Browse > Article
http://dx.doi.org/10.7780/kjrs.2022.38.6.2.10

Observation of Ice Gradient in Cheonji, Baekdu Mountain Using Modified U-Net from Landsat -5/-7/-8 Images  

Lee, Eu-Ru (Department of Geoinformatics, University of Seoul)
Lee, Ha-Seong (Earthquake and Volcano Research Division, Korea Meteorological Administration)
Park, Sun-Cheon (Earthquake and Volcano Research Division, Korea Meteorological Administration)
Jung, Hyung-Sup (Department of Geoinformatics, University of Seoul)
Publication Information
Korean Journal of Remote Sensing / v.38, no.6_2, 2022 , pp. 1691-1707 More about this Journal
Abstract
Cheonji Lake, the caldera of Baekdu Mountain, located on the border of the Korean Peninsula and China, alternates between melting and freezing seasonally. There is a magma chamber beneath Cheonji, and variations in the magma chamber cause volcanic antecedents such as changes in the temperature and water pressure of hot spring water. Consequently, there is an abnormal region in Cheonji where ice melts quicker than in other areas, freezes late even during the freezing period, and has a high-temperature water surface. The abnormal area is a discharge region for hot spring water, and its ice gradient may be used to monitor volcanic activity. However, due to geographical, political and spatial issues, periodic observation of abnormal regions of Cheonji is limited. In this study, the degree of ice change in the optimal region was quantified using a Landsat -5/-7/-8 optical satellite image and a Modified U-Net regression model. From January 22, 1985 to December 8, 2020, the Visible and Near Infrared (VNIR) band of 83 Landsat images including anomalous regions was utilized. Using the relative spectral reflectance of water and ice in the VNIR band, unique data were generated for quantitative ice variability monitoring. To preserve as much information as possible from the visible and near-infrared bands, ice gradient was noticed by applying it to U-Net with two encoders, achieving good prediction accuracy with a Root Mean Square Error (RMSE) of 140 and a correlation value of 0.9968. Since the ice change value can be seen with high precision from Landsat images using Modified U-Net in the future may be utilized as one of the methods to monitor Baekdu Mountain's volcanic activity, and a more specific volcano monitoring system can be built.
Keywords
Cheonji; Landsat; Ice gradient; Multispectral image; Deep learning; Volcano monitoring;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 Chavez, P.S., 1996. Image-based atmospheric corrections revisited and improved, American Society for Photogrammetry and Remote Sensing, 62: 1025-1036.
2 Horn, S. and H.U. Schmincke, 2000. Volatile emission during the eruption of Baitoushan volcano (China/North Korea) ca. 969 AD, Bulletin of Volcanology, 61: 537-555. https://doi.org/10.1007/s004450050004   DOI
3 KMA (Korea Meteorological Administration), 2021. Development of Monitoring Technology through Analysis of Changes in Surface Temperature before and after Volcanic eruption, Korea Meteorological Administration, Seoul, Korea, 54pp (in Korean).
4 Schmidt, J., M.R. Marques, S. Botti, and M.A. Marques, 2019. Recent advances and applications of machine learning in solid-state materials science, npj Computational Materials, 5(1): 1-36. https://doi.org/10.1038/s41524-019-0221-0   DOI
5 Wei, H.Q., G.M. Liu, and J. Gill, 2013. Review of eruptive activity at Tianchi volcano, Changbaishan, northeast China: implications for possible future eruptions, Bulletin of Volcanology, 75(4): 1-14. https://doi.org/10.1007/s00445-013-0706-5   DOI
6 Yu, Z., T. Li, G. Luo, H. Fujita, N. Yu, and Y. Pan, 2018. Convolutional networks with cross-layer neurons for image recognition, Information Sciences, 433: 241-254. https://doi.org/10.1016/j.ins.2017.12.045   DOI
7 Yun, S.H., 2013. Conceptual Design for the Dispersal and Deposition Modelling of Fallout Ash from Mt. Baekdu Volcano, The Petrological Society of Korea, 22(4): 273-289. https://doi.org/10.7854/JPSK.2013.22.4.273   DOI
8 Guangming, W.U., C.H.E.N. Qi, R. Shibasaki, G.U.O. Zhiling, S.H.A.O. Xiaowei, and X.U. Yongwei, 2018. High precision building detection from aerial imagery using a U-Net like convolutional architecture, Acta Geodaetica et Cartographica Sinica, 47(6): 864. https://doi.org/10.11947/j.AGCS.2018.20170651   DOI
9 Egghe, L. and L. Leydesdorff, 2009. The relation between Pearson's correlation coefficient and Salton's cosine measure, Journal of the American Society for information Science and Technology, 60(5): 1027-1036. https://doi.org/10.1002/asi.21009   DOI
10 D'Allestro, P. and C. Parente, 2015. GIS application for NDVI calculation using Landsat 8 OLI images, International Journal of Applied Engineering Research, 10(21): 42099-42102.
