Uso do classificador Support Vector Machines para o mapeamento da cobertura do solo usando imagens de Sensoriamento Remoto

Autores

DOI:

https://doi.org/10.26848/rbgf.v16.3.p1304-1319

Resumo

O mapeamento do uso/cobertura da terra desempenha um papel vital no planejamento e supervisão da utilização dos recursos naturais com base no aumento gradual das demandas humanas no ecossistema atual. As detecções de mudanças na cobertura do solo são essenciais para entender quais vetores de degradação atuam na região, além do monitoramento do risco ambiental no entorno de reservatórios de abastecimento de água no Bioma Caatinga. O sensoriamento remoto e o classificador SVM fornecem uma plataforma consistente para estudar as transformações da paisagem em toda a superfície da Terra. Este estudo objetiva o mapeamento de uso e ocupação do solo no entorno da Barragem barra do Juá localizado no estado de Pernambuco através da comparação entre sensores orbitais, o Câmera Multiespectral Regular (MUX) e o Operational Land Instrument (OLI) dos satélites CBERS-4 e Landsat-8 respectivamente. A análises foram baseadas em Tabela de Contingência obtidas por meio de um mapa oficial de referência. Após a verificações comparativas com o produto de referência, foram obtidos uma acurácia do produtor e de usuário médio de 62,44% e 71,74% para o MUX e 60,88% e 62,38% para o OLI, respectivamente. As diferentes especificações e capacidades técnicas entre os sensores na captura bem como o comportamento espectral dos alvos foram relevantes para a variabilidade espacial e temática entre os mapas de uso do solo MUX e OLI.  Os resultados obtidos mostraram que o MUX apresentou mapas de cobertura da terra com melhor desempenho em relação aos dados OLI.      

 

Support Vector Machines classifier for land cover mapping using CBERS-4/MUX and Landsat-8/OLI images

 

A B S T R A C T

Land use/land cover mapping plays a vital role in planning and supervising the use of natural resources based on the gradual increase in human demands on today's ecosystem. The detection of changes in land cover is essential to understand which degradation vectors act in the region, in addition to monitoring the environmental risk around water supply reservoirs in the Caatinga Biome. Remote sensing and the SVM classifier provide a consistent platform for studying landscape transformations across the Earth's surface. This study aims to map land use and occupation around the Barra do Juá dam located in the state of Pernambuco through the comparison between orbital sensors, the Regular Multispectral Camera (MUX) and the Operational Land Instrument (OLI) of the CBERS-4 satellites and Landsat-8 respectively. The analyzes were based on a Contingency Table obtained through an official reference map. After comparative verifications with the reference product, an accuracy of 62.44% and 71.74% for the MUX and 60.88% and 62.38% for the OLI were obtained for the average producer and user, respectively. The different specifications and technical capabilities between the sensors in the capture as well as the spectral behavior of the targets were relevant to the spatial and thematic variability between the MUX and OLI land use maps. The results obtained showed that the MUX presented land cover maps with better performance in relation to the OLI data

Referências

Antonio da Silva Júnior, J., Joaquim da Silva Júnior, U., & Da Penha Pacheco, A. (2021). Análise de acurácia para o mapeamento de áreas queimadas utilizando uma cena VIIRS 1Km e classificação por Random Forest. Revista Brasileira de Geografia Física, 14(6), 3225. https://doi.org/10.26848/rbgf.v14.6.p3225-3240

APAC. (2019). APAC - Agência Pernambucana de Águas e Climas - Início. APAC - Agência Pernambucana de Águas E Climas. https://www.apac.pe.gov.br/

Batalha, M. A., Mantovani, W., & Mesquita Júnior, H. N. de. (2001). Vegetation structure in cerrado physiognomies in South-eastern Brazil. Brazilian Journal of Biology, 61(11), 475–483. https://doi.org/10.1590/S1519-69842001000300018

Benbriqa, H., Abnane, I., Idri, A., & Tabiti, K. (2021). Deep and Ensemble Learning Based Land Use and Land Cover Classification. Computational Science and Its Applications – ICCSA 2021, 21(01), 588–604. https://doi.org/10.1007/978-3-030-86970-0_41

Bolton, D. K., Gray, J. M., Melaas, E. K., Moon, M., Eklundh, L., & Friedl, M. A. (2020). Continental-scale land surface phenology from harmonized Landsat 8 and Sentinel-2 imagery. Remote Sensing of Environment, 240(45), 111685. https://doi.org/10.1016/j.rse.2020.111685

Braimoh, A. K. (2006). Random and systematic land-cover transitions in northern Ghana. Agriculture, Ecosystems & Environment, 113(1-4), 254–263. https://doi.org/10.1016/j.agee.2005.10.019

