Combined time series coherence and backscattering coefficient for wetland classification in the Yellow River Delta

doi:10.13474/j.cnki.11-2246.2023.0040

Abstract

Abstract: To solve the problem that the backscattering coefficient is difficult to complete the high-precision wetland classification, this paper takes 16 VH Sentinel-1A images as the data source, and constructs a classification method combining time series coherence and backscattering coefficient. By analyzing the long time series backscattering coefficient and coherence, the backscattering coefficients map in three times (June 27 (R), November 18 (G) and November 30 (B)) that Spartina alterniflora is easily confused with other ground objects are selected as the synthetic data sources. Then the coherence map from November 18 to November 30 is introduced to replace the backscattering coefficients map in November 18. SVM and RF classifier are used to explore the accuracy variation before and after introducing coherence in the Yellow River Delta wetlands. The results show that the overall accuracy of classification results by SVM and RF improves by 3.07% and 3.85%, and the accuracy of Spartina alterniflora improves by 9.39% and 11.42%.

Key words: wetland classification, coherence, backscattering coefficient, Yellow River Delta, spartina alterniflora

CLC Number:

P237

LI Zhenjin, WANG Zhiyong, YE Kaile, LIU Xiaotong, TIAN Kang. Combined time series coherence and backscattering coefficient for wetland classification in the Yellow River Delta[J]. Bulletin of Surveying and Mapping, 2023, 0(2): 52-57,71.

References

[1] 苏锐.保护黄河流域生态助推文旅事业高质量发展: 习近平总书记考察山东引发热烈反响[N].中国文化报, 2021-10-25(1).
[2] 李禄康.湿地与湿地公约[J].世界林业研究, 2001, 14(1): 1-7.
[3] KONG Dongxian,MIAO Chiyuan,BORTHWICK A G L,et al.Evolution of the Yellow River Delta and its relationship with runoff and sediment load from 1983 to 2011[J].Journal of Hydrology,2015,520: 157-167.
[4] ZHANG Bowen,WANG R,DENG Yunkai,et al.Mapping the Yellow River Delta land subsidence with multitemporal SAR interferometry by exploiting both persistent and distributed scatterers[J].ISPRS Journal of Photogrammetry and Remote Sensing,2019,148: 157-173.
[5] PENG Mimi,ZHAO Chaoying,ZHANG Qin,et al.Multi-scale and multi-dimensional time series InSAR characterizing of surface deformation over Shandong peninsula,China[J].Applied Sciences,2020,10(7): 2294.
[6] ZUO Ping,ZHAO Shuhe,LIU Chang'an,et al.Distribution of Spartina spp.along China＆apos;s coast[J].Ecological Engineering,2012,40: 160-166.
[7] WAN Shuwen,QIN Pei,LIU Jine,et al.The positive and negative effects of exotic Spartina alterniflora in China[J].Ecological Engineering,2009,35(4): 444-452.
[8] 谢宝华,韩广轩.外来入侵种互花米草防治研究进展[J].应用生态学报,2018,29(10): 3464-3476.
[9] ZHANG Xi,XIAO Xiangming,WANG Xinxin,et al.Quantifying expansion and removal of Spartina alterniflora on Chongming Island,China,using time series Landsat images during 1995-2018[J].Remote Sensing of Environment,2020,247: 111916.
[10] ZHU Xudong,MENG Lingxuan,ZHANG Yihui,et al.Tidal and meteorological influences on the growth of invasive spartina alterniflora: evidence from UAV remote sensing[J].Remote Sensing,2019,11(10): 1208.
[11] 李春升,王伟杰,王鹏波,等.星载SAR技术的现状与发展趋势[J].电子与信息学报,2016,38(1):229-240.
[12] HU Yuekai,TIAN Bo,YUAN Lin,et al.Mapping coastal salt marshes in China using time series of Sentinel-1 SAR[J].ISPRS Journal of Photogrammetry and Remote Sensing,2021,173: 122-134.
[13] PAN Zhuokun,HU Yueming,WANG Guangxing.Detection of short-term urban land use changes by combining SAR time series images and spectral angle mapping[J].Frontiers of Earth Science,2019,13(3): 495-509.
[14] 刘睿,王志勇,高瑞.时序SAR影像的干旱地区土地利用分类应用[J].测绘科学,2021,46(10): 90-97.
[15] CANISIUS F,BRISCO B,MURNAGHAN K,et al.SAR backscatter and InSAR coherence for monitoring wetland extent,flood pulse and vegetation: a study of the Amazon lowland[J].Remote Sensing,2019,11(6): 720.
[16] NIKAEIN T,IANNINI L,MOLIJN R A,et al.On the value of Sentinel-1 InSAR coherence time-series for vegetation classification[J].Remote Sensing,2021,13(16): 3300.
[17] ZHANG Rui,TANG Zhanzhong,LUO Dong,et al.Combined multi-time series SAR imagery and InSAR technology for rice identification in cloudy regions[J].Applied Sciences,2021,11(15): 6923.
[18] 梁志锋,凌飞龙.基于ALOS PALSAR数据的森林/非森林分类[J].遥感信息,2013,28(2): 51-55.
[19] 高瑞,王志勇,周晓东,等.利用多时相遥感监测与分析黄河三角洲湿地变化动态[J].测绘通报,2021(4): 22-27.
[20] FENG Quanlong,YANG Jianyu,ZHU Dehai,et al.Integrating multitemporal Sentinel-1/2 data for coastal land cover classification using a multibranch convolutional neural network: a case of the Yellow River Delta[J].Remote Sensing,2019,11(9): 1006.
[21] 任广波,周莉,梁建,等.“高分五号”高光谱互花米草遥感识别与制图研究[J].海洋科学进展,2021,39(2): 312-326.
[22] CORTES C,VAPNIK V.Support-vector networks[J].Machine Learning,1995,20(3): 273-297.
[23] BREIMAN L.Random forests[J].Machine Learning,2001,45: 5-32.
[24] WANG Zhiyong,YE Kaile,ZHANG Mengyue,et al.Monitoring the wetland of the Yellow River Delta by combining GF-3 polarimetric synthetic aperture radar and Sentinel-2A multispectral data[J].Frontiers in Ecology and Evolution,2022,10: 806978.
[25] 曹爽,潘锁艳,管海燕.机载多光谱LiDAR的随机森林地物分类[J].测绘通报,2019(11): 79-84.