Assessment of resources for mapping land cover in the Capibaribe-PE river sub-basin using kompsat-2 image
DOI:
https://doi.org/10.29150/jhrs.v13.2.p270-280Keywords:
Random Forest, Remote Sensing, NDVI, Water Resources.Abstract
Land use and cover mapping is an important factor in geospatial analysis in river basin management. The integration of remote sensing images and Machine Learning classification techniques enable the identification and environmental monitoring of landscape elements. The MSC (MultiSpectral Camara) sensor on the Kompsat-2 satellite captures high spatial resolution images, which allows the identification of terrestrial resources on a local scale. Six data models were developed to classify land use and cover by Random Forest in a sub-basin of the Capibaribe River. These models were created based on spectral indices and variable importance rankings. The results were evaluated through spatial quantification and accuracy analysis. Products based on bands and spectral indices presented global accuracy ranging between 94 and 98%, where the Tree and Shrub Vegetation classes stood out with producer and user accuracy estimates above 80%. Products with the smallest data resources showed poor accuracy performance with overall accuracy values concentrated below 60%. This study is the first to use adaptations of Kompsat-2 spectral data and computational learning methods to demonstrate the application of high-performance land cover mapping. In this way, this article contributed to the monitoring of the soil surface in urban sub-watersheds that require precise spatial information about the environmental conversation status.
References
Archer, Kellie J.; Kimes, Ryan V, 2008. Empirical characterization of random forest variable importance measures. Computational Statistics & Data Analysis, [S.L.], v. 52, p. 2249-2260, jan.. Elsevier BV. http://dx.doi.org/10.1016/j.csda.2007.08.015
AVCI, Cengiz; Budak, Muhammed; Yağmur, Nur; Balçik, Filiz, 2021. Comparison Between Random Forest and Support Vector Machine Algorithms for LULC Classification. International Journal Of Engineering And Geosciences, [S.L.], v. 8, p. 1-10, 30 nov.. International Journal of Engineering and Geoscience. http://dx.doi.org/10.26833/ijeg.987605
Alves, W. S; Martins, A. P; Pôssa, E. M; Moura, D. M. B. Morais, W. A.; Ferreira, R. S, Santos, L. N. S, 2021. Geotechnologies applied in the analysis of land use and land cover (LULC) transition in a hydrographic basin in the Brazilian Cerrado. Remote Sensing Applications: Society and Environment, [S.L.], v. 22, p. 100495, abr. 2021. Elsevier BV. http://dx.doi.org/10.1016/j.rsase.2021.100495
Assis, J. Lacerda, F. F.; Sobral, M. C, 2012 Análise de Detecção De Tendências no Padrão Pluviométrico na Bacia Hidrográfica do Rio Capibaribe. Revista Brasileira de Geografia Física, [S.L.], v. 5, p. 320, 11 out. 2012. Revista Brasileira de Geografia Fisica. http://dx.doi.org/10.26848/rbgf.v5i2.232796
Breiman, L, 2001. Random Forests. Machine Learning. 45, 5–32 2001. https://doi.org/10.1023/A:1010933404324
Behnamian, Amir; Millard, Koreen; Banks, Sarah N.; White, Lori; Richardson, Murray; PASHER, Jon, 2017. A Systematic Approach for Variable Selection With Random Forests: achieving stable variable importance values. Ieee Geoscience And Remote Sensing Letters, [S.L.], v. 14, p. 1988-1992, nov. 2017. Institute of Electrical and Electronics Engineers (IEEE). http://dx.doi.org/10.1109/lgrs.2017.2745049
Congalton, R. G., Green, K., Group, F., & Raton, B. 2009. Assessing the accuracy of remotely sensed data—Principles and practices. International Journal of Applied Earth Observation and Geoinformation, 11, 448–449. https://doi.org/10.1016/j.jag.2009.07.002.
Cunha, E. R; Santos, C. A. G; Silva, R. M. Bacani, V. M ; Teodoro, P. E. Panachuki, E ; Oliveira, N. S, 2020. Mapping LULC types in the Cerrado-Atlantic Forest ecotone region using a Landsat time series and object-based image approach: a case study of the prata river basin, mato grosso do sul, brazil. Environmental Monitoring And Assessment, [S.L.], v. 192, p. 136-146, 24 jan. 2020. Springer Science and Business Media LLC. http://dx.doi.org/10.1007/s10661-020-8093-9
Chaves, M E. D.; Soares, A. R.; Mataveli, G, A. V.; Sánchez, A, H.; Sanches, I, D. A, 2023 Semi-Automated Workflow for LULC Mapping via Sentinel-2 Data Cubes and Spectral Indices. Automation, [S.L.], v. 4, p. 94-109, 23. MDPI AG. http://dx.doi.org/10.3390/automation4010007
Chughtai, Ali Hassan; Abbasi, Habibullah; Karas, Ismail Rakip. 2021. A review on change detection method and accuracy assessment for land use land cover. Remote Sensing Applications: Society and Environment, [S.L.], v. 22, p. 100482, abr. 2021. Elsevier BV. http://dx.doi.org/10.1016/j.rsase.2021.100482
ESA, European Space Agency. KOMPSAT-2 Image data Manual. 2008.
