Mapping Pinus spp. Forestry and Land Cover Classes Using High-resolution PlanetScope Satellite Data: Experimenting Images from Different Seasons and Machine Learning Methods
Article Sidebar
Main Article Content
Abstract
The Remote Sensing and machine learning techniques are cost-effective ways of mapping land use and cover, especially forestry areas. This is essential for the management and planning of such resources. The purpose of this study was to identify which classifier (Random Forest or Support Vector Machine) reach the best accuracy in land use and cover classification and determine which is the best season of year for Pinus spp. forest mapping. PlanetScope multispectral image was used with 3.7 m of spatial resolution, collected over the coastal region of Rio Grande do Sul state. The input variables for the classifiers were the four spectral bands: RGB and NIR, and the NDVI vegetation index. In both classifiers, high accuracy values were obtained, as well as for all seasons of the year.
The Random Forest classifier obtained better results in the spring and summer seasons, while in the autumn and winter seasons there was no significant difference between the classifiers for the classification of Pinus spp. forests. The results reached an adequate precision to be used for the management and monitoring of the land use and cover in the municipality of São José do Norte, RS.
Downloads
Metrics
Article Details
This work is licensed under a Creative Commons Attribution 3.0 Unported 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").
References
ADAM, E.; MUTANGA, O.; ODINDI, J.; ABDEL-RAHMAN, E. M. Land-use/cover classification in a heterogeneous coastal landscape using RapidEye imagery: evaluating the performance of random forest and support vector machines classifiers. International Journal of Remote Sensing, v. 35, n. 10, p. 3440–3458, 2014. Disponível em: <https://www.tandfonline.com/doi/full/10.1080/01431161.2014.903435>. .
ALVARES, C. A.; STAPE, J. L.; SENTELHAS, P. C.; DE MORAES GONÇALVES, J. L.; SPAROVEK, G. Köppen’s climate classification map for Brazil. Meteorologische Zeitschrift, v. 22, n. 6, p. 711–728, 2013. Disponível em: <http://www.schweizerbart.de/papers/metz/detail/22/82078/Koppen_s_climate_classification_map_for_Brazil?af=crossref>. .
BANSKOTA, A.; WYNNE, R. H.; KAYASTHA, N. Improving within-genus tree species discrimination using the discrete wavelet transform applied to airborne hyperspectral data. International Journal of Remote Sensing, v. 32, n. 13, p. 3551–3563, 2011. Disponível em: <https://www.tandfonline.com/doi/full/10.1080/01431161003698302>. .
BEHERA, M. D.; BARNWAL, S.; PARAMANIK, S.; et al. Species-Level Classification and Mapping of a Mangrove Forest Using Random Forest—Utilisation of AVIRIS-NG and Sentinel Data. Remote Sensing, v. 13, n. 11, p. 2027, 2021. Disponível em: <https://www.mdpi.com/2072-4292/13/11/2027>. .
BELGIU, M.; DRĂGUŢ, L. Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, v. 114, p. 24–31, 2016. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S0924271616000265>. .
BREUNIG, F. M. Classification of soybean varieties using different techniques: case study with Hyperion and sensor spectral resolution simulations. Journal of Applied Remote Sensing, v. 5, n. 1, p. 053533, 2011. Disponível em: <http://remotesensing.spiedigitallibrary.org/article.aspx?doi=10.1117/1.3604787>. .
BREUNIG, F. M.; GALVÃO, L. S.; DALAGNOL, R.; DAUVE, C. E.; et al. Delineation of management zones in agricultural fields using cover–crop biomass estimates from PlanetScope data. International Journal of Applied Earth Observation and Geoinformation, v. 85, p. 102004, 2020. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S0303243419309481>. .
BREUNIG, F. M.; GALVÃO, L. S.; DALAGNOL, R.; SANTI, A. L.; et al. Assessing the effect of spatial resolution on the delineation of management zones for smallholder farming in southern Brazil. Remote Sensing Applications: Society and Environment, v. 19, p. 100325, 2020. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S2352938519304409>. .
