Earthquake-triggered landslides detection in cloudy area of Haiti based on Google Earth Engine and Sentinel-2 time series data
-
摘要:
受云雾影响，强震震后的高分辨率光学影像质量较低，限制了震后地震滑坡调查和评估工作的开展。本文以2021年8月14日海地尼普斯（Nippes） MW7.2地震附近区域为研究区，基于谷歌地球引擎（Google Earth Engine）云平台和Sentinel-2时间序列影像，提出了一种遥感序列影像去云和地震滑坡识别的方法。首先，利用Sentinel-2遥感影像及机器学习算法获取的Sentinel-2云概率数据产品，对长时间序列遥感影像进行去云处理，镶嵌融合得到无云的影像数据；然后对无云光学影像进行多尺度最优分割，利用遥感数据的光谱特征、植被指数、不同类别的空间邻近关系特征等，构建了面向对象的地震滑坡识别模型。结果显示，本文提出的去云和滑坡识别方法有益于多云地区强震震后滑坡空间分布的准确识别，能够为灾后应急调查和评估提供技术支撑。
Abstract:Earthquakes can trigger numerous and widely distributed landslides. Rapid mapping of landslides with high accuracy is crucial for understanding their spatial patterns, and assessing landslide hazards and risks. Visual interpretation or automatic recognition are conventional methods for earthquake-triggered landslide mapping. Due to the influence of post-earthquake rainfall, cloud coverage rate of high-resolution optical remote sensing images is generally high, which limit investigation and assessment of earthquake-triggered landslides. Based on the Google Earth Engine platform, this work proposed a method for removing cloud and cloudless images using Sentinel-2 time series data and the cloud probability dataset. Through comparing performance of different time period, Sentinel-2 time series from 14th August 2021 to 31th January 2022 were chosen with 20% cloud coverage rate. This work masked all pixels covering by cloud and replaced them with cloud-free pixels in the images of adjacent time, producing high quality cloudless mosaic images covering the study area. The proposed method can improve the quality of post-earthquake images effectively. Then, an object-oriented model for earthquake-triggered landslide recognition is constructed based on the cloud-free mosaic images. Firstly, the multiscale segmentation algorithm was applied to the cloudless mosaic images to generate numerous objects. Then, multiple features were calculated based on every object, including spectral features, vegetation index and spatial proximity relationship between adjacent objects belonging to different class. Finally, earthquake-triggered landslides were classified used membership function based on thresholds of multiple features. Taking 2021 Haiti Nippes Earthquake as a case study, this work implemented the proposed method. Meanwhile, evaluation of classification results was carried out based on using manually interpreted landslides using high-resolution Planet images with 3-meter resolution in the validating area. The precision of the method is 77.5%, recall is 52.77% and F1 index is 62.79%. The results show that the proposed methods benefit earthquake-triggered landslides detection in the cloudy area and can provide technical support for post-disaster emergency investigation and assessment.