11 Han, Y., Y. Gao, Y. Zhang, J. Wang, and S. Yang, 2019. Hyperspectral sea ice image classification based on the spectral-spatial-joint feature with deep learning, Remote Sensing, 11(18): 2170. https://doi.org/10.3390/rs11182170   DOI
12 Simonyan, K. and A. Zisserman, 2014. Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556. https://doi.org/10.48550/arXiv.1409.1556   DOI
13 Hou, B., Q. Liu, H. Wang, and Y. Wang, 2019. From W-Net to CDGAN: Bitemporal change detection via deep learning techniques, IEEE Transactions on Geoscience and Remote Sensing, 58(3): 1790-1802. https://doi.org/10.1109/TGRS.2019.2948659   DOI
14 Park, S.H., M.J. Lee, and H.S. Jung, 2012. Analysis on the Snow Cover Variations at Mt. Kilimanjaro Using Landsat Satellite Images, Korean Journal of Remote Sensing, 28(4): 409-420 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2012.28.4.5   DOI
15 Perez, L. and J. Wang, 2017. The effectiveness of data augmentation in image classification using deep learning, arXiv preprint arXiv:1712.04621. https://doi.org/10.48550/arXiv.1712.04621   DOI
16 Suh, J., H. Yi, S.M. Kim, and H.D. Park, 2013. Prediction of the Area Inundated by Lake Effluent According to Hypothetical Collapse Scenaros of Cheonji Ground at Mt. Baekdu, The Journal of Engineering Geology, 23(4): 409-425 (in Korean with English abstract). https://doi.org/10.9720/kseg.2013.4.409   DOI
17 Xu, J., G. Liu, J. Wu, Y. Ming, Q. Wang, D. Cui, and J. Liu, 2012. Recent unrest of Changbaishan volcano, northeast China: A precursor of a future eruption?, Geophysical Research Letters, 39(16). https://doi.org/10.1029/2012GL052600   DOI
18 Yao, W., Z. Zeng, C. Lian, and H. Tang, 2018. Pixel-wise regression using U-Net and its application on pansharpening, Neurocomputing, 312: 364-371. https://doi.org/10.1016/j.neucom.2018.05.103   DOI
19 Yun, S.M. and C.H. Oh, 2014. Invited Editor's Note: Impact of Probable Volcanic Eruption of Mt. Baekdusan to Han Peninsula and the Corresponding Actions, International Area Studies, 18(3): 7-10 (in Korean with English abstract). https://doi.org/10.18327/jias.2014.09.18.3.7   DOI
20 Yun, S.H. and J.H. Lee, 2012. Analysis of Unrest Signs of Activity at the Baegdusan Volcano, The Journal of the Petrological Society of Korea, 21(1): 1-12 (in Korean with English abstract). https://doi.org/10.7854/JPSK.2012.21.1.001   DOI
21 KMA (Korea Meteorological Administration), 2017. A Study on the Trend Analysis of Surface Temperature Change and System Construction for Monitoring the Distance of Volcanic Activity (III), Korea Meteorological Administration, Seoul, Korea, pp. 78-80 (in Korean).
22 Han, H. and C.K. Lee, 2018. Analysis of ice velocity variations of Nansen ice shelf, East Antarctica, from 2000 to 2017 using Landsat multispectral image matching, Korean Journal of Remote Sensing, 34(6-2): 1165-1178. http://dx.doi.org/10.7780/kjrs.2018.34.6.2.2   DOI
23 Chai, T. and R.R. Draxler, 2014. Root mean square error (RMSE) or mean absolute error (MAE)-Arguments against avoiding RMSE in the literature, Geoscientific Model Development, 7(3): 1247-1250. https://doi.org/ 10.5194/gmd-7-1247-2014   DOI
24 Baek, W.K., 2022. Phase Unwrapping Using Modified U-Net Regression Model: Focusing on Network Structure and Training Data Optimization, University of Seoul, Seoul, Korea (in Korean with English abstract).