PREDIÇÃO DO TEOR DE CLOROFILA EM UMA PLANTAÇÃO DE ARROZ IRRIGADO UTILIZANDO IMAGENS AÉREAS E REDES NEURAIS ARTIFICIAIS

Abstract

O objetivo deste artigo foi desenvolver modelos computacionais para predição do teor de clorofila em uma plantação de arroz irrigado utilizando imagens aéreas e Redes Neurais Artificiais. Através do dispositivo clorofiLOG, foram realizadas medições dos níveis de clorofila nas folhas das plantas do arroz e correlacionados com imagens aéreas coletadas por uma câmera digital portátil, embarcada em um Veículo Aéreo Não Tripulado. As imagens foram coletadas com a aeronave em movimento com velocidade de 2 m/s a uma altura de 50 m sobre o local do experimento. Utilizando Processamento Digital de Imagens, foram gerados 42 índices espectrais, posteriormente selecionados pelo método de seleção por filtro. Os índices foram atribuídos como entradas e as medições de clorofila como saída dos modelos de predição. Desta forma foram desenvolvidos quatro modelos de redes neurais com os respectivos índices de desempenho de R²=0,80, R²=0,7395, R²=0,7775 e R²=0,799. Todos os modelos demonstraram que atingiram ao objetivo desta pesquisa. Desta forma evidencia-se a utilidade destes modelos de predição como ferramentas de auxílio às ciências agronômicas para identificação dos níveis de clorofila na rizicultura. Podem fornecer novas perspectivas na gestão da adubação nitrogenada e melhorias nos custos entre as safras de arroz.

Author Biographies

Rodrigo Cesar Nunes Maciel, Universidade Federal de Santa Catarina (UFSC)

Mestre em Tecnologias da Informação e Comunicação pela Universidade Federal de Santa Catarina (UFSC). Graduação em Engenharia da Computação pela Universidade Federal de Santa Catarina (UFSC).

Roderval Marcelino, Universidade Federal de Santa Catarina (UFSC)

Pós-doutorado pela University na Irlanda do Norte. Doutor em Engenharia pela Universidade Federal do Rio Grande do Sul (UFRGS). Mestre em Engenharia pela Universidade Federal do Rio Grande do Sul (UFRGS). Professor da Universidade Federal de Santa Catarina (UFSC).

Bruno Pansera Espíndola, Instituto Federal Catarinense (IFC)

Doutor em Engenharia pela Universidade do Estado de Santa Catarina (UDESC). Mestre em Produção Vegetal pela Universidade do Estado de Santa Catarina (UDESC). 

References

ADHIKARI, C et al. On-farm soil N supply and N nutrition in the rice–wheat system of Nepal and Bangladesh. Field Crops Research, v. 64, n. 3, p. 273–286, dez. 1999. ISSN 03784290. DOI: 10.1016/S0378-4290(99)00063-5.

BALAFOUTIS, A. et al. Precision Agriculture Technologies Positively Contributing to GHG Emissions Mitigation, Farm Productivity and Economics. Sustainability, v. 9, n. 8, p. 1339, jul. 2017. ISSN 2071-1050. DOI:10.3390/su9081339.

BARMAN, U.; CHOUDHURY, R. Smartphone image based digital chlorophyll meter to estimate the value of citrus leaves chlorophyll using Linear Regression, LMBP-ANN and SCGBP-ANN. Journal of King Saud University - Computer and Information Sciences, The Authors, n. 40, 2020. ISSN 22131248. DOI: 10.1016/j.jksuci.2020.01.005.

CALISKAN, O. et al. Estimating Chlorophyll Concentration Index in Sugar Beet Leaves Using an Artificial Neural Network. Polish Journal of Environmental Studies, ago. 2019. DOI: 10.15244/pjoes/95031.

CEN, H. et al. Dynamic monitoring of biomass of rice under different nitrogen treatments using a lightweight UAV with dual image-frame snapshot cameras. Plant Methods, BioMed Central, v. 15, n. 1, p. 1–16, 2019. ISSN 17464811. DOI:10.1186/s13007-019-0418-8.

CHEN, W. et al. AgriTalk: IoT for Precision Soil Farming of Turmeric Cultivation. IEEE Internet of Things Journal, v. 6, n. 3, p. 5209–5223, 2019. DOI: 10.1109/JIOT.2019.2899128.