-
-
![]()
![]()
![]()
图 3 面向对象识别滑坡的方法流程
Figure 3. Flow-chart of identifying landslides with object-oriented method
![]()
图 4 海地地震发生后研究区Sentinel-2真彩色影像
Figure 4. True-color Sentinel-2 imagery of the study area after the Haiti earthquake
![]()
图 5 研究区2021年8月14日至2022年1月31日68幅Sentinel-2影像的云量覆盖情况
Figure 5. Cloud cover percentages of all 68 Sentinel-2 images in the study area from August 14 2021 to January 31 2022
![]()
图 6 ID为20210908T153619_20210908T153615_T18QWF的Sentinel-2影像（红框内为部分研究区）
Figure 6. A Sentinel-2 image with ID of 20210908T153619_20210908T153615_T18QWF （red boundary polygon is part of the study area）
![]()
图 7 利用时间序列影像融合去云方法处理后的海地地震灾区低云量真彩色镶嵌影像
Figure 7. Cloud-free true-color mosaic image of the study area by using time-series images
![]()
图 8 利用面向对象方法自动识别的研究区地震滑坡分布
Figure 8. Distribution of earthquake-triggered landslides identified by object-oriented method
![]()
![]()
10 不同时段的Sentinel-2影像融合去云结果
10. A cloud-free image produced with Sentinel-2 images in different periods
（a） 2021−01−14—2021−11−30；（b） 2021−08−14—2021−12−31
![]()
10 不同时段的Sentinel-2影像融合去云结果
10. A cloud-free image produced with Sentinel-2 images in different periods
（c） 2021−08−14—2022−01−31；（d） 2021−08−14—2022−03−31；（e） 2021−08−14—2022−08−31
表 1 Sentinel-2光谱波段的详细信息
Table 1 Brief information of all spectral bands of the Sentinel-2 imagery
波段号 Sentinel-2光谱波段 中心波长 /nm 空间分辨率 /m 1 海岸/气溶胶 443.9 60 2 蓝 496.6 10 3 绿 560 10 4 红 664.5 10 5 红边 703.9 20 6 红边 740.2 20 7 红边 782.5 20 8 近红外 835.1 10 8A 红边 864.8 20 9 水蒸气 945 60 10 短波红外 1 373.5 60 11 短波红外 1 613.7 20 12 短波红外 2 202.4 20 
下载: 导出CSV
-
戴岚欣,许强,范宣梅,常鸣,杨琴,杨帆,任敬. 2017. 2017年8月8日四川九寨沟地震诱发地质灾害空间分布规律及易发性评价初步研究[J]. 工程地质学报,25(4):1151–1164. Dai L X,Xu Q,Fan X M,Chang M,Yang Q,Yang F,Ren J. 2017. A preliminary study on spatial distribution patterns of landslides triggered by Jiuzhaigou earthquake in Sichuan on August 8th,2017 and their susceptibility assessment[J]. Journal of Engineering Geology,25(4):1151–1164 (in Chinese).
杜妍开,龚丽霞,李强,张景发. 2020. 基于最优分割的高分辨率遥感影像震害建筑物识别技术[J]. 地震学报,42(6):760–768. Du Y K,Gong L X,Li Q,Zhang J F. 2020. Earthquake damage building identification technology based on high resolution remote sensing image with optimal segmentation[J]. Acta Seismologica Sinica,42(6):760–768 (in Chinese).
郭保. 2021. 基于Sentinel-2卫星遥感影像的去云方法研究[J]. 测绘与空间地理信息,44(10):150–152. Guo B. 2021. Research on cloud removal method based on Sentinel-2 satellite remote sensing image[J]. Geomatics &Spatial Information Technology,44(10):150–152 (in Chinese).
李月臣,陈晋,刘春霞,曹鑫. 2006. 一种除去遥感影像薄云雾的方法[J]. 成都理工大学学报(自然科学版),33(1):58–63. Li Y C,Chen J,Liu C X,Cao X. 2006. An effective approach to remove cloud-fog cover and enhance remote sensing imagery[J]. Journal of Chengdu University of Technology (Science &Technology Edition),33(1):58–63 (in Chinese).
刘广进,王光辉,毕卫华,刘慧杰,杨化超. 2022. 基于DenseNet与注意力机制的遥感影像云检测算法[J]. 自然资源遥感,34(2):88–96. Liu G J,Wang G H,Bi W H,Liu H J,Yang H C. 2022. Cloud detection algorithm of remote sensing image based on DenseNet and attention mechanism[J]. Remote Sensing for Natural Resources,34(2):88–96 (in Chinese).
彭令,徐素宁,梅军军,苏凤环. 2017. 地震滑坡高分辨率遥感影像识别[J]. 遥感学报,21(4):509–518. Peng L,Xu S N,Mei J J,Su F H. 2017. Earthquake-induced landslide recognition using high-resolution remote sensing images[J]. Journal of Remote Sensing,21(4):509–518 (in Chinese).
