A multi-scale mesh river system classification matching method based on graph neural network

doi:10.11947/j.AGCS.2025.20240145

Abstract

Abstract:

Multi-scale mesh river system matching is an important part of river system data integration, fusion and update. In view of the fact that the existing mesh river system matching methods do not pre-identify the matching patterns and lack a targeted matching strategy, this paper proposes a multi-scale mesh river system classification matching method based on graph neural networks. Firstly, constructing the large-scale mesh river system as a graph structure, label the matching patterns between it and the small-scale river system as nodes, and compute the node features; and then the graph neural network is used to sample and aggregate the node features to establish the mapping relationship between the river segment features and matching patterns; finally, according to the category of the matching patterns of each river segment in the river system, the matching strategy is adopted accordingly. The experimental results show that the method in this paper effectively improves the matching accuracy of the mesh river system, and has good theoretical and application value.

Key words: multi-scale data, matching patterns, matching strategies, mesh river systems, graph neural network

CLC Number:

P208

Zhekun HUANG, Haizhong QIAN, Zhongxiang CAI, Xiao WANG, Junwei WANG, Linghui KONG. A multi-scale mesh river system classification matching method based on graph neural network[J]. Acta Geodaetica et Cartographica Sinica, 2025, 54(2): 371-384.

Figures/Tables 17

Fig. 1

Tab. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Tab. 2

Fig. 8

Tab. 3

Tab. 4

Fig. 9

Fig. 10

Fig. 11

Tab. 5

Tab. 6

References 42

[1]	CHEN Jun, LI Zhilin, LI Songnian, et al. From digitalized to intelligentized surveying and mapping: fundamental issues and research agenda[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(2): 148-160.
[2]	MENG Liqun. Proliferation of cartographic education in the age of big data[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(3): 7-18.
[3]	SHEN Yilang, ZHAO Rong, AI Tinghua, et al. A raster-based method for the hierarchical selection of river networks based on stream characteristics[J]. International Journal of Geographical Information Science, 2023, 37(10): 2262-2287.
[4]	HERZOG S P, WARD A S, WONDZELL S M. Multiscale feature-feature interactions control patterns of hyporheic exchange in a simulated headwater mountain stream[J]. Water Resources Research, 2019, 55(12): 10976-10992.
[5]	DURIGHETTO N, VINGIANI F, BERTASSELLO L E, et al. Intraseasonal drainage network dynamics in a headwater catchment of the Italian Alps[J]. Water Resources Research, 2020, 56(4): e2019WR025563.
[6]	LKHAZRAJI H, KANAKIS T, AL-SHERBAZ A, et al. Enhancing map matching accuracy using backtracking technique[J]. International Journal of Applied Earth Observation and Geoinformation, 2024, 132: 103988.
[7]	WU Hangbin, XU Shan, HUANG Shengke, et al. Optimal road matching by relaxation to min-cost network flow[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 114: 103057.
[8]	CHEHREGHAN A, ALI ABBASPOUR R. A geometric-based approach for road matching on multi-scale datasets using a genetic algorithm[J]. Cartography and Geographic Information Science, 2018, 45(3): 255-269.
[9]	刘凌佳, 朱道也, 朱欣焰, 等. 基于MBR组合优化算法的多尺度面实体匹配方法[J]. 测绘学报, 2018, 47(5): 652-662. DOI:. doi: 10.11947/j.AGCS.2018.20160625
	LIU Lingjia, ZHU Daoye, ZHU Xinyan, et al. A multi-scale polygonal object matching method based on MBR combinatorial optimization algorithm[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(5): 652-662. DOI:. doi: 10.11947/j.AGCS.2018.20160625
[10]	陈竞男, 钱海忠, 王骁, 等. 提高线要素匹配率的动态化简方法[J]. 测绘学报, 2016, 45(4): 486-493. DOI:. doi: 10.11947/j.AGCS.2016.20150074
	CHEN Jingnan, QIAN Haizhong, WANG Xiao, et al. Improving the matching rate of line feature by using dynamic simplification[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(4): 486-493. DOI:. doi: 10.11947/j.AGCS.2016.20150074
[11]	GUO Wenyue, YU Anzhu, SUN Qun, et al. A multisource contour matching method considering the similarity of geometric features[J]. Journal of Geodesy and Geoinformation Science, 2020, 3(3): 76-87.
[12]	安晓亚, 孙群, 肖强, 等. 一种形状多级描述方法及在多尺度空间数据几何相似性度量中的应用[J]. 测绘学报, 2011, 40(4): 495-501, 508.
	AN Xiaoya, SUN Qun, XIAO Qiang, et al. A shape multilevel description method and application in measuring geometry similarity of multi-scale spatial data[J]. Acta Geodaetica et Cartographica Sinica, 2011, 40(4): 495-501, 508.
[13]	DENG Min, LI Zhilin, CHEN Xiaoyong. Extended Hausdorff distance for spatial objects in GIS[J]. International Journal of Geographical Information Science, 2007, 21(4): 459-475.
[14]	ZHANG Meng, MENG Liqiu, BOBRICH J. A road-network matching approach guided by “structure”[J]. Annals of GIS, 2010, 16(3): 165-176.
[15]	ABDOLMAJIDI E, MANSOURIAN A, WILL J, et al. Matching authority and VGI road networks using an extended node-based matching algorithm[J]. Geo-spatial Information Science, 2015, 18(2/3): 65-80.
[16]	郭庆胜, 谢育武, 刘纪平, 等. 顾及尺度变化和数据更新的道路网匹配算法[J]. 测绘学报, 2017, 46(3): 381-388. DOI:. doi: 10.11947/j.AGCS.2017.20160364
	GUO Qingsheng, XIE Yuwu, LIU Jiping, et al. Algorithms for road networks matching considering scale variation and data update[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(3): 381-388. DOI:. doi: 10.11947/j.AGCS.2017.20160364
[17]	邵世维, 刘辉, 肖立霞, 等. 一种基于Fréchet距离的复杂线状要素匹配方法[J]. 武汉大学学报(信息科学版), 2018, 43(4): 516-521.
	SHAO Shiwei, LIU Hui, XIAO Lixia, et al. A complex linear feature of Fréchet distance matching method[J]. Geomatics and Information Science of Wuhan University, 2018, 43(4): 516-521.
[18]	禄小敏, 闫浩文, 王中辉. 群组目标空间方向关系建模[J]. 地球信息科学学报, 2018, 20(6): 721-729.
