Identification of loess landform types jointly affected by contour morphological knowledge and the graph neural network

doi:10.11947/j.AGCS.2024.20230445

Abstract

Abstract:

Landform type identification is a complex decision-making problem jointly affected by multi-factors. Due to the extensiveness and differences of landform regional environments and the complexity of the roles of geological elements, it is not possible to obtain satisfactory results by simply introducing artificial intelligence (AI) methods and supervising learning through typical samples. Thus, this study tries to integrate the knowledge of contour morphology as the natural intelligence in surveying and mapping into AI technology and carries out the research on loess landform type identification by hybrid intelligence integrating landform sample training and landform morphological representation rules. This paper presents a landform type recognition method that integrates contour morphological knowledge with the graph neural network (GNN). In this method, the contours of the landform unit are modeled as a graph structure composed of nodes and connecting edges, and the extracted contour vertex morphology knowledge is embedded in the graph nodes. A GNN model with pooling operations is used to mine high-level features and context information in the graph structure to identify unit types. The experimental results demonstrate the effectiveness of the proposed approach in identifying loess landform types, achieving an F₁ score of 86.1% on the test dataset, which represents a 3.0%~8.2% improvement over the two comparative methods.

Key words: loess landforms, pattern identification, contour data, graph neural networks

CLC Number:

P208

Bo KONG, Tinghua AI, Min YANG, Hao WU, Huafei YU, Tianyuan XIAO. Identification of loess landform types jointly affected by contour morphological knowledge and the graph neural network[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(6): 1154-1164.

