Estimate of soybean crop productivity in the 2021/22 season: Vegetation indices and Machine Learning

Authors

  • Victor Messias Moreira University Center of Southwest Goiano, UniBRAS, Rio Verde, Goiás, Brazil https://orcid.org/0000-0002-8631-3635
  • Daniel Noe Coaguila Nuñez University Center of Southwest Goiano, UniBRAS, Rio Verde, Goiás, Brazil

DOI:

https://doi.org/10.14295/bjs.v2i1.247

Keywords:

Glycine max, random forest, Google Colaboratory, remote sensing

Abstract

Soybean is one of the most economically important crops in the world, with Brazil being the world's largest producer of this grain. Knowing the productivity is not always possible since these are linked to the type of technology that the farm has and allows an indirect evaluation of the quality of management. Thus, the objective was to estimate the productivity of the soybean crop in the 21/22 season in southwest Goiás using vegetation indices and machine learning. The vegetation indices EVI, NDRE, NDVI, NDWI and the reflectance values of the RGB composition of the Sentinel 2A and 2B satellite were used, harmonized images, free of clouds with one before sowing, during plowing and one image after harvesting. Random points were obtained for each of the six productivity classes and vegetation index values were assigned for each date and class. The data matrix was processed on the Google Collaboratory platform using the Random Forest classifier from the Scikit-learn package. Evaluating all parameters allowed by Random Forest, the best score (0.6825) to estimate soybean productivity was obtained using the gini criteria, 85% of samples and 120 estimators, using all recurrent images of the harvest period 21/22 and images before sowing and after harvesting.

References

Acosta, J. J. B., Cabrera, M. G., Ibras, R. F., González, J. D., Chamorro, S. M. & Escobar, J. (2018). Variabilidade espacial da produtividade, perdas na colheita e lucratividade da cultura de soja. Revista Agrogeoambiental, 10(1), 27-46. http://dx.doi.org/10.18406/2316-1817v10n120181050 DOI: https://doi.org/10.18406/2316-1817v10n120181050

Alvares, C. A., Stape, J. L., Sentelhas, P. C. Gonçalves, J. D. M. & Sparovek, G. (2013). Koppen’s climate classification map for Brazil. Meteorologische Zeitschrift, 22(6), 711-728. http://dx.doi.org/10.1127/0941-2948/2013/0507 DOI: https://doi.org/10.1127/0941-2948/2013/0507

Amado, T. J. C., Santi, A. L., Moreira, J. H. & Souza, L. A. (2007). Variabilidade espacial e temporal da produtividade de culturas sob sistema plantio direto. Pesquisa Agropecuária Brasileira, 42(8), 1101-1110. https://doi.org/10.1590/S0100-204X2007000800006 DOI: https://doi.org/10.1590/S0100-204X2007000800006

Atzberger, C. & Rembold, F. (2013). Mapping the spatial distribution of winter crops at sub-pixel level using AVHRR NDVI time series and neural nets. Remote Sensing, 5(3), 1335-1354. https://doi.org/10.3390/rs5031335 DOI: https://doi.org/10.3390/rs5031335

Azzari, G., Jain, M. & Lobell, D. B. (2017). Towards fine resolution global maps of crop yields: Testing multiple methods and satellites in three countries. Remote Sensing of Environment, 202, 129-141. https://doi.org/10.1016/j.rse.2017.04.014 DOI: https://doi.org/10.1016/j.rse.2017.04.014

Casado-García, Á., Heras, J. & Sanz-Sáez, A. (2019). Google Colaboratory for Quantifying Stomata in Images. In: International Conference on Computer Aided Systems Theory. Springer, Cham., 231-238. DOI: https://doi.org/10.1007/978-3-030-45096-0_29

Chioderoli, C. A., Silva, R. P., Noronha, R. H. F., Cassia, M. T. & Santos, E. P. (2012). Perdas de grãos e distribuição de palha na colheita mecanizada de soja. Revista Bragantia, 71(1), 112-121. https://doi.org/10.1590/S0006-87052012005000003 DOI: https://doi.org/10.1590/S0006-87052012005000003

Conab - Companhia Nacional de Abastecimento. Acompanhamento da safra brasileira de grãos, v. 12 – Safra 2021/22, n. 12 – Décimo segundo levantamento, setembro de 2022. Brasília, 2022.

