Comparison of Statistical Modeling for SAR Data in Land Cover Classification: a Case Studyin the Brazilian Amazon Region
Article Sidebar
Main Article Content
Abstract
SAR images are an alternative for land cover classification since these sensors obtain images almost independently
of weather conditions. Parametric image classification methods are often based on a Gaussian distribution, simplifying statistical modeling. However, the assumption of a Gaussian distribution may not be suitable for modeling samples from SAR images. Therefore, this study aimed to compare the results of land cover classification using SAR images modeled with statistical distributions. To this end, 1000 supervised classifications were carried out on a PALSAR/ALOS image of the Lower Tapajós/PA region, using the maximum likelihood classifier adapted to the Gaussian, Gamma, and Intensity joint distribution. The analysis classes were defined as Agriculture, Exposed Soil, Pasture, Forest, and Secondary Vegetation. As a result, models with the same dimensionality and polarizations had similar overall classification performances, but it
should be noted that the bivariate models showed better overall accuracy than the univariate ones. The Gaussian distribution can replace specific distributions for SAR data without compromising overall classification performance in some cases. Concerning metrics by class, no models were found that separate all classes well, especially the Forest and Secondary Vegetation classes, whose separability is difficult. However, the Exposed Soil class is well classified in all models.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish in this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors can enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) before and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (see "The Effect of Open Access").
How to Cite
References
ALMEIDA, C. A.; COUTINHO, A. C.; ESQUERDO, J. C. D. M.; ADAMI, M.; VENTURIERI, A.;
DINIZ, C. G.; DESSAY, N.; DURIEUX, L.; GOMES, A. R. High spatial resolution land use
and land cover mapping of the Brazilian Legal Amazon in 2008 using Landsat-5/TM and
MODIS data. [S.l.], 2016. P. 291–302. DOI: 10.1590/1809-4392201505504. Disponível em:
<https://doi.org/10.1590/1809-4392201505504>.
ANFINSEN, S. N.; DOULGERIS, A. P.; ELTOFT, T. Estimation of the equivalent number of looks
in polarimetric Synthetic Aperture Radar imagery. IEEE Transactions on Geoscience and
Remote Sensing, IEEE, v. 47, n. 11, p. 3795–3809, 2009. DOI: 10.1109/TGRS.2009.2019269.
BESAG, J. On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society. Series
B (Methodological), v. 48, p. 259–302, 1986.
BRASIL. Dispõe sobre a criação da Floresta Nacional do Tapajóse e dá outras providências.
[S.l.: s.n.], 1974. Decreto Federal n.º 73.684, de 21 de novembro de 1974. Disponível em:
https://legislacao.presidencia.gov.br/atos/?tipo=DEC&numero=73684&ano=1974&ato=
5c3oXQE1EMnRVT95b. Acesso em: 25 out. 2025.
CORREIA, A. H. Projeto, desenvolvimento e avaliação de classificadores estatísticos pontuais
e contextuais para imagens SAR polarimétricas. 1999. F. 1999. 162. Mestrado em Sensoriamento
Remoto – Instituto Nacional de Pesquisas Espaciais (INPE), São José dos Campos.
Disponível em: <http://urlib.net/sid.inpe.br/deise/1999/09.14.14.45>.
DUTRA, L. V.; RENNÓ, C. D.; REIS, M. S.; GAMBA, P. A Generative Method for Simultaneous
Classification of Remote Sensing Time Series Data Using and Ensemble of Decision Tree
Classifiers. In: SIMPÓSIO BRASILEIRO DE SENSORIAMENTO REMOTO, 10., 2023,
Florianópolis. ANAIS... São José dos Campos: INPE, 2023. P. 179–182. ISBN 978-65-89159-
04-9.
EUROPEAN SPACE AGENCY. Information on ALOS PALSAR products for ADEN users. [S.l.],
2007. P. 18.
FRERY, A. C.; CORREA, A.; RENNO, C. D.; FREITAS, C. C; JACOBO-BERLLES, J.; VASCONCELLOS,
K. L. P.; MEJAIL, M.; SANT’ANNA, S. J. S. Models for Synthetic Aperture Radar
image analysis. Resenhas do Instituto de Matematica e Estatistica da Universidade de São
Paulo, v. 4, n. 1, p. 45–77, 1999.
FRERY, A. C.; CORREIA, A. H.; FREITAS, C. C. Classifying multifrequency fully polarimetric
imagery with multiple sources of statistical evidence and contextual information. IEEE
Transactions on Geoscience and Remote Sensing, v. 45, n. 10, p. 3098–3109, 2007. DOI:
/10.1109/TGRS.2007.903828.
