A Hybrid SVD–Log Ratio Framework for Satellite-Based Disaster Damage Segmentation and Impact Mapping
DOI:
https://doi.org/10.55749/ijdrr.v1i1.186Keywords:
Disaster, Image Segmentation, Log-Ratio, Singular value DecompositionAbstract
Indonesia is a region prone to various natural disasters, requiring a monitoring system capable of detecting changes in impacted areas quickly and accurately. This study proposes a method for segmenting satellite images that combines singular value decomposition and log ratio approaches to identify disaster impacts using Sentinel-2 satellite images. The segmentation process consists of preprocessing steps such as RGB to HSV colour conversion and histogram matching. The processing stage involves applying singular value decomposition on each 2×2 kernel block, where the smallest singular value is used as an indicator of local differences. This is then combined with a log operation to reduce speckle noise. The segmentation results are refined through postprocessing by overlaying satellite data to enhance the visibility of affected areas. Quantitative evaluation using ROC curves and AUC shows that this combination achieves high detection accuracy, with a maximum AUC value of 0.9216, outperforming the Otsu method (0.8123), Region Growing (0.8349), and K-Means (0.8731). This combination has proven effective in distinguishing image changes in detail and holds potential for application in an automatic, real-time disaster impact monitoring system in disaster-prone areas.
References
[1] R. Cribb and M. Ford, “1 Indonesia as an Archipelago: Managing Islands, Managing the Seas,” in Indonesia beyond the Water’s Edge, ISEAS Publishing, 2009, pp. 1–27. doi: 10.1355/9789812309815-005.
[2] S. Munawaroh, “Penerapan sanksi penenggelaman kapal asing pelaku illegal fishing oleh pemerintah Indonesia (Perspektif hukum internasional),” MIMBAR YUSTITIA, vol. 3, no. 1, pp. 27–43, May 2019, doi: 10.52166/mimbar.v3i1.1739.
[3] A. White et al., “Marine protected area networks in Indonesia: Progress, lessons and a network design case study covering six eastern provinces,” Coastal Management, vol. 49, no. 6, pp. 575–597, Nov. 2021, doi: 10.1080/08920753.2021.1967560.
[4] M. P. Amarda and Syafriani, “Analysis of seismic hazards and vulnerability throughout Indonesia based on 1999-2003 earthquake data using the microseismic method,” PILLAR OF PHYSICS, vol. 14, no. 2, Dec. 2021, doi: 10.24036/11929171074.
[5] P. A. Kaban, R. Kurniawan, R. E. Caraka, B. Pardamean, B. Yuniarto, and Sukim, “Biclustering method to capture the spatial pattern and to identify the causes of social vulnerability in Indonesia: A new recommendation for disaster mitigation policy,” Procedia Comput. Sci., vol. 157, pp. 31–37, 2019, doi: 10.1016/j.procs.2019.08.138.
[6] B. Kusumasari, “Natural Hazards Governance in Indonesia,” in Oxford Research Encyclopedia of Natural Hazard Science, Oxford University PressNew York, NY, 2019. doi: 10.1093/acrefore/9780199389407.013.234.
[7] R. Djalante, “Identifying drivers, barriers and opportunities for integrating disaster risk reduction and climate change adaptation in Indonesia: An analysis based on the earth system governance framework,” 2013, pp. 131–147. doi: 10.1007/978-3-642-31110-9_9.
[8] R. Djalante, “Research trends on hazards, disasters, risk reduction and climate change in Indonesia: A systematic literature review,” May 11, 2016. doi: 10.5194/nhess-2016-112.
[9] R. Djalante, “Review article: A systematic literature review of research trends and authorships on natural hazards, disasters, risk reduction and climate change in Indonesia,” Natural Hazards and Earth System Sciences, vol. 18, no. 6, pp. 1785–1810, Jun. 2018, doi: 10.5194/nhess-18-1785-2018.
[10] W. Mao and V. I. O. Agyapong, “The role of social determinants in mental health and resilience after disasters: Implications for public health policy and practice,” Front. Public Health, vol. 9, May 2021, doi: 10.3389/fpubh.2021.658528.
[11] S. K. Patel, G. Agrawal, and B. Mathew, “Understanding the resilience and mental health impacts of natural disasters in India: A narrative review,” Int. J. Popul. Stud., vol. 6, no. 1, p. 82, Aug. 2024, doi: 10.18063/ijps.v6i1.1183.