Cunha, R. L. F., Silva, B. & Netto, M. A. S. (2018). A scalable machine learning system for preseason agriculture yield forecast. Proceedings - IEEE 14th International Conference on e-Science, e-Science 2018, 423–430. DOI: https://doi.org/10.1109/eScience.2018.00131

Gao, B. C. (1996). Ndwi - A normalized difference water index for remote sensing of vegetation liquid water from space. Remote sensing of environment, 58(3), 257-266. https://doi.org/10.1016/S0034-4257(96)00067-3 DOI: https://doi.org/10.1016/S0034-4257(96)00067-3

Gorelick, N., Hancher, M., Dixon, M., Ilyushchenko, S., Thau, D. & Moore, R. (2017). Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sensing of Environment, 202, 18-27. https://doi.org/10.1016/j.rse.2017.06.031 DOI: https://doi.org/10.1016/j.rse.2017.06.031

Jiang, X., Fang, S., Huang, X., Liu, Y. & Guo, L. (2021). Rice mapping and growth monitoring based on time series GF-6 images and red-edge bands. Remote Sensing, 13(4), 579. https://doi.org/10.3390/rs13040579 DOI: https://doi.org/10.3390/rs13040579

Jin, Z., Azzari, G. & Lobell, D. B. (2017). Improving the accuracy of satellite-based highresolution yield estimation: A test of multiple scalable approaches. Agricultural and Forest Meteorology, 247, 207-220. https://doi.org/10.1016/j.agrformet.2017.08.001 DOI: https://doi.org/10.1016/j.agrformet.2017.08.001

Johnson, D. M. (2014). An assessment of pre- and within-season remotely sensed variables for forecasting corn and soybean yields in the United States. Remote Sensing of Environment, 141, 116-128. https://doi.org/10.1016/j.rse.2013.10.027 DOI: https://doi.org/10.1016/j.rse.2013.10.027

Kuechly, H. U., Cozacu, A., Kodl, G., Nicolai, C. & Vallentin, C. (2020) Grundlagen der Fernerkundung. Inforeihe SAPIENS: Satellitendaten für Planung, Industrie, Energiewirtschaft und Naturschutz, Deutsches Geo Forschungs Zentrum GFZ. https://doi.org/10.2312/sapiens.2020.001

Lobell, D. B. (2013). The use of satellite data for crop yield gap analysis. Field Crops Research, 43, 56-64. https://doi.org/10.1016/j.fcr.2012.08.008 DOI: https://doi.org/10.1016/j.fcr.2012.08.008

Maldaner, L. F. & Molin, J. P. (2019). Data processing within rows for sugarcane yield mapping. Scientia Agricola, 77(5), 1-8. https://doi.org/10.1590/1678-992X-2018-0391 DOI: https://doi.org/10.1590/1678-992x-2018-0391

McFeeters, S. K. (1996). The use of the Normalized Diference Water Index (NDWI) in the delineation of open water features. International Journal of Remote Sensing, 17(7), 1425-1432. https://doi.org/10.1080/01431169608948714 DOI: https://doi.org/10.1080/01431169608948714

Michels, R. N., Canteri, M. G., De Aguiar, M. A., Bertozzi, J. & Dal Bosco, T. C. (2018). Reflectance as a decision-making tool for the application of fungicide to the Asian Soybean Rust. Revista de Ciências Agrárias, 41(3), 832-840. https://doi.org/10.19084/RCA17333 DOI: https://doi.org/10.19084/RCA17333

Peel, M. C., Finlayson, B. L. & Mcmahon, T. A. (2007). Updated world map of the Köppen-Geiger climate classification. Hydrology and Earth System Sciences, 11(5), 1633–1644. https://doi.org/10.5194/hess-11-1633-2007 DOI: https://doi.org/10.5194/hess-11-1633-2007

Pereira, L. M., Santos, S. C. C. C., Do Nascimento, J. M. & Secretti, M. L. (2021). Correlação da produtividade da soja com os atributos químicos do solo e o NDVI. Revista Brasileira de Agropecuária Sustentável, 11(1), 430-438. https://doi.org/10.21206/rbas.v11i1.12711

Ponzoni, F. J., Shimabukuro, Y. E.; Kuplich, T. M. (2012). Sensoriamento remoto aplicado ao estudo da vegetação. 2. ed. São José Dos Campos: Saraiva.

