Top > JDR > Machine Learning Based Building Damage Mapping from the ALOS-2 ...

single-dr.php

JDR Vol.12 No.sp pp. 646-655
(2017)
doi: 10.20965/jdr.2017.p0646

Paper:

Views over last 60 days: 1,876

Machine Learning Based Building Damage Mapping from the ALOS-2/PALSAR-2 SAR Imagery: Case Study of 2016 Kumamoto Earthquake

Yanbing Bai*,†, Bruno Adriano**, Erick Mas** and Shunichi Koshimura**

*Graduate School of Engineering, Tohoku University
6-6-4 Aramaki-Aza Aoba, Aob-ku, Senda, Miyagi 980-8579, Japan

†Corresponding author

**International Research Institute of Disaster Science, Tohoku University, Miyagi, Japan

Received:
December 28, 2016
Accepted:
June 20, 2017
Published:
June 30, 2017
Creative Commons License
Keywords:
2016 Kumamoto earthquake, building damage mapping, ALOS-2/PALSAR-2, synthetic aperture radar, machine learning
Abstract

Synthetic Aperture Radar (SAR) remote sensing is a useful tool for mapping earthquake-induced building damage. A series of operational methodologies based on SAR data using either multi-temporal or only post-event SAR images have been developed and used to serve disaster activities. This presents a critical problem: which method is more likely to obtain reliable results and should be adopted for disaster response when both pre- and post-event SAR data are available? To explore this question, this study takes the 2016 Kumamoto earthquake as a case study. ALOS-2/PALSAR-2 SAR images were employed with a machine learning framework to quantitatively compare the performance of building damage mapping using only post-event SAR images and mapping using multi-temporal SAR images. The results show that an overall accuracy of 64.5% was achieved when only post-event SAR images were used, which is 2.3% higher than the overall accuracy when multi-temporal SAR images were used. The estimated building damage ratio for the former and the latter are 29.7% and 31.1%, respectively, which are both close to the building damage ratio obtained from an optical image.