CHEN, L.; LI, S.; BAI, Q.; et al. Review of Image Classification Algorithms Based on Convolutional Neural Networks. Remote Sensing, v. 13, n. 22, p. 4712, 2021. Disponível em: <https://www.mdpi.com/2072-4292/13/22/4712>. .
CHUVIECO, E. Fundamentos de teledection espacial. 2.a ed. Madrid: RIALF SA, 1990
CONGALTON, R. G. Accuracy assessment and validation of remotely sensed and other spatial information. International Journal of Wildland Fire, v. 10, n. 4, p. 321, 2001. Disponível em: <http://www.publish.csiro.au/?paper=WF01031>.
CORTES, C.; VAPNIK, V. Support-vector networks. Machine Learning, v. 20, n. 3, p. 273–297, 1995. Disponível em: <http://link.springer.com/10.1007/BF00994018>. .
DHINGRA, S.; KUMAR, D. A review of remotely sensed satellite image classification. International Journal of Electrical and Computer Engineering (IJECE), v. 9, n. 3, p. 1720, 2019. Disponível em: <http://ijece.iaescore.com/index.php/IJECE/article/view/12927>. .
FACELI, K; LORENA, A. C; GAMA, J.; ALMEIDA T.A.; et al. Inteligência artificial: uma abordagem de aprendizado de máquina. 2.a ed. Rio de Janeiro, 2021.
FAGAN, M. E.; MORTON, D. C.; COOK, B. D.; et al. Mapping pine plantations in the southeastern U.S. using structural, spectral, and temporal remote sensing data. Remote Sensing of Environment, v. 216, p. 415–426, 2018. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S0034425718303341>.
FERNÁNDEZ-DELGADO, M.; CERNADAS, E.; BARRO, S.; AMORIM D. Do we need hundreds of classifiers to solve real world classification problems? The journal of machine learning research, v. 15, n. 1, p. 3133-3181, 2014.
FOODY, G. M. Status of land cover classification accuracy assessment. Remote Sensing of Environment, v. 80, n. 1, p. 185–201, 2002. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S0034425701002954>. .
GIANUCA, K. S.; TAGLIANI, C. R. A. Análise em um Sistema de Informação Geográfica (SIG) das alterações na paisagem em ambientes adjacentes a plantios de pinus no Distrito do Estreito, município de São José do Norte, Brasil. Revista da Gestão Costeira Integrada, v. 12, n. 1, p. 43–55, 2012.
GRABSKA, E.; HOSTERT, P.; PFLUGMACHER, D.; OSTAPOWICZ, K. Forest Stand Species Mapping Using the Sentinel-2 Time Series. Remote Sensing, v. 11, n. 10, p. 1197, 2019. Disponível em: <https://www.mdpi.com/2072-4292/11/10/1197>. .
HADDAD, I.; GALVÃO, L. S.; BREUNIG, F. M.; et al. On the combined use of phenological metrics derived from different PlanetScope vegetation indices for classifying savannas in Brazil. Remote Sensing Applications: Society and Environment, v. 26, p. 100764, 2022. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S2352938522000726>. .
HILL, R. A.; WILSON, A. K.; GEORGE, M.; HINSLEY, S. A. Mapping tree species in temperate deciduous woodland using time-series multi-spectral data. Applied Vegetation Science, v. 13, n. 1, p. 86–99, 2010. Disponível em: <https://onlinelibrary.wiley.com/doi/10.1111/j.1654-109X.2009.01053.x>. .
HUETE, A.; DIDAN, K.; MIURA, T.; et al. Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sensing of Environment, v. 83, n. 1–2, p. 195–213, 2002. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S0034425702000962>. .
INSTITUTO BRASILEIRO DE GEOGRAFIA E ESTATÍSTICA (IBGE). Cidades de Estados (São José do Norte). Disponível em: https://www.ibge.gov.br/cidades-e-estados/rs/sao-jose-do-norte.html. Acesso em: 23 junho 2022.
