Análise de metacaracterísticas para classificação de uso e cobertura do solo utilizando Random Forest
Resumo
Este trabalho analisa o impacto do uso de metacaracterísticas geradas pelo algoritmo TWDTW para mapeamento do uso e cobertura do solo utilizando Random Forest. Os testes foram realizados classificando nove classes, para um conjunto de amostras da região do Mato Grosso, no Brasil. Nossos resultados mostram que as metacaracterísticas são promissoras para a melhora de acurácia, aumentando a acurácia global dos modelos testados. As melhoras mais significativas ocorrem na acurácia do produtor das classes de maior dificuldade de classificação. A importância das metacaracterísticas na classificação foi significativamente maior do que as características extraídas dos Índices EVI e NDVI e Bandas NIR e MIR.
Palavras-chave:
Algoritmo TWDTW, mapeamento de uso e cobertura do solo, Random Forest
Referências
Ayala-Izurieta, J. E., Márquez, C. O., García, V. J., Recalde-Moreno, C. G., Rodríguez- Llerena, M. V., and Damián-Carrión, D. A. (2017). Land cover classification in an ecuadorian mountain geosystem using a random forest classifier, spectral vegetation indices, and ancillary geographic data. Geosciences, 7(2):34.
Bala, G., Caldeira, K., Wickett, M., Phillips, T., Lobell, D., Delire, C., and Mirin, A. (2007). Combined climate and carbon-cycle effects of large-scale deforestation. Proceedings of the National Academy of Sciences, 104(16):6550–6555.
Belgiu, M. and Csillik, O. (2018). Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis. Remote sensing of environment, 204:509–523.
Belgiu, M. and Dragut¸, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114:24–31.
Bonan, G. B. (2008). Forests and climate change: forcings, feedbacks, and the climate benefits of forests. science, 320(5882):1444–1449.
Breiman, L. (2001). Random forests. Machine learning, 45(1):5–32. Canovas-Garcia, F. and Alonso-Sarria, F. (2015). Optimal combination of classification algorithms and feature ranking methods for object-based classification of submeter resolution z/i-imaging dmc imagery. Remote Sensing, 7(4):4651–4677.
Dadi, M. M. (2019). Assessing the transferability of random forest and time-weighted dynamic time warping for agriculture mapping. Master’s thesis, University of Twente, Enschede.
Duro, D. C., Franklin, S. E., and Dub´e, M. G. (2012). Multi-scale object-based image analysis and feature selection of multi-sensor earth observation imagery using random forests. International Journal of Remote Sensing, 33(14):4502–4526.
Foody, G. M. (2002). Status of land cover classification accuracy assessment. Remote Sensing of Environment, 80(1):185–201.
Georganos, S., Grippa, T., Vanhuysse, S., Lennert, M., Shimoni, M., Kalogirou, S., and Wolff, E. (2018). Less is more: Optimizing classification performance through feature selection in a very-high-resolution remote sensing object-based urban application. GIScience & remote sensing, 55(2):221–242.
Gislason, P. O., Benediktsson, J. A., and Sveinsson, J. R. (2006). Random forests for land cover classification. Pattern Recognition Letters, 27(4):294–300.
Laliberte, A. S., Browning, D., and Rango, A. (2012). A comparison of three feature selection methods for object-based classification of sub-decimeter resolution ultracaml imagery. International Journal of Applied Earth Observation and Geoinformation, 15:70–78.
Ma, L., Fu, T., Blaschke, T., Li, M., Tiede, D., Zhou, Z., Ma, X., and Chen, D. (2017). Evaluation of feature selection methods for object-based land cover mapping of unmanned aerial vehicle imagery using random forest and support vector machine classifiers. ISPRS International Journal of Geo-Information, 6(2):51.
Maus, V., Cˆamara, G., Cartaxo, R., Sanchez, A., Ramos, F. M., and De Queiroz, G. R. (2016). A time-weighted dynamic time warping method for land-use and land-cover mapping. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(8):3729–3739.
Mountrakis, G., Im, J., and Ogole, C. (2011). Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 66(3):247–259.
Nepstad, D., McGrath, D., Stickler, C., Alencar, A., Azevedo, A., Swette, B., Bezerra, T., DiGiano, M., Shimada, J., da Motta, R. S., et al. (2014). Slowing amazon deforestation through public policy and interventions in beef and soy supply chains. science, 344(6188):1118–1123.
