Automatic extraction of mountain river information from multiple Chinese high-resolution remote sensing satellite images

XUE Yuan; QIN Chao; WU Baosheng; LI Dan; FU Xudong

doi:10.16511/j.cnki.qhdxxb.2022.22.043

PDF(15407 KB)

Journal of Tsinghua University(Science and Technology) ›› 2023, Vol. 63 ›› Issue (1) : 134-145. DOI: 10.16511/j.cnki.qhdxxb.2022.22.043

CIVIL ENGINEERING

Automatic extraction of mountain river information from multiple Chinese high-resolution remote sensing satellite images

{{article.zuoZhe_EN}}

Author information +

History +

Abstract

High-resolution geomorphic information from remote sensing images is a key part of mountain river research. However, the complete information about narrow rivers is difficult to extract automatically and accurately from complex backgrounds, especially with mountain shadows. This research uses a random forest (RF) algorithm with an artificial neural network (ANN), RF-ANN, to analyze remote sensing images. This method supports parallel operations and reduces the scale of the infrared data for noise removal to achieve pixel-level extraction of the river surfaces. The RivWidthCloud (RWC) method is improved using Laplacian and edge algorithms for automatic extraction of the bankfull river widths. The improved RWC method is generalizable since it does not require setting the discriminant threshold manually. The method is then applied to the Huangfuchuan River Basin on the Loess Plateau, China using images from the Chinese GF-1 and ZY-3 satellites as the primary data source to extract the river surfaces and widths of the rivers above level 2. The results show that the RF-ANN method has a 94.7% accuracy for extracting river surfaces. The bankfull river width extraction error is 1.07 m (about 0.5 pixels) and the minimum river width extracted by these methods is 6.1 m (about 3 pixels). R² is 0.93 and the root men square errors (RMSE) is 1.52 for fitting the extracted river widths and the test river widths. For small rivers narrower than 10 m, the extraction error is 18.5%, for widths from 10 to 30 m the error is 8.8%, for widths from 30 to 90 m the error is 2.0%, and for rivers wider than 90 m the error is 0.7%. These results provide accurate datasets for watershed topography research in mountainous and other complex topographic regions.

Key words

Chinese high-resolution satellites / mountain river surface information / bankfull river width / automatic extraction

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

XUE Yuan, QIN Chao, WU Baosheng, LI Dan, FU Xudong. Automatic extraction of mountain river information from multiple Chinese high-resolution remote sensing satellite images[J]. Journal of Tsinghua University(Science and Technology). 2023, 63(1): 134-145 https://doi.org/10.16511/j.cnki.qhdxxb.2022.22.043

