Remote Sensing and GIS Applications in Environmental Sciences

Development of a semi-automatic method based on object-based analysis and data mining algorithm in landslide detection (case study of Mohammad Abad forest watershed in Golestan)

Document Type : Original Article

Authors

1 PhD student in Watershed Management, Department of Watershed & Rangeland Management, Gorgan University of Agricultural Sciences & Natural Resources, Iran.

2 Gorgan University of Agricultural Sciences and Natural Resources

3 Associate Prof. of Remote Sensing and Geographic Information System, Department of Humanities, Tarbiat Modares University, Iran.

4 4. Prof. of Watershed Science and Engineering, Department of Agriculture, Shiraz University, Iran.

5 Assistant Prof. of Desert Department, Department of Pasture and Watershed Management, Gorgan University of Agricultural Sciences and Natural Resources, Iran.

10.22034/rsgi.2024.63550.1101

Abstract

This research aims to develop a semi-automated method based on remote sensing and data mining algorithms on improved images in order to identify landslides in Mohammad Abad forest watershed in Golestan province. This area is prone to landslides due to the special conditions of topography and human manipulations, and every year it causes significant financial losses to residents and infrastructure destruction. In this study, two Gaofen-1 satellite images from June 1402 and March 1401 were used. Due to the different imaging seasons, all the processes were done separately on two images and finally combined for the entire study area. In order to increase the clarity of the images, three image combining methods named Brovey, PCA and Wavelet-PCA were tested. The Wavelet-PCA method was selected as the best method of image synthesis with a correlation coefficient of 97% and the closest entropy value to the original image. In the next stage, 218 landslide cases were recorded in the region through field visits, 70% of which were used for model training and 30% for model validation. Image segmentation was done along with optimization of scale parameter by local variance method and shape and compression parameters by trial and error. The optimal parameters included scale = 33, shape = 0.6 and compression = 0.5. Then the selection of features was done from textural, spectral, height, geometric and auxiliary layers using the random forest method and 16 main features were selected from among the 53 extracted features. Finally, the selected images were

Keywords

Main Subjects

نخستین گام مدیریت و کاهش خسارات‌ ناشی از زمین‌لغزش‌، شناسایی محل وقوع موارد پیشین است. با افزایش سرعت تخریب و تغییر کاربری اراضی به دلیل فعالیت‌های انسانی و عوامل محیطی، استفاده از روش‌های دقیق، سریع و ارزان برای شناسایی زمین‌لغزش‌ها ضروری است. این تحقیق به توسعه یک روش نیمه‌خودکار مبتنی بر سنجش ‌از ‌دور و الگوریتم‌های داده‌کاوی برای شناسایی زمین‌لغزش‌ها در حوزه آبخیز جنگلی محمدآباد در استان گلستان پرداخته است. این منطقه به دلیل شرایط توپوگرافی خاص و دست‌کاری‌های انسانی مستعد وقوع زمین‌لغزش بوده و هرساله خسارات اجتماعی، اقتصادی و زیست‌محیطی زیادی را متحمل می‌شود. در این مطالعه، دو تصویر ماهواره گائوفن-1 مربوط به خردادماه 1402 و اسفندماه 1401 مورد استفاده قرار گرفت. به‌منظور افزایش وضوح تصاویر، سه روش ترکیب تصویر با عنوان Brovey، PCA و Wavelet-PCA مورد آزمون قرار گرفت. در مرحله بعد با بازدید صحرایی 218 مورد زمین‌لغزش در منطقه ثبت شد که 70 درصد آن برای آموزش مدل و 30 درصد برای اعتبارسنجی استفاده شد. قطعه‌بندی تصاویر همراه با بهینه‌سازی پارامتر مقیاس با روش واریانس محلی و پارامترهای شکل و فشردگی به‌صورت آزمون‌وخطا صورت گرفت. به‌منظور انجام طبقه‌بندی، انتخاب ویژگی با روش جنگل تصادفی انجام شد و درنهایت طبقه‌بندی تصویر با استفاده از روش طبقه‌بندی نظارت‌شده ماشین بردار پشتیبان انجام شد. بر اساس نتایج روش Wavelet-PCA با ضریب همبستگی بالای 97 درصد و نزدیک‌ترین مقدار آنتروپی به تصویر اصلی بهترین روش ترکیب تصویر انتخاب شد. پارامترهای بهینه قطعه‌بندی شامل مقیاس= 33، شکل= 6/0 و فشردگی= 5/0 بود. نتایج نشان داد که روش پیشنهادی با صحت کلی بالای 92 درصد و ضریب کاپا بالای 85/0 قادر به شناسایی زمین‌لغزش‌های منطقه مطالعاتی بوده است.