Oliveira, S. S., Cardoso, M. d. C., Bueno, E., Rodrigues, V. J., and Martins, W. S. (2019). Exploiting parallelism to generate meta-features for land use and land cover classification with remote sensing time series. Brazilian Symposium on Geoinformatics (GeoInfo), pages 135–146.
Oliveira, S. S., Pascoal, L. M., Ferreira, L., Cardoso, M. d. C., Bueno, E., Rodrigues, V. J., and Martins, W. S. (2018). Sp-twdtw: A new parallel algorithm for spatio-temporal analysis of remote sensing images. Brazilian Symposium on Geoinformatics (GeoInfo), pages 46–57.
Pal, M. (2005). Random forest classifier for remote sensing classification. International Journal of Remote Sensing, 26(1):217–222.
Parente, L. and Ferreira, L. (2018). Assessing the spatial and occupation dynamics of the brazilian pasturelands based on the automated classification of modis images from 2000 to 2016. Remote Sensing, 10(4):606.
Parente, L., Mesquita, V., Miziara, F., Baumann, L., and Ferreira, L. (2019). Assessing the pasturelands and livestock dynamics in brazil, from 1985 to 2017: A novel approach based on high spatial resolution imagery and google earth engine cloud computing. Remote Sensing of Environment, 232:111301.
Picoli, M. C. A., Camara, G., Sanches, I., Sim˜oes, R., Carvalho, A., Maciel, A., Coutinho, A., Esquerdo, J., Antunes, J., Begotti, R. A., et al. (2018). Big earth observation time series analysis for monitoring brazilian agriculture. ISPRS journal of photogrammetry and remote sensing, 145:328–339.
Rodriguez-Galiano, V. F., Ghimire, B., Rogan, J., Chica-Olmo, M., and Rigol-Sanchez, J. P. (2012). An assessment of the effectiveness of a random forest classifier for landcover classification. ISPRS Journal of Photogrammetry and Remote Sensing, 67:93– 104.
Tsai, Y. H., Stow, D., Chen, H. L., Lewison, R., An, L., and Shi, L. (2018). Mapping vegetation and land use types in fanjingshan national nature reserve using google earth engine. Remote Sensing, 10(6):927.
Vapnik, V. N. (1995). The Nature of Statistical Learning Theory. Springer New York. Wiens, T. S., Dale, B. C., Boyce, M. S., and Kershaw, G. P. (2008). Three way k-fold cross-validation of resource selection functions. Ecological Modelling, 212(3-4):244– 255.
Bala, G., Caldeira, K., Wickett, M., Phillips, T., Lobell, D., Delire, C., and Mirin, A. (2007). Combined climate and carbon-cycle effects of large-scale deforestation. Proceedings of the National Academy of Sciences, 104(16):6550–6555.
Belgiu, M. and Csillik, O. (2018). Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis. Remote sensing of environment, 204:509–523.
Belgiu, M. and Dragut¸, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114:24–31.
Bonan, G. B. (2008). Forests and climate change: forcings, feedbacks, and the climate benefits of forests. science, 320(5882):1444–1449.
Breiman, L. (2001). Random forests. Machine learning, 45(1):5–32. Canovas-Garcia, F. and Alonso-Sarria, F. (2015). Optimal combination of classification algorithms and feature ranking methods for object-based classification of submeter resolution z/i-imaging dmc imagery. Remote Sensing, 7(4):4651–4677.
Dadi, M. M. (2019). Assessing the transferability of random forest and time-weighted dynamic time warping for agriculture mapping. Master’s thesis, University of Twente, Enschede.
Duro, D. C., Franklin, S. E., and Dub´e, M. G. (2012). Multi-scale object-based image analysis and feature selection of multi-sensor earth observation imagery using random forests. International Journal of Remote Sensing, 33(14):4502–4526.
Foody, G. M. (2002). Status of land cover classification accuracy assessment. Remote Sensing of Environment, 80(1):185–201.
Georganos, S., Grippa, T., Vanhuysse, S., Lennert, M., Shimoni, M., Kalogirou, S., and Wolff, E. (2018). Less is more: Optimizing classification performance through feature selection in a very-high-resolution remote sensing object-based urban application. GIScience & remote sensing, 55(2):221–242.
Gislason, P. O., Benediktsson, J. A., and Sveinsson, J. R. (2006). Random forests for land cover classification. Pattern Recognition Letters, 27(4):294–300.
