水流精细化模拟的较优解析方式,为海岸工程、环境、地质等问题提供了实用和高效的研究手段。本文对已有Boussinesq类模型的研究进行了评述,深入探讨其重要发展、实际应用和理论瓶颈,从高阶非静压修正、GPU准三维高性能算法编译、波浪破碎和泥沙运移沉积等4个方面提出未来可能的科学突破方向。  相似文献   

考虑不确定性的地震灾害应急救援设备并行优化设计   总被引：1，自引：0，他引：1       下载免费PDF全文

刘航 《地震工程学报》2018,40(5):1118-1123

由于地震灾害的不确定性，使得应急救援设备运行速率及使用效率均受到影响，需要进行并行优化处理。对此，提出基于双向并行计算的地震灾害应急救援设备优化方法。以地震灾区灾情等级评估结果为基础，将地震等级及应急救援设备，设备及设备之间的关系进行标准化处理，转化为求解最优解问题；在考虑不确定性的情况下，通过通信时间与救援设备需求进行双向并行处理，优化地震灾害应急救援设备。实验结果表明，采用改进方法进行地震灾害应急救援设备并行优化，能够对地震灾害应急救援设备需求量进行准确预测，提高应急救援设备的运行速率，缩短通信时间，提高应急救援设备的使用效率，具有一定的优势。  相似文献