References

[1] FRIEDL M A, SULLA-MENASHE D, TAN B, et al. MODIS Collection 5 global land cover: Algorithm refinements and characterization of new datasets [J]. Remote Sensing of Environment, 2010, 114(1): 168-182.
[2] FEYISA G L, MEILBY H, FENSHOLT R, et al. Automated water extraction index: A new technique for surface water mapping using Landsat imagery [J]. Remote Sensing of Environment, 2014, 140: 23-35.
[3] 李丹, 吴保生, 陈博伟, 等. 基于卫星遥感的水体信息提取研究进展与展望[J]. 清华大学学报(自然科学版), 2020, 60(2): 147-161. LI D, WU B S, CHEN B W, et al. Review of water body information extraction based on satellite remote sensing [J]. Journal of Tsinghua University (Science and Technology), 2020, 60(2): 147-161. (in Chinese)
[4] MEDINA C, GOMEZ-ENRI J, ALONSO J J, et al. Water volume variations in Lake Izabal (Guatemala) from in situ measurements and ENVISAT radar altimeter (RA-2) and advanced synthetic aperture radar (ASAR) data products [J]. Journal of Hydrology, 2010, 382(1-4): 34-48.
[5] NATH R K, DEB S K. Water-body area extraction from high resolution satellite images: An introduction, review, and comparison [J]. International Journal of Image Processing, 2010, 3(6): 353-372.
[6] FRAZIER P S, PAGE K J. Water body detection and delineation with Landsat TM data [J]. Photogrammetric Engineering and Remote Sensing, 2000, 66(12): 1461-1467.
[7] 毛海颖, 冯仲科, 巩垠熙, 等. 多光谱遥感技术结合遗传算法对永定河土壤归一化水体指数的研究[J]. 光谱学与光谱分析, 2014, 34(6): 1649-1655. MAO H Y, FENG Z K, GONG Y X, et al. Researches of soil normalized difference water index (NDWI) of Yongding River based on multispectral remote sensing technology combined with genetic algorithm [J]. Spectroscopy and Spectral Analysis, 2014, 34(6): 1649-1655. (in Chinese)
[8] SHARMA O, MIOC D, ANTON F. Feature extraction and simplification from colour images based on colour image segmentation and skeletonization using the quad-edge data structure [C]//Proceedings of the International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision. Plzen, Czech, 2007: 225-232.
[9] LI D, WANG G, QIN C, et al. River extraction under bankfull discharge conditions based on Sentinel-2 imagery and DEM data [J]. Remote Sensing, 2021, 13(14): 2650.
[10] 王航, 秦奋. 遥感影像水体提取研究综述[J]. 测绘科学, 2018, 43(5): 23-32. WANG H, QIN F. Summary of the research on water body extraction and application from remote sensing image [J]. Science of Surveying and Mapping, 2018, 43(5): 23-32. (in Chinese)
[11] MCFEETERS S K. The use of the normalized difference water index (NDWI) in the delineation of open water features [J]. International Journal of Remote Sensing, 1996, 17(7): 1425-1432.
[12] WANG S D, BAIG M H A, ZHANG L F, et al. A simple enhanced water index (EWI) for percent surface water estimation using Landsat data [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(1): 90-97.
[13] SUN F D, SUN W X, CHEN J, et al. Comparison and improvement of methods for identifying waterbodies in remotely sensed imagery [J]. International Journal of Remote Sensing, 2012, 33(21): 6854-6875.
[14] SAFAVIAN S R, LANDGREBE D. A survey of decision tree classifier methodology [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1991, 21(3): 660-674.
[15] 张红梅, 王大卫, 高杨, 等. 基于OLI数据与决策树法的去山体阴影水体信息提取研究[J]. 测绘工程, 2017, 26(11): 45-48, 54. ZHANG H M, WANG D W, GAO Y, et al. A study of extraction method of mountain surface water based on OLI data and decision tree method [J]. Engineering of Surveying and Mapping, 2017, 26(11): 45-48, 54. (in Chinese)
[16] ACHARYA T D, LEE D H, YANG I T, et al. Identification of water bodies in a Landsat 8 OLI image using a J48 decision tree [J]. Sensors, 2016, 16(7): 1075.
[17] PEKEL J F, COTTAM A, GORELICK N, et al. High- resolution mapping of global surface water and its long-term changes [J]. Nature, 2016, 540(7633): 418-422.
[18] ALLEN G H, PAVELSKY T M. Global extent of rivers and streams [J]. Science, 2018, 361(6402): 585-588.
[19] 葛锦涛, 姜琦刚, 李相坤, 等. 基于高分一号影像的半干旱地区土地利用信息提取方法对比分析: 以建平为例[J]. 世界地质, 2017, 36(4): 1303-1308. GE J T, JIANG Q G, LI X K, et al. Comparison and analysis of information extraction methods of semiarid land utilization based on GF1 image: Taking Jianping as an example [J]. Global Geology, 2017, 36(4): 1303-1308. (in Chinese)
[20] 刘兆祎, 李鑫慧, 沈润平, 等. 高分辨率遥感图像分割的最优尺度选择[J]. 计算机工程与应用, 2014, 50(6): 144-147. LIU Z Y, LI X H, SHEN R P, et al. Selection of the best segmentation scale in high-resolution image segmentation [J]. Computer Engineering and Applications, 2014, 50(6): 144-147. (in Chinese)