Forkuor, Gerald; Dimobe, Kangbeni; SERME, Idriss; Tondoh, Jerome, 2017. Ebagnerin. Landsat-8 vs. Sentinel-2: examining the added value of sentinel-2⠹s red-edge bands to land-use and land-cover mapping in burkina faso. Giscience & Remote Sensing, [S.L.], v. 55, p. 331-354, 31 ago. 2017. Informa UK Limited. http://dx.doi.org/10.1080/15481603.2017.1370169
Ghosh, A; Sharma, R; Joshi, P.K 2014. Random forest classification of urban landscape using Landsat archive and ancillary data: combining seasonal maps with decision level fusion. Applied Geography, [S.L.], v. 48, p. 31-41, mar. 2014. Elsevier BV. http://dx.doi.org/10.1016/j.apgeog.2014.01.003.
Gao, Bo-Cai. 1996 NDWI—A normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sensing Of Environment, [S.L.], v. 58, p. 257-266, dez. 1996. Elsevier BV. http://dx.doi.org/10.1016/s0034-4257(96)00067-3
Gameiro, S; Nascimento, V; Facco, D; Sfredo, G; Ometto, J, 2022. Multitemporal Spatial Analysis of Land Use and Land Cover Changes in the Lower Jaguaribe Hydrographic Sub-Basin, Ceará, Northeast Brazil. Land, [S.L.], v. 11, p. 103, 8 jan. 2022. MDPI AG. http://dx.doi.org/10.3390/land11010103
Hussain, Sajjad; Mubeen, Muhammad; Karuppannan, Shankar, 2022. Land use and land cover (LULC) change analysis using TM, ETM+ and OLI Landsat images in district of Okara, Punjab, Pakistan. Physics And Chemistry Of The Earth, Parts A/B/C, [S.L.], v. 126, p. 103117, jun. 2022. Elsevier BV. http://dx.doi.org/10.1016/j.pce.2022.103117
Huete.1997 A comparison of vegetation indices over a global set of TM images for EOS-MODIS. Remote Sensing Of Environment, [S.L.], v. 59, p. 440-451, mar. 1997. Elsevier BV. http://dx.doi.org/10.1016/s0034-4257(96)00112-5
KIM, Jinsoo; JIN, Cheonggil; CHOI, Chuluong; AHN, Hoyong. Radiometric characterization and validation for the KOMPSAT-3 sensor. Remote Sensing Letters, [S.L.], v. 6, p. 529-538, 10 jun. 2015. Informa UK Limited. http://dx.doi.org/10.1080/2150704x.2015.1054043
Körting, Thales; Fonseca, Leila; Castejon, Emiliano; Namikawa, Laercio, 2014. Improvements in Sample Selection Methods for Image Classification. Remote Sensing, [S.L.], v. 6, p. 7580-7591, 15 ago. 2014. MDPI AG. http://dx.doi.org/10.3390/rs6087580
LU, Dengsheng; LI, Guiying; MORAN, Emilio; HETRICK, Scott. Spatiotemporal analysis of land-use and land-cover change in the Brazilian Amazon. International Journal of Remote Sensing, [S.L.], v. 34, n. 16, p. 5953-5978, 28 maio 2013. Informa UK Limited. http://dx.doi.org/10.1080/01431161.2013.802825
MA, Lei; LI, Manchun; MA, Xiaoxue; CHENG, Liang; DU, Peijun; Liu, Yongxue, 2017. A review of supervised object-based land-cover image classification. ISPRS Journal Of Photogrammetry And Remote Sensing, [S.L.], v. 130, p. 277-293, ago. 2017. Elsevier BV. http://dx.doi.org/10.1016/j.isprsjprs.2017.06.001
Mcfeeters, S. K, 1996. The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. International Journal Of Remote Sensing, [S.L.], v. 17, p. 1425-1432, maio 1996. Informa UK Limited. http://dx.doi.org/10.1080/01431169608948714
Machado, A. M. B, 2020. Comparação de imagens OLI/Landsat-8 e MSI/Sentinel-2 no mapeamento de uso e cobertura da terra na ilha do Maranhão. Revista Equador, [S.L.], v. 9, p. 209-232, 2 jul. 2020. Universidade Federal do Piaui. http://dx.doi.org/10.26694/equador.v9i3.10451
Noi, Phan Thanh; Kappas, Martin, 2017 Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery. Sensors, [S.L.], v. 18, p. 18, 22 dez. 2017. MDPI AG. http://dx.doi.org/10.3390/s18010018
Nedd, R; Light, K; Owens, Marcia; James, Neil; Johnson, Elijah; Anandhi, Aavudai. 2021, A Synthesis of Land Use/Land Cover Studies: definitions, classification systems, meta-studies, challenges and knowledge gaps on a global landscape. Land, [S.L.], v. 10, p. 994, 21 set. 2021. MDPI AG. http://dx.doi.org/10.3390/land10090994
Oliveira, N.; Maciel, M.; Lúcia, A.; Ulisses A. B.; C, 2018. A. Uso e cobertura do solo utilizando geoprocessamento em municípios do Agreste de Pernambuco. Revista Brasileira de Meio Ambiente, v. 4, 2018. Disponível em: https://revistabrasileirademeioambiente.com/index.php/RVBMA/article/view/95/96
Ponzoni, F. J; Shimabukuro, Y. E; Kuplich, T. M, 2015. Sensoriamento remoto da vegetação. Oficina de Textos, 2015.
