APRENDIZADO DE MÁQUINA APLICADO EM IMAGEM NDVI PARA PREVISÃO DA PRODUTIVIDADE DA CANA-DE-AÇÚCAR
Palavras-chave:
Machie Learning, Sugar Cane, NDVIResumo
Este artigo apresenta uma abordagem através de modelos baseados em ML (Machine Learning) aplicados em Imagens NDVI (Normalized Difference Vegetation Index) para estimativas da produtividade na cultura da Cana-de-Açúcar. O uso de técnicas humanas baseadas em experiências cognitivas é predominante para prever a produtividade. As imagens utilizadas foram o NDVI fornecido pelo satélite Sentinel-2, sendo que os conjuntos de dados foram obtidos a partir dos pontos de georreferenciamento dos talhões e aplicados às imagens para extração e processadas. Os modelos dos algoritmos preditivos utilizados foram: (i) CNN (Convolution Neural Network), (ii) KNN (K-Nearest Neighbors), (iii) RF (Random Forest), (iv) SVM (Support Vector Machie), (v) AdaBoost (Adaptive Boosting). O algoritmo de RF apresentou-se o mais eficiente, de modo que os resultados para o DP (Desvio Padrão) e a fórmula para o MSE (Mean Square Error) obtiveram 30,71 toneladas (t) e o MAE (Mean Absolute Error) obteve 3,73 (t). Na relação das estimativas, a fórmula do DP para o MSE obteve 34,71 (t) e o MAE de 3,97 (t). O EM (Erro Médio) para as estimativas foi de -8,80% e o algoritmo RF de 0,012%. Os resultados mostraram-se consistentes para as estimavas da produtividade na cultura da Cana-de-Açúcar.
Downloads
Referências
ABBAS, M. A. Improving deep learning performance using random forest HTM cortical learning algorithm. In: INTERNATIONAL WORKSHOP ON DEEP AND REPRESENTATION LEARNING (IWDRL), 1., 2018. Cairo. Anais […]. Cairo, Egito, 2018, p. 13-18. . https://doi.org/10.1109/IWDRL.2018.8358209
ASADI, M.; POURHOSSEIN, K. Locating Renewable Energy Generators Using K-Nearest Neighbors (KNN) Algorithm, Iranian. In: CONFERENCE ON RENEWABLE ENERGY & DISTRIBUTED GENERATION (ICREDG), 2019, [S.l.], . 2019. p. 1-6https://doi.org/10.1109/ICREDG47187.2019.190179
BRASIL. Decreto nº 76.593, de 14 de novembro de 1975. Institui o Programa Nacional do Álcool e dá outras Providências, Diário Oficial da União, Brasília, DF, Nov, 1975.
CHAROEN-UNG, P.; MITTRAPIYANURUK, P. Sugarcane Yield Grade Prediction using Random Forest and Gradient Boosting Tree Techniques. In: INTERNATIONAL JOINT CONFERENCE ON COMPUTER SCIENCE AND SOFTWARE ENGINEERING (JCSSE), 15., 2018. Nakhonpathom. THA, 2018. p. 1-6. https://doi.org/10.1109/JCSSE.2018.8457391
CHEN, G. Y.; KÉGL, B. Invariant pattern recognition using contourlets and AdaBoost, Pattern Recognition, v. 43, n. 3, , p. 579-583, 2010. . https://doi.org/10.1016/j.patcog.2009.08.020
COBEÑA CEVALLOS, J. P.; ATIENCIA VILLAGOMEZ, J. M.; ANDRYSHCHENKO, I. S. Convolutional Neural Network in the Recognition of Spatial Images of Sugarcane Crops in the Troncal Region of the Coast of Ecuador. In: INTERNATIONAL SYMPOSIUM “INTELLIGENT SYSTEMS” (INTELS’18), 13., 2019. Moscou, Russia. Anais […]. Moscou, 2019. p. 757-763https://doi.org/10.1016/j.procs.2019.02.001
DATASETS de imagens usadas no treinamento e testes das redes para predição da produtividade na cultura Cana-da-açúcar. Disponível em: https://drive.google.com/drive/folders/1sf2VSJGsQAJecCrYFVx4W-xu1XTJ3-8d?usp=sharing. Acesso em: 10 fev. 2021.