Congalton, R. G. (1991). A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment, 37(1), 35–46. https://doi.org/10.1016/0034-4257(91)90048-b

Deilmai, B. R., Ahmad, B. B., & Zabihi, H. (2014). Comparison of two Classification methods (MLC and SVM) to extract land use and land cover in Johor Malaysia. IOP Conference Series: Earth and Environmental Science, 20(91), 012052. https://doi.org/10.1088/1755-1315/20/1/012052

Dragozi, E., Gitas, I., Stavrakoudis, D., & Theocharis, J. (2014). Burned Area Mapping Using Support Vector Machines and the FuzCoC Feature Selection Method on VHR IKONOS Imagery. Remote Sensing, 6(12), 12005–12036. https://doi.org/10.3390/rs61212005

ESA. (2021). Sentinel-2 - Missions - Resolution and Swath - Sentinel Handbook. Sentinel.esa.int. https://sentinel.esa.int/web/sentinel/missions/sentinel-2/instrument-payload/resolution-and-swath

Eva, H., & Lambin, E. F. (1998). Remote Sensing of Biomass Burning in Tropical Regions. Remote Sensing of Environment, 64(3), 292–315. https://doi.org/10.1016/s0034-4257(98)00006-6

Fichera, C. R., Modica, G., & Pollino, M. (2012). Land Cover classification and change-detection analysis using multi-temporal remote sensed imagery and landscape metrics. European Journal of Remote Sensing, 45(1), 1–18. https://doi.org/10.5721/eujrs20124501

Foody, G. M. (2020). Explaining the unsuitability of the kappa coefficient in the assessment and comparison of the accuracy of thematic maps obtained by image classification. Remote Sensing of Environment, 239(01), 111630. https://doi.org/10.1016/j.rse.2019.111630

Giannini, M. F. C., Harari, J., & Ciotti, A. M. (2017). The use of CBERS (China-Brazil Earth Resources Satellite) to trace the dynamics of total suspended matter at an urbanized coastal area. Brazilian Journal of Oceanography, 65(2), 309–323. https://doi.org/10.1590/s1679-87592017135006502

Gibril, M. B. A., Bakar, S. A., Yao, K., Idrees, M. O., & Pradhan, B. (2016). Fusion of RADARSAT-2 and multispectral optical remote sensing data for LULC extraction in a tropical agricultural area. Geocarto International, 32(7), 735–748. https://doi.org/10.1080/10106049.2016.1170893

Giglio, L., Boschetti, L., Roy, D. P., Humber, M. L., & Justice, C. O. (2018). The Collection 6 MODIS burned area mapping algorithm and product. Remote Sensing of Environment, 217(06), 72–85. https://doi.org/10.1016/j.rse.2018.08.005

GLASS. (2013). Interpreting Aerial Photographs to Identify Natural Hazards. Elsevier. https://doi.org/10.1016/c2012-0-06726-9

Gonçalves, R. V. S., Cardoso, J. C. F., Oliveira, P. E., & Oliveira, D. C. (2021). Changes in the Cerrado vegetation structure: insights from more than three decades of ecological succession. Web Ecology, 21(08), 55–64. https://doi.org/10.5194/we-21-55-2021

Hosseini, M., McNairn, H., Mitchell, S., Robertson, L. D., Davidson, A., Ahmadian, N., Bhattacharya, A., Borg, E., Conrad, C., Dabrowska-Zielinska, K., de Abelleyra, D., Gurdak, R., Kumar, V., Kussul, N., Mandal, D., Rao, Y. S., Saliendra, N., Shelestov, A., Spengler, D., & Verón, S. R. (2021). A Comparison between Support Vector Machine and Water Cloud Model for Estimating Crop Leaf Area Index. Remote Sensing, 13(7), 1348. https://doi.org/10.3390/rs13071348

Hu, B., Xu, Y., Huang, X., Cheng, Q., Ding, Q., Bai, L., & Li, Y. (2021). Improving Urban Land Cover Classification with Combined Use of Sentinel-2 and Sentinel-1 Imagery. ISPRS International Journal of Geo-Information, 10(8), 533. https://doi.org/10.3390/ijgi10080533

Huang, C., Yang, J., & Jiang, P. (2018). Assessing Impacts of Urban Form on Landscape Structure of Urban Green Spaces in China Using Landsat Images Based on Google Earth Engine. Remote Sensing, 10(10), 1569. https://doi.org/10.3390/rs10101569

Jia, K., Wei, X., Gu, X., Yao, Y., Xie, X., & Li, B. (2014). Land cover classification using Landsat 8 Operational Land Imager data in Beijing, China. Geocarto International, 29(8), 941–951. https://doi.org/10.1080/10106049.2014.894586