COLORADO, J. D. et al. Estimation of nitrogen in rice crops from UAV-captured images. Remote Sensing, v. 12, n. 20, p. 1–31, 2020. ISSN 20724292. DOI: 10.3390/rs12203396.

CONANT, R. T.; BERDANIER, A. B.; GRACE, P. R. Patterns and trends in nitrogen use and nitrogen recovery efficiency in world agriculture. Global Biogeochemical Cycles, v. 27, n. 2, p. 558–566, jun. 2013. ISSN 08866236. DOI: 10.1002/gbc.20053.

CURRAN, P.; WINDHAM, W.; GHOLZ, H. Exploring the relationship between reflectance red edge and chlorophyll concentration in slash pine. Tree physiology, v. 15, p. 203–6, abr. 1995. DOI: 10.1093/treephys/15.3.203.

EPAGRI; CEPA. Síntese Anual da Agricultura de Santa Catarina 2018-2019, 2019. P. 197.

FAGERIA, N. K.; MOREIRA, A.; COELHO, A. M. Yield and yeld components of upland rice as influenced by nitrogen sources. Journal of Plant Nutrition, v. 34, n. 3, p. 361–370, jan. 2011. ISSN 0190-4167. DOI: 10.1080/01904167.2011.536878.

GUO, Y. et al. Scaling effects on chlorophyll content estimations with RGB camera mounted on a UAV platform using machine-learning methods. Sensors (Switzerland), v. 20, n. 18, p. 1–22, 2020. ISSN 14248220. DOI: 10.3390/s20185130.

HU, H. et al. Estimation of leaf chlorophyll content of rice using image color analysis. Canadian Journal of Remote Sensing, v. 39, p. 185–190, jan. 2014. DOI: 10.5589/m13-026.

HUANG, J. et al. Nitrogen and phosphorus losses and eutrophication potential associated with fertilizer application to cropland in China. Journal of Cleaner Production, v. 159, p. 171–179, ago. 2017. ISSN 09596526. DOI: 10.1016/j.jclepro.2017.05.008.

JINWEN, L. Determination of Canopys Average SPAD Readings Based on the Analysis of Digital Images. Agrotechnology, v. 03, jan. 2014. DOI: 10.4172/2168-9881.1000121.

KAWASHIMA, S.; NAKATANI, M. An algorithm for estimating chlorophyll content in leaves using a video camera. Annals of Botany, v. 81, n. 1, p. 49–54, 1998. ISSN 03057364. DOI: 10.1006/anbo.1997.0544.

LIN, F. et al. Investigation of SPAD meter-based indices for estimating rice nitrogen status. Computers and Electronics in Agriculture, v. 71, abr. 2010. DOI: 10.1016/j.compag.2009.09.006.

LIU, Y. et al. From Industry 4.0 to Agriculture 4.0: Current Status, Enabling Technologies, and Research Challenges. IEEE Transactions on Industrial Informatics, p. 1–1, 2020. DOI: 10.1109/TII.2020.3003910.

MOGHADDAM, P.; DERAFSHI, M.; G. SHAYESTEH, M. A new method in assessing sugar beet leaf nitrogen status through color image processing and artificial neural network. Journal of Food, Agriculture and Environment, v. 8, abr. 2010.

MOHAN, P. J.; GUPTA, S. D. Intelligent image analysis for retrieval of leaf chlorophyll content of rice from digital images of smartphone under natural light. Photosynthetica, Photosynthetica, v. 57, n. 2, p. 388–398, 2019. ISSN 15739058. DOI: 10.32615/ps.2019.046.

MUÑOZ-HUERTA, R. et al. A Review of Methods for Sensing the Nitrogen Status in Plants: Advantages, Disadvantages and Recent Advances. Sensors (Basel, Switzerland), v. 13, p. 10823–43, ago. 2013. DOI: 10.3390/s130810823.

NASCENTE, A. S. et al. Produtividade do arroz de terras altas em função do manejo do solo e da época de aplicação de nitrogênio. Pesquisa Agropecuária Tropical, v. 41, n. 1, jan. 2011. ISSN 1983-4063. DOI: 10.5216/pat.v41i1.6509.

NOVICHONOK, E. et al. Use of the chlorophyll meter for a nondestructive estimate of chlorophyll content. Photosynthetica, v. 54, ago. 2015. DOI: 10.1007/s11099-015-0172-8.

PAGOLA, M. et al. New method to assess barley nitrogen nutrition status based on image colour analysis Comparison with SPAD-502. Computers and Electronics in Agriculture - COMPUT ELECTRON AGRIC, v. 65, p. 213–218, mar. 2009. DOI: 10.1016/j.compag.2008.10.003.