Cite this article as:
Y. Bai, B. Adriano, E. Mas, and S. Koshimura, “Machine Learning Based Building Damage Mapping from the ALOS-2/PALSAR-2 SAR Imagery: Case Study of 2016 Kumamoto Earthquake,” J. Disaster Res., Vol.12 No.sp, pp. 646-655, 2017.
Data files:
References
  1. [1] S.-H. Yun, K. Hudnut, S. Owen, F. Webb, M. Simons, P. Sacco, E. Gurrola, G. Manipon, C. Liang, E. Fielding, P. Milillo, H. Hua, and A. Coletta, “Rapid Damage Mapping for the 2015 M w 7.8 Gorkha Earthquake Using Synthetic Aperture Radar Data from COSMO-SkyMed and ALOS-2 Satellites,” Seismological Research Letters, Vol.86, No.6, pp. 1549-1556, 2015.
  2. [2] A. O. F. Geophysics, F. Track, and I. Nazionale, “A multisensor approach for the 2016 Amatrice earthquake damage assessment,” No.1981, pp. 1-6, 2016.
  3. [3] L. Ge, A. H.-M. Ng, X. Li, Y. Liu, Z. Du, and Q. Liu, “Near real-time satellite mapping of the 2015 Gorkha earthquake, Nepal,” Annals of GIS, Vol.21, No.3, pp. 175-190, 2015.
  4. [4] T. Balz and M. S. Liao, “Building-damage detection using postseismic high-resolution SAR satellite data,” Int. J. of Remote Sensing, Vol.31, No.13, pp. 3369-3391, 2010.
  5. [5] M. Matsuoka and F. Yamazaki, “Characteristics of satellite SAR images in the areas damaged by earthquakes,” Int. Geoscience and Remote Sensing Symposium (IGARSS), Vol.6, pp. 2693-2696, 2000.
  6. [6] M. Matsuoka and F. Yamazaki, “Building damage detection using satellite SAR intensity images for the 2003 Algeria and Iran earthquakes,” Geoscience and Remote Sensing Symposium, Vol.2, pp. 1099-1102, 2004.
  7. [7] M. Matsuoka and F. Yamazaki, “Building damage detection using SAR intensity images for recent earthquakes,” European Space Agency, (Special Publication) ESA SP, No.572, pp. 2021-2026, 2005.
  8. [8] M. Matsuoka and M. Estrada, “Development of earthquake-induced building damage estimation model based on ALOS/PALSAR observing the 2007 Peru earthquake,” J. of Disaster Research, Vol.8, No.2, pp. 346–355, 2013.
  9. [9] W. Liu, F. Yamazaki, and T. Sasagawa, “Monitoring of the Recovery Process of the Fukushima Daiichi Nuclear Power Plant from VHR SAR Images,” Vol.11, No.2, 2016.
  10. [10] F. Yamazaki, Y. Iwasaki, W. Liu, T. Nonaka, and T. Sasagawa, “Detection of damage to building side-walls in the 2011 Tohoku, Japan earthquake using high-resolution TerraSAR-X images,” Vol.8892, pp. 1-9, 2013.
  11. [11] S. Plank, “Rapid damage assessment by means of multi-temporal SAR-A comprehensive review and outlook to Sentinel-1,” Remote Sensing, Vol.6, pp. 4870-4906, 2014.
  12. [12] H. Miura, S. Midorikawa, and M. Matsuoka, “Building Damage Assessment Using High-Resolution Satellite SAR Images of the 2010 Haiti Earthquake,” Earthquake Spectra, Vol.32, No.1, pp. 591-610, 2015.
  13. [13] L. Dong and J. Shan, “A comprehensive review of earthquake-induced building damage detection with remote sensing techniques,” ISPRS J. of Photogrammetry and Remote Sensing, Vol.84, pp. 85-99, 2013.
  14. [14] R. Guida, A. Iodice, and D. Riccio, “Monitoring of collapsed builtup areas with high resolution SAR images,” Geoscience and Remote Sensing Symposium (IGARSS), 2010 IEEE Int., pp. 2422-2425, 2010.
  15. [15] S.-w. Chen, S. Member, and M. Sato, “Tsunami Damage Investigation of Built-Up Areas Using Multi-temporal Spaceborne Full Polarimetric SAR Images,” Vol.51, No.4, pp. 1985-1997, 2013.
  16. [16] J. Hoffmann, “Mapping damage during the Bam (Iran) earthquake using interferometric coherence,” Int. J. of Remote Sensing, Vol.28, No.6, pp. 1199-1216, 2007.
  17. [17] G. A. Arciniegas, W. Bijker, N. Kerle, and V. A. Tolpekin, “Coherence- and amplitude-based analysis of seismogenic damage in Bam, Iran, using ENVISAT ASAR data,” IEEE Trans. on Geoscience and Remote Sensing, Vol.45, No.6, pp. 1571-1581, 2007.
