Automatic Prediction of Landslides Over InSAR Techniques and Differential Detection Using High-Resolution Remote Sensing Images: Application to Jinsha River

  • Yueying Zhang
  • Haonan Ran
  • Yuexing Peng
  • Yu ZhengEmail author
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 657)


With a rapidly increasing population on or near steep terrain in southwest of China, landslides have become one of the most significant natural hazards. Thus, quick detection, prediction, and identification of early signals of landslide occurrence are critical for prompt emergency information, rescue efforts, and mitigation of further damage such as collapse of a landslide dam. Accordingly, in this paper, a prototype of early-stage-landslide detection is introduced. We construct a new automatic approach to extract landslides from remote sensing imagery, both optical and radar for quick prediction and detection before disasters, achieved by combining interferometric synthetic aperture radar (InSAR) with differential detection method using multi-temporal high-resolution optical images. The idea behind the novel approach is to identify potential landslides by typical distribution features, deformation, and tendency of landslides, including the result of expert second opinion. To verify the feasibility of this landslide prediction system, a case study was performed in Jinsha River area. It is found that the use of automatic detection of the potential landslides over satellite imagery allows the identification and characterization of the affected areas based on landslide features. It is expected that the prototype of landslide prediction can provide early recognitions before severe landslides occur. Total of eight active small-scaled landslides in early edge covering study region are automatically detected.


Landslides Early recognition Remote sensing InSAR 



This work was supported by Henan Key Laboratory of Spatial Information Application on Eco-environmental Protection. The authors also appreciate the efforts and suggestions from Liqiang Tong, an expert in Remote Sensing Geology from AGRS, China.


  1. 1.
    Ministry of Natural Resources (2019) National geologic disasters in 2018 and prediction of geologic disasters trends in 2019Google Scholar
  2. 2.
  3. 3.
    Yu Z, Xu S, Zhang S et al (2012) Distributed detection in landslide prediction based on wireless sensor networks. In: World automation congress 2012, pp 235–238Google Scholar
  4. 4.
    Liu Z, Tsuda T, Watanabe H et al (2019) Data driven cyber-physical system for landslide detection. Mob Netw Appl 24:991–1002CrossRefGoogle Scholar
  5. 5.
    Nichol JE, Shaker A, Wong MS (2016) Application of high-resolution stereo satellite images to detailed landslide hazard assessment. Geomorphology 76:68–75CrossRefGoogle Scholar
  6. 6.
    Tarolli P, Sofia G, Fontana GD (2012) Geomorphic features extraction from high-resolution topography: landslide crowns and bank erosion. Nat Hazard 61:65–83CrossRefGoogle Scholar
  7. 7.
    Lira C, Lousada M, Falcão AP et al (2011) Automatic detection of landslide features with remote sensing techniques: application to Madera Island. In: Geoscience & remote sensing symposium 2011, pp 1997–2000Google Scholar
  8. 8.
    Bayer B, Schmidt D, Simoni A (2017) The influence of external digital elevation models on PS-InSAR and SBAS results: implications for the analysis of deformation signals caused by slow moving landslides in the northern Apennines (Italy). IEEE Trans Geosci Remote Sens 55:2618–2630CrossRefGoogle Scholar
  9. 9.
    Yamada M, Hashimoto M, Fukushima Y (2013) Automatic detection of landslides from SAR images: application to the 2011 Kii landslides. In: Synthetic aperture radar, pp 245–248Google Scholar
  10. 10.
    Zhao C, Lu Z, Zhang Q et al (2012) Large-area landslide detection and monitoring with ALOS/PALSAR imagery data over Northern California and Southern Oregon, USA. Remote Sens Environ 124:348–359CrossRefGoogle Scholar
  11. 11.
    Li Y, Jiao Q, Hu X et al (2020) Detecting the slope movement after the 2018 Baige landslides based on ground-based and space-borne radar observations. Int J Appl Earth Obs Geoinf 84:101949CrossRefGoogle Scholar
  12. 12.
  13. 13.
    Yamaguchi Y, Tanaka S, Odajima T et al (2002) Detection of a landslide movement as geometric misregistration in image matching of SPOT HRV data of two different dates. Int J Remote Sens 1–12Google Scholar
  14. 14.
    Zhang Y, Ran H et al (2019) A novel framework of artificial intelligent geologic hazards detection over comprehensive remote sensing. In: Submitted to China high resolution earth observation conferenceGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Yueying Zhang
    • 1
  • Haonan Ran
    • 2
  • Yuexing Peng
    • 2
  • Yu Zheng
    • 1
    Email author
  1. 1.Henan Key Laboratory of Spatial Information Application on Eco-Environmental ProtectionZhengzhouChina
  2. 2.Beijing University of Posts and TelecommunicationsBeijingChina

Personalised recommendations