DEN BESTEN, N. I.; KASSING, R. C.; MUCHANGA, E.; EARNSHAW, C.; de JEU, R. A. M.; KARIMI, P.; van der ZAAG, P. A novel approach to the use of earth observation to estimate daily evaporation in a sugarcane plantation in Xinavane, Mozambique. Physics and Chemistry of the Earth, Parts A/B/C, 102940, 2020. https://doi.org/10.1016/j.pce.2020.102940
DO VALLE GONÇALVES, R. R.; ZULLO, J.; ROMANI, L. A. S.; do AMARAL, B. F.; SOUSA, E. P. M. Agricultural monitoring using clustering techniques on satellite image time series of low spatial resolution. In: INTERNATIONAL WORKSHOP ON THE ANALYSIS OF MULTITEMPORAL REMOTE SENSING IMAGES (MULTISTEP), 9., 2017, Bruges, BEL. Anais […]. Bruges, 2017, p. 1-4.https://doi.org/10.1109/Multi-Temp.2017.8035234
DUFT, D. G.; PICOLI, M. C. A. Uso de imagens do sensor modis para identificação da seca na cana-de-açúcar através de índices espectrais. Scientia agraria, Curitiba,v. 19, n. 1, p. 52-63, jan./mar. 2018.. https://doi.org/10.5380/rsa.v19i1.54005
EBADI, A.; GAUTHIER, Y.; TREMBLAY, S.; PAUL, P. How can Automated Machine Learning Help Business Data Science Teams? In: IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA). 18., Boca Raton, FL, Anais […]. Raton, FL, 2019, p. 1186-1191.https://doi.org/10.1109/ICMLA.2019.00196
FERNANDES, J. L.; EBECKEN, N. F. F.; ESQUERDO, J. C. D. M. Sugarcane yield prediction in Brazil using NDVI time series and neural networks ensemble. International Journal of Remote Sensing, v. 38, n. 16, p. 4631–4644, maio, 2017.. https://doi.org/10.1080/01431161.2017.1325531
GEETHARAMANI, G.; ARUN PANDIAN, J. Identification of plant leaf diseases using a nine-layer deep convolutional neural network. Computers & Electrical Engineering, p. 323–338, 2019. https://doi.org/10.1016/j.compeleceng.2019.08.010
GHOSAL, S.; SARKAR, K. Rice Leaf Diseases Classification Using CNN With Transfer Learning, 2020 IEEE Calcutta Conference (CALCON), Kolkata, India, p. 230-236, 2020. https://doi.org/10.1109/CALCON49167.2020.9106423
HOSSAIN, E.; HOSSAIN, M. F.; RAHAMAN, M. A. A Color and Texture Based Approach for the Detection and Classification of Plant Leaf Disease Using KNN Classifier, INTERNATIONAL CONFERENCE ON ELECTRICAL, COMPUTER AND COMMUNICATION ENGINEERING (ECCE), 2019. Cox’sBazar. Anais […]. Cox'sBazar, Bangladesh, 2019 , p. 1-6. https://doi.org/10.1109/ECACE.2019.8679247
HU, G.; YIN, C.; WAN, M.; ZHANG, Y.; FANG, Y. Recognition of diseased Pinus trees in UAV images using deep learning and AdaBoost classifier. Biosystems Engineering, v. 194, p. 138–151, 2020. https://doi.org/10.1016/j.biosystemseng.2020.03.021
KAI, P. M.; COSTA, R. M.; OLIVEIRA, B. M.; FERNANDES, D. S. A.; FELIX, J.; SOARES, F. Discrimination of Sugarcane Varieties by Remote Sensing: A Review of Literature.In: IEEE ANNUAL COMPUTERS, SOFTWARE, AND APPLICATIONS CONFERENCE (COMPSAC), 44., Madrid, Spain, p. 1212-1217, 2020. https://doi.org/10.1109/COMPSAC48688.2020.00-91
KHAN, W. et al. On the Performance of Temporal Stacking and Vegetation Indices for Detection and Estimation of Tobacco Crop. IEEE Access, v. 8, p. 103020-103033, 2020. Acesso em: 28 mar. 2021. https://doi.org/10.1109/ACCESS.2020.2998079
KHETKEEREE, S. Infrared Normalized Difference Vegetation Index for Sentinel-2A Imagery. In: INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING/ELECTRONICS, COMPUTER, TELECOMMUNICATIONS AND INFORMATION TECHNOLOGY (ECTI-CON), 2020, [S.l.], 2020. p. 405-408. https://doi.org/10.1109/ECTI-CON49241.2020.9158105
LANEVE, G.; MARZIALETTI, P.; LUCIANI, R.; FUSILLI, L.; MULIANGA, B. Sugarcane biomass estimate based on sar imagery: A radar systems comparison. In: IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2017, Fort Worth, TX. Anais […].Fort Worth, TX 2017, p. 5834-5837.. Disponível em: https://ieeexplore.ieee.org/document/8128335. Acesso em: 13 abr. 2020.