唐川,齐信,丁军,杨泰平,罗真富. 2010. 汶川地震高烈度区暴雨滑坡活动的遥感动态分析[J]. 地球科学,35(2):317–323. Tang C,Qi X,Ding J,Yang T P,Luo Z F. 2010. Dynamic analysis on rainfall-induced landslide activity in high seismic intensity areas of the Wenchuan earthquake using remote sensing image[J]. Earth Science,35(2):317–323 (in Chinese). doi: 10.3799/dqkx.2010.033
王小娜,田金炎,李小娟,王乐,宫辉力,陈蓓蓓,李向彩,郭婧涵. 2022. Google Earth Engine云平台对遥感发展的改变[J]. 遥感学报,26(2):299–309. Wang X N,Tian J Y,Li X J,Wang L,Gong H L,Chen B B,Li X C,Guo J H. 2022. Benefits of Google Earth Engine in remote sensing[J]. National Remote Sensing Bulletin,26(2):299–309 (in Chinese). doi: 10.11834/jrs.20211317
许冲,徐锡伟. 2012. 俯冲带地区压扭断裂型地震触发滑坡及其剥蚀厚度空间分布规律分析[J]. 工程地质学报,20(5):732–744. Xu C,Xu X W. 2012. Spatial distribution of seismic landslides and their erosion thickness in subduction zone associated with shear-thrust earthquake faulting mode[J]. Journal of Engineering Geology,20(5):732–744 (in Chinese).
杨文涛,汪明,史培军,沈玲玲,刘连友. 2015. 基于地形因子分割、分类的面向对象滑坡快速识别方法[J]. 自然灾害学报,24(4):1–6. Yang W T,Wang M,Shi P J,Shen L L,Liu L Y. 2015. Object-oriented rapid identification of landslides based on terrain factors segmentation and classification[J]. Journal of Natural Disasters,24(4):1–6 (in Chinese).
姚鑫,邓建辉,刘星洪,周振凯,姚佳明,戴福初,任开瑀,李凌婧. 2020. 青藏高原泛三江并流区活动性滑坡InSAR初步识别与发育规律分析[J]. 工程科学与技术,52(5):16–37. Yao X,Deng J H,Liu X H,Zhou Z K,Yao J M,Dai F C,Ren K Y,Li L J. 2020. Primary recognition of active landslides and development rule analysis for pan three-river-parallel territory of Tibet Plateau[J]. Advanced Engineering Sciences,52(5):16–37 (in Chinese).
张诗茄,蒋建军,缪亚敏,白世彪. 2018. 基于SBAS技术的岷江流域潜在滑坡识别[J]. 山地学报,36(1):91–97. Zhang S J,Jiang J J,Miao Y M,Bai S B. 2018. Application of the SBAS technique in potential landslide identification in the Minjiang watershed[J]. Mountain Research,36(1):91–97 (in Chinese).
赵孟银,郑小慎,刘文静. 2016. 基于相似像元替换的遥感影像厚云去除方法研究[J]. 计算机应用研究,33(11):3509–3512. Zhao M Y,Zheng X S,Liu W J. 2016. Study of thick clouds removal from remotely sensed images based on similar pixel substitution approach[J]. Application Research of Computers,33(11):3509–3512 (in Chinese).
Aimaiti Y,Liu W,Yamazaki F,Maruyama Y. 2019. Earthquake-induced landslide mapping for the 2018 Hokkaido eastern Iburi earthquake using PALSAR-2 data[J]. Remote Sens,11(20):2351. doi: 10.3390/rs11202351
Comert R,Avdan U,Gorum T,Nefeslioglu H A. 2019. Mapping of shallow landslides with object-based image analysis from unmanned aerial vehicle data[J]. Eng Geol,260:105264. doi: 10.1016/j.enggeo.2019.105264
Dou J,Chang K T,Chen S S,Yunus A,Liu J K,Xia H,Zhu Z F. 2015. Automatic case-based reasoning approach for landslide detection:Integration of object-oriented image analysis and a genetic algorithm[J]. Remote Sens,7(4):4318–4342. doi: 10.3390/rs70404318
Fan X M,Scaringi G,Korup O,West A J,van Westen C J,Tanyas H,Hovius N,Hales T C,Jibson R W,Allstadt K E,Zhang L M,Evans S G,Xu C,Li G,Pei X J,Xu Q,Huang R Q. 2019. Earthquake-induced chains of geologic hazards:Patterns,mechanisms,and impacts[J]. Rev Geophys,57(2):421–503. doi: 10.1029/2018RG000626
Guzzetti F,Mondini A C,Cardinali M,Fiorucci F,Santangelo M,Chang K T. 2012. Landslide inventory maps:New tools for an old problem[J]. Earth-Sci Rev,112(1/2):42–66.
