ASTER GDEM and SRTM1 Elevation Data Integration with RProp Neural Network
-
摘要: 由于数据获取与后期处理方式不同，先进星载热发射和反射辐射仪全球数字高程模型(advanced spaceborne thermal emission and reflection radiometer global digital elevation model，ASTER GDEM)和航天飞机雷达地形测绘任务(shuttle radar topography mission，SRTM)数据在高程精度上存在差异，采用弹性反馈（resilient backpropagation，RProp）神经网络算法对二者进行融合处理，实现优势互补以提升高程精度。选取两个黄土丘陵沟壑地貌样区分别用于模型建立与效果验证，1∶10 000高程精度为参考数据，在建模样区应用RProp神经网络算法构建ASTER GDEM高程校正模型、SRTM1高程校正模型、ASTER GDEM与SRTM1高程融合模型，同时应用误差反向传播(back propagation，BP)神经网络建立ASTER GDEM与SRTM1高程融合模型，将这些模型的高程精度优化效果进行对比，并在验证样区检验RProp融合模型的可行性。结果表明，RProp融合模型的高程校正效果整体上优于ASTER GDEM高程校正模型、SRTM1高程校正模型和BP神经网络融合模型，高程均方根误差分别降低6.81 m、0.34 m与0.19 m，具有良好的适用性与误差校正效果。Abstract:Objectives There exist some differences between the elevation accuracy of advanced spaceborne thermal emission and reflection radiometer global digital elevation model (ASTER GDEM) and shuttle radar topography mission (SRTM) data, because their methods of data acquisition and post-processing are different.Methods To improve the DEM accuracy by taking advantages of ASTER GDEM and SRTM, the resilient backpropagation (RProp) neural network algorithm is adopted to integrate them. First, we use two units in loess hilly gully topography as test areas to construct models and validate their effects. Second, we take 1∶10 000 DEM as the reference data to construct the corrected ASTER GDEM elevation model, the corrected SRTM1 elevation model and the integrated elevation model of ASTER GDEM and SRTM1 by RProp neural network algorithm. Meanwhile, the integrated elevation model of ASTER GDEM and SRTM1 is created with back propagation (BP) neural network. Then, the optimized effects of elevation precision of these models are analyzed. Finally, the model integrated by RProp is tested in the validation site.Results The results show that the model integrated by RProp is better than the corrected ASTER GDEM elevation model, the corrected SRTM1 elevation model, and the model integrated by BP neural network, and its elevation deviation is reduced by 6.81 m, 0.34 m, 0.19 m, respectively.Conclusions It confirms that the model integrated by RProp has good applicability and error correction effect.
-
-
表 1 RProp模型预测精度/m
Table 1 Prediction Accuracy of RProp Models/m
类型 1/4分位数 3/4分位数 RMSE MAE GDEM $ - $3.26 15.47 14.63 12.48 SRTM1 $ - $4.80 12.00 11.79 10.03 RProp(GDEM) $ - $8.03 8.29 13.52 10.45 RProp(SRTM1) $ - $4.96 5.08 8.58 6.28 RProp(GDEM, SRTM1) 0.98 $ - $4.90 7.71 6.03 
下载: 导出CSV
表 2 RProp(GDEM, SRTM1)和BP(GDEM, SRTM1)分析结果/m
Table 2 Analysis Results of RProp(GDEM, SRTM1) and BP(GDEM, SRTM1)/m
模型 t p 最小值 最大值 MAE RMSE GDEM SRTM1 GDEM SRTM1 RProp(GDEM, SRTM1) 26.83 23.60 < $ 2.2\times {10}^{-16} $ < $ 2.2\times {10}^{-16} $ $ - $33.92 26.92 6.03 7.71 BP(GDEM, SRTM1) 25.87 22.18 < $ 2.2\times {10}^{-16} $ < $ 2.2\times {10}^{-16} $ $ - $34.26 28.56 6.47 8.32 差值 0.96 1.42 0 0 0.34 $ - $1.64 $ - $0.44 $ - $0.61
