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.     

西部大开发中的科技伦理调控

在阐述西部大开发中科技主导地位的基础上 ,从科技应用成效二重性的视角 ,探讨了关注西部科技伦理的必要性 ,并初步提出了西部大开发战略的科技伦理调控机制     

智能照明系统在现代建筑照明中的应用研究

在对传统照明系统和智能照明系统进行对比分析的基础上,剖析了智能照明系统的控制策略,并结合实际的工程应用,着重讨论了基于ABB I-Bus产品的智能照明控制系统的实现,结果表明该系统具有高效、便捷、节约能源等优点.同时,还对系统与建筑物楼宇自控系统问的系统集成方式进行了研究.     

GPS变形监测平差计算及不确定度分析

全球定位系统（GPS）是一种全天候、高精度的连续定位系统,它以速度快、方法灵活多样、操作简便等优势被广泛应用于工程测量和变形监测中。结合水厂铁矿GPS边坡变形监测实例,对GPS监测网的星历预报、基线向量平差计算、网平差计算、结果及残差不确定度进行了细致分析研究,以验证GPS技术在边坡变形监测中的可靠性和精度。     

Effects of chemical ecological adjustment and control experiment on phytoplankton community in the Aoshan Bay

There is a low nutrient level in the Aoshan Bay. In June 1999, the chemical adjustmentand control experiment was made in the Aoshan Bay. Following tracts investigation was carried out before the experiment and on the 1st, 2nd, 4th, 5th, 6th and 45th day/after the experiment. While the variance of amount of phytoplankton, the replacement of superior species and the species composition of phytoplankton were researched. The results show that the amount of phytoplankton in the Aoshan Bay rises gradually after the experiment. Ceratium macroceros Cleve of pyrophyta was the dominant species before the experiment, its dominant index was 37.7％. Six days after the experiment, its dominant index dropped to 17.6％ . Meanwhile the dominant index of Asterionella japanics Cleve rose from 7.1％ to 39.2％ , it became the first dominant species. Forty-five days after the experiment, the amount of phytoplankton in the Aoshan Bay was 5.15 to 137.32 times more than that in 1997.     

无公害刺参稳产健康养殖新技术

本文针对目前刺参养殖中存在的问题,简单明了叙述刺参无公害健康养殖一系列新技术和新方法,对推动海参养殖业持续、稳定、健康发展,起到积极作用和效果。     

渭河下游河道调整过程中的复杂响应现象

应用系统复杂响应的原理研究三门峡水库上游渭河河道调整过程,表明上游河道河床形态对基面上升所作出的响应是复杂的,弯曲系数的变化为先减小而后增大,宽深比的变化是先增大后减小,比降由先减小而后增大,最后均趋于稳定.     

CPⅢ测量数据处理系统开发若干关键技术研究

本文首先介绍了无砟轨道的相关内容,指出CPⅢ测量数据处理是整个建设中的关键,提出系统开发的总体目标与要求且设计了系统总体结构,详细阐述了系统开发中涉及的关键技术与基本理论,文中最后结合具体工程实例验证系统开发成果。     

一种Brovey变换图像融合法的改进算法

分析了的Brovey变换融合算法,提出了一种新的基于Brovey变换、对数变换亮度调整的图像融合方法,试验数据的对比和分析证明了其保留多光谱影像的光谱信息.     

模拟退火算法在控制网平差中的应用

线性最小二乘估计在对非线性函数进行线性近似的过程中会产生模型误差,而一些非线性参数估计方法可能因为函数复杂而难以求导,法方程系数矩阵秩亏或呈病态矩阵时难以求解,非线性迭代解法有时对初始值的选择存在依赖性,不恰当的初始值会导致迭代无法收敛。针对这些问题,引入了模拟退火算法,介绍了该算法的基本原理、计算步骤和收敛性,并以3个控制网平差应用为例,说明该算法具有无需求导求逆,简洁实用,易于编程等优势,并能实现全局优化,获得高精度的平差结果。