Huang Y D,Xie C C,Li T,Xu C,He X L,Shao X Y,Xu X W,Zhan T,Chen Z N. 2023. An open-accessed inventory of landslides triggered by the MS6.8 Luding earthquake,China on September 5,2022[J]. Earthq Res Adv,3(1):100181. doi: 10.1016/j.eqrea.2022.100181
Intrieri E,Raspini F,Fumagalli A,Lu P,Del Conte S,Farina P,Allievi J,Ferretti A,Casagli N. 2018. The Maoxian landslide as seen from space:Detecting precursors of failure with Sentinel-1 data[J]. Landslides,15(1):123–133. doi: 10.1007/s10346-017-0915-7
Jia H Y,Wang Y J,Ge D Q,Deng Y K,Wang R. 2020. Improved offset tracking for predisaster deformation monitoring of the 2018 Jinsha river landslide (Tibet,China)[J]. Remote Sens Environ,247:111899. doi: 10.1016/j.rse.2020.111899
Keefer D K. 2002. Investigating landslides caused by earthquakes:A historical review[J]. Surv Geophys,23(6):473–510. doi: 10.1023/A:1021274710840
Kurtz C,Stumpf A,Malet J P,Gançarski P,Puissant A,Passat N. 2014. Hierarchical extraction of landslides from multiresolution remotely sensed optical images[J]. ISPRS J Photogramm Remote Sens,87:122–136. doi: 10.1016/j.isprsjprs.2013.11.003
Lambert M L,Gaudin J,Cohen R. 1987. Carte Geologique D’Haiti,Feuille Sud-Est:Port-au-Prince ,1∶250 000[CM].Paris:Paris Digital image and georeferencing.
Li M H,Zhang L,Ding C,Li W L,Luo H,Liao M S,Xu Q. 2020. Retrieval of historical surface displacements of the Baige landslide from time-series SAR observations for retrospective analysis of the collapse event[J]. Remote Sens Environ,240:111695. doi: 10.1016/j.rse.2020.111695
Li Q,Wang W,Wang J F,Zhang J F,Geng D. 2021. Exploring the relationship between InSAR coseismic deformation and earthquake-damaged buildings[J]. Remote Sens Environ,262:112508. doi: 10.1016/j.rse.2021.112508
Li Z B,Shi W Z,Myint S W,Lu P,Wang Q M. 2016. Semi-automated landslide inventory mapping from bitemporal aerial photographs using change detection and level set method[J]. Remote Sens Environ,175:215–230. doi: 10.1016/j.rse.2016.01.003
Lu P,Stumpf A,Kerle N,Casagli N. 2011. Object-oriented change detection for landslide rapid mapping[J]. IEEE Geosci Remote Sens Lett,8(4):701–705. doi: 10.1109/LGRS.2010.2101045
Lu P,Qin Y Y,Li Z B,Mondini A C,Casagli N. 2019. Landslide mapping from multi-sensor data through improved change detection-based Markov random field[J]. Remote Sens Environ,231:111235. doi: 10.1016/j.rse.2019.111235
Martinez S N,Allstadt K E,Slaughter S L,Schmitt R G,Collins E,Schaefer L N,Ellison S. 2021. Landslides Triggered by the August 14,2021,Magnitude 7.2 Nippes,Haiti,Earthquake[R]. Reston:U. S. Geological Survey:Open-File Report 2021-1112,17.