Mohammady M, Noor H. (2020). Landslide Susceptibility Zoning Using New Synthetic Method in the GIS Environment. Environmental Science and Technology, 21 (12), 135-146. SID. https://sid.ir/paper/360912/fa. (In Persian).
Acerbi-Junior, F., Clevers, J., & Schaepman, M. (2006). The assessment of multi-sensor image fusion using wavelet transforms for mapping the Brazilian Savanna. International Journal of Applied Earth Observation and Geoinformation, 8(4), 278-288. https://doi.org/10.1016/j.jag.2006.01.001
Agarwal, S., Vailshery, L., Jaganmohan, M., & Nagendra, H. (2013). Mapping Urban Tree Species Using Very High Resolution Satellite Imagery: Comparing Pixel-Based and Object-Based Approaches. ISPRS International Journal of Geo-Information, 2(1), 220-236. https://doi.org/10.3390/ijgi2010220
Aguilar, M. A., Aguilar, F. J., García Lorca, A., Guirado, E., Betlej, M., Cichón, P., & Parente, C. (2016). Assessment of multiresolution segmentation for extracting greenhouses from WorldView-2 imagery. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 41, 145-152.‏ https://doi.org/10.5194/isprs-archives-XLI-B7-145-2016, 2016.
Amatya, P., Kirschbaum, D., Stanley, T., & Tanyas, H. (2021). Landslide mapping using object-based image analysis and open source tools. Engineering geology, 282, 106000. https://doi.org/10.1016/j.enggeo.2021.106000
Bekkari, A., Idbraim, S., Elhassouny, A., Mammass, D., El Yassa, M., & Ducrot, D. (2012). Spectral and Spatial Classification of High Resolution Urban Satellites Images Using Haralick Features and SVM with SAM and EMD Distance Metrics. International Journal of Computer Applications, 46(11), 28-37.
Breiman, L. (1996). Bagging Predictors, Machine learning, 24(2), 123-140.
Cai, L., Shi, W., Miao, Z., & Hao, M. (2018). Accuracy assessment measures for object extraction from remote sensing images. Remote Sensing, 10(2), 303. https://doi.org/10.3390/rs10020303
Casagli, N., Intrieri, E., Tofani, V., Gigli, G., & Raspini, F. (2023). Landslide detection, monitoring and prediction with remote-sensing techniques. Nature Reviews Earth & Environment, 4(1), 51-64.
Deng, H. (2013). Guided Random Forest in the RRF Package. ArXiv13060237 Cs. https://doi.org/10.48550/arXiv.1306.0237
Dhruval, L., & Richard, S. (2015). Advance SFIM technique for image fusion in remote sensing domain. International Journal of Innovative Research in Technology, 2(1), 148-161.
Donatti, C. I., Nicholas, K., Fedele, G., Delforge, D., Speybroeck, N., Moraga, P., & Zvoleff, A. (2024). Global hotspots of climate-related disasters. International Journal of Disaster Risk Reduction, 108, 104488.
Drăguţ, L., Csillik, O., Eisank, C., & Tiede, D. (2014). Automated parameterisation for multi-scale image segmentation on multiple layers. ISPRS Journal of photogrammetry and Remote Sensing, 88, 119-127. https://doi.org/10.1016/j.isprsjprs.2013.11.018
Esposito, G., Marchesini, I., Mondini, A. C., Reichenbach, P., Rossi, M., & Sterlacchini, S. (2020). A spaceborne SAR-based procedure to support the detection of landslides. Natural Hazards and Earth System Sciences, 20(9), 2379-2395. https://doi.org/10.5194/nhess-20-2379-2020
Han, S. S., Li, H. T., & Gu, H. Y. (2008). The study on image fusion for high spatial resolution remote sensing images. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. XXXVII. Part B, 7, 1159-1164.
Hölbling, D., Betts, H., Spiekermann, R., & Phillips, C. (2016). Identifying spatio-temporal landslide hotspots on North Island, New Zealand, by analyzing historical and recent aerial photography. Geosciences, 6(4), 48. https://doi.org/10.3390/geosciences6040048.
Keyport, R. N., Oommen, T., Martha, T. R., Sajinkumar, K. S., & Gierke, J. S. (2018). A comparative analysis of pixel-and object-based detection of landslides from very high-resolution images. International journal of applied earth observation and geoinformation, 64, 1-11. https://doi.org/10.1016/j.jag.2017.08.015
