陆军工程大学通信工程学院,江苏 南京,210007
高凡,博士,讲师,主要从事高性能地理计算、地理信息服务方面的研究。fgao_lgd@163.com
路威,博士,副教授。luwei_lgd@163.com
收稿:2025-02-25,
纸质出版:2026-05-05
移动端阅览
高凡,路威,甘麟露.基于卷积神经网络的地理空间域计算强度预测与分解方法[J].武汉大学学报(信息科学版),2026,51(5):1048-1058.
GAO Fan,LU Wei,GAN Linlu.A CNN-Based Method for Computational Intensity Prediction and Geospatial Domain Decomposition[J].Geomatics and Information Science of Wuhan University,2026,51(5):1048-1058.
高凡,路威,甘麟露.基于卷积神经网络的地理空间域计算强度预测与分解方法[J].武汉大学学报(信息科学版),2026,51(5):1048-1058. DOI:10.13203/j.whugis20240119
GAO Fan,LU Wei,GAN Linlu.A CNN-Based Method for Computational Intensity Prediction and Geospatial Domain Decomposition[J].Geomatics and Information Science of Wuhan University,2026,51(5):1048-1058. DOI:10.13203/j.whugis20240119
地理空间域分解是并行地理计算中实现负载均衡的核心问题,而如何准确提取地理空间域上特征并预测域上计算强度是地理空间域均衡分解的关键。然而,在地理空间域特征提取和计算强度模型建模方面,现有方法过于依赖专家知识,存在特征适用性差、建模过程复杂、模型精度低的问题。为摆脱专家知识依赖,实现高精度、自动化地理空间域计算强度预测,提出一种基于人工智能深度学习的地理空间域计算强度预测和分解方法。所提方法从数据驱动角度出发,将地理空间域对齐卷积神经网络输入结构,利用卷积神经网络自动化捕捉地理空间域特征,预测域上计算强度,并将计算强度预测模型嵌入地理空间域分解,实现任务的均衡划分。以矢量空间相交为例,证明了所提方法在计算性能和自动化程度两个方面的优势。
Objectives
2
The evaluation of heterogeneity is essential for domain decomposition in parallel geocomputation. According to the theory of geospatial domain
the assessment of heterogeneity can be transformed to the computational intensity (CI) modelling
thus the key of domain decomposition is feature extraction and computational intensity prediction. However
the existing methods rely on expert knowledge for feature extraction and CI modelling of geospatial domain
suffering from poor feature applicability
complex modelling process and low model accuracy. In order to relieve the dependence on expert knowledge and achieve accurate computational intensity prediction
a computational intensity prediction and decomposition method for geospatial domain based on artificial intelligence (AI) deep learning is proposed.
Methods
2
We use convolutional neural network (CNN) to capture the features of geospatial domain automatically
and a fully connected layer is used to predict the computational intensity. An added component is developed to match the geospatial domain and the input of CNN.
Results
2
Spatial intersection on vector data is implemented to compare the proposed method and traditional methods. The results demonstrate the advantages of the proposed method in terms of the usability and parallel performance.
Conclusions
2
The proposed method optimizes computational intensity prediction and domain decomposition from data science perspective
which provides a reference on how AI deep learning can be used in high-performance geocomputation.
ZHU S Q , YU T , XU T , et al . Intelligent Computing: The Latest Advances, Challenges, and Future [J]. Intelligent Computing , 2023 , 2 : 6 .
李德仁 . 论时空大数据的智能处理与服务 [J]. 地球信息科学学报 , 2019 , 21 ( 12 ): 1825 - 1831 .
LI Deren . The Intelligent Processing and Service of Spatiotemporal Big Data [J]. Journal of Geo⁃Information Science , 2019 , 21 ( 12 ): 1825 - 1831 .
ZHOU C , CHEN Z J , LI M C . A Parallel Method to Accelerate Spatial Operations Involving Polygon Intersections [J]. International Journal of Geographical Information Science , 2018 , 32 ( 12 ): 2402 - 2426 .
ZHOU C , LI M C . A Systematic Parallel Strategy for Generating Contours from Large-Scale DEM Data Using Collaborative CPUs and GPUs [J]. Cartography and Geographic Information Science , 2021 , 48 ( 3 ): 187 - 209 .
WANG Y J , AI B B , QIN C Z , et al . A Load-Balancing Strategy for Data Domain Decomposition in Parallel Programming Libraries of Raster-Based Geocomputation [J]. International Journal of Geographical Information Science , 2022 , 36 ( 5 ): 968 - 991 .
QIN C , WANG X B , ZHAO N . EMFEM: A Parallel 3D Modeling Code for Frequency-Domain Electromagnetic Method Using Goal-Oriented Adaptive Finite Element Method [J]. Computers & Geosciences , 2023 , 178 : 105403 .