Ponzoni, F. J., Pacheco, L. R. F., Santos, S. B. & Andrades-Filho, C. O. (2015). Caracterização espectrotemporal de dosséis de Eucalyptus spp. mediante dados radiométricos TM/Landsat5. Cerne, 2(2), 267-275. DOI: https://doi.org/10.1590/01047760201521021457

Romansini, V.A., Martins, J. A., Pivetta, L. G. & et al. (2020). Índices de vegetação derivados de imagens orbitais como indicadores de produtividade da cultura da soja. In: Ribeiro, J.C. (Org.). Desenvolvimento Social e Sustentável das Ciências Agrárias 2. Ponta Grossa: Atena, 2020. DOI: https://doi.org/10.22533/at.ed.71920091010

Sakamoto, T., Gitelson, A. A. & Arkebauer, T. J. (2014). Near real-time prediction of U.S. corn yields based on time-series MODIS data. Remote Sensing of Environment, 147, 219–231. https://doi.org/10.1016/j.rse.2014.03.008 DOI: https://doi.org/10.1016/j.rse.2014.03.008

Santos, H. G., Jacomine, P. K. T., Anjos, L. H. C., Oliveira, V. A., Lumbreras, J. F., Coelho, M. R., Almeida, J. A., Araujo Filho, J. C., Oliveira, J. B. & Cunha, T. J. F. (2018). Sistema brasileiro de classificação de solos. Brasília, DF: Embrapa.

Schirmbeck, L. W., Fontana, D. C., Dalmago, G. A., Schirmbeck, J., Vargas, P. R. & Fernandes, J. M. C. (2020). Condições hídricas de lavoura de soja usando sensoriamento remoto terrestre. Agrometeoros, 27(1), 173-181. http://dx.doi.org/10.31062/agrom.v27i1.26565 DOI: https://doi.org/10.31062/agrom.v27i1.26565

Shao, Y., Campbell, J. B., Taff, G. N. & Zheng, B. (2015). An analysis of cropland mask choice and ancillary data for annual corn yield forecasting using MODIS data. International Journal of Applied Earth Observation and Geoinformation, 38, 78-87. https://doi.org/10.1016/j.jag.2014.12.017 DOI: https://doi.org/10.1016/j.jag.2014.12.017

Sharma, L. K., Bu, H., Denton, A. & Franzen, D. W. (2015). Active-optical sensors using red NDVI compared to red edge NDVI for Prediction of corn grain yield in North Dakota, USA. Sensors. 15, 27832–27853.

https://doi.org/10.3390/s151127832 DOI: https://doi.org/10.3390/s151127832

Shelestov, A.; Lavreniuk, M.; Kussul, N.; Novikov, A.; Skakun, S. (2017). Exploring Google Earth Engine platform for big data processing: Classification of multi-temporal satellite imagery for crop mapping. Frontiers in Earth Science, 5(17), 1-10. https://doi.org/10.3389/feart.2017.00017 DOI: https://doi.org/10.3389/feart.2017.00017

Trindade, F. S., De Carvalho Alves, M., Noetzold, R., De Andrade, I. C. & Pozza, A. A. A. (2019). Relação espectro-temporal de índices de vegetação com atributos do solo e produtividade da soja. Revista de Ciências Agrárias, 62, 1-11. http://200.129.150.26/index.php/ajaes/article/view/2928 DOI: https://doi.org/10.22491/rca.2019.2928

Zanzarini, F. V., Pissarra, T. C., Brandão, F. J. & Teixeira, D. D. (2013). Correlação espacial do índice de vegetação (NDVI) de imagem Landsat/ETM+ com atributos do solo. Revista Brasileira de Engenharia Agrícola e Ambiental, 17, 608-614. https://doi.org/10.1590/S1415-43662013000600006 DOI: https://doi.org/10.1590/S1415-43662013000600006

Zarei, A. R.. Mahmoudi, M. R. & Moghimi, M. M. (2022). Determining the most appropriate drought index using the random forest algorithm with an emphasis on agricultural drought. Natural Hazards, 1-24. https://doi.org/10.1007/s11069-022-05579-2 DOI: https://doi.org/10.1007/s11069-022-05579-2

Published

2023-01-01

How to Cite

Moreira, V. M., & Nuñez, D. N. C. (2023). Estimate of soybean crop productivity in the 2021/22 season: Vegetation indices and Machine Learning. Brazilian Journal of Science, 2(1), 7–15. https://doi.org/10.14295/bjs.v2i1.247

Issue

Section

Agrarian and Biological Sciences