[12] S. A. Saeed and S. P. Gargano, “Natural disasters and mental health,” International Review of Psychiatry, vol. 34, no. 1, pp. 16–25, Jan. 2022, doi: 10.1080/09540261.2022.2037524.
[13] A. Bănică, K. Kourtit, and P. Nijkamp, “Natural disasters as a development opportunity: A spatial economic resilience interpretation,” Review of Regional Research, vol. 40, no. 2, pp. 223–249, Oct. 2020, doi: 10.1007/s10037-020-00141-8.
[14] S. Lazzaroni and P. A. G. van Bergeijk, “Natural disasters’ impact, factors of resilience and development: A meta-analysis of the macroeconomic literature,” Ecological Economics, vol. 107, pp. 333–346, Nov. 2014, doi: 10.1016/j.ecolecon.2014.08.015.
[15] M. Y. Omelicheva, “Natural disasters: Triggers of political instability?,” International Interactions, vol. 37, no. 4, pp. 441–465, Oct. 2011, doi: 10.1080/03050629.2011.622653.
[16] G. A. Arpitha, A. L. Choodarathnakara, A. Rajaneesh, G. S. Sinchana, and K. S. Sajinkumar, “Creation of a landslide inventory for the 2018 storm event of kodagu in the western ghats for landslide susceptibility mapping using machine learning,” Journal of the Indian Society of Remote Sensing, vol. 52, no. 11, pp. 2443–2459, Nov. 2024, doi: 10.1007/s12524-024-01953-8.
[17] A. Balasundaram, A. B. Abdul Aziz, A. Gupta, A. Shaik, and M. S. Kavitha, “A fusion approach using GIS, green area detection, weather API and GPT for satellite image based fertile land discovery and crop suitability,” Sci. Rep., vol. 14, no. 1, p. 16241, Jul. 2024, doi: 10.1038/s41598-024-67070-1.
[18] S. Sadeghi, E. S. Teshnizi, R. R. Pash, and M. Golian, “Extraction of lineaments using landsat image and digital elevation model: A case study of zagros orogenic belt, West Iran,” Journal of the Indian Society of Remote Sensing, vol. 52, no. 11, pp. 2361–2373, Nov. 2024, doi: 10.1007/s12524-024-01956-5.
[19] S. Zhang and J. Ma, “CascadeDumpNet: Enhancing open dumpsite detection through deep learning and AutoML integrated dual-stage approach using high-resolution satellite imagery,” Remote Sens. Environ., vol. 313, p. 114349, Nov. 2024, doi: 10.1016/j.rse.2024.114349.
[20] J. Doshi, S. Basu, and G. Pang, “From satellite imagery to disaster insights,” Dec. 2018.
[21] B. K. Jones, T. S. Stryker, A. Mahmood, and G. R. Platzeck, “The international charter ‘Space and major disasters,’” in Time-Sensitive Remote Sensing, New York, NY: Springer New York, 2015, pp. 79–89. doi: 10.1007/978-1-4939-2602-2_6.
[22] S. Liu and M. E. Hodgson, “Satellite image collection modeling for large area hazard emergency response,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 118, pp. 13–21, Aug. 2016, doi: 10.1016/j.isprsjprs.2016.04.007.
[23] F. Gouveia, V. Silva, J. Lopes, R. S. Moreira, J. M. Torres, and M. Simas Guerreiro, “Automated identification of building features with deep learning for risk analysis,” Discover Applied Sciences, vol. 6, no. 9, p. 466, Aug. 2024, doi: 10.1007/s42452-024-06070-2.
[24] Z. Su et al., “A new and robust index for water body extraction from sentinel-2 imagery,” Remote Sens. (Basel)., vol. 16, no. 15, p. 2749, Jul. 2024, doi: 10.3390/rs16152749.
[25] B. Wu, Y. Wang, H. Huang, S. Liu, and B. Yu, “Potential of SDGSAT-1 nighttime light data in extracting urban main roads,” Remote Sens. Environ., vol. 315, p. 114448, Dec. 2024, doi: 10.1016/j.rse.2024.114448.
[26] S. Cottrell, R. Wang, and G.-W. Wei, “PLPCA: Persistent laplacian-enhanced PCA for microarray data analysis,” J. Chem. Inf. Model., vol. 64, no. 7, pp. 2405–2420, Apr. 2024, doi: 10.1021/acs.jcim.3c01023.
[27] S. Duan, J. Yang, X. Han, and G. Liu, “Adaptive dimensionality reduction method for high-dimensional data,” Journal of Mechanical Engineering, vol. 60, no. 17, p. 283, 2024, doi: 10.3901/JME.2024.17.283.