下载: 导出CSV
表 3 验证区RProp与BP神经网络模型比较结果/m
Table 3 Comparison of Results Obtained by RProp and BP Neural Network Models in the Verification Area/m
模型 最小值 1/4分位数 中位数 MAE 3/4分位数 最大值 RMSE GDEM $ - $69.69 $ - $7.11 2.80 12.82 12.90 75.57 16.36 SRTM1 $ - $38.83 $ - $5.59 3.10 10.82 11.91 40.99 13.14 RProp(GDEM) $ - $54.58 $ - $9.57 0.86 12.36 10.38 64.61 15.85 RProp(SRTM1) $ - $28.17 $ - $5.35 1.09 7.37 6.77 35.05 9.38 RProp(GDEM, SRTM1) $ - $27.53 $ - $5.97 0.31 7.27 6.72 28.87 9.04 BP(GDEM, SRTM1) $ - $29.58 $ - $5.75 0.40 7.35 6.83 31.65 9.23
下载: 导出CSV
-
[1] 汤国安. 我国数字高程模型与数字地形分析研究进展[J]. 地理学报, 2014, 69(9): 1305-1325. https://www.cnki.com.cn/Article/CJFDTOTAL-DLXB201409007.htm Tang Guoan. Progress of DEM and Digital Terrain Analysis in China[J]. Acta Geographica Sinica, 2014, 69(9): 1305-1325 https://www.cnki.com.cn/Article/CJFDTOTAL-DLXB201409007.htm
[2] 苟娇娇, 王飞, 罗明良, 等. 基于DEM的黄土高原沟谷节点分形特征研究[J]. 水土保持学报, 2016, 30(3): 109-114. doi: 10.13870/j.cnki.stbcxb.2016.03.020 Gou Jiaojiao, Wang Fei, Luo Mingliang, et al. Fractal Characteristics of Channel Junctions(CJs)Based on DEM[J]. Journal of Soil and Water Conservation, 2016, 30(3): 109-114 doi: 10.13870/j.cnki.stbcxb.2016.03.020
[3] 陈加兵, 李慧, 陈文惠, 等. 基于DEM与DLG的福建省地貌形态自动分类[J]. 地球信息科学学报, 2013, 15(1): 75-80. https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX201301012.htm Chen Jiabing, Li Hui, Chen Wenhui, et al. Auto-classification of Geomorphological Types Based on DLG and DEM for Fujian Province[J]. Journal of Geo-Information Science, 2013, 15(1): 75-80 https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX201301012.htm
[4] 关小荣. SRTM DEM和ASTER GDEM误差的空间分布特征[D]. 南京: 南京师范大学, 2017. Guan Xiaorong. Spatial Distribution of SRTM DEM and ASTER GDEM Error[D]. Nanjing: Nanjing Normal University, 2017
[5] 张泉, 杨勤科, 程洁, 等. 中国地区3″ SRTM高程误差特征[J]. 武汉大学学报(信息科学版), 2018, 43(5): 684-690. doi: 10.13203/j.whugis20160347 Zhang Quan, Yang Qinke, Cheng Jie, et al. Characteristics of 3″ SRTM Errors in China[J]. Geomatics and Information Science of Wuhan University, 2018, 43(5): 684-690 doi: 10.13203/j.whugis20160347
[6] Sun G, Ranson K J, Kimes D S, et al. Forest Vertical Structure from GLAS: An Evaluation Using LVIS and SRTM Data[J]. Remote Sensing of Environment, 2008, 112(1): 107-117. doi: 10.1016/j.rse.2006.09.036
[7] Hu Z H, Peng J W, Hou Y L, et al. Evaluation of Recently Released Open Global Digital Elevation Models of Hubei, China[J]. Remote Sensing, 2017, 9(3): 262. doi: 10.3390/rs9030262
[8] Zhang Q, Yang Q K, Wang C M. SRTM Error Distribution and Its Associations with Landscapes Across China[J]. Photogrammetric Engineering & Remote Sensing, 2016, 82(2): 135-148.