WANG S W , ARMSTRONG M P . A Theoretical Approach to the Use of Cyberinfrastructure in Geographical Analysis [J]. International Journal of Geographical Information Science , 2009 , 23 ( 2 ): 169 - 193 .
亢晓琛 , 刘纪平 . 图划分支持下的大规模点要素并行缓冲分析方法 [J]. 武汉大学学报(信息科学版) , 2023 , 48 ( 6 ): 979 - 987 .
KANG Xiaochen , LIU Jiping . Parallel Buffer Analysis of Large Scale Point Features Based on Graph Partitioning [J]. Geomatics and Information Science of Wuhan University , 2023 , 48 ( 6 ): 979 - 987 .
ARMSTRONG M P , DENSHAM P J . Domain Decomposition for Parallel Processing of Spatial Problems [J]. Computers, Environment and Urban Systems , 1992 , 16 ( 6 ): 497 - 513 .
YUE P , GAO F , SHANGGUAN B Y , et al . A Machine Learning Approach for Predicting Computational Intensity and Domain Decomposition in Parallel Geoprocessing [J]. International Journal of Geographical Information Science , 2020 , 34 ( 11 ): 2243 - 2274 .
王鸿琰 , 关雪峰 , 吴华意 . 一种面向CPU/GPU异构环境的协同并行空间插值算法 [J]. 武汉大学学报(信息科学版) , 2017 , 42 ( 12 ): 1688 - 1695 .
WANG Hongyan , GUAN Xuefeng , WU Huayi . A Collaborative Parallel Spatial Interpolation Algorithmon Oriented Towards the Heterogeneous CPU/GPU System [J]. Geomatics and Information Science of Wuhan University , 2017 , 42 ( 12 ): 1688 - 1695 .
REN Y B , CHEN Z J , CHEN G , et al . A Hybrid Process/Thread Parallel Algorithm for Generating DEM from LiDAR Points [J]. ISPRS International Journal of Geo⁃Information , 2017 , 6 ( 10 ): 300 .
ZHOU C , CHEN Z J , LIU Y X , et al . Data Decomposition Method for Parallel Polygon Rasterization Considering Load Balancing [J]. Computers & Geosciences , 2015 , 85 : 196 - 209 .
GAO F , YUE P , CAO Z P , et al . A Multi-source Spatiotemporal Data Cube for Large-Scale Geospatial Analysis [J]. International Journal of Geographical Information Science , 2022 , 36 ( 9 ): 1853 - 1884 .
HERNÁNDEZ Á B , PEREZ M S , GUPTA S , et al . Using Machine Learning to Optimize Parallelism in Big Data Applications [J]. Future Generation Computer Systems , 2018 , 86 : 1076 - 1092 .
ALZUBAIDI L , ZHANG J L , HUMAIDI A J , et al . Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions [J]. Journal of Big Data , 2021 , 8 ( 1 ): 53 .
KRIZHEVSKY A , SUTSKEVER I , HINTON G E . ImageNet Classification with Deep Convolutional Neural Networks [J]. Communications of the ACM , 2017 , 60 ( 6 ): 84 - 90 .
SIMONYAN K , ZISSERMAN A . Very Deep Convolutional Networks for Large-Scale Image Recognition [EB/OL]. [ 2014-09-15 ]. https://arxiv.org/abs/1409.1556 https://arxiv.org/abs/1409.1556
SZEGEDY C , LIU W , JIA Y Q , et al . Going Deeper with Convolutions [C]// IEEE Conference on Computer Vision and Pattern Recognition , Boston, USA , 2015 .
HE K M , ZHANG X Y , REN S Q , et al . Deep Residual Learning for Image Recognition [C]// IEEE Conference on Computer Vision and Pattern Recognition , Las Vegas, USA , 2016 .
HUANG G , LIU Z , VAN DER MAATEN L , et al . Densely Connected Convolutional Networks [C]// IEEE Conference on Computer Vision and Pattern Recognition , Honolulu, USA , 2017 .
PATEL J M , DEWITT D J . Partition Based Spatial-Merge Join [J]. ACM SIGMOD Record , 1996 , 25 ( 2 ): 259 - 270 .
AJI A , WANG F S , VO H , et al . Hadoop GIS: A High Performance Spatial Data Warehousing System over Mapreduce [J]. Proceedings of the VLDB Endowment , 2013 , 6 ( 11 ): 1009 - 1020 .
DU Z H , ZHAO X W , YE X Y , et al . An Effective High-Performance Multiway Spatial Join Algorithm with Spark [J]. ISPRS International Journal of Geo⁃Information , 2017 , 6 ( 4 ): 96 .
DITTRICH J P , SEEGER B . Data Redundancy and Duplicate Detection in Spatial Join Processing [C]// The 16th International Conference on Data Engineering , San Diego, USA , 2002 .
0
浏览量
1
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621