Kranjčić, N., Medak, D., Župan, R., & Rezo, M. (2019). Support Vector Machine Accuracy Assessment for Extracting Green Urban Areas in Towns. Remote Sensing, 11(6), 655. https://doi.org/10.3390/rs11060655

Lagbas, A. J. (2019). Social valuation of regulating and cultural ecosystem services of Arroceros Forest Park: A man-made forest in the city of Manila, Philippines. Journal of Urban Management, 8(1), 159–177. https://doi.org/10.1016/j.jum.2018.09.002

Lamine, S., Petropoulos, G. P., Singh, S. K., Szabó, S., Bachari, N. E. I., Srivastava, P. K., & Suman, S. (2017). Quantifying land use/land cover spatio-temporal landscape pattern dynamics from Hyperion using SVMs classifier and FRAGSTATS®. Geocarto International, 33(8), 862–878. https://doi.org/10.1080/10106049.2017.1307460

Li, C., Wang, J., Wang, L., Hu, L., & Gong, P. (2014). Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery. Remote Sensing, 6(2), 964–983. https://doi.org/10.3390/rs6020964

Li, Q., Qiu, C., Ma, L., Schmitt, M., & Zhu, X. (2020). Mapping the Land Cover of Africa at 10 m Resolution from Multi-Source Remote Sensing Data with Google Earth Engine. Remote Sensing, 12(4), 602. https://doi.org/10.3390/rs12040602

Liu, Q., Song, H., Liu, G., Huang, C., & Li, H. (2019). Evaluating the Potential of Multi-Seasonal CBERS-04 Imagery for Mapping the Quasi-Circular Vegetation Patches in the Yellow River Delta Using Random Forest. Remote Sensing, 11(10), 1216. https://doi.org/10.3390/rs11101216

Mei, J., Liu, M., Wang, Y.-F., & Gao, H. (2016). Learning a Mahalanobis Distance-Based Dynamic Time Warping Measure for Multivariate Time Series Classification. IEEE Transactions on Cybernetics, 46(6), 1363–1374. https://doi.org/10.1109/tcyb.2015.2426723

Meyer, D., Dimitriadou, E., Hornik, K., Weingessel, A., Leisch, F., C++-code), C.-C. C. (libsvm, & C++-code), C.-C. L. (libsvm. (2022, June 7). e1071: Misc Functions of the Department of Statistics, Probability

Theory Group (Formerly: E1071), TU Wien. R-Packages. https://cran.r-project.org/web/packages/e1071/index.html

Mountrakis, G., Im, J., & Ogole, C. (2011). Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 66(3), 247–259. https://doi.org/10.1016/j.isprsjprs.2010.11.001

Naikoo, M. W., Rihan, M., Ishtiaque, M., & Shahfahad. (2020). Analyses of land use land cover (LULC) change and built-up expansion in the suburb of a metropolitan city: Spatio-temporal analysis of Delhi NCR using landsat datasets. Journal of Urban Management, 9(01). https://doi.org/10.1016/j.jum.2020.05.004

NASA. (2013, June 28). Spectral Response of the Operational Land Imager In-Band, Band-Average Relative Spectral Response | Landsat Science. Spectral Response of the Operational Land Imager In-Band, Band-Average Relative Spectral Response. https://landsat.gsfc.nasa.gov/article/preliminary-spectral-response-of-the-operational-land-imager-in-band-band-average-relative-spectral-response/

Pal, M., & Mather, P. M. (2005). Support vector machines for classification in remote sensing. International Journal of Remote Sensing, 26(5), 1007–1011. https://doi.org/10.1080/01431160512331314083

Parida, B. R., & Mandal, S. P. (2020). Polarimetric decomposition methods for LULC mapping using ALOS L-band PolSAR data in Western parts of Mizoram, Northeast India. SN Applied Sciences, 2(6). https://doi.org/10.1007/s42452-020-2866-1

Pereira, A., Pereira, J., Libonati, R., Oom, D., Setzer, A., Morelli, F., Machado-Silva, F., & de Carvalho, L. (2017). Burned Area Mapping in the Brazilian Savanna Using a One-Class Support Vector Machine Trained by Active Fires. Remote Sensing, 9(11), 1161. https://doi.org/10.3390/rs9111161

Pinto, C., Ponzoni, F., Castro, R., Leigh, L., Mishra, N., Aaron, D., & Helder, D. (2016). First in-Flight Radiometric Calibration of MUX and WFI on-Board CBERS-4. Remote Sensing, 8(5), 405. https://doi.org/10.3390/rs8050405