[21] 刘小丹, 于宁. 河流湿地遥感图像分层次多尺度分割[J]. 网络新媒体技术, 2016, 5(5): 51-59. LIU X D, YU N. Hierarchical multi-scale segmentation of riverine wetland remote sensing image [J]. Journal of Network New Media, 2016, 5(5): 51-59. (in Chinese)
[22] LIANG X, HU W Y. A coupled co-occurrence matrix/multi-scale segmentation method to extract water from high resolution remote sensing image [C]//201826th International Conference on Geoinformatics. Kunming, China, 2018: 1-4.
[23] 薛源, 李丹, 吴保生, 等. 利用国产GF-1卫星数据实现山区细小河流河宽的自动提取[J]. 测绘通报, 2020(3): 12-16. XUE Y, LI D, WU B S, et al. Automatic extraction of small mountain river information and width based on China-made GF-1 satellites remote sensing images [J]. Bulletin of Surveying and Mapping, 2020(3): 12-16. (in Chinese)
[24] BREIMAN L. Random forests [J]. Machine Learning, 2001, 45(1): 5-32.
[25] TALUKDAR S, SINGHA P, MAHATO S, et al. Land-use land-cover classification by machine learning classifiers for satellite observations: A review [J]. Remote Sensing, 2020, 12(7): 1135.
[26] ACHARYA T D, SUBEDI A, LEE D H. Evaluation of machine learning algorithms for surface water extraction in a Landsat 8 scene of Nepal [J]. Sensors, 2019, 19(12): 2769.
[27] PAL M, MATHER P M. An assessment of the effectiveness of decision tree methods for land cover classification [J]. Remote Sensing of Environment, 2003, 86(4): 554-565.
[28] AUNG E M M, TINT T. Ayeyarwady river regions detection and extraction system from Google Earth imagery [C]//2018 IEEE International Conference on Information Communication and Signal Processing (ICICSP). Singapore, 2018: 74-78.
[29] 李玲玲. 若干典型地物温度变化特征试验研究[D]. 沈阳: 东北大学, 2009. LI L L. Experimental study of the temperature variation characteristic of some typical ground objects [D]. Shenyang: Northeastern University, 2009. (in Chinese)
[30] 王爱辉, 杨英宝, 潘鑫, 等. 地表温度日变化模型偏差系数解算的地表温度降尺度[J]. 遥感学报, 2021, 25(8): 1735-1748. WANG A H, YANG Y B, PAN X, et al. Research on land surface temperature downscaling method based on diurnal temperature cycle model deviation coefficient calculation [J]. National Remote Sensing Bulletin, 2021, 25(8): 1735-1748. (in Chinese)
[31] SHEN Y, SHEN H F, LI H F, et al. Long-term urban impervious surface monitoring using spectral mixture analysis: A case study of Wuhan City in China [C]//2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Beijing, China, 2016: 6754-6757.
[32] LIU T, YANG X J. Mapping vegetation in an urban area with stratified classification and multiple endmember spectral mixture analysis [J]. Remote Sensing of Environment, 2013, 133: 251-264.
[33] ZHANG Y. A method for continuous extraction of multispectrally classified urban rivers [J]. Photogrammetric Engineering and Remote Sensing, 2000, 66(8): 991-999.
[34] WEI H, BI F K, LIU F Q, et al. Water body extraction based on the LBV transformation analysis for China GF-1 multi-spectral images [C]//IET International Radar Conference 2015. Hangzhou, China, 2015: 1-5.
[35] LI D, WU B S, CHEN B W, et al. Open-surface river extraction based on Sentinel-2 MSI imagery and DEM data: Case study of the upper Yellow River [J]. Remote Sensing, 2020, 12(17): 2737.
[36]章斯腾, 陆欣, 陆瑶, 等. 青藏高原河流网络高分CubeSat遥感监测[J]. 遥感学报, 2021, 25(10): 2142-2152. ZHANG S T, LU X, LU Y, et al. Tracking dynamic river networks in the Tibetan Plateau with high-resolution CubeSat imagery [J]. National Remote Sensing Bulletin, 2021, 25(10): 2142-2152. (in Chinese)
[36] YANG X, PAVELSKY T M, ALLEN G H, et al. RivWidthCloud: An automated Google Earth engine algorithm for river width extraction from remotely sensed imagery [J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(2): 217-221.
[37] RAYMOND P A, HARTMANN J, LAUERWALD R, et al. Global carbon dioxide emissions from inland waters [J]. Nature, 2013, 503(7476): 355-359.
[38] WANG G Q, FU X D, SHI H Y, et al. Watershed sediment dynamics and modeling: A watershed modeling system for Yellow River [M]//YANG C T, WANG L K. Advances in water re- sources engineering. Cham, Switzerland: Springer, 2015: 1-40.
[39] YANG D W, HERATH S, MUSIAKE K. A hillslope-based hydrological model using catchment area and width functions [J]. Hydrological Sciences Journal, 2002, 47(1): 49-65.