[28] R. A. Kolajoobi, C. MacBeth, and J. Landa, “Improving 4D seismic history matching through data analysis: A localized sensitivity analysis workflow,” SPE Journal, vol. 29, no. 09, pp. 4815–4826, Sep. 2024, doi: 10.2118/221467-PA.
[29] F. Rajabi and J. J. McArthur, “Applying OPTICS with and without PCA for fault detection of fan coil units using building automation system data,” Energy Build., vol. 317, p. 114368, Aug. 2024, doi: 10.1016/j.enbuild.2024.114368.
[30] A. Abdurrazzaq, A. K. Junoh, Z. Yahya, and I. Mohd, “New white blood cell detection technique by using singular value decomposition concept,” Multimed. Tools Appl., vol. 80, no. 3, pp. 4627–4638, Jan. 2021, doi: 10.1007/s11042-020-09946-8.
[31] S. D’Iorio, L. Forzani, R. García Arancibia, and I. Girela, “Predictive power of composite socioeconomic indices for targeted programs: Principal components and partial least squares,” Qual. Quant., vol. 58, no. 4, pp. 3497–3534, Aug. 2024, doi: 10.1007/s11135-023-01811-8.
[32] H. Wang, J. Shi, Y. Yang, K. Ma, and Y. Xue, “Machine learning methods predict recurrence of pN3b gastric cancer after radical resection,” Transl. Cancer Res., vol. 13, no. 3, pp. 1519–1532, Mar. 2024, doi: 10.21037/tcr-23-1367.
[33] T. Yan, Y. Wang, and P. Wang, “Rational polynomial coefficient estimation via adaptive sparse PCA-based method,” Remote Sens. (Basel)., vol. 16, no. 16, p. 3018, Aug. 2024, doi: 10.3390/rs16163018.
[34] X. Hu, C. V. Tao, and B. Prenzel, “Automatic segmentation of high-resolution satellite imagery by integrating texture, intensity, and color features,” Photogramm. Eng. Remote Sensing, vol. 71, no. 12, pp. 1399–1406, Dec. 2005, doi: 10.14358/PERS.71.12.1399.
[35] Z. Hu, Z. Wu, Q. Zhang, Q. Fan, and J. Xu, “A spatially-constrained color–texture model for hierarchical VHR image segmentation,” IEEE Geoscience and Remote Sensing Letters, vol. 10, no. 1, pp. 120–124, Jan. 2013, doi: 10.1109/LGRS.2012.2194693.
[36] T. Sai Kumar, M. Chandra M, and S. Murthy P, “Colour-based image segmentation using fuzzy C-Means clustering,” International Journal on Intelligent Electronic Systems, vol. 5, no. 2, pp. 47–51, 2011, doi: 10.18000/ijies.30099.
[37] S. Liu, Z. Cao, and J. Li, “A SVD-based visual attention detection algorithm of SAR image,” in Lecture Notes in Electrical Engineering, 2014. doi: 10.1007/978-3-319-00536-2_55.
[38] Copernicus Browser, “Copernicus Open Access Hub.” [Online]. Available: https://browser.dataspace.copernicus.eu/
[39] K. Yang et al., “Semantic change detection with asymmetric siamese networks,” May 2021.
[40] Y. Du, H. Yuan, K. Jia, and F. Li, “Research on threshold segmentation method of two-dimensional otsu image based on improved sparrow search algorithm,” IEEE Access, vol. 11, pp. 70459–70469, 2023, doi: 10.1109/ACCESS.2023.3293191.
[41] G. Surówka and M. Ogorzałek, “Segmentation of the melanoma lesion and its border,” International Journal of Applied Mathematics and Computer Science, vol. 32, no. 4, 2022, doi: 10.34768/amcs-2022-0047.
[42] D. G. Olle, J. Z. Bisse, and G. A. Alo’o, “Application and comparison of K-means and PCA based segmentation models for Alzheimer disease detection using MRI,” Discover Artificial Intelligence, vol. 4, no. 1, p. 11, Feb. 2024, doi: 10.1007/s44163-024-00106-7.
[43] L. Carrington, L. Hale, C. Freeman, D. Smith, and M. Perry, “The effectiveness of play as an intervention using International classification of functioning outcome measures for children with disabilities – a systematic review and meta-synthesis,” Disabil. Rehabil., vol. 46, no. 17, pp. 3827–3848, Aug. 2024, doi: 10.1080/09638288.2023.2259305.