[9] 胡加佩, 关小荣, 刘学军. 中国区域SRTM DEM与ASTER GDEM误差空间分布特征[J]. 地理与地理信息科学, 2017, 33(4): 28-33. https://www.cnki.com.cn/Article/CJFDTOTAL-DLGT201704005.htm Hu Jiapei, Guan Xiaorong, Liu Xuejun. Spatial Distribution of SRTM DEM and ASTER GDEM Error in China[J]. Geography and Geo-Information Science, 2017, 33(4): 28-33 https://www.cnki.com.cn/Article/CJFDTOTAL-DLGT201704005.htm
[10] Pham H T, Marshall L, Johnson F, et al. A Method for Combining SRTM DEM and ASTER GDEM2 to Improve Topography Estimation in Regions Without Reference Data[J]. Remote Sensing of Environment, 2018, 210: 229-241. doi: 10.1016/j.rse.2018.03.026
[11] 陈传法, 郑作亚, 岳天祥. 基于快速傅里叶变换的ASTER与SRTM有效融合研究[J]. 国土资源遥感, 2010, 22(4): 19-22. https://www.cnki.com.cn/Article/CJFDTOTAL-GTYG201004006.htm Chen Chuanfa, Zheng Zuoya, Yue Tianxiang. Efficient Fusion of ASTER and SRTM Based on Fast Fourier Transform[J]. Remote Sensing for Land & Resources, 2010, 22(4): 19-22 https://www.cnki.com.cn/Article/CJFDTOTAL-GTYG201004006.htm
[12] 孙亮, 严薇, 刘平芝, 等. 采用小波分析的SRTM DEM与ASTER DEM数据融合[J]. 测绘科学技术学报, 2014, 31(4): 388-392. https://www.cnki.com.cn/Article/CJFDTOTAL-JFJC201404013.htm Sun Liang, Yan Wei, Liu Pingzhi, et al. Data Fusion of SRTM DEM and ASTER DEM Based on Wavelet Analysis[J]. Journal of Geomatics Science and Technology, 2014, 31(4): 388-392 https://www.cnki.com.cn/Article/CJFDTOTAL-JFJC201404013.htm
[13] 沈焕锋, 刘露, 岳林蔚, 等. 多源DEM融合的高差拟合神经网络方法[J]. 测绘学报, 2018, 47(6): 854-863. https://www.cnki.com.cn/Article/CJFDTOTAL-CHXB201806019.htm Shen Huanfeng, Liu Lu, Yue Linwei, et al. A Multi-source DEM Fusion Method Based on Elevation Difference Fitting Neural Network[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(6): 854-863 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXB201806019.htm
[14] 岳林蔚. 多源多尺度DEM数据融合方法与应用研究[D]. 武汉: 武汉大学, 2017. Yue Linwei. Research on DEM Fusion Blending Multi-source and Multi-scale Elevation Data[D]. Wuhan: Wuhan University, 2017
[15] 岳林蔚, 刘修国, 沈焕锋, 等. 基于深度置信网络的多源DEM点面融合模型[J]. 武汉大学学报(信息科学版), 2021, 46(7): 1090-1097. doi: 10.13203/j.whugis20190238 Yue Linwei, Liu Xiuguo, Shen Huanfeng, et al. A Deep Belief Network Based Multi-source DEM Fusion Model[J]. Geomatics and Information Science of Wuhan University, 2021, 46(7): 1090-1097 doi: 10.13203/j.whugis20190238
[16] Riedmiller M, Braun H. A Direct Adaptive Method for Faster Backpropagation Learning: The RProp Algorithm[C]//IEEE International Conference on Neural Networks, San Francisco, USA, 2002.
[17] Suwandana E, Kawamura K, Sakuno Y, et al. Thematic Information Content Assessment of the ASTER GDEM: A Case Study of Watershed Delineation in West Java, Indonesia[J]. Remote Sensing Letters, 2012, 3(5): 423-432.