[40] 王冰洁, 傅旭东. 皇甫川流域含沙量-流量关系年内年际变化特性[J]. 应用基础与工程科学学报, 2020, 28(3): 642-651. WANG B J, FU X D. Intra- and inter-annual variations in the relationship between suspended sediment concentration and discharge of the Huangfuchuan watershed [J]. Journal of Basic Science and Engineering, 2020, 28(3): 642-651. (in Chinese)
[41] XU H, TAYLOR R G, XU Y. Quantifying uncertainty in the impacts of climate change on river discharge in sub-catchments of the Yangtze and Yellow River Basins, China [J]. Hydrology and Earth System Sciences, 2011, 15(1): 333-344.
[42] PAGE K, READ A, FRAZIER P, et al. The effect of altered flow regime on the frequency and duration of bankfull discharge: Murrumbidgee River, Australia [J]. River Research and Applications, 2005, 21(5): 567-578.
[43] 钱宁, 张仁, 周志德. 河床演变学[M]. 北京: 科学出版社, 1987. QIAN N, ZHANG R, ZHOU Z D. Fluvial processes [M]. Beijing: Science Press, 1987. (in Chinese)
[44] ZHANG X B, ZWIERS F W, HEGERL G C, et al. Detection of human influence on twentieth-century precipitation trends [J]. Nature, 2007, 448(7152): 461-465.
[45] 覃超, 吴保生, 傅旭东, 等. 时空维度拓展的河相关系研究进展[J]. 泥沙研究, 2022, 47(2): 73-80. QIN C, WU B S, FU X D, et al. Progresses of hydraulic geometry study regarding the extension of spatiotemporal dimensions[J]. Journal of Sediment Research, 2022, 47(2): 73-80. (in Chinese)
[46] 覃超, 吴保生, 汪舸, 等. 青藏高原山区河流广义河相关系与多频率沿程河相关系[J]. 水利学报, 2022, 53(2): 176-187. QIN C, WU B S, WANG G, et al. Generalized hydraulic geometry and multi-frequency downstream hydraulic geometry of mountain rivers originated from the Qinghai-Tibet Plateau [J]. Journal of Hydraulic Engineering, 2022, 53(2): 176-187. (in Chinese)
[47] 唐新明, 胡芬. 卫星测绘发展现状与趋势[J]. 航天返回与遥感, 2018, 39(4): 26-35. TANG X M, HU F. Development status and trend of satellite mapping [J]. Spacecraft Recovery & Remote Sensing, 2018, 39(4): 26-35. (in Chinese)
[48] STEHMAN S V, CZAPLEWSKI R L. Design and analysis for thematic map accuracy assessment: Fundamental principles [J]. Remote Sensing of Environment, 1998, 64(3): 331-344.
[49] MUKHERJEE S, JOSHI P K, MUKHERJEE S, et al. Evaluation of vertical accuracy of open source digital elevation model (DEM) [J]. International Journal of Applied Earth Observation and Geoinformation, 2013, 21: 205-217.
[50] 唐新明, 王鸿燕, 祝小勇. 资源三号卫星测绘技术与应用[J]. 测绘学报, 2017, 46(10): 1482-1491. TANG X M, WANG H Y, ZHU X Y. Technology and applications of surveying and mapping for ZY-3 satellites [J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10): 1482-1491. (in Chinese)
[51] WU T, LI J Y, LI T J, et al. High-efficient extraction of drainage networks from digital elevation models constrained by enhanced flow enforcement from known river maps [J]. Geomorphology, 2019, 340: 184-201.
[52] 陈桥驿, 蔡宜泳. 热红外遥感反演地表温度研究进展[J]. 安徽农业科学, 2013, 41(4): 1832-1835, 1843. CHEN Q Y, CAI Y Y. Research progress in retrieving land surface temperature based on thermal infrared remote sensing technologies [J]. Journal of Anhui Agricultural Sciences, 2013, 41(4): 1832-1835, 1843. (in Chinese)
[53] 段四波, 茹晨, 李召良, 等. Landsat卫星热红外数据地表温度遥感反演研究进展[J]. 遥感学报, 2021, 25(8): 1591-1617. DUAN S B, RU C, LI Z L, et al. Reviews of methods for land surface temperature retrieval from Landsat thermal infrared data [J]. Journal of Remote Sensing, 2021, 25(8): 1591-1617. (in Chinese)
[54] QIN Z, KARNIELI A, BERLINER P. A mono-window algorithm for retrieving land surface temperature from Landsat TM data and its application to the Israel-Egypt border region [J]. International Journal of Remote Sensing, 2001, 22(18): 3719-3746.
[55] JIMÉNEZ-MUÑOZ J C, SOBRINO J A. A generalized single-channel method for retrieving land surface temperature from remote sensing data [J]. Journal of Geophysical Research: Atmospheres, 2003, 108(D22): 4688.
[56] LI Z L, TANG B H, WU H, et al. Satellite-derived land surface temperature: Current status and perspectives [J]. Remote Sensing of Environment, 2013, 131: 14-37.
[57] KOHAVI R. A study of cross-validation and bootstrap for accuracy estimation and model selection [C]//Proceedings of the 14th International Joint Conference on Artificial Intelligence. Montréal, Canada: Morgan Kaufmann Publishers, 1995: 1137-1143.
[58] FISHER A, FLOOD N, DANAHER T. Comparing Landsat water index methods for automated water classification in eastern Australia [J]. Remote Sensing of Environment, 2016, 175: 167-182.
[59] PAVELSKY T M, SMITH L C. RivWidth: A software tool for the calculation of river widths from remotely sensed imagery [J]. IEEE Geoscience and Remote Sensing Letters, 2008, 5(1): 70-73.