GF-1 images-based information extraction of natural roads in arid and semi-arid regions of the Mongolian Plateau: A case study of Gurvantes Soum, Mongolia
LIANG Xiya1,2(), WANG Juanle1,3(), LI Pengfei2, DAVAADORJ Davaasuren4
1. State Key Laboratory of Resources and Environment Information System, Institute of Geographic Sciences and Natural Resources Research,Chinese Academy of Sciences,Beijing 100101,China 2. College of Geomatics, Xi’an University of Science and Technology, Xi’an 710054, China 3. Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application,Nanjing 210023,China 4. School of the Art & Sciences, National University of Mongolia, Ulaanbaatar 14201, Mongolia
Many unplanned natural roads, which are also known as temporary roads or unpaved roads, exist in the vast arid and semi-arid regions of the Mongolian Plateau. These natural roads, which were formed due to the arbitrary running of vehicles, will influence the surface ecology and its stability and aggravate land degradation in arid and semi-arid regions. They have a large quantity, are distributed irregularly, and tend to change with regional development. Therefore, there is an urgent need for the efficient and accurate information acquisition of natural roads in large-scale grassland regions, which is a challenge. Based on domestic high-resolution satellite (GF-1) images, this study extracted information on the natural roads in Mongolia using the object-oriented method. First, the data of GF-1 images covering the study area were preprocessed, and the image objects were segmented using the multiresolution segmentation method. Then, the characteristics of the natural roads were analyzed for information extraction. By calculating the parameters of spectral and geometric features and randomly selecting road samples to statistically analyze the characteristic values of samples, the parameters that could characterize the natural roads were selected to construct a set of rules for information extraction of roads. Finally, information on roads was extracted and optimized by combining multiple methods for classification, among which the nearest neighbor classification method was used for preliminary extraction while other classification algorithms such as threshold classification were used for optimization. Consequently, natural roads with a length of 3 708.745 km were extracted in the study area, with a density of 0.129 km/km2. This result shows that the natural roads in the study area are densely distributed in the southeast and sparsely distributed in the north and west overall. These distribution characteristics are consistent with the actual production of coal mine enterprises and the living of local residents in the study area. Therefore, the method proposed in this study can extract almost complete information about natural roads in the study area and thus can be used as a reference for the information extraction of natural roads in vast arid and semi-arid regions of the Mongolian Plateau.
梁茜亚, 王卷乐, 李朋飞, DAVAADORJ Davaasuren. 基于GF-1影像的蒙古高原干旱半干旱地区自然道路提取——以蒙古国古尔班特斯苏木为例[J]. 自然资源遥感, 2023, 35(2): 122-131.
LIANG Xiya, WANG Juanle, LI Pengfei, DAVAADORJ Davaasuren. GF-1 images-based information extraction of natural roads in arid and semi-arid regions of the Mongolian Plateau: A case study of Gurvantes Soum, Mongolia. Remote Sensing for Natural Resources, 2023, 35(2): 122-131.
Zhang D P, De L, Zhao J M, et al. Research progress of grassland desertification caused by vehicle rolling[J]. Journal of Hulunbeier University, 2011, 19(3):82-88.
Zhang D P, Wang X K, Ha S, et al. HulunBuir sandy grassland blowouts:Geomorphology,classification,and significances[J]. Journal of Desert Research, 2006, 26(6):894-902,1052-1058.
Zhao X L, Yang G S. Reclamation of steppe and related desertification in three temperate zones of North Hemisphere[J]. Journal of Desert Research, 2002, 22(5):39-44.
[4]
Keshkamat S S, Tsendbazar N E, Zuidgeest M H P, et al. The environmental impact of not having paved roads in arid regions:An example from Mongolia[J]. Ambio, 2012, 41(2):202-205.
doi: 10.1007/s13280-011-0155-3
[5]
Lovich J E, Bainbridge D. Anthropogenic degradation of the southern California desert ecosystem and prospects for natural recovery and restoration[J]. Environmental Management, 1999, 24(3):309-326.
pmid: 10486042
[6]
Kinugasa T, Oda S. Effects of vehicle track formation on soil seed banks in grasslands with different vegetation in the Mongolian steppe[J]. Ecological Engineering, 2014, 67:112-118.
doi: 10.1016/j.ecoleng.2014.03.078
[7]
Stebbins R C. Off-Road and the fragile desert[J]. American Biology Teacher, 1974, 36(4):203-208,220.
doi: 10.2307/4444747
Chang Y M, Lei J Y, Li Y X, et al. Study on the road erosion characteristics and the effect factors in semiarid hilly region:Take the Southeast Siziwang County,Inner Mongolia as an example[J]. Research of Soil and Water Conservation, 2014, 21(5):116-121.
[9]
Batkhishig O. Human impact and land degradation in Mongolia[M]// Dryland East Asia:Land Dynamics amid Social and Climate Change.De Gruyter, 2013:265-282.
[10]
Davaadorj D, Byambabayar G, Oyunkhand B, et al. Soil erosion assessment in southern Mongolia:Case Study of Gurvates Soum[J]. Journal of Young Scientists, 2016(4):169-181.
[11]
MNEM(The Ministry of Nature and Environment of Mongolia). Country report on natural disasters in Mongolia[M]. Ulaanbaatar: MNEM, 1999.