	LU Xiaomin, YAN Haowen, WANG Zhonghui. The modeling of spatial direction relationship between object groups[J]. Journal of Geo-information Science, 2018, 20(6): 721-729.
[19]	付仲良, 杨元维, 高贤君, 等. 道路网多特征匹配优化算法[J]. 测绘学报, 2016, 45(5): 608-615. DOI:. doi: 10.11947/j.AGCS.2016.20150388
	FU Zhongliang, YANG Yuanwei, GAO Xianjun, et al. An optimization algorithm for multi-characteristics road network matching[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(5): 608-615. DOI:. doi: 10.11947/j.AGCS.2016.20150388
[20]	KIM I H, FENG C C, WANGY C. A simplified linear feature matching method using decision tree analysis, weighted linear directional mean, and topological relationships[J]. International Journal of Geographical Information Science, 2017, 31(5): 1042-1060.
[21]	HUANGB H, ZHONG W, ZHAI R J, et al. Hierarchical area partitioning method of urban road networks matching[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(3): 55-67.
[22]	闫浩文, 张鑫港, 禄小敏, 等. DP算法自动实现方法：以河流化简为例[J]. 武汉大学学报(信息科学版), 2024, 49(2): 264-270.
	YAN Haowen, ZHANG Xingang, LU Xiaomin, et al. Approach to automating DP algorithm: taking river simplification as an example[J]. Geomatics and Information Science of Wuhan University, 2024, 49(2): 264-270.
[23]	ZHANG Jianchen, WANG Yanhui, ZHAO Wenji. An improved probabilistic relaxation method for matching multi-scale road networks[J]. International Journal of Digital Earth, 2018, 11(6): 635-655.
[24]	LI L N, GOODCHILD M F. An optimisation model for linear feature matching in geographical data conflation[J]. International Journal of Image and Data Fusion, 2011, 2(4): 309-328.
[25]	TONG Xiaohua, LIANG Dan, JIN Yanmin. A linear road object matching method for conflation based on optimization and logistic regression[J]. International Journal of Geographical Information Science, 2014, 28(4): 824-846.
[26]	张云菲, 杨必胜, 栾学晨. 利用概率松弛法的城市路网自动匹配[J]. 测绘学报, 2012, 41(6): 933-939.
	ZHANG Yunfei, YANG Bisheng, LUAN Xuechen. Automated matching urban road networks using probabilistic relaxation[J]. Acta Geodaetica et Cartographica Sinica, 2012, 41(6): 933-939.
[27]	YANG Bisheng, ZHANG Yunfei, LUAN Xuechen. A probabilistic relaxation approach for matching road networks[J]. International Journal of Geographical Information Science, 2013, 27(2): 319-338.
[28]	LEI T L. Geospatial data conflation: a formal approach based on optimization and relational databases[J]. International Journal of Geographical Information Science, 2020, 34(11): 2296-2334.
[29]	LEI T L. Large scale geospatial data conflation: a feature matching framework based on optimization and divide-and-conquer[J]. Computers, Environment and Urban Systems, 2021, 87: 101618.
[30]	YU Wenhao, LIU Mengqi. An iterative framework with active learning to match segments in road networks[J]. Cartography and Geographic Information Science, 2023, 50(4): 333-350.
[31]	武芳, 杜佳威, 钱海忠, 等. 地图综合智能化研究的发展与思考[J]. 武汉大学学报(信息科学版), 2022, 47(10): 1675-1687.
	WU Fang, DU Jiawei, QIAN Haizhong, et al. Overview of research progress and reflections in intelligent map generalization[J]. Geomatics and Information Science of Wuhan University, 2022, 47(10): 1675-1687.
[32]	艾廷华. 深度学习赋能地图制图的若干思考[J]. 测绘学报, 2021, 50(9): 1170-1182. DOI:. doi: 10.11947/j.AGCS.2021.20210091
	AI Tinghua. Some thoughts on deep learning enabling cartography[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(9): 1170-1182. DOI:. doi: 10.11947/j.AGCS.2021.20210091
[33]	张新长, 何显锦, 孙颖, 等. 多尺度空间数据联动更新技术研究现状及展望[J]. 测绘学报, 2022, 51(7): 1520-1535. DOI:. doi: 10.11947/j.AGCS.2022.20220095
	ZHANG Xinchang, HE Xianjin, SUN Ying, et al. Advance and future development of the multi-scale spatial data linkage updating[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(7): 1520-1535. DOI:. doi: 10.11947/j.AGCS.2022.20220095
[34]	YU Huafei, AI Tinghua, YANG Min, et al. Automatic segmentation of parallel drainage patterns supported by a graph convolution neural network[J]. Expert Systems with Applications, 2023, 211: 118639.
[35]	WANG Wenning, YAN Haowen, LU Xiaomin, et al. Drainage pattern recognition method considering local basin shape based on graph neural network[J]. International Journal of Digital Earth, 2023, 16(1): 593-619.
[36]	武芳, 谭笑, 王辉连, 等. 顾及网络特征的复杂人工河网的自动选取[J]. 中国图象图形学报, 2007, 12(6): 1103-1109.
	WU Fang, TAN Xiao, WANG Huilian, et al. Study on automated canal selection[J]. Journal of Image and Graphics, 2007, 12(6): 1103-1109.
[37]	翟仁健, 武芳, 邓红艳, 等. 基于遗传多目标优化的人工河网自动选取模型[J]. 测绘学报, 2008, 37(1): 108-113.
	ZHAI Renjian, WU Fang, DENG Hongyan, et al. An automated selection model of ditch based on multi-objective optimization by genetic algorithm[J]. Acta Geodaetica et Cartographica Sinica, 2008, 37(1): 108-113.
[38]	段佩祥, 钱海忠, 何海威, 等. 案例支撑下的朴素贝叶斯树状河系自动分级方法[J]. 测绘学报, 2019, 48(8): 975-984. DOI:. doi: 10.11947/j.AGCS.2019.20180370
	DUAN Peixiang, QIAN Haizhong, HE Haiwei, et al. Naive Bayes-based automatic classification method of tree-like river network supported by cases[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(8): 975-984. DOI:. doi: 10.11947/j.AGCS.2019.20180370
[39]	WANG Di, QIAN Haizhong. Graph neural network method for the intelligent selection of river system[J]. Geocarto International, 2023, 38(1): 2252762.
[40]	YU Huafei, AI Tinghua, YANG Min, et al. A recognition method for drainage patterns using a graph convolutional network[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 107: 102696.
[41]	MAAS A L, HANNUN A Y, NG A Y. Rectifier nonlinearities improve neuralnetwork acoustic models[C]//Proceedings of 2013 International Conference on Machine Learning. Atlanta: JMLR, 2013.
[42]	刘海龙, 钱海忠, 王骁, 等. 采用层次分析法的道路网整体匹配方法[J]. 武汉大学学报(信息科学版), 2015, 40(5): 644-651.
	LIU Hailong, QIAN Haizhong, WANG Xiao, et al. Road networks global matching method using analytical hierarchy process[J]. Geomatics and Information Science of Wuhan University, 2015, 40(5): 644-651.