FRERY, A. C.; FREITAS, C.; SANT’ANNA, Sidnei J. S.; RENNÓ, Camilo D. Statistical properties of
SAR data and their consequences. United Nations Programme on Space Applications, v. 10,
p. 53, 1999.
FRERY, A. C.; VIEIRA, P. R.; SANT’ANNA, S. J. S.; RENNÓ, C. D. et al. A user-friendly system for
Synthetic Aperture Radar image classification based on grayscale distributional properties and
context. In: IEEE. PROCEEDINGS X Brazilian Symposium on Computer Graphics and Image
Processing. [S.l.: s.n.], 1997. P. 211–218.
GAO, G. Statistical modeling of SAR images: A survey. Sensors, Molecular Diversity Preservation
International (MDPI), v. 10, n. 1, p. 775–795, 2010.
GARG, A.; SINGH, D. Development of an efficient contextual algorithm for discrimination of tall
vegetation and urban for PALSAR data. IEEE Transactions on Geoscience and Remote
Sensing, IEEE, v. 56, n. 6, p. 3413–3420, 2018.
JENSEN, J. R. Remote Sensing of the environment: an earth resource perspective. Harlow: Pearson
Education Limited, 2014. v. 2, p. 592. ISBN 978-1-292-02170-6.
KOLMOGOROV, A. Sulla determinazione empirica di una legge di distribuzione. Giornale dell’Istituto
Italiano degli Attuari, v. 4, p. 83–91, 1933.
KWAK, S.; KIM, Jong Hae. Central limit theorem: the cornerstone of modern statistics. Korean
Journal of Anesthesiology, v. 70, p. 144–156, 2017. DOI: 10.4097/kjae.2017.70.2.144.
LAMBIN, E. F.; GEIST, H.; RINDFUSS, R. R. Introduction: local processes with global impacts.
Land-use and land-cover change: Local processes and global impacts, Springer, p. 1–8,
2006.
LEE, J. S.; HOPPEL, K.W.; MANGO, S. A; MILLER, A. R. Intensity and phase statistics of multilook
polarimetric and interferometric SAR imagery. IEEE Transactions on Geoscience and
Remote Sensing, v. 32, n. 5, p. 1017–1028, 1994. ISSN 0196-2892. DOI: 10.1109/36.312890.
LEE, J.S.; POTTIER, E. Polarimetric radar imaging: from basics to applications. [S.l.]: CRC press,
2017.
MAHAPATRA, D. K.; FRERY, A. C.; PRADHAN, Bibhuti B.; ROY, L. P. A Review on parametric
and semiparametric distributions in characterizing Synthetic Aperture Radar clutter data. IEEE
Access, v. 12, p. 83340–83362, 2024.
MARTINS, V. S.; NOVO, E. M.L.M.; LYAPUSTIN, A.; ARAGÃO, L. E.O.C.; FREITAS, S. R.;
BARBOSA, C. C.F. Seasonal and interannual assessment of cloud cover and atmospheric
constituents across the Amazon (2000–2015): insights for remote sensing and climate analysis.
ISPRS Journal of Photogrammetry and Remote Sensing, Elsevier, v. 145, p. 309–327, 2018.
MEYER, F. Spaceborn Synthetic Aperture Radar: principles data access and basic process techniques.
In: FLORES-ANDERSON, A. I.; HERNDON, K. E.; THAPA, R. B.; CHERRINGTON, E. (Ed.).
The SAR handbook: comprehensive methodologies for forest monitoring and biomass
estimation. Huntsville: National Space Science e Technology Center, 2019. Astrophysics and
Space Science Proceedings. P. 21–64.
NEGRI, R. G.; DUTRA, L. V.; FREITAS, C. C.; LU, D. Exploring the Capability of ALOS PALSAR
L-Band Fully Polarimetric Data for Land Cover Classification in Tropical Environments. IEEE
Journal of Selected Topics in Applied Earth Observations and Remote Sensing, v. 9, n. 12,
p. 5369–5384, 2016a.
NEGRI, R. G.; DUTRA, L. V.; SANT’ANNA, S. J. S.; LU, D. Examining region-based methods for
land cover classification using stochastic distances. International Journal of Remote Sensing,
Taylor & Francis, v. 37, n. 8, p. 1902–1921, 2016.
OLIVER, C.; QUEGAN, S. Understanding Synthetic Aperture Radar images. Raleigh: SciTech
Publishing, 2004. ISBN 1-891121-31-6.
PEREIRA, L. O.; FREITAS, C. C.; SANT’ANNA, S. J. S.; REIS, M. S. ALOS/PALSAR data evaluation
for land use and land cover mapping in the Amazon region. IEEE Journal of Selected Topics
in Applied Earth Observations and Remote Sensing, v. 9, n. 12, p. 5413–5423, 2016. DOI:
10.1109/JSTARS.2016.2622481.