INSTITUTO NACIONAL DE METEREOLOGIA (INMET). Banco de Dados Meteorológicos. Disponível em: https://bdmep.inmet.gov.br. Acesso em: 23 junho 2022.
JANSSEN, L. LF; VANDERWEL, F. JM. Accuracy assessment of satellite derived land-cover data: a review. Photogrammetric engineering and remote sensing. v. 60, n. 4, 1994.
JENSEN, J. R. Sensoriamento Remoto do Ambiente: uma perspectiva em recursos terrestres. 2. ed. São José dos Campos: Parêntese, 2011.
KUHN, M. Caret: classification and regression training. Astrophysics Source Code Library, p. ascl: 1505.003, 2015.
LANDIS, J. R.; KOCH, G. G. The measurement of observer agreement for categorical data. Biometrics, p. 159-174, 1977.
LARY, D. J.; ALAVI, A. H.; GANDOMI, A. H.; WALKER, A. L. Machine learning in geosciences and remote sensing. Geoscience Frontiers, v. 7, n. 1, p. 3–10, 2016. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S1674987115000821>.
LEITE, A. P.; SANTOS, G. R.; SANTOS, J. É. O. Análise temporal dos índices de vegetação NDVI e SAVI na Estação Experimental de Itatinga utilizando imagens Landsat 8. Revista Brasileira de Energias Renováveis, v. 6, n. 4, 2017. Disponível em: <http://revistas.ufpr.br/rber/article/view/45830>. .
LI, M.; ZANG, S.; ZHANG, B.; LI, S.; WU, C. A Review of Remote Sensing Image Classification Techniques: the Role of Spatio-contextual Information. European Journal of Remote Sensing, v. 47, n. 1, p. 389–411, 2014. Disponível em: <https://www.tandfonline.com/doi/full/10.5721/EuJRS20144723>.
LUO, H.; LI, M.; DAI, S.; et al. Combinations of Feature Selection and Machine Learning Algorithms for Object-Oriented Betel Palms and Mango Plantations Classification Based on Gaofen-2 Imagery. Remote Sensing, v. 14, n. 7, p. 1757, 2022. Disponível em: <https://www.mdpi.com/2072-4292/14/7/1757>. .
MEYER, D. et al. Package ‘e1071’. The R Journal, 2019.
MONNET, J.-M.; CHANUSSOT, J.; BERGER, F. Support Vector Regression for the Estimation of Forest Stand Parameters Using Airborne Laser Scanning. IEEE Geoscience and Remote Sensing Letters, v. 8, n. 3, p. 580–584, 2011. Disponível em: <http://ieeexplore.ieee.org/document/5682006/>. .
MOUNTRAKIS, G.; IM, J.; OGOLE, C. Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, v. 66, n. 3, p. 247–259, 2011. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S0924271610001140>.
NOVO, E. M. L. de Moraes. Sensoriamento Remoto: princípios e aplicações. 4. ed. São Paulo: Blucher. p. 387, 2010.
OK, A. O.; AKAR, O.; GUNGOR, O. Evaluation of random forest method for agricultural crop classification. European Journal of Remote Sensing, v. 45, n. 1, p. 421–432, 2012. Disponível em: <https://www.tandfonline.com/doi/full/10.5721/EuJRS20124535>. .
PAL, M.; FOODY, G. M. Feature Selection for Classification of Hyperspectral Data by SVM. IEEE Transactions on Geoscience and Remote Sensing, v. 48, n. 5, p. 2297–2307, 2010. Disponível em: <http://ieeexplore.ieee.org/document/5419028/>. .
PERKO, R.; RAGGAM, H.; SCHARDT, M.; MICHAEL ROTH, P. Very High Resolution Mapping with the Pléiades Satellite Constellation. American Journal of Remote Sensing, v. 6, n. 2, p. 89, 2018. Disponível em: <http://www.sciencepublishinggroup.com/journal/paperinfo?journalid=138&doi=10.11648/j.ajrs.20180602.14>. .