Kim, Y., Lee, C., Han, D., Kim, Y., & Kim, Y. (2011). Improved additive-wavelet image fusion. IEEE Geoscience and Remote Sensing Letters, 8(2), 263-267. DOI: 10.1109/LGRS.2010.2067192
Knevels, R., Petschko, H., Leopold, P., & Brenning, A. (2019). Geographic object-based image analysis for automated landslide detection using open source GIS software. ISPRS International Journal of Geo-Information, 8(12), 551. https://doi.org/10.3390/ijgi8120551
Laben, C.A., & Brower, B.V. (2000). Process for enhancing the spatial resolution of multispectral imagery using pan-sharpening. US Patent 6 (11), 875.
Li, S., Kang, X., Fang, L., Hu, J. & Yin, H. (2017). Pixel-level image fusion: A survey of the state of the art. Information Fusion, 33, 100-112. https://doi.org/10.1016/j.inffus.2016.05.004
Liu, X., Frey, J., Denter, M., Zielewska-Büttner, K., Still, N., & Koch, B. (2021). Mapping standing dead trees in temperate montane forests using a pixel-and object-based image fusion method and stereo WorldView-3 imagery. Ecological Indicators, 133, 108438. https://doi.org/10.1016/j.ecolind.2021.108438
Liu, Y., Wang, L., Cheng, J., Li, C., & Chen, X. (2020). Multi-focus image fusion: A survey of the state of the art. Information Fusion, 64, 71-91. https://doi.org/10.1016/j.inffus.2020.06.013.
Martha, T.R., Kerle, N., Jetten, V., van Westen, C.J., & Kumar, K.V. (2010). Characterising spectral, spatial and morphometric properties of landslides for semi-automatic detection using object-oriented methods. Geomorphology 116, 24–36.
Nikolakopoulos, K. G., Kavoura, K., Sabatakakis, N., & Vaiopoulos, A. D. (2014). Fusion of declassified airphotos and Landsat MSS data for old landslides detection. In Earth Resources and Environmental Remote Sensing/GIS Applications, 9245, 58-69. SPIE. https://doi.org/10.1117/12.2068128
Nitze, I., Schulthess, U., & Asche, H. (2012). Comparison of machine learning algorithms random forest, artificial neural network and support vector machine to maximum likelihood for supervised crop type classification. Proceedings of the 4th GEOBIA, Rio de Janeiro, Brazil, 79, 3540.
Sharma, K. V., Kumar, V., Singh, K., & Mehta, D. J. (2023). LANDSAT 8 LST Pan sharpening using novel principal component based downscaling model. Remote Sensing Applications: Society and Environment, 30, 100963. https://doi.org/10.1016/j.rsase.2023.100963.
Santurri, L., Carlà, R., Fiorucci, F., Aiazzi, B., Baronti, S., Mondini, A., & Cardinali, M. (2010). Assessment of very high resolution satellite data fusion techniques for landslide recognition. na.
Singh, A.K. (2010). Bioengineering techniques of slope stabilization and landslide mitigation. Disaster Prevention and Management: An International Journal, 19(3), 384-397. https://doi.org/10.1108/09653561011052547
Stumpf, A., & Kerle, N. (2011). Object-oriented mapping of landslides using random forests. Remote Sens. Environ. 115, 2564–2577. https://doi.org/10.1016/j.rse.2011.05.013
Tavakkoli Piralilou, S., Shahabi, H., Jarihani, B., Ghorbanzadeh, O., Blaschke, T., Gholamnia, K., Meena, S.R., & Aryal, J. (2019). Landslide detection using multi-scale image segmentation and different machine learning models in the higher Himalayas. Remote Sens. 11, 2575. https://doi.org/10.3390/rs11212575
Van der Linden, S., Rabe, A., Okujeni, A. & Hostert, P. (2009). Image SVM Classification, Application Manual: Image SVM Version, 2.
Wei, X., Gardoni, P., Zhang, L., Tan, L., Liu, D., Du, C., & Li, H. (2024). Improving pixel-based regional landslide susceptibility mapping. Geoscience Frontiers, 15(4), 101782. https://doi.org/10.1016/j.gsf.2024.101782
Zhao, W., Du, S., & Emery, W. J. (2017). Object-based convolutional neural network for high-resolution imagery classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(7), 3386-3396. DOI: 10.1109/JSTARS.2017.2680324
Remote Sensing and GIS Applications in Environmental Sciences
Volume 4, Issue 12
November 2024
Pages 71-49
  • Receive Date: 18 September 2024
  • Revise Date: 04 November 2024
  • Accept Date: 10 November 2024