  18. [18] M. Watanabe, R. B. Thapa, T. Ohsumi, H. Fujiwara, C. Yonezawa, N. Tomii, and S. Suzuki, “Detection of damaged urban areas using interferometric SAR coherence change with PALSAR-2,” Earth, Planets and Space, Vol.68, No.1, p. 131, 2016.
  19. [19] W. Zhai and C. Huang, “Fast building damage mapping using a single post-earthquake PolSAR image: a case study of the 2010 Yushu earthquake,” Earth, Planets and Space, Vol.68, No.1, p. 86, 2016.
  20. [20] X. Li, H. Guo, L. Zhang, X. Chen, and L. Liang, “A New Approach to Collapsed Building Extraction Using RADARSAT-2 Polarimetric SAR Imagery,” Vol.9, No.4, pp. 677-681, 2012.
  21. [21] L. Shi, W. Sun, J. Yang, P. Li, and L. Lu, “Building Collapse Assessment by the Use of Postearthquake Chinese VHR Airborne SAR,” IEEE Geoscience and Remote Sensing Letters, Vol.12, No.10, pp. 2021-2025, 2015.
  22. [22] L. Gong, C. Wang, F. Wu, J. Zhang, H. Zhang, and Q. Li, “Earthquake-Induced Building Damage Detection with Post-Event Sub-Meter VHR TerraSAR-X Staring Spotlight Imagery,” Remote Sensing, Vol.8, No.12, p. 887, 2016.
  23. [23] Y. Hata, H. Goto, and M. Yoshimi, “Preliminary Analysis of Strong Ground Motions in the Heavily Damaged Zone in Mashiki Town, Kumamoto, Japan, during the Mainshock of the 2016 Kumamoto Earthquake (Mw7.0) Observed by a Dense Seismic Array,” Seismological Research Letters, Vol.87, No.5, pp. 1044-1049, 2016.
  24. [24] Map data Imagery@ Google, 2016, https://www.google.co.jp/maps [accessed December 1,2016]
  25. [25] F. Dell’Acqua, C. Bignami, M. Chini, G. Lisini, D. A. Polli, and S. Stramondo, “Earthquake damages rapid mapping by satellite remote sensing data: L’Aquila april 6th, 2009 event,” IEEE J. of Selected Topics in Applied Earth Observations and Remote Sensing, Vol.4, No.4, pp. 935-943, 2011.
  26. [26] M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I. H. Witten, “The WEKA data mining software,” ACM SIGKDD Explorations Newsletter, Vol.11, No.1, p. 10, 2009.
  27. [27] ENVI/SARscape, http://sarmap.ch/tutorials/Basic.pdf [accessed May 1, 2016]
  28. [28] Sentinel Toolboxes, 2016, https://sentinel.esa.int/web/sentinel/toolboxes [accessed May 12, 2016]
  29. [29] A. B. Owen, “Infinitely Imbalanced Logistic Regression,” J. of Machine Learning Research, No.1, pp. 1-13, 2006.
  30. [30] H. He and E. Garcia, “Learning from Imbalanced Data Sets.,” IEEE Trans. on knowledge and data engineering, Vol.21, No.9, pp. 1263-1264, 2010.
  31. [31] L. Zeng, “Logistic Regression in Rare Events Data,” Political Analysis Vol.9, Issue 2, pp. 137-163, 2016.
  32. [32] R. Blagus and L. Lusa, “Class prediction for high-dimensional class-imbalanced data,” BMC Bioinformatics, Vol.11, No.1, p. 523, 2010.
  33. [33] J. Burez and D. Van den Poel, “Handling class imbalance in customer churn prediction,” Expert Systems with Applications, Vol.36, No.3 PART 1, pp. 4626-4636, 2009.
  34. [34] M. Kajimoto and J. Susaki, “Urban Density Estimation From Polarimetric SAR Images Based on a POA Correction Method,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol.6, Issue: 3, pp. 1418-1429, 2013.
  35. [35] Y. Yamaguchi, “Four-component scattering power decomposition using coherency matrix,” Int. Geoscience and Remote Sensing Symposium (IGARSS), Vol.49, No.6, pp. 1044-1047, 2011.
  36. [36] Y. Bai, B. Adriano, E. Mas, H. Gokon, and S. Koshimura, “Object-Based Building Damage Assessment Methodology Using Only Post Event ALOS-2/PALSAR-2 Dual Polarimetric SAR Intensity Images,” J. of Disaster Research, Vol.12, No.2, p. 259, 2017.
  37. [37] R. M. Haralick and K. Shanmugam, “Textural features for image classification,” IEEE Trans. on systems, Man, and Cybernetics, Vol.SMC-3, Issue 6, pp. 610-621, 1973.
  38. [38] A. B. Girisha, M. C. Chandrashekhar, and D. M. Kurian, “FPGA implementation of GLCM,” Int. J. of Advanced Research in Electrical, Electronics and Instrumentation Engineering, Vol.2, Issue 6, 2013.

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Apr. 22, 2024