Mapeamento e classificação do solo fazendo uso de índices de vegetação e arquitetura de aprendizagem profunda
Resumo
A presente pesquisa teve por objetivo desenvolver um sistema com o uso de imagens multi espectrais capturadas via VANT em diferentes espectros de cor, e classificá-las mediante técnica de aprendizagem profunda CNN, possibilitando correlacionar as imagens conforme índices de vegetação e propriedades do solo. Foi obtida uma acurácia média de 63,54% para K e 75,00% para P, destacando-se os índices CARI, MCARI_OSAVI, CHLGREEN, FE3, NORMR e MCARI para classificar K, e GEMI, MYVI, TC_YVIMSS, DATT4, FE3 e NGRDI para classificar P. Desta forma, observa-se que os métodos utilizados e dados obtidos nesta pesquisa, viabilizam o objetivo proposto, com resultados que podem auxiliar a identificação de propriedades de solo aproximadas.
Palavras-chave:
Análise química e física do solo, rede neural convolucional, propriedades do solo, índices de vegetação, índices espectrais
Referências
DONG, W.; SUN, Y.; LUO, J. Fine mapping of key soil nutrient content using high resolution remote sensing image to support precision agriculture in Northwest China. In: 2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics). Istanbul, Turkey: IEEE, 2019. p. 1–5.
DONG, W. et al. Digital Mapping of Soil Available Phosphorus Supported by AI Technology for Precision Agriculture. In: 2018 7th International Conference on Agro-geoinformatics (Agrogeoinformatics). Hangzhou: IEEE, 2018.
FAO; IFAD; WFP. The State of Food Insecurity in the World 2013: The Multiple Dimensions of Food Security. [S.l.]: FAO, 2014. ISBN 9251079161.
FASHENG Zhang et al. Mapping surface soil organic matter based on multispectral image. In: 2010 International Conference on Image Analysis and Signal Processing. Zhejiang, China: IEEE, 2010.
FERENTINOS, K. P. Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, v. 145, p. 311 – 318, 2018. ISSN 0168-1699.
KRIZHEVSKY, A.; SUTSKEVER, I.; HINTON, G. E. Imagenet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1. USA: Curran Associates Inc., 2012.
KUMAR, V. et al. Determination of soil pH by using digital image processing technique. JANS, v. 6, n. 1, p. 14–18, jun. 2014.
KUSSUL, N. et al. Deep learning classification of land cover and crop types using remote sensing data. IEEE Geoscience and Remote Sensing Letters, PP, p. 1–5, 03 2017.
LECUN, Y.; KAVAKCUOGLU, K.; FARABET, C. Convolutional networks and applications in vision. In: Proceedings of ISCAS. Paris: [s.n.], 2010. p. 253–256.
MITISHITA, P. P. e Alzir Antunes e E. Ortoretificação de imagens de alta resolução utilizando os modelos apm (affine projection model) e rpc (rational polynomial coeffycient). Boletim de Ciências Geodésicas, v. 13, n. 1, 2007. ISSN 1982-2170.
PADARIAN, J.; MINASNY, B.; MCBRATNEY, A. Using deep learning to predict soil properties from regional spectral data. p. e00198, 11 2018.
PANTAZI, X. et al. Wheat yield prediction using machine learning and advanced sensing techniques. Computers and Electronics in Agriculture, v. 121, p. 57 – 65, 2016. ISSN 0168-1699.
QIANG Ma; WANTAI Yu; HUA Zhou. The relationship between soil nutrient properties andremote sensing indices in the Phaeozem region of Northeast China. In: 2010 Second International Conference on Computational Intelligence and Natural Computing. Wuhan, China: IEEE, 2010. p. 109–112.
REGALADO, R. G.; CRUZ, J. C. D. Soil pH and nutrient (Nitrogen, Phosphorusand Potassium) analyzer using colorimetry. In: 2016 IEEE Region 10 Conference(TENCON). Singapore: IEEE, 2016.
SU, Y. xue; XU, H.; YAN, L. jiao. Support vector machine-based open crop model (sbocm): Case of rice production in china. Saudi Journal of Biological Sciences, v. 24, n. 3, p. 537 – 547, 2017. ISSN 1319-562X.
SUMIHARTO, R.; HARDIYANTO, R. NPK Soil Nutrient Measurement Prototype Based onLocal Binary Pattern And Back- Propagation. In: 2018 IEEE International Conference on Internet of Things and Intelligence System (IOTAIS). Bali: IEEE, 2018.
XU, Q. et al. Extraction of leaf biophysical attributes based on a computer graphic-based algorithm using terrestrial laser scanning data. Remote Sensing, v. 11, p. 15, 12 2018.