Rouse, J. W. et al, 1974. Monitoring vegetation systems in the Great Plains with ERTS. NASA Spec. Publ, v. 351, p. 309, 1974. https://ntrs.nasa.gov/citations/19740022614
Sunwoo, W.; Kim, D.; Kang, S.; Choi, M, 2016. Application of KOMSAT-2 Imageries for Change Detection of Land use and Land Cover in the West Coasts of the Korean Peninsula. Korean Journal of Remote Sensing, v. 32, p. 141–153, 2016. https://doi.org/10.7780/kjrs.2016.32.2.7
Silva J. J. A. Pacheco, A. P; Ruiz-A. A. M; Henriques, R. F. F, 2022 Evaluation of the Ability of SLSTR (Sentinel-3B) and MODIS (Terra) Images to Detect Burned Areas Using Spatial-Temporal Attributes and SVM Classification. Forests, [S.L.], v. 14, p. 32, 24 dez. 2022. MDPI AG. http://dx.doi.org/10.3390/f14010032
Souza, B. S; Cantalice, W. L. B. C; Braga, C. C; Silva, M. T; Silva, E. A, 2022. Resposta do índice de vegetação evi a anomalias de precipitação no estado da Paraíba. Journal Of Hyperspectral Remote Sensing, [S.L.], v. 12, p. 10, 25 maio 2022. Universidade Federal de Pernambuco. http://dx.doi.org/10.29150/2237-2202.2022.252412.
Sheykhmousa, Mohammadreza; Mahdianpari, Masoud; Ghanbari, Hamid; Mohammadimanesh, Fariba; Ghamisi, Pedram; Homayouni, 2020, Saeid. 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, [S.L.], v. 13, p. 6308-6325. Institute of Electrical and Electronics Engineers (IEEE). http://dx.doi.org/10.1109/jstars.2020.3026724
Santos, J. Y. G; Montenegro, S. M. G. L; Silva, R. M; Santos, C. A. G; Quinn, N. Wyndham; Dantas, A. P. Xavier; R. N, A, 2021 Modeling the impacts of future LULC and climate change on runoff and sediment yield in a strategic basin in the Caatinga/Atlantic forest ecotone of Brazil. Catena, [S.L.], v. 203, p. 105308, ago. 2021. Elsevier BV. http://dx.doi.org/10.1016/j.catena.2021.105308
Talukdar, S; Singha, P; Mahato, S; Shahfahad; Pal, Swades; Liou, Y; Rahman, A, 2020. Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations—A Review. Remote Sensing, [S.L.], v. 12, p. 1135, 2 abr. 2020. MDPI AG. http://dx.doi.org/10.3390/rs12071135
ThenkabaiL, P S; Schull, M; Turral, H, 2005 Ganges and Indus river basin land use/land cover (LULC) and irrigated area mapping using continuous streams of MODIS data. Remote Sensing Of Environment, [S.L.], v. 95, p. 317-341, abr. 2005. Elsevier BV. http://dx.doi.org/10.1016/j.rse.2004.12.018
Tavares, P; Beltrão, N; Guimarães, U; Teodoro, A, 2019. Integration of Sentinel-1 and Sentinel-2 for Classification and LULC Mapping in the Urban Area of Belém, Eastern Brazilian Amazon. Sensors, [S.L.], v. 19, p. 1140, 6 mar. 2019. MDPI AG. http://dx.doi.org/10.3390/s19051140
Zhang, X; Tan, B; Yu, Y, 2014 Interannual variations and trends in global land surface phenology derived from enhanced vegetation index during 1982–2010. International Journal Of Biometeorology, [S.L.], v. 58, p. 547-564, 18 mar. 2014. Springer Science and Business Media LLC. http://dx.doi.org/10.1007/s00484-014-0802-z
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Journal of Hyperspectral Remote Sensing
This work is licensed under a Creative Commons Attribution 4.0 International License.
Material protegido por direitos autorais e plágio. No caso de material com direitos autorais a ser reproduzido no manuscrito, a atribuição integral deve ser informada no texto; um documento comprobatório de autorização deve ser enviado para a Comissão Editorial como documento suplementar. É da responsabilidade dos autores, não da RBGF ou dos editores ou revisores, informar, no artigo, a autoria de textos, dados, figuras, imagens e/ou mapas publicados anteriormente em outro lugar. Se existir alguma suspeita sobre a originalidade do material, a Comissão Editorial pode verificar o manuscrito por plágio. Nos casos em que o plágio for confirmado, o manuscrito será devolvido sem revisão adicional e sem a possibilidade de re-submissão. Auto-plágio (ou seja, o uso de frases idênticas de documentos publicados anteriormente pelo mesmo autor) também não é aceitável.
