Early detection of weed in sugarcane using convolutional neural network

João Pedro do Santos Verçosa; Flávio Henrique dos Santos Silva; Fabricio Almeida Araujo; Regla Toujaguez la Rosa Massahud; Francisco Rafael da Silva Pereira; Henrique Ravi Rocha de Carvalho Almeida; Marcus de Barros Braga; Arthur Costa Falcão Tavares

doi:10.31686/ijier.vol10.iss11.4004

Authors

João Pedro do Santos Verçosa Universidade Federal de Alagoas
Flávio Henrique dos Santos Silva
Fabricio Almeida Araujo
Regla Toujaguez la Rosa Massahud
Francisco Rafael da Silva Pereira
Henrique Ravi Rocha de Carvalho Almeida
Marcus de Barros Braga
Arthur Costa Falcão Tavares

DOI:

https://doi.org/10.31686/ijier.vol10.iss11.4004

Keywords:

Deep Learning, planetscope, precision agriculture

Abstract

Weed infestation is an essential factor in sugarcane productivity loss. The use of remote sensing data in conjunction with Artificial Intelligence (AI) techniques, can lead the cultivation of sugarcane to a new level in terms of weed control. For this purpose, an algorithm based on Convolutional Neural Networks (CNN) was developed to detect, quantify, and map weeds in sugarcane areas located in the state of Alagoas, Brazil. Images of the PlanetScope satellite were subdivided, separated, trained in different scenarios, classified and georeferenced, producing a map with weed information included. Scenario one of the CNN training and test presented overall accuracy (0,983), and it was used to produce the final mapping of forest areas, sugarcane, and weed infestation. The quantitative analysis of the area (ha) