Results of principal component analysis using multisource data
DOI:
https://doi.org/10.5564/mjgg.v62i46.4231Keywords:
Hyperspectral data, SAR data, AnalysisAbstract
In the processing of aerospace digital data, Principal Component Analysis (PCA) is utilized to enhance the spectral brightness of images by identifying new features, as well as compressing and reducing the dimensionality of multidimensional datasets. PCA reduces the size of hyperspectral data and generates new features, known as principal components (PCs). The first PC contains the most information, while the last PC contains the least. This enables the representation of hundreds of channels of multidimensional data with a small number of components. The primary objective of this study is to analyze the 234-channel hyperspectral data from the PRISMA satellite, both independently and in conjunction with VV and VH polarization synthetic aperture radar (SAR) data obtained from the Sentinel-1B satellite. Ulaanbaatar was selected as the test area for this research. When the 202 channels of PRISMA satellite data were processed and analyzed using the PCA, it was found that 98.9% of the total information was contained in the first five components, with PC1 accounting for 53.66% of the total variance of the original 202 channels. In contrast, when the combined hyperspectral and SAR data were processed, the first five components represented 99.1% of the total information, resulting in an increase of 0.2% in total information content. Overall, the results of the study show that the use of multiple source data and integration can further improve the quality of thematic interpretation and analysis.
Олон эх сурвалжийн мэдээг гол компонентын аргаар шинжилсэн дүн
ХУРААНГУЙ: Агаар-сансрын тоон өгөгдлийг боловсруулахад гол компонентын шинжилгээ (ГКШ)-ний арга нь сувгуудыг шинээр тодорхойлон дүрс зургийн спектр тодролыг сайжруулахаас гадна, олон хэмжээст өгөгдлийг шахаж, хэмжээсийг нь багасгахад ашиглагдана. Хайперспектрийн мэдээг ГКШ-ний аргаар хэмжээсийг нь багасган, шинэ сувгуудыг буюу гол компонент (ГК)-уудыг үүсгэхэд, эхний ГК хамгийн их мэдээллийг, сүүлийн ГК хамгийн бага мэдээллийг агуулдаг. Ингэснээр, олон зуун сувгийн өгөгдлийг цөөн тооны компонентуудаар илэрхийлэх боломжтой болдог. Энэхүү судалгаа нь PRISMA дагуулын 234 сувгийн хайперспектрийн мэдээг тусад нь болон Sentinel-1В дагуулаас VV, VH туйлшралуудаар хүлээн авсан синтетик апертурт радар (САР)-ын өгөгдөлтэй нийлүүлэн ГКШ-ний аргаар дүн шинжилгээ хийх үндсэн зорилготой бөгөөд судалгааны загвар талбай болгон Улаанбаатар хотыг сонгон авав. PRISMA дагуулын 202 сувгийн мэдээг ГКШ-ний аргаар боловсруулан, шинжилгээ хийхэд нийт мэдээллийн 98.9% нь эхний 5 компонентэд агуулагдаж байсан ба ГК1 нь анхдагч 202 сувгийн мэдээний нийт дисперсийн 53.66 хувийг агуулж байв. Харин хайперспектрийн болон САР-ын нэгдмэл мэдээг ГКШ-ний аргаар боловсруулан шинжлэхэд эхний 5 компонент нийт мэдээллийн 99.1%-ийг агуулж, нийт мэдээллийн агууламж 0.2%-иар нэмэгдсэн байлаа. Судалгааны үр дүнгээс харахад, олон эх сурвалжийн мэдээг нийлмэл байдлаар ашигласнаар сэдэвчилсэн тайлал болон дүн шинжилгээний чанарыг илүү сайжруулах боломжтой байна.
Түлхүүр үгс: Хайперспектрийн мэдээ, САР-ын мэдээ, Дүн шинжилгээ
Downloads
232
References
[1] D. Amarsaikhan and M. Ganzorig, “Different approaches in feature extraction for hyperspectral image classification,” in Proc. 20th Asian Conf. Remote Sensing, Hong Kong, pp. 434–438, 1999.
[2] Д. Амарсайхан, Ц. Адьяасүрэн, and М. Саандарь, “Зайнаас тандах судлал, газарзүйн мэдээллийн системийг байгалийн нөөцийн менежментэд ашиглах нь,” 5 дахь хэвлэл, 43.7 хэвл. хуудас, Улаанбаатар, 2014.
[3] O. B. Özdemir, A. Koz, and Y. Çetin, “Non-linear hyperspectral unmixing with 3D convolutional encoders,” Int. J. Remote Sens., vol. 43, no. 9, pp. 3236–3257, 2022, https://doi.org/10.1080/01431161.2022.2088258.
[4] D. Amarsaikhan, M. Ganzorig, P. Ache, and H. Blotevogel, “The integrated use of optical and InSAR data for urban land cover mapping,” Int. J. Remote Sens., vol. 28, no. 6, pp. 1161–1171, 2007, https://doi.org/10.1080/01431160600784267.
[5] L. Zhang, M. Zhang, and X. Sun et al., “Cloud removal for hyperspectral remotely sensed images based on hyperspectral information fusion,” Int. J. Remote Sens., vol. 39, no. 20, pp. 6646–6656, 2018, https://doi.org/10.1080/01431161.2018.1466068.
[6] D. Amarsaikhan, A. Enkhmanlai, V. Battsengel, and V. Batsaikhan, “Feature extraction and classification of hyperspectral images,” in Proc. Asian Conf. Remote Sensing, Pattaya, Thailand, 2012, https://doi.org/10.1080/01431161.2020.1736732.
[7] B. Cui, J. Cui, and S. Hao, “Spectral-spatial hyperspectral image classification based on superpixel and multi-classifier fusion,” Int. J. Remote Sens., vol. 41, no. 16, pp. 6157–6182, 2020, https://doi.org/10.1080/01431161.2020.1736730.
[8] D. Amarsaikhan, A. Enkhmanlai, Ts. Bat-Erdene, E. Jargaldalai, and Ch. Bolorchuluun, “Feature extraction and classification of hyperspectral data of Mongolia using machine learning methods,” in eProc. Asian Conf. Remote Sensing, Ulaanbaatar, Mongolia, 2022.
[9] L. Jiaju, “Development of principal component analysis applied to multitemporal Landsat TM data,” Int. J. Remote Sens., vol. 9, no. 12, pp. 1895–1907, 1988, https://doi.org/10.1080/01431168808954988.
[10] A. Picchiotti, R. Casacchia, and R. Salvatori, “Multitemporal principal component analysis of spectral and spatial features of the Venice Lagoon,” Int. J. Remote Sens., vol. 18, no. 1, pp. 183–196, 1997, https://doi.org/10.1080/014311697219358.
[11] L. Jing and A. Panahi, “Principal component analysis with optimum order sample correlation coefficient for image enhancement,” Int. J. Remote Sens., vol. 27, no. 16, pp. 3387–3401, 2006, https://doi.org/10.1080/01431160600606882.
[12] N. Neeti and J. R. Eastman, “Characterizing implications of two-dimensional space–time orientations for principal component analysis of geographic time series,” Int. J. Remote Sens., vol. 36, no. 1, pp. 290–299, 2015, https://doi.org/10.1080/01431161.2014.994717.
[13] [13] X. Xu, R. Gao, and Y. Qing et al., “Hyperspectral image mixed noise removal via tensor robust principal component analysis with tensor-ring decomposition,” Int. J. Remote Sens., vol. 44, no. 5, pp. 1556–1578, 2023, https://doi.org/10.1080/01431161.2023.2187720.
[14] D. Amarsaikhan, B. Gorte, and W. Nieuwenhuis, “Knowledge-based approach to update a land use layer of an operational GIS,” in Proc. 13th Asian Conf. Remote Sensing, Ulaanbaatar, Mongolia, pp. G-5-1–G-5-3, 1992.
[15] A. Munkh-Erdene, D. Amarsaikhan, G. Odontuya, D. Enkhjargal, and E. Jargaldalai, “Feature extraction approach in hyperspectral data,” Advances in Engineering Research, vol. 206, Proc. ESTIC 2021, Atlantis Press – Springer Nature, pp. 102–108, 2021.
[16] JPL, “PRISMA data are now available for access,” https://sbg.jpl.nasa.gov/news-events/prisma-data-are-now-available-for-access.
[17] J. A. Richards and S. Jia, Remote Sensing Digital Image Analysis — An Introduction, 3rd ed., Berlin: Springer-Verlag, 2014.
[18] P. M. Mather and B. Koh, Computer Processing of Remotely-Sensed Images: An Introduction, 4th ed., Chichester, UK: Wiley-Blackwell, 2011.
[19] ERDAS, ERDAS Field Guide, Atlanta, GA, USA, 2009.
[20] ENVI, User’s Guide, Research Systems, USA, 2009.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Amarsaikhan Damdinsuren, Enkhjargal Damdinsuren, Odontuya Gendaram, Tsogzol Gurjav, Ochirhuyag Lkhamjav
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright on any research article in the Mongolian Journal of Geography and Geoecology is retained by the author(s).
The authors grant the Mongolian Journal of Geography and Geoecology a license to publish the article and identify itself as the original publisher.
Articles in the Mongolian Journal of Geography and Geoecology are Open Access articles published under a Creative Commons Attribution 4.0 International License CC BY.
This license permits use, distribution and reproduction in any medium, provided the original work is properly cited.