PRASERTSAK, A.; FUKAI, S. Nitrogen availability and water stress interaction on rice growth and yield. Field Crops Research, v. 52, n. 3, p. 249–260, jun. 1997. ISSN 03784290. DOI: 10.1016/S0378-4290(97)00016-6.

RAVIER, C.; QUEMADA, M.; JEUFFROY, M. Use of a chlorophyll meter to assess nitrogen nutrition index during the growth cycle in winter wheat. Field Crops Research, v. 214, p. 73–82, ago. 2017. DOI: 10.1016/j.fcr.2017.08.023.

SDR, Secretaria de Desenvolvimento Regional. Caracterização Regional. Florianópolis, 2003. P. 51.

SHI, P. et al. Rice nitrogen nutrition estimation with RGB images and machine learning methods. Computers and Electronics in Agriculture, Elsevier B.V., October, p. 105860, 2020. ISSN 01681699. DOI: 10.1016/j.compag.2020.105860.

STAVRAKOUDIS, D. et al. Estimating Rice Agronomic Traits Using Drone-Collected Multispectral Imagery. Remote Sensing, v. 11, n. 5, p. 545, mar. 2019. ISSN 2072-4292. DOI: 10.3390/rs11050545.

SUN, Y. et al. Identification of nitrogen, phosphorus, and potassium deficiencies based on temporal dynamics of leaf morphology and color. Sustainability (Switzerland), v. 10, n. 3, 2018. ISSN 20711050. DOI: 10.3390/su10030762.

TKÁˇC, M.; MESÁROŠ, P. Utilizing drone technology in the civil engineering. Selected Scientific Papers - Journal of Civil Engineering, v. 14, p. 27–37, dez. 2019. DOI: 10.1515/sspjce-2019-0003.

VEÇOZZI, T. A. et al. Soil solution and plant nitrogen on irrigated rice under controlled release nitrogen fertilizers. Ciência Rural, v. 48, n. 1, dez. 2017. ISSN 1678-4596. DOI: 10.1590/0103-8478cr20170279.

WANG, Y.; WANG, D.; SHI, P. et al. Estimating rice chlorophyll content and leaf nitrogen concentration with a digital still color camera under natural light. Plant Methods, v. 10, n. 1, p. 36, 2014. ISSN 1746-4811. DOI: 10.1186/1746-4811-10-36.

WANG, Y.; WANG, D.; ZHANG, G. et al. Estimating nitrogen status of rice using the image segmentation of G-R thresholding method. Field Crops Research, v. 149, p. 33–39, ago. 2013. ISSN 03784290. DOI: 10.1016/j.fcr.2013.04.007.

WEISS, M.; JACOB, F.; DUVEILLER, G. Remote sensing for agricultural applications: A meta-review. Remote Sensing of Environment, v. 236, nov. 2019. DOI: 10.1016/j.rse.2019.111402.

YADAV, S.; IBARAKI, Y.; DUTTA GUPTA, S. Estimation of the chlorophyll content of micropropagated potato plants using RGB based image analysis. Plant Cell, Tissue and Organ Culture (PCTOC), v. 100, p. 183–188, fev. 2010. DOI:10.1007/s11240-009-9635-6.

YU, F. et al. Inversion model of chlorophyll content in japonica rice canopy based on PSO-ELM and hyper-spectral remote sensing. Journal of South China Agricultural University, v. 41, n. 6, p. 59–66, 2020. ISSN 1001411X. DOI: 10.7671/j.issn.1001-411X.202007044.

YUAN, Z. et al. Indicators for diagnosing nitrogen status of rice based on chlorophyll meter readings. Field Crops Research, v. 185, p. 12–20, jan. 2016. DOI: 10.1016/j.fcr.2015.10.003.

YUHAO, A. et al. Rice chlorophyll content monitoring using vegetation indices from multispectral aerial imagery. Pertanika Journal of Science and Technology, v. 28, n. 3, p. 779–795, 2020. ISSN 22318526.

ZHENG, H. et al. Evaluation of RGB, color-infrared and multispectral images acquired from unmanned aerial systems for the estimation of nitrogen accumulation in rice. Remote Sensing, v. 10, n. 6, 2018. ISSN 20724292. DOI: 10.3390/rs10060824.

Published
2022-02-16
Section
FLUXO CONTÍNUO - Artigos