综合操作	大比例尺数据	小比例尺数据	大比例尺数据对应的匹配模式
选取			1∶0、1∶1和m∶1
化简			1∶1

方法	向量维度或决策树数	准确率/（%）
本文方法	64	90.7
	128	91.5
	256	91.2
GCN	64	75.4
	128	76.7
	256	76.2
GAT	64	73.1
	128	74.6
	256	74.7
RF	50	82.2
	100	84.1
	200	84.9

匹配模式（真实）	匹配模式（预测）	案例数
1∶0	1∶1	16
1∶0	m∶1	10
1∶1	1∶0	25
1∶1	m∶1	72
m∶1	1∶0	25
m∶1	1∶1	29

匹配模式	C	M	A	精准率/（%）	召回率/（%）	F₁值/（%）
1∶0	650	714	661	91.0	98.3	94.5
1∶1	778	794	796	98.0	97.7	97.8
m∶1	549	634	610	86.6	90.0	88.3
总计	1338	1441	1424	92.9	94.0	93.4

试验区域	匹配模式	精准率/（%）	召回率/（%）	F₁值/（%）
试验区2	1∶0	90.8	94.18	92.47
	1∶1	83.5	82.15	82.82
	m∶1	76.6	75.23	75.93
试验区3	1∶0	90.1	89.1	89.6
	1∶1	81.8	80.6	81.2
	m∶1	79.8	81.8	80.8