ZANZARINI, F. V. et al. Correlação espacial do Índice de vegetação (NDVI) de imagem Landsat/ETM+ com atributos do solo. Revista Brasileira de Engenharia Agrícola e Ambiental, scielo, v. 17, p. 608 – 614, 06 2013. ISSN 1415-4366.
DONG, W. et al. Digital Mapping of Soil Available Phosphorus Supported by AI Technology for Precision Agriculture. In: 2018 7th International Conference on Agro-geoinformatics (Agrogeoinformatics). Hangzhou: IEEE, 2018.
FAO; IFAD; WFP. The State of Food Insecurity in the World 2013: The Multiple Dimensions of Food Security. [S.l.]: FAO, 2014. ISBN 9251079161.
FASHENG Zhang et al. Mapping surface soil organic matter based on multispectral image. In: 2010 International Conference on Image Analysis and Signal Processing. Zhejiang, China: IEEE, 2010.
FERENTINOS, K. P. Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, v. 145, p. 311 – 318, 2018. ISSN 0168-1699.
KRIZHEVSKY, A.; SUTSKEVER, I.; HINTON, G. E. Imagenet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1. USA: Curran Associates Inc., 2012.
KUMAR, V. et al. Determination of soil pH by using digital image processing technique. JANS, v. 6, n. 1, p. 14–18, jun. 2014.
KUSSUL, N. et al. Deep learning classification of land cover and crop types using remote sensing data. IEEE Geoscience and Remote Sensing Letters, PP, p. 1–5, 03 2017.
LECUN, Y.; KAVAKCUOGLU, K.; FARABET, C. Convolutional networks and applications in vision. In: Proceedings of ISCAS. Paris: [s.n.], 2010. p. 253–256.
MITISHITA, P. P. e Alzir Antunes e E. Ortoretificação de imagens de alta resolução utilizando os modelos apm (affine projection model) e rpc (rational polynomial coeffycient). Boletim de Ciências Geodésicas, v. 13, n. 1, 2007. ISSN 1982-2170.
PADARIAN, J.; MINASNY, B.; MCBRATNEY, A. Using deep learning to predict soil properties from regional spectral data. p. e00198, 11 2018.
PANTAZI, X. et al. Wheat yield prediction using machine learning and advanced sensing techniques. Computers and Electronics in Agriculture, v. 121, p. 57 – 65, 2016. ISSN 0168-1699.
QIANG Ma; WANTAI Yu; HUA Zhou. The relationship between soil nutrient properties andremote sensing indices in the Phaeozem region of Northeast China. In: 2010 Second International Conference on Computational Intelligence and Natural Computing. Wuhan, China: IEEE, 2010. p. 109–112.
REGALADO, R. G.; CRUZ, J. C. D. Soil pH and nutrient (Nitrogen, Phosphorusand Potassium) analyzer using colorimetry. In: 2016 IEEE Region 10 Conference(TENCON). Singapore: IEEE, 2016.
SU, Y. xue; XU, H.; YAN, L. jiao. Support vector machine-based open crop model (sbocm): Case of rice production in china. Saudi Journal of Biological Sciences, v. 24, n. 3, p. 537 – 547, 2017. ISSN 1319-562X.
SUMIHARTO, R.; HARDIYANTO, R. NPK Soil Nutrient Measurement Prototype Based onLocal Binary Pattern And Back- Propagation. In: 2018 IEEE International Conference on Internet of Things and Intelligence System (IOTAIS). Bali: IEEE, 2018.
XU, Q. et al. Extraction of leaf biophysical attributes based on a computer graphic-based algorithm using terrestrial laser scanning data. Remote Sensing, v. 11, p. 15, 12 2018.
ZANZARINI, F. V. et al. Correlação espacial do Índice de vegetação (NDVI) de imagem Landsat/ETM+ com atributos do solo. Revista Brasileira de Engenharia Agrícola e Ambiental, scielo, v. 17, p. 608 – 614, 06 2013. ISSN 1415-4366.
Publicado
02/12/2020
Como Citar
JANISZEVSKI, Fábio Leandro; PAULA FILHO, Pedro Luiz de; LUCHESE, Augusto Vaghetti.
Mapeamento e classificação do solo fazendo uso de índices de vegetação e arquitetura de aprendizagem profunda. In: CONGRESSO LATINO-AMERICANO DE SOFTWARE LIVRE E TECNOLOGIAS ABERTAS (LATINOWARE), 17. , 2020, Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 101-105.
DOI: https://doi.org/10.5753/latinoware.2020.18615.