[18] 汪凌. 美国航天飞机雷达地形测绘使命简介[J]. 测绘通报, 2000(12): 38-40. https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB200012019.htm Wang Ling. Brief Introduction of Radar Topographic Mapping Mission of US Space Shuttle[J]. Bulletin of Surveying and Mapping, 2000(12): 38-40 https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB200012019.htm
[19] 马延慈, 明艳芳, 王凯, 等. 基于高分辨率人工识别地表类型的GlobeLand30产品精度评价[J]. 山东科技大学学报(自然科学版), 2018, 37(5): 1-10. https://www.cnki.com.cn/Article/CJFDTOTAL-SDKY201805001.htm Ma Yanci, Ming Yanfang, Wang Kai, et al. Precision Evaluation of GlobeLand30 Products Based on High-Resolution Artificial Identification Land Type[J]. Journal of Shandong University of Science and Technology (Natural Science), 2018, 37(5): 1-10 https://www.cnki.com.cn/Article/CJFDTOTAL-SDKY201805001.htm
[20] Tran T A, Raghavan V, Masumoto S, et al. A Geomorphology-based Approach for Digital Elevation Model Fusion—Case Study in Danang City, Vietnam[J]. Earth Surface Dynamics, 2014, 2(2): 403-417.
[21] Dong Y F, Shortridge A M. A Regional ASTER GDEM Error Model for the Chinese Loess Plateau[J]. International Journal of Remote Sensing, 2019, 40(3): 1048-1065.
[22] 郭海荣, 焦文海, 杨元喜. 1985国家高程基准与全球似大地水准面之间的系统差及其分布规律[J]. 测绘学报, 2004, 33(2): 100-104. https://www.cnki.com.cn/Article/CJFDTOTAL-CHXB200402002.htm Guo Hairong, Jiao Wenhai, Yang Yuanxi. The Systematic Difference and Its Distribution Between the 1985 National Height Datum and the Global Quasigeoid[J]. Acta Geodaetica et Cartographic Sinica, 2004, 33(2): 100-104 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXB200402002.htm
[23] Shortridge A, Messina J. Spatial Structure and Landscape Associations of SRTM Error[J]. Remote Sensing of Environment, 2011, 115(6): 1576-1587.
[24] Sarkar D. Methods to Speed up Error Back-Propagation Learning Algorithm[J]. ACM Computing Surveys, 1995, 27(4): 519-544.
[25] 曹海迪. 基于RPROP神经网络的输电线路故障分析研究[D]. 淮南: 安徽理工大学, 2017. Cao Haidi. Fault Analysis of Transmission Line Based on RProp Neural Network[D]. Huainan: Anhui University of Science & Technology, 2017
[26] 李卫红, 闻磊, 陈业滨. 改进的GA-BP神经网络模型在财产犯罪预测中的应用[J]. 武汉大学学报(信息科学版), 2017, 42(8): 1110-1116. doi: 10.13203/j.whugis20160911 Li Weihong, Wen Lei, Chen Yebin. Property Crime Forecast Based on Improved GA-BP Neural Network Model[J]. Geomatics and Information Science of Wuhan University, 2017, 42(8): 1110-1116 doi: 10.13203/j.whugis20160911
-
期刊类型引用(3)
1. 周永章，陈川，张旗，王功文，肖凡，沈文杰，卞静，王亚，杨威，焦守涛，刘艳鹏，韩枫. 地质大数据分析的若干工具与应用. 大地构造与成矿学. 2020(02): 173-182 . 
百度学术
2. 王叶晨梓，杜震洪，张丰，刘仁义. 面向分片地图的多分辨率格点数据统一存取方法. 浙江大学学报(理学版). 2017(05): 584-590 . 百度学术
3. 朱建章，石强，陈凤娥，史晓丹，董泽民，秦前清. 遥感大数据研究现状与发展趋势. 中国图象图形学报. 2016(11): 1425-1439 . 百度学术
其他类型引用(6)
计量
- 文章访问数: 392
- HTML全文浏览量: 106
- PDF下载量: 51
- 被引次数: 9