Laliberte, A. S., Browning, D., and Rango, A. (2012). A comparison of three feature selection methods for object-based classification of sub-decimeter resolution ultracaml imagery. International Journal of Applied Earth Observation and Geoinformation, 15:70–78.
Ma, L., Fu, T., Blaschke, T., Li, M., Tiede, D., Zhou, Z., Ma, X., and Chen, D. (2017). Evaluation of feature selection methods for object-based land cover mapping of unmanned aerial vehicle imagery using random forest and support vector machine classifiers. ISPRS International Journal of Geo-Information, 6(2):51.
Maus, V., Cˆamara, G., Cartaxo, R., Sanchez, A., Ramos, F. M., and De Queiroz, G. R. (2016). A time-weighted dynamic time warping method for land-use and land-cover mapping. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(8):3729–3739.
Mountrakis, G., Im, J., and Ogole, C. (2011). Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 66(3):247–259.
Nepstad, D., McGrath, D., Stickler, C., Alencar, A., Azevedo, A., Swette, B., Bezerra, T., DiGiano, M., Shimada, J., da Motta, R. S., et al. (2014). Slowing amazon deforestation through public policy and interventions in beef and soy supply chains. science, 344(6188):1118–1123.
Oliveira, S. S., Cardoso, M. d. C., Bueno, E., Rodrigues, V. J., and Martins, W. S. (2019). Exploiting parallelism to generate meta-features for land use and land cover classification with remote sensing time series. Brazilian Symposium on Geoinformatics (GeoInfo), pages 135–146.
Oliveira, S. S., Pascoal, L. M., Ferreira, L., Cardoso, M. d. C., Bueno, E., Rodrigues, V. J., and Martins, W. S. (2018). Sp-twdtw: A new parallel algorithm for spatio-temporal analysis of remote sensing images. Brazilian Symposium on Geoinformatics (GeoInfo), pages 46–57.
Pal, M. (2005). Random forest classifier for remote sensing classification. International Journal of Remote Sensing, 26(1):217–222.
Parente, L. and Ferreira, L. (2018). Assessing the spatial and occupation dynamics of the brazilian pasturelands based on the automated classification of modis images from 2000 to 2016. Remote Sensing, 10(4):606.
Parente, L., Mesquita, V., Miziara, F., Baumann, L., and Ferreira, L. (2019). Assessing the pasturelands and livestock dynamics in brazil, from 1985 to 2017: A novel approach based on high spatial resolution imagery and google earth engine cloud computing. Remote Sensing of Environment, 232:111301.
Picoli, M. C. A., Camara, G., Sanches, I., Sim˜oes, R., Carvalho, A., Maciel, A., Coutinho, A., Esquerdo, J., Antunes, J., Begotti, R. A., et al. (2018). Big earth observation time series analysis for monitoring brazilian agriculture. ISPRS journal of photogrammetry and remote sensing, 145:328–339.
Rodriguez-Galiano, V. F., Ghimire, B., Rogan, J., Chica-Olmo, M., and Rigol-Sanchez, J. P. (2012). An assessment of the effectiveness of a random forest classifier for landcover classification. ISPRS Journal of Photogrammetry and Remote Sensing, 67:93– 104.
Tsai, Y. H., Stow, D., Chen, H. L., Lewison, R., An, L., and Shi, L. (2018). Mapping vegetation and land use types in fanjingshan national nature reserve using google earth engine. Remote Sensing, 10(6):927.
Vapnik, V. N. (1995). The Nature of Statistical Learning Theory. Springer New York. Wiens, T. S., Dale, B. C., Boyce, M. S., and Kershaw, G. P. (2008). Three way k-fold cross-validation of resource selection functions. Ecological Modelling, 212(3-4):244– 255.
Publicado
30/06/2020
Como Citar
PAIVA, Roberto; OLIVEIRA, Sávio; MARTINS, Wellington; PARENTE, Leandro.
Análise de metacaracterísticas para classificação de uso e cobertura do solo utilizando Random Forest. In: WORKSHOP DE COMPUTAÇÃO APLICADA À GESTÃO DO MEIO AMBIENTE E RECURSOS NATURAIS (WCAMA), 11. , 2020, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 71-80.
ISSN 2595-6124.
DOI: https://doi.org/10.5753/wcama.2020.11021.