PEREIRA, L. O.; FREITAS, C. C.; SANT´ANNA, S. J. S.; REIS, M. S. Evaluation of optical and
radar images integration methods for LULC classification in Amazon region. IEEE Journal of
Selected Topics in Applied Earth Observations and Remote Sensing, v. 11, n. 9, p. 3062–
3074, 2018.
QUEIROZ, V. D. B. Classificação de trajetórias de cobertura da terra utilizando uma abordagem
de máximo a posteriori composto em imagens de multissensores. 2025. Diss. (Mestrado)
– Instituto Nacional de Pesquisas Espaciais (INPE), São José dos Campos. Disponível em:
<http://urlib.net/ibi/8JMKD3MGP3W34T/4BRJ5G5>.
QUEVEDO, R. P. Do land use and land cover and spatial heterogeneity influence on landslide
occurrence? An analysis of susceptibility. 2023. F. 2023. 193. Doutorado em Sensoriamento
Remoto – Instituto Nacional de Pesquisas Espaciais (INPE), São José dos Campos. Disponível
em: <http://urlib.net/ibi/8JMKD3MGP3W34T/49AT9R8>.
REIS, M. S. Detection and analysis of forest regeneration trajectories in the lower Tapajós
region. 2022. F. 220. Tese (Doutorado em Ciência do Sistema Terrestre) – Instituto Nacional
de Pesquisas Espaciais (INPE), São José dos Campos. Disponível em: <http://urlib.net/ibi/
8JMKD3MGP3W34T/47E2TRB>.
REIS, M. S.; BARROS, L. S.; RODRIGUES NETO, M. R.; MORAES, D. R. V.; MOREIRA, N. A. P.;
ALVES, G. M. R.; ADORNO, B. V.; MESSIAS, C. G.; DUTRA, L. V.; RENNÓ’, C. D.;
SANT’ANNA, S. J. S.; ESCADA, M. I. S. Assessing interpreter’s disagreements in land
cover reference data collection from historical Landsat time series in Amazon. International Journal of Remote Sensing, Taylor & Francis, v. 45, n. 15, p. 5192–5223, 2024. DOI:
10.1080/01431161.2024.2373340.
REIS, M. S.; DUTRA, L. V.; ESCADA, M. I. S. Simultaneous multi-source and multi-temporal
land cover classification using a compound maximum likelihood classifier. GEOINFO, v. 18,
p. 74–85, 2017.
REIS, M. S.; DUTRA, L. V.; ESCADA, M. I. S.; SANT’ANNA, S. J. S. Avoiding invalid transitions in
land cover trajectory classification with a Compound Maximum a Posteriori approach. IEEE
Access, IEEE, v. 8, p. 98787–98799, 2020b. DOI: 10.1109/ACCESS.2020.2997019.
REIS, M. S.; DUTRA, L. V. D.; SANT’ANNA, S. J. S.; ESCADA, M. I. S. Multi-source change detection
with PALSAR data in the Southern of Pará state in the Brazilian Amazon. International Journal
of Applied Earth Observation and Geoinformation, v. 84, p. 101945, 2020a. ISSN 1569-8432.
DOI: https://doi.org/10.1016/j.jag.2019.101945.
REIS, M. S.; ESCADA, M. I. S.; DUTRA, L. V.; SANT’ANNA, S. J. S.; VOGT, N. D. Towards a
reproducible LULC hierarchical class legend for use in the southwest of Pará state, Brazil:
A comparison with Remote Sensing data-driven hierarchies. Land, v. 7, n. 2, 2018. ISSN
2073-445X. DOI: 10.3390/land7020065. Disponível em: <https://www.mdpi.com/2073-
445X/7/2/65>.
RICHARDS, J. A. Remote sensing digital image analysis: an introduction. Berlin: Springer, 2022.
v. 6, p. 567. ISBN 978-3-030-82326-9.
. Remote Sensing with imaging Radar. Berlin: Springer, 2009. v. 1, p. 361. ISBN 978-3-
642-02019-3. DOI: 10.1007/978-3-642-02020-9.
SAGRILLO, M.; GUERRA, R. R.; BAYER, F. M.; MACHADO, R. A new probability distribution for
SAR image modeling. Remote Sensing, v. 14, n. 12, 2022. ISSN 2072-4292.
