Fusing Ascending and Descending Time-Series SAR Images with Dual-Polarized Pixel Attention UNet for Landslide Recognition

Bin Pan; Xianjian Shi

doi:10.3390/rs15235619

journal article Open Access Dec 04, 2023

Fusing Ascending and Descending Time-Series SAR Images with Dual-Polarized Pixel Attention UNet for Landslide Recognition

Bin Pan

Xianjian Shi

Remote Sensing Vol. 15 No. 23 pp. 5619 · MDPI AG

View at Publisher Save 10.3390/rs15235619

Abstract

Conducting landslide recognition research holds notable practical significance for disaster management. In response to the challenges posed by noise, information redundancy, and geometric distortions in single-orbit SAR imagery during landslide recognition, this study proposes a dual-polarization SAR image landslide recognition approach that combines ascending and descending time-series information while considering polarization channel details to enhance the accuracy of landslide identification. The results demonstrate notable improvements in landslide recognition accuracy using the ascending and descending fusion strategy compared to single-orbit data, with F1 scores increasing by 5.19% and 8.82% in Hokkaido and Papua New Guinea, respectively. Additionally, utilizing time-series imagery in Group 2 as opposed to using only pre- and post-event images in Group 4 leads to F1 score improvements of 6.94% and 9.23% in Hokkaido and Papua New Guinea, respectively, confirming the effectiveness of time-series information in enhancing landslide recognition accuracy. Furthermore, employing dual-polarization strategies in Group 4 relative to single-polarization Groups 5 and 6 results in peak F1 score increases of 7.46% and 12.07% in Hokkaido and Papua New Guinea, respectively, demonstrating the feasibility of dual-polarization strategies. However, due to limitations in Sentinel-1 imagery resolution and terrain complexities, omissions and false alarms may arise near landslide edges. The improvements achieved in this study hold critical implications for landslide disaster assessment and provide valuable insights for further enhancing landslide recognition capabilities.

Topics

No keywords indexed for this article. Browse by subject →

References

65

[1]

Yao "Performance comparison of landslide susceptibility mapping under multiple machine-learning based models considering InSAR deformation: A case study of the upper Jinsha River" Geomat. Nat. Hazards Risk (2023) 10.1080/19475705.2023.2212833

[2]

Liu "Geomorphological transformations and future deformation estimations of a large potential landslide in the high-order position area of Diexi, China" Geocarto Int. (2023) 10.1080/10106049.2023.2197514

[3]

He "An identification method of potential landslide zones using InSAR data and landslide susceptibility" Geomat. Nat. Hazards Risk (2023) 10.1080/19475705.2023.2185120

[4]

Dong "Potential landslides identification based on temporal and spatial filtering of SBAS-InSAR results" Geomat. Nat. Hazards Risk (2023) 10.1080/19475705.2022.2154574

[5]

Fang "Centrifuge modelling of landslides and landslide hazard mitigation: A review" Geosci. Front. (2023) 10.1016/j.gsf.2022.101493

[6]

Dai "Applicability Analysis of Potential Landslide Identification by InSAR in Alpine-Canyon Terrain—Case Study on Yalong River" IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. (2022) 10.1109/jstars.2022.3228948

[7]

Bhuyan "Generating multi-temporal landslide inventories through a general deep transfer learning strategy using HR EO data" Sci. Rep. (2023) 10.1038/s41598-022-27352-y

[8]

Hussain, M.A., Chen, Z., Zheng, Y., Shoaib, M., Shah, S.U., Ali, N., and Afzal, Z. (2022). Landslide susceptibility mapping using machine learning algorithm validated by persistent scatterer In-SAR technique. Sensors, 22. 10.3390/s22093119

[9]

Zhang, X., Pun, M.-O., and Liu, M. (2021). Semi-supervised multi-temporal deep representation fusion network for landslide mapping from aerial orthophotos. Remote Sens., 13. 10.3390/rs13040548

[10]

Ye "Landslide detection of hyperspectral remote sensing data based on deep learning with constrains" IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. (2019) 10.1109/jstars.2019.2951725

[11]

Chen, Z., Zhang, Y., Ouyang, C., Zhang, F., and Ma, J. (2018). Automated landslides detection for mountain cities using multi-temporal remote sensing imagery. Sensors, 18. 10.3390/s18030821

[12]

Earthquake-induced landslides susceptibility assessment: A review of the state-of-the-art

Xiaoyi Shao, Chong Xu

Natural Hazards Research 2022 10.1016/j.nhres.2022.03.002

[13]