LUCIANO, A. C. S.; PICOLI, M. C. A.; ROCHA, J. V.; FRANCO, H. C. J.; SANCHES, G. M.; LEAL, M. R. L. V.; le MAIRE, G. Generalized space-time classifiers for monitoring sugarcane areas in Brazil. Remote Sens. Environ, Campinas, v. 215, p. 438–451, 2018. https://doi.org/10.1016/j.rse.2018.06.017. Acesso em: 28 mar. 2020. https://doi.org/10.1016/j.rse.2018.06.017
LUCIANO, A. C. S.; PICOLI, M. C. A.; ROCHA, J. V.; DUFT, D. G.; LAMPARELLI, R. A. C.; LEAL, M. R. L. V.; LE MAIRE, G. A generalized space-time OBIA classification scheme to map sugarcane areas at regional scale, using Landsat images time-series and the random forest algorithm. International Journal of Applied Earth Observation and Geoinformation, v. 80, p. 127–136, abr. 2019a. https://doi.org/10.1016/j.jag.2019.04.013
LUCIANO, A. C. dos S.; DUFT, D. G.; PICOLI, M. C. A.; ROCHA, J. V.; Le MAIRE, G. Estimativa da produtividade de cana-de-açúcar utilizando imagens landsat e random forest. In: SIMPÓSIO BRASILEIRO DE SENSORIAMENTO REMOTO, 19., 2019, Santos, SP. Anais [...]. Santos, 2019b. Disponível em: http://marte2.sid.inpe.br/attachment.cgi/sid.inpe.br/marte2/2019/10.23.11.40/doc/97833.pdf. Acesso em: 14 abr. 2020.
MILITANTE, S. V.; GERARDO, B. D.; MEDINA, R. P. Sugarcane Disease Recognition using Deep Learning. In: IEEE EURASIA CONFERENCE ON IOT, COMMUNICATION AND ENGINEERING (ECICE), 2019, Yunlin, Taiwan. Anais […].Yunlin, Taiwan, 2019. p. 575-578, https://doi.org/10.1109/ECICE47484.2019.8942690
NUGRAHAENI, R. A.; MUTIJARSA, K. Comparative analysis of machine learning KNN, SVM, and random forests algorithm for facial expression classification. In: INTERNATIONAL SEMINAR ON APPLICATION FOR TECHNOLOGY OF INFORMATION AND COMMUNICATION (ISEMANTIC), 2016, Semarang, Anais […]. Semarang,2016, p. 163-168https://doi.org/10.1109/ISEMANTIC.2016.7873831
RADU, M. D.; COSTEA, I. M.; STAN, V. A. Automatic Traffic Sign Recognition Artificial Inteligence - Deep Learning Algorithm. In: INTERNATIONAL CONFERENCE ON ELECTRONICS, COMPUTERS AND ARTIFICIAL INTELLIGENCE (ECAI), 12., 2020. Anais […]. [S.l.], 2020,p. 1-4. https://doi.org/10.1109/ECAI50035.2020.9223186
ROUSE Jr, J. W.; HAAS, R. H.; SCHELL, J. A.; DEERING, D. W. Monitoring vegetation systems in the great plains with ERTS. Third In: ERTS-1 SYMPOSIUM, 3., 1973, Washington, D.C Anais […]. Washington, 1973, v. 1, p. 309-317. Disponível em: https://ntrs.nasa.gov/citations/19740022614. Acesso em: 28 mar. 2021.