SANT’ANNA, Sidnei Joao Siqueira; BRAGA, Bruna Cristina; OLIVEIRA, Jony Martins; OLIVEIRA,
Maria Antônia Falcão; REIS, Mariane Souza; MOREIRA, Noeli Aline Particcelli; ALBUQUERQUE,
Paulo Cesar Gurgel. Field data from the Tapajós region - August-September of
2016. [S.l.: s.n.], 2016.
SCHOWENGERDT, A. Robert. Remote sensing: models and methods for image processing. 3. ed.
Burlington: Academic Press, 2007. P. 515. ISBN 978-0-12-369407-2.
SERVELLO, E. L. Dados polarimétricos do RADARSAT-2 (banda C) na discriminação de uso e
cobertura da terra na região da Floresta Nacional do Tapajós, 2010.
SHIMADA, M.; ISOGUCHI, O.; TADONO, T.; ISONO, K. PALSAR radiometric and geometric
calibration. IEEE Transactions on Geoscience and Remote Sensing, v. 47, n. 12, p. 3915–
3932, 2009. DOI: 10.1109/TGRS.2009.2023909.
SMIRNOV, N. On the estimation of discrepancy between empirical curves of distribution for two
independent samples. Bulletin Mathématique de LUniversité de Moscow, v. 2, n. 2, p. 3–11,
1939.
THEODORIDIS, S.; KOUTROUMBAS, K. Pattern recognition. 4. ed. San Diego: Academic Press,
2009. ISBN 978-1-59749-272-0.
TORRES, L. J. T. M. Um novo algoritmo para filtragem de speckle em imagens SAR de intensidade
baseado em distâncias estocásticas. 2012. F. 2012. 73. Mestrado em Modelagem Computacional
de Conhecimento – Universidade Federal de Alagoas (UFAL), Maceió. Disponível em:
<http://www.repositorio.ufal.br/jspui/handle/riufal/1829>.
TURNER, B.; MEYER, W. Global land-use and land-cover change: an overview. In: MEYER, W. B.;
TURNER, B. L. (Ed.). Changes in land use and land cover: a global perspective. Cambridge:
Cambridge University Press, 1994. Total volume: 537 p.
VECI, L. ALOS PALSAR Orthorectification Tutorial. [S.l.], 2015. Issued March 2015; Updated
August 2016. Disponível em: <https://step.esa.int/docs/tutorials/ALOS%20PALSAR%
20Orthorectification%20Tutorial.pdf>.
VELOSO, H. P.; RANGEL FILHO, A. L. R.; LIMA, J. C. A. Classificação da vegetação brasileira,
adaptada a um sistema universal. Rio de Janeiro: IBGE, 1991. P. 124. ISBN 85-240-0384-7.
WARD JR, J. H. Hierarchical grouping to optimize an objective function. Journal of the American
Statistical Association, Taylor & Francis, v. 58, n. 301, p. 236–244, 1963. DOI: 10.1080/
01621459.1963.10500845.
WOODHOUSE, I. H. Introduction to microwave Remote Sensing. Boca Raton: CRC press Taylor &
Francis, 2006. P. 370. ISBN 0-415-27123-1.
WRIGHT, P. A.;MEADOWS, P. J.;MACK, G.; MIRANDA,N.; LAVALLE, M. ADEN ALOS PALSAR
product verification. In: ALOS PI 2008 SYMPOSIUM, 2008, Rhodes. PROCEEDINGS...
[S.l.: s.n.], 2009. Disponível em: <https://earth.esa.int/eogateway/documents/20142/37627/
ALOS-PI-Symposium-PALSAR-Verification.pdf>.
WULDER, M. A; HILKER, T.; WHITE, J. C.; COOPS, N. C.; MASEK, J. G.; PFLUGMACHER, D.;
CREVIER, Y. Virtual constellations for global terrestrial monitoring. Remote Sensing of
Environment, Elsevier, v. 170, p. 62–76, 2015.
YANASSE, C. C. F. Statistical analysis of Synthetic Aperture Radar images and its applications
to system analysis and change detection. 1991. F. 1991. 298. Doutorado em Probabilidade e
Estatística – University of Sheffield, Sheffield.
YANASSE, C. S. F.; SANT’ANNA, S. J. S.; FRERY, A. C.; RENNÓ, C. D.; SOARES, J. V.;
LUCKMAN, A. J. Exploratory study of the relationship between tropical forest regeneration
stages and SIR-C L and C data. Remote Sensing of Environment, Elsevier, v. 59, n. 2,
p. 180–190, 1997. DOI: 10.1016/s0034-4257(96)00149-6.
YUE, D. X.; XU, F.; FRERY, A. C.; JIN, Y. Q. SAR image statistical modeling part I: single-pixel
statistical models. IEEE Geoscience and Remote Sensing Magazine, v. 9, n. 1, p. 82–114,
2021.