Catani "Landslide detection by deep learning of non-nadiral and crowdsourced optical images" Landslides (2021) 10.1007/s10346-020-01513-4

[14]

Guo "A methodology to predict the run-out distance of submarine landslides" Comput. Geotech. (2023) 10.1016/j.compgeo.2022.105073

[15]

Hamidi "Fast Flood Extent Monitoring With SAR Change Detection Using Google Earth Engine" IEEE Trans. Geosci. Remote Sens. (2023) 10.1109/tgrs.2023.3240097

[16]

Nava "Improving landslide detection on SAR data through deep learning" IEEE Geosci. Remote Sens. Lett. (2021)

[17]

Scardigli "Integrating Unordered Time Frames in Neural Networks: Application to the Detection of Natural Oil Slicks in Satellite Images" IEEE Trans. Geosci. Remote Sens. (2023) 10.1109/tgrs.2023.3241681

[18]

Shi "LADSDIn: LiCSAR-Based Anomaly Detector of Seismic Deformation in InSAR" IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. (2023) 10.1109/jstars.2023.3272026

[19]

Samsonov "Satellite interferometry for regional assessment of landslide hazard to pipelines in northeastern British Columbia, Canada" Int. J. Appl. Earth Obs. Geoinf. (2023)

[20]

Shen "Rapid and Automatic Detection of New Potential Landslide Based on Phase-Gradient DInSAR" IEEE Geosci. Remote Sens. Lett. (2022)

[21]

Mondini "Landslide failures detection and mapping using Synthetic Aperture Radar: Past, present and future" Earth-Sci. Rev. (2021) 10.1016/j.earscirev.2021.103574

[22]

How climate change and unplanned urban sprawl bring more landslides

Ugur Ozturk, Elisa Bozzolan, Elizabeth A. Holcombe et al.

Nature 2022 10.1038/d41586-022-02141-9

[23]

Dong "Detection and displacement characterization of landslides using multi-temporal satellite SAR interferometry: A case study of Danba County in the Dadu River Basin" Eng. Geol. (2018) 10.1016/j.enggeo.2018.04.015

[24]

Liu, Z., Qiu, H., Zhu, Y., Liu, Y., Yang, D., Ma, S., Zhang, J., Wang, Y., Wang, L., and Tang, B. (2022). Efficient identification and monitoring of landslides by time-series InSAR combining single-and multi-look phases. Remote Sens., 14. 10.3390/rs14041026

[25]

Yang, S., Li, D., Liu, Y., Xu, Z., Sun, Y., and She, X. (2023). Landslide Identification in Human-Modified Alpine and Canyon Area of the Niulan River Basin Based on SBAS-InSAR and Optical Images. Remote Sens., 15. 10.3390/rs15081998

[26]

Goorabi "Detection of landslide induced by large earthquake using InSAR coherence techniques–Northwest Zagros, Iran" Egypt. J. Remote Sens. Space Sci. (2020)

[27]

Burrows "A systematic exploration of satellite radar coherence methods for rapid landslide detection" Nat. Hazards Earth Syst. Sci. (2020) 10.5194/nhess-20-3197-2020

[28]

Biondi "Measurements of surface river doppler velocities with along-track InSAR using a single antenna" IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. (2020) 10.1109/jstars.2020.2976529

[29]

Elyouncha "Empirical relationship between the Doppler centroid derived from X-band spaceborne InSAR data and wind vectors" IEEE Trans. Geosci. Remote Sens. (2021) 10.1109/tgrs.2021.3066106

[30]

Fast Mapping of Large-Scale Landslides in Sentinel-1 SAR Images Using SPAUNet

Xianjian Shi, Yifei Wu, Qing Guo et al.

IEEE Journal of Selected Topics in Applied Earth O... 2023 10.1109/jstars.2023.3310153

[31]

Niu "Using a fully polarimetric SAR to detect landslide in complex surroundings: Case study of 2015 Shenzhen landslide" ISPRS J. Photogramm. Remote Sens. (2021) 10.1016/j.isprsjprs.2021.01.022

[32]

Exploring event landslide mapping using Sentinel-1 SAR backscatter products

Michele Santangelo, Mauro Cardinali, Francesco Bucci et al.