RUBIRA CRULHAS, J. P.; ARTERO, A. O.; PITERI, M. A.; SILVA, F. A.; PEREIRA, D. R.; ELER, D. M.; ALBUQUERQUE, V. H. C. Blank Spots Identification on Plantations. IEEE Latin America Transactions, v. 16, n. 8, p. 2115-2121, Aug. 2018.. https://doi.org/10.1109/TLA.2018.8528224
SCRIVANI, R.; ZULLO, J.; ROMANI, L. A. S. SITS for estimating sugarcane production. In: INTERNATIONAL WORKSHOP ON THE ANALYSIS OF MULTITEMPORAL REMOTE SENSING IMAGES (MultiTemp), 2017. Brugge, Belgium,. Anais […]Brugge, Belgium, 2017 p. 1-4. https://doi.org/10.1109/Multi-Temp.2017.8035254
SKITTOU, M.; MADHOUM, O.; KHANNOUSS, A.; MERROUCHI, M.; GADI, T. Classification of land use areas using remote sensing data with machine learning.In: IEEE INTERNATIONAL CONFERENCE OF MOROCCAN GEOMATICS (MORGEO), Casablanca, Morocco. Anais […]. Casablenca, Marocco, 2020. p. 1-5. Disponível em: https://ieeexplore.ieee.org/document/9121883. Acesso em: 15 fev. 2021. https://doi.org/10.1109/Morgeo49228.2020.9121883
SOUZA, M. F. DE; AMARAL, L. R, OLIVEIRA, S. R. M.; COUTINHO, M. A. N.; NETTO, C. F. Spectral differentiation of sugarcane from weeds, Biosystems Engineering, , Campinas, SP, v. 190, p. 41-46, 2020. https://doi.org/10.1016/j.biosystemseng.2019.11.023
SPERANZA, E. A.; ANTUNES, J. F. G.; INAMASU, R. Y. Uso de imagens de sensoriamento remoto para identificação de variabilidade espacial em Agricultura de Precisão. In: SIMPÓSIO DE GEOTECNOLOGIAS NO PANTANAL, JARDIM, MATO GROSSO DO SUL, Brasil, 7.,2018. Jardim. Anais [...]. Jardim, MS, 2018. Disponível em: https://www.alice.cnptia.embrapa.br/handle/doc/1099230. Acesso em: 14 abr. 2020.
TREEBUPACHATSAKUL, T.; POOMRITTIGUL, S. Bacteria Classification using Image Processing and Deep learning. INTERNATIONAL TECHNICAL CONFERENCE ON CIRCUITS/SYSTEMS, COMPUTERS AND COMMUNICATIONS (ITC-CSCC), 34., 2019. JeJu, Korea (South). Anais […]. JeJu, Korea (South), 2019. p. 1-3. https://doi.org/10.1109/ITC-CSCC.2019.8793320
VASCONCELLOS, B. C.; TRINDADE, J. P. P.; VOLK, L. B. DA S.; DE PINHO, L. B. Method Applied To Animal MonitoringThrough VANT Images.IEEE Latin America Transactions, v. 18, n. 07, p. 1280-1287, jul., 2020. https://doi.org/10.1109/TLA.2020.9099770
WANG, M.; LIU, Z.; ALI, B. M. H.; WANG, Y.; Li, Y.; CHEN, Y. Mapping sugarcane in complex landscapes by integrating multi-temporal Sentinel-2 images and machine learning algorithms. Land Use Policy, China, v. 88, p. 1-11,2019. Disponível em: https://doi.org/10.1016/j.landusepol.2019.104190
ZHANG, T.; SU, J.; LIU, C.; CHEN, W.; LIU, H.; LIU, G. Band selection in sentinel-2 satellite for agriculture applications., In: INTERNATIONAL CONFERENCE ON AUTOMATION AND COMPUTING (ICAC). 23., 2017, Huddersfield, UK. Anais […].Huddersfield, UK, 2017. p. 1-6. https://doi.org/10.23919/IConAC.2017.8081990