Mondini A C,Guzzetti F,Reichenbach P,Rossi M,Cardinali M,Ardizzone F. 2011. Semi-automatic recognition and mapping of rainfall induced shallow landslides using optical satellite images[J]. Remote Sens Environ,115(7):1743–1757. doi: 10.1016/j.rse.2011.03.006
Pan American Health Organization. 2021. Haiti earthquake situation report,MW7 (4 September 2021)[EB/OL].[2022−10−08]. https://iris.paho.org/handle/10665.2/54876.
Qiu H J,Cui P,Regmi A D,Hu S,Wang X G,Zhang Y Z. 2018. The effects of slope length and slope gradient on the size distributions of loess slides:Field observations and simulations[J]. Geomorphology,300:69–76. doi: 10.1016/j.geomorph.2017.10.020
Sentinel H. 2022. Sentinel-2 cloud detector[EB/OL]. [2022−04−16]. https://github.com/sentinel-hub/sentinel2-cloud-detector.
Shao X Y,Xu C,Wang P,Li L,He X L,Chen Z N,Huang Y D,Xu X W. 2022. Two public inventories of landslides induced by the 10 June 2022 Maerkang earthquake swarm,China and ancient landslides in the affected area[J]. Nat Hazards Res,2(4):269–272. doi: 10.1016/j.nhres.2022.09.001
Stumpf A,Kerle N. 2011. Object-oriented mapping of landslides using Random Forests[J]. Remote Sens Environ,115(10):2564–2577. doi: 10.1016/j.rse.2011.05.013
Sun W Y,Tian Y S,Mu X M,Zhai J,Gao P,Zhao G J. 2017. Loess landslide inventory map based on GF-1 satellite imagery[J]. Remote Sens,9(4):314. doi: 10.3390/rs9040314
Tian J Y,Wang L,Li X J,Gong H L,Shi C,Zhong R F,Liu X M. 2017. Comparison of UAV and WorldView-2 imagery for mapping leaf area index of Mangrove Forest[J]. Int J Appl Earth Obs Geoinf,61:22–31.
USGS. 2021. A magnitude 7.2 (M7.2) earthquake struck Haiti on August 14,2021,at 8:29 am local time (August 14,2021 12:29 UTC)[EB/OL].[2022−09−08]. https://www.usgs.gov/news/featured-story/magnitude-72-earthquake-haiti.
Xu C,Xu X W,Yao X,Dai F C. 2014a. Three (nearly) complete inventories of landslides triggered by the May 12,2008 Wenchuan MW7.9 earthquake of China and their spatial distribution statistical analysis[J]. Landslides,11(3):441–461. doi: 10.1007/s10346-013-0404-6
Xu C,Shyu J B H,Xu X. 2014b. Landslides triggered by the 12 January 2010 Port-au-Prince,Haiti,MW7.0 earthquake:Visual interpretation,inventory compiling,and spatial distribution statistical analysis[J]. Nat Hazards Earth Syst Sci,14(7):1789–1818. doi: 10.5194/nhess-14-1789-2014
Zhang C,Sargent I,Pan X,Li H P,Gardiner A,Hare J,Atkinson P M. 2018. An object-based convolutional neural network (OCNN) for urban land use classification[J]. Remote Sens Environ,216:57–70. doi: 10.1016/j.rse.2018.06.034
Zhao B,Wang Y S,Li W L,Lu H Y,Li Z Y. 2022. Evaluation of factors controlling the spatial and size distributions of landslides,2021 Nippes earthquake,Haiti[J]. Geomorphology,415:108419. doi: 10.1016/j.geomorph.2022.108419
Zhou W,Ming D P,Lv X W,Zhou K Q,Bao H Q,Hong Z L. 2020. SO–CNN based urban functional zone fine division with VHR remote sensing image[J]. Remote Sens Environ,236:111458. doi: 10.1016/j.rse.2019.111458
计量
- 文章访问数: 261
- HTML全文浏览量: 60
- PDF下载量: 89