Geomorphology 2022 10.1016/j.geomorph.2021.108021

[33]

Nava, L., Bhuyan, K., Meena, S.R., Monserrat, O., and Catani, F. (2022). Rapid mapping of landslides on SAR data by attention U-Net. Remote Sens., 14. 10.3390/rs14061449

[34]

Plank, S., Twele, A., and Martinis, S. (2016). Landslide mapping in vegetated areas using change detection based on optical and polarimetric SAR data. Remote Sens., 8. 10.3390/rs8040307

[35]

Antara "An application of SegNet for detecting landslide areas by using fully polarimetric SAR data" Ecotrophic (2019) 10.24843/ejes.2019.v13.i02.p09

[36]

Huang "An open-accessed inventory of landslides triggered by the MS 6.8 Luding earthquake, China on September 5, 2022" Earthq. Res. Adv. (2023) 10.1016/j.eqrea.2022.100181

[37]

Zhong "Landslide mapping with remote sensing: Challenges and opportunities" Int. J. Remote Sens. (2020) 10.1080/01431161.2019.1672904

[38]

Zhou "Characteristic comparison of seepage-driven and buoyancy-driven landslides in Three Gorges Reservoir area, China" Eng. Geol. (2022) 10.1016/j.enggeo.2022.106590

[39]

Ohki "Landslide detection in mountainous forest areas using polarimetry and interferometric coherence" Earth Planets Space (2020) 10.1186/s40623-020-01191-5

[40]

Colesanti "Investigating landslides with space-borne Synthetic Aperture Radar (SAR) interferometry" Eng. Geol. (2006) 10.1016/j.enggeo.2006.09.013

[41]

Ren, T., Gong, W., Bowa, V.M., Tang, H., Chen, J., and Zhao, F. (2021). An Improved R-Index Model for Terrain Visibility Analysis for Landslide Monitoring with InSAR. Remote Sens., 13. 10.3390/rs13101938

[42]

Trebing "SmaAt-UNet: Precipitation nowcasting using a small attention-UNet architecture" Pattern Recognit. Lett. (2021) 10.1016/j.patrec.2021.01.036

[43]

Armenakis "Evaluation of UNet and UNet++ architectures in high resolution image change detection applications" Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. (2020)

[44]

Hameed "Back-propagation algorithm with variable adaptive momentum" Knowl.-Based Syst. (2016) 10.1016/j.knosys.2016.10.001

[45]

Farahnakian, F., Sheikh, J., Farahnakian, F., and Heikkonen, J. (2023). A comparative study of state-of-the-art deep learning architectures for rice grain classification. J. Agric. Food Res., 100890. 10.1016/j.jafr.2023.100890

[46]

Kothyari "Identification of active deformation zone associated with the April 28 2021 Assam earthquake (Mw 6.4) using the PSInSAR time series" J. Appl. Geophys. (2022) 10.1016/j.jappgeo.2022.104811

[47]

Confuorto "Sentinel-1-based monitoring services at regional scale in Italy: State of the art and main findings" Int. J. Appl. Earth Obs. Geoinf. (2021)

[48]

Friedl "Global time series and temporal mosaics of glacier surface velocities derived from Sentinel-1 data" Earth Syst. Sci. Data (2021) 10.5194/essd-13-4653-2021

[49]

Zhang "Characteristics of landslides triggered by the 2018 Hokkaido Eastern Iburi earthquake, Northern Japan" Landslides (2019) 10.1007/s10346-019-01207-6

[50]

Shao, X., Ma, S., Xu, C., Zhang, P., Wen, B., Tian, Y., Zhou, Q., and Cui, Y. (2019). Planet image-based inventorying and machine learning-based susceptibility mapping for the landslides triggered by the 2018 Mw 6.6 Tomakomai, Japan Earthquake. Remote Sens., 11. 10.3390/rs11080978

Showing 50 of 65 references

Metrics

15

Citations

65

References

Details

Published: Dec 04, 2023
Vol/Issue: 15(23)
Pages: 5619
License: View

Authors

B

Bin Pan

School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China; Hubei Luojia Laboratory, Wuhan 430079, China

X

Xianjian Shi

School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China

Funding

Fengjian Highway Safety Intelligent Construction Technology Demonstration Project Award: 1504-250071559

Cite This Article

Bin Pan, Xianjian Shi (2023). Fusing Ascending and Descending Time-Series SAR Images with Dual-Polarized Pixel Attention UNet for Landslide Recognition. Remote Sensing, 15(23), 5619. https://doi.org/10.3390/rs15235619

Fusing Ascending and Descending Time-Series SAR Images with Dual-Polarized Pixel Attention UNet for Landslide Recognition

You May Also Like