[12]
National Statistics Office of Mongolia. Mongolia statistical yearbook 2016[M]. Ulaanbaatar: National Statistics Office of Mongolia, 2017.
Li X L, Zhang Y. Summary of road information extraction methods[J]. Bulletin of Surveying and Mapping, 2020(6):22-27.
doi: 10.13474/j.cnki.11-2246.2020.0174
Lyu J G. Road extraction based on object-oriented from high-resolution remote sensing images[J]. Journal of Shaanxi Normal University (Natural Science Edition), 2008, 36(s2):80-82.
He Y, Chen C M, Xiong Z L, et al. Object-oriented rural roads extraction based on eCognition[J]. Journal of Chongqing Jiaotong University (Natural Science), 2012, 31(6):1194-1197.
Gu H J. Research status of road network information extraction based on high resolution remote sensing images[J]. China Non-metallic Minerals Industry, 2018(4):53-54.
Chen C M. Rural road extraction base on object-oriented method with high-resolution remote sensing image[D]. Chongqing: Chongqing Jiaotong University, 2011.
[20]
Das S, Mirnalinee T T, Varghese K. Use of salient features for the design of a multistage framework to extract roads from high-resolution multispectral satellite images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(10):3906-3931.
doi: 10.1109/TGRS.2011.2136381
[21]
Courtrai L, Lefèvre S. Road network extraction from remote sensing using region-based mathematical morphology[C]// 2014 8th IAPR Workshop on Pattern Recognition in Remote Sensing.IEEE, 2014:1-4.
Zhou A X, Yu L, Feng J, et al. Road information extraction from high-resolution remote sensing image based on object-oriented image analysis method[J]. Geomatics & Spatial Information Technology, 2017, 40(2):1-4.
Wang Y, He H Y, Tan W, et al. High-resolution remote sensing image road extraction algorithm based on multi-feature fusion[J]. Remote Sensing Information, 2019, 34(1):111-116.
Yu B L, Liu H X, Wu J P. Exploring the theoretical framework of object-oriented analysis for urban spatial information using remote sensing data[J]. Journal of East China Normal University (Natural Science), 2010(6):12-25,63.
Xu G H, Liu Q H, Chen L F, et al. Remote sensing for China’s sustainable development:Opportunities and challenges[J]. Journal of Remote Sensing, 2016, 20(5):679-688.
[27]
白照广. 高分一号卫星的技术特点[J]. 中国航天, 2013(8):5-9.
Bai Z G. Technical characteristics of GF-1 satellite[J]. Aerospace China, 2013(8):5-9.
[28]
张宏伟. 高分辨率影像中农村道路提取方法研究[D]. 重庆: 重庆大学, 2016.
Zhang H W. The rural road extraction method research based on high resolution images[D]. Chongqing: Chongqing University, 2016.
Na Y T, Qin F Y, Jia G S, et al. Change trend and regional differen-tiation of precipitation over the Mongolian Plateau in recent 54 years[J]. Arid Land Geography, 2019, 42(6):1253-1261.
Sa C L, Liu G X, Bao G, et al. The spatial and temporal changes of snow cover of the Mongolian Plateau in recent 10 years[J]. Journal of Inner Mongolia Normal University (Natural Science Edition), 2012, 41(5):531-536.
Kang Y, Guo E L, Wang Y F, et al. Application of temperature vegetation dryness index for drought monitoring in Mongolian Plateau[J]. Chinese Journal of Applied Ecology, 2021, 32(7):2534-2544.
doi: 10.13287/j.1001-9332.202107.018
Sun W W, Yang G, Chen C, et al. Development status and literature analysis of China’s earth observation remote sensing satellites[J]. Journal of Remote Sensing (Chinese), 2020, 24(5):479-510.
Yu A J, Li G F, Zhang J B. Analysis on key points of data processing for GF-1 satellite in geographical situation monitoring[J]. Geomatics & Spatial Information Technology, 2020, 43(s1):91-93.
He Z Q, Liang S Y. Automatic extraction method of road information from high-resolution remote sensing image based on eCognition[J]. Sci-tech Innovation and Productivity, 2018(2):40-42,46.
[40]
胡建青. 面向对象的高分辨率遥感影像道路信息提取[D]. 北京: 北京交通大学, 2019.
Hu J Q. Object-oriented road information extraction from high resolution remote sensing images[D]. Beijing: Beijing Jiaotong University, 2019.
Zhang Y G, Zhang S W, Chen D Q. Analysis of elevation gradient change and land use landscape heterogeneity in Tonghua City[J]. System Sciences and Comprehensive Studies in Agriculture, 2010, 26(3):271-276.
Li Z L. Ceke port of Inner Mongolia imported of raw coal from Mongolia exceeded 2 million tons[EB/OL]. https://www.imsilkroad.com/news/p/30707.html,2014-04-15/2021-12-04.
Meng X Y, Qi X M, Tong B Q. Research on the influence of mineral resources exploitation on economic development in Mongolian[J]. Journal of Arid Land Resources and Environment, 2021, 35(12):100-105.
[46]
Mongolian Statistical Information Service[EB/OL]. http://1212.mn/,2021-12-02.