Figures/Tables 15

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Tab.1

Fig.11

Tab.2

Fig.12

Fig.13

References 39

[1]	OUYANG Shubing, XU Jiahui, CHEN Weitao, et al. A fine-grained genetic landform classification network based on multimodal feature extraction and regional geological context[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:4511914.
[2]	陈军, 艾廷华, 闫利, 等. 智能化测绘的混合计算范式与方法研究[J/OL]. 测绘学报: 1-19 [2024-04-25]. http://kns.cnki.net/kcms/detail/11.2089.p.20240415.1049002.html.
	CHEN Jun, AI Tinghua, YAN Li, et al. Hybrid computational paradigm and methods for intelligentized surveying and mapping [J/OL]. Acta Geodaetica et Cartographica Sinica: 1-19 [2024-04-25]. http://kns.cnki.net/kcms/detail/11.2089.p.20240415.1049002.html.
[3]	陈军, 刘万增, 武昊, 等. 智能化测绘的基本问题与发展方向[J]. 测绘学报, 2021, 50(8):995-1005.DOI:10.11947/j.AGCS.2021.20210235.
	CHEN Jun, LIU Wanzeng, WU Hao, et al. Smart surveying and mapping: fundamental issues and research agenda[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8):995-1005. DOI:10.11947/j.AGCS.2021.20210235.
[4]	张永生, 张振超, 童晓冲, 等. 地理空间智能研究进展和面临的若干挑战[J]. 测绘学报, 2021, 50(9):1137-1146.DOI:10.11947/j.AGCS.2021.20200420.
	ZHANG Yongsheng, ZHANG Zhenchao, TONG Xiaochong, et al. Progress and challenges of geospatial artificial intelligence[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(9):1137-1146. DOI:10.11947/j.AGCS.2021.20200420.
[5]	张广运, 张荣庭, 戴琼海, 等. 测绘地理信息与人工智能2.0融合发展的方向[J]. 测绘学报, 2021, 50(8):1096-1108. DOI:10.11947/j.AGCS.2021.20210200.
	ZHANG Guangyun, ZHANG Rongting, DAI Qionghai, et al. The direction of integration surveying and mapping geographic information and artificial intelligence 2.0[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8):1096-1108. DOI:10.11947/j.AGCS.2021.20210200.
[6]	WANG Sizhe, LI Wenwen. GeoAI in terrain analysis: enabling multi-source deep learning and data fusion for natural feature detection[J]. Computers, Environment and Urban Systems, 2021, 90:101715.
[7]	LIN Siwei, XIE Jing, DENG Jiayin, et al. Landform classification based on landform geospatial structure: a case study on Loess Plateau of China[J]. International Journal of Digital Earth, 2022, 15(1):1125-1148.
[8]	LI Wenwen, HSU C Y. Automated terrain feature identification from remote sensing imagery: a deep learning approach[J]. International Journal of Geographical Information Science, 2020, 34(4):637-660.
[9]	LI Sijin, XIONG Liyang, TANG Guoan, et al. Deep learning-based approach for landform classification from integrated data sources of digital elevation model and imagery[J]. Geomorphology, 2020, 354:107045.
[10]	周访滨, 邹联华, 刘学军, 等. 栅格DEM微地形分类的卷积神经网络法[J]. 武汉大学学报(信息科学版), 2021, 46(8):1186-1193.
	ZHOU Fangbin, ZOU Lianhua, LIU Xuejun, et al. Micro landform classification method of grid DEM based on convolutional neural network[J]. Geomatics and Information Science of Wuhan University, 2021, 46(8):1186-1193.
[11]	XIONG Liyang, ZHU Axing, ZHANG Lei, et al. Drainage basin object-based method for regional-scale landform classification: a case study of loess area in China[J]. Physical Geography, 2018, 39(6):1-19.
[12]	NA Jiaming, DING Hu, ZHAO Wufan, et al. Object-based large-scale terrain classification combined with segmentation optimization and terrain features: a case study in China[J]. Transactions in GIS, 2021, 25(6):2939-2962.
[13]	HUANG Wei, DENG Chengbin, DAY M J. Differentiating tower Karst (Fenglin) and cockpit Karst (Fengcong) using DEM contour, slope, and centroid [J]. Environmental earth sciences, 2014, 72:407-416.
[14]	AI Tinghua. The drainage network extraction from contour lines for contour line generalization [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2007, 62(2):93-103.
[15]	CHENG Lu, GUO Qingsheng, FEI Lifan, et al. Multi-criterion methods to extract topographic feature lines from contours on different topographic gradients[J]. International Journal of Geographical Information Science, 2022, 36(8):1629-1651.
[16]	郭庆胜, 杨族桥, 冯科. 基于等高线提取地形特征线的研究[J]. 武汉大学学报(信息科学版), 2008, 33(3):253-256, 301.
	GUO Qingsheng, YANG Zuqiao, FENG Ke. Extracting topographic characteristic line from contours[J]. Geomatics and Information Science of Wuhan University, 2008, 33(3):253-256, 301.
[17]	熊汉江, 李秀娟. 一种提取山脊线和山谷线的新方法[J]. 武汉大学学报(信息科学版), 2015, 40(4):498-502, 515.
	XIONG Hanjiang, LI Xiujuan. A new method to extract terrain feature lines[J]. Geomatics and Information Science of Wuhan University, 2015, 40(4):498-502, 515.