PINHEIRO, R. M.; DA SILVA, M. D. Paisagens Ameaçadas Da Restinga Da Lagoa Dos Patos (Rs): Ecologia Da Paisagem Como Contribuição Para O Zoneamento Ecológico Econômico Do Litoral Médio / Threatened Landscapes Of The Restinga Da Lagoa Dos Patos (Rs): Landscape Ecology As Contribution To Th. Geographia Meridionalis, v. 4, n. 2, p. 269, 2019. Disponível em: <https://periodicos.ufpel.edu.br/ojs2/index.php/Geographis/article/view/14483>. .
PLANET LABS. 2019. “Planet Surface Reflectance Product.” San Francisco: Planet Labs. Disponível em: https://assets.planet.com/marketing/PDF/Planet_Surface_Reflectance_Technical_White_Paper.pdf. Acesso em: 23 junho 2022.
ROUSE JR, J. W. et al. Paper a 20. In: Third Earth Resources Technology Satellite-1 Symposium: The Proceedings of a Symposium Held by Goddard Space Flight Center at Washington, DC on. 1973. p. 309.
R CORE TEAM (2021). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL https://www.R-project.org/.
SCHULZ, D.; YIN, H.; TISCHBEIN, B.; et al. Land use mapping using Sentinel-1 and Sentinel-2 time series in a heterogeneous landscape in Niger, Sahel. ISPRS Journal of Photogrammetry and Remote Sensing, v. 178, p. 97–111, 2021. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S0924271621001635>.
SHERMAN, Gary. QGIS - A Free and Open Source Geographic Information System. Viena: GNU - Free Software Foundation, Inc. Disponível em: <http://www.qgis.org/en/site/>. , 2002.
SHEYKHMOUSA, M.; MAHDIANPARI, M.; GHANBARI, H.; et al. 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, v. 13, p. 6308–6325, 2020. Disponível em: <https://ieeexplore.ieee.org/document/9206124/>. .
SOUZA, C. G.; CARVALHO, L.; AGUIAR, P.; ARANTES, T. B. Algoritmos de Aprendizagem de Máquina e Variáveis de Sensoriamento Remoto para o Mapeamento da Cafeicultura. Boletim de Ciências Geodésicas, v. 22, n. 4, p. 751–773, 2016. Disponível em: <http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1982-21702016000400751&lng=pt&tlng=pt>. .
SOZZI, M.; KAYAD, A.; GIORA, D.; SARTORI, L.; MARINELLO, F. Cost-effectiveness and performance of optical satellites constellation for Precision Agriculture. Precision agriculture ’19. Anais... . p.501–507, 2019. The Netherlands: Wageningen Academic Publishers. Disponível em: <https://www.wageningenacademic.com/doi/10.3920/978-90-8686-888-9_62>. .
TAGLIANI, C. R. A.; VICENZ, R. S. Mapeamento da vegetação e uso do solo nos entornos do estuário da Laguna dos Patos, RS, utilizando técnicas de processamento digital de imagem do SIG SPRING. Anais eletrônicos, XI Simpósio Brasileiro de Sensoriamento Remoto, Belo Horizonte - MG, p. 1461 – 1468, 2003.
WULDER, M. A.; LOVELAND, T. R.; ROY, D. P.; et al. Current status of Landsat program, science, and applications. Remote Sensing of Environment, v. 225, p. 127–147, 2019. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S0034425719300707>. .
XIE, Z.; CHEN, Y.; LU, D.; LI, G.; CHEN, E. Classification of Land Cover, Forest, and Tree Species Classes with ZiYuan-3 Multispectral and Stereo Data. Remote Sensing, v. 11, n. 2, p. 164, 2019. Disponível em: <http://www.mdpi.com/2072-4292/11/2/164>. .
XU, K.; ZHANG, Z.; YU, W.; et al. How Spatial Resolution Affects Forest Phenology and Tree-Species Classification Based on Satellite and Up-Scaled Time-Series Images. Remote Sensing, v. 13, n. 14, p. 2716, 2021. Disponível em: <https://www.mdpi.com/2072-4292/13/14/2716>. .