Time-series analysis of Sentinel-1/2 data for flood detection using a discrete global grid system and seasonal decomposition

被引:15
作者
Fichtner, Florian [1 ]
Mandery, Nico [1 ]
Wieland, Marc [1 ]
Groth, Sandro [1 ]
Martinis, Sandro [1 ]
Riedlinger, Torsten [1 ]
机构
[1] German Aerosp Ctr DLR, German Remote Sensing Data Ctr DFD, Munchner Str 20, D-82234 Wessling, Germany
关键词
Flood detection; H3; Time-series analysis; Seasonal decomposition; Anomaly detection; Sentinel-1; Sentinel-2; Copernicus EMS; WATER;
D O I
10.1016/j.jag.2023.103329
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
Automated flood detection using earth observation data is a crucial task for efficient flood disaster man-agement. Current solutions to identify flooded areas usually rely on calculating the difference between new observations and static, pre-calculated water extents derived by either single acquisitions or timely aggregated products. Such pre-calculated datasets, however, lack representation of real-world seasonality and short-term changes in trend.In this paper we present a complete workflow to automatically detect hydrological extreme events and their spatial extent, which automatically adapts to local seasonality and trend. For that we rely on a novel combination of well-established algorithms and tools to detect anomalies in time-series of water extent across large study areas. The data is binned into a discrete global grid system H3, which greatly simplifies aggregation across spatial and temporal resolutions. For each grid cell of an H3 resolution we perform a time-series decomposition using Seasonal and Trend decomposition using Loess (STL) of the cell's proportion which is covered with surface water. All cells receive an anomaly score, calculated with extended isolation forest (EIF) on the residuals for each step in time. A burst of anomalies represents a hydrological extreme event like a flood or low water level.The presented methodology is applied on Sentinel-1/2 data for two study areas, one near Sukkur, Pakistan and the other one in Mozambique. The detected anomalies correlate with reported floods and seasonal variations of the study areas. The performance of the process and the possibility to use different H3 resolutions make the proposed methodology suitable for large scale monitoring.
引用
收藏
页数:12
相关论文
共 31 条
  • [11] GDACS, 2022, OV RED AL FLOOD PAK
  • [12] GDACS, 2022, GLOB DIS AL COORD SY
  • [13] Extended Isolation Forest
    Hariri, Sahand
    Kind, Matias Carrasco
    Brunner, Robert J.
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2021, 33 (04) : 1479 - 1489
  • [14] Change detection approaches for flood extent mapping: How to select the most adequate reference image from online archives?
    Hostache, R.
    Matgen, P.
    Wagner, W.
    [J]. INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2012, 19 : 205 - 213
  • [15] Mapping spatio-temporal flood inundation dynamics at large river basin scale using time-series flow data and MODIS imagery
    Huang, Chang
    Chen, Yun
    Wu, Jianping
    [J]. INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2014, 26 : 350 - 362
  • [16] Kleppmann M., 2017, Designing Data-Intensive Applications: The Big Ideas Behind Reliable, Scalable, and Maintainable Systems
  • [17] Geospatial Operations of Discrete Global Grid Systems-a Comparison with Traditional GIS
    Li, Mingke
    Stefanakis, Emmanuel
    [J]. JOURNAL OF GEOVISUALIZATION AND SPATIAL ANALYSIS, 2020, 4 (02)
  • [18] Mandery N., 2022, H3RON
  • [19] Mandery Nico, 2023, Zenodo, DOI 10.5281/ZENODO.7534213
  • [20] Towards a global seasonal and permanent reference water product from Sentinel-1/2 data for improved flood mapping
    Martinis, Sandro
    Groth, Sandro
    Wieland, Marc
    Knopp, Lisa
    Rattich, Michaela
    [J]. REMOTE SENSING OF ENVIRONMENT, 2022, 278