Roy, A., & Inamdar, A. B. (2019). Multi-temporal Land Use Land Cover (LULC) change analysis of a dry semi-arid river basin in western India following a robust multi-sensor satellite image calibration strategy. Heliyon, 5(4), e01478. https://doi.org/10.1016/j.heliyon.2019.e01478

Sheykhmousa, M., Mahdianpari, M., Ghanbari, H., Mohammadimanesh, F., Ghamisi, P., & Homayouni, S. (2020). Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13(04), 6308–6325. https://doi.org/10.1109/jstars.2020.3026724

Silva Junior, J. A. da, & Pacheco, A. D. P. (2020). Análise do Modelo Linear de Mistura Espectral na Avaliação de Incêndios Florestais no Parque Nacional do Araguaia, Tocantins, Brasil: Imagens EO-1/Hyperion e Landsat-7/ETM+. Anuário Do Instituto de Geociências, 43(4). https://doi.org/10.11137/2020_4_440_450

Simões, J. M., Almeida, F. T. de, Uliana, E. M., & Vendrusculo, L. G. (2021). Uso de sensoriamento remoto no monitoramento de sólidos em suspensão do reservatório de uma usina hidrelétrica na transição Cerrado-Amazônia. Gaia Scientia, 15(3). https://doi.org/10.22478/ufpb.1981-1268.2021v15n3.57559

Smith, D. M., Tabrett, S. J., Glencross, B. D., Irvin, S. J., & Barclay, M. C. (2007). Digestibility of lupin kernel meals in feeds for the black tiger shrimp, Penaeus monodon. Aquaculture, 264(1-4), 353–362. https://doi.org/10.1016/j.aquaculture.2006.12.002

Thanh Noi, P., & Kappas, M. (2017). Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery. Sensors (Basel, Switzerland), 18(1), 18. https://doi.org/10.3390/s18010018

Tharwat, A. (2018). Classification assessment methods. Applied Computing and Informatics, 01(06). https://doi.org/10.1016/j.aci.2018.08.003

Ul Din, S., & Mak, H. W. L. (2021). Retrieval of Land-Use/Land Cover Change (LUCC) Maps and Urban Expansion Dynamics of Hyderabad, Pakistan via Landsat Datasets and Support Vector Machine Framework. Remote Sensing, 13(16), 3337. https://doi.org/10.3390/rs13163337

Vapnik, V. The support vector method of function estimation. In Nonlinear Modeling; Springer: Berlin/Heidelberg, Germany, 1998; pp. 55–85.

Wulder, M. A., Loveland, T. R., Roy, D. P., Crawford, C. J., Masek, J. G., Woodcock, C. E., Allen, R. G., Anderson, M. C., Belward, A. S., Cohen, W. B., Dwyer, J., Erb, A., Gao, F., Griffiths, P., Helder, D., Hermosilla, T., Hipple, J. D., Hostert, P., Hughes, M. J., & Huntington, J. (2019). Current status of Landsat program, science, and applications. Remote Sensing of Environment, 225(06), 127–147. https://doi.org/10.1016/j.rse.2019.02.015

Yan, J., Wang, L., Song, W., Chen, Y., Chen, X., & Deng, Z. (2019). A time-series classification approach based on change detection for rapid land cover mapping. ISPRS Journal of Photogrammetry and Remote Sensing, 158(10), 249–262. https://doi.org/10.1016/j.isprsjprs.2019.10.003

Zanaga, D., Van De Kerchove, R., De Keersmaecker, W., Souverijns, N., Brockmann, C., Quast, R., Wevers, J., Grosu, A., Paccini, A., Vergnaud, S., Cartus, O., Santoro, M., Fritz, S., Georgieva, I., Lesiv, M., Carter, S., Herold, M., Li, L., Tsendbazar, N.-E., & Ramoino, F. (2021, October 20). ESA WorldCover 10 m 2020 v100. Zenodo; Zenodo. https://zenodo.org/record/5571936#.ZD3jzHbMLIU

Zeng, L., Wardlow, B. D., Xiang, D., Hu, S., & Li, D. (2020). A review of vegetation phenological metrics extraction using time-series, multispectral satellite data. Remote Sensing of Environment, 237(04), 111511. https://doi.org/10.1016/j.rse.2019.111511

Downloads

Publicado

2023-06-01

Como Citar

Antônio da Silva Júnior, J., & da Penha Pacheco, A. (2023). Uso do classificador Support Vector Machines para o mapeamento da cobertura do solo usando imagens de Sensoriamento Remoto. Revista Brasileira De Geografia Física, 16(3), 1304–1319. https://doi.org/10.26848/rbgf.v16.3.p1304-1319

Edição

Seção

Geoprocessamento e Sensoriamento Remoto