[18]	LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553):436-444.
[19]	LI Wenwen, HSU C Y, HU Maosheng. Tobler's first law in GeoAI: a spatially explicit deep learning model for terrain feature detection under weak supervision[J]. Annals of the American Association of Geographers, 2021, 111(7):1887-1905.
[20]	HSU C Y, LI Wenwen, WANG Sizhe. Knowledge-driven GeoAI: integrating spatial knowledge into multi-scale deep learning for Mars Crater detection[J]. Remote Sensing, 2021.13(11), 2116.
[21]	JENNY B, HEITZLER M, SINGH D, et al. Cartographic relief shading with neural networks[J]. IEEE Transactions on Visualization and Computer Graphics, 2021, 27(2):1225-1235.
[22]	LI Sijin, HU Guanghui, CHENG Xinghua, et al. Integrating topographic knowledge into deep learning for the void-filling of digital elevation models[J]. Remote Sensing of Environment, 2022, 269:112818.
[23]	JENNY B. Terrain generalization with line integral convolution[J]. Cartography and Geographic Information Science, 2021, 48(1):78-92.
[24]	ZHANG Junxiang, LI Peiran, ZHANG Haoran, et al. Investigation on the relationship between population density and satellite image features: a deep learning based approach[J]. The Journal of Geodesy and Geoinformation Science, 2022, 5(4):50-58.
[25]	REICHSTEIN M, CAMPS-VALLS G, STEVENS B, et al. Deep learning and process understanding for data-driven Earth system science [J]. Nature, 2019, 566(7743):195-204.
[26]	王米琪, 艾廷华, 晏雄锋, 等. 图卷积网络模型识别道路正交网格模式[J]. 武汉大学学报(信息科学版), 2020, 45(12):1960-1969.
	WANG Miqi, AI Tinghua, YAN Xiongfeng, et al. Grid pattern recognition in road networks based on graph convolution network model[J]. Geomatics and Information Science of Wuhan University, 2020, 45(12):1960-1969.
[27]	YAN Xiongfeng, AI Tinghua, YANG Min, et al. A graph convolutional neural network for classification of building patterns using spatial vector data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 150:259-273.
[28]	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.
[29]	FU Honghao, SHEN Yilang, LIU Yuxuan, et al. SGCN: a multi-order neighborhood feature fusion landform classification method based on superpixel and graph convolutional network[J]. International Journal of Applied Earth Observation and Geoinformation, 2023, 122:103441.
[30]	ZHANG Baoyi, LI Manyi, HUAN Yuke, et al. Bedrock mapping based on terrain weighted directed graph convolutional network using stream sediment geochemical samplings[J]. Transactions of Nonferrous Metals Society of China, 2023, 33(9):2299-2814.
[31]	龙毅, 周侗, 汤国安, 等. 典型黄土地貌类型区的地形复杂度分形研究[J]. 山地学报, 2007, 25(4):385-392.
	LONG Yi, ZHOU Tong, TANG Guoan, et al. Research on terrain complexity of several typical regions of Loess Landform based on fractal method[J]. Journal of Mountain Science, 2007, 25(4):385-392.
[32]	陈晋北, 陈霄文, 贾伟, 等. 黄土高原塬区近地面层大涡多点观测研究[J]. 中国科学：地球科学, 2023, 53(4):856-865.
	CHEN Jinbei, CHEN Xiaowen, JIA Wei, et al. Multi-sites observation of large-scale eddy in surface layer of Loess Plateau [J]. Science China Earth Sciences, 2023, 53(4):856-865.
[33]	ZHUANG Jianqi, PENG Jianbing, WANG Gonghui, et al. Distribution and characteristics of landslide in Loess Plateau: a case study in Shaanxi province[J]. Engineering Geology, 2018, 236:89-96.
[34]	LI Yanrong, SHI Wenhui, AYDIN A, et al. Loess genesis and worldwide distribution[J]. Earth-Science Reviews, 2020, 201:102947.
[35]	艾廷华. Delaunay三角网支持下的空间场表达[J]. 测绘学报, 2006, 35(1):71-76, 82.
	AI Tinghua. A spatial field representation model based on Delaunay triangulation[J]. Acta Geodaetica et Cartographica Sinica, 2006, 35(1):71-76, 82.
[36]	艾廷华, 刘耀林. 保持空间分布特征的群点化简方法[J]. 测绘学报, 2002, 31(2):175-181.
	AI Tinghua, LIU Yaolin. A method of point cluster simplification with spatial distribution properties preserved[J]. Acta Geodaetica et Cartographic Sinica, 2002, 31(2):175-181.
[37]	YANG Min, KONG Bo, DANG Ruirong, et al. Classifying urban functional regions by integrating buildings and points-of-interest using a stacking ensemble method[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 108:102753.
[38]	张根寿. 现代地貌学[M]. 北京: 科学出版社, 2005.
	ZHANG Genshou. Modern geomorphology[M]. Beijing: Science Press, 2005.
[39]	VAN DER MAATEN L, HINTON G. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9:2579-2625.

标注结果	预测结果			统计值
标注结果	黄土塬	黄土墚	黄土峁	精确度	召回率	F₁值
黄土塬	154	4	2	89.5	96.3	92.8
黄土墚	4	142	14	81.1	88.8	84.8
黄土峁	14	29	117	88.0	73.1	80.0

方法	召回率	精确度	F₁值
RF	75.6	80.4	77.9
GCNN	82.1	84.2	83.1
本文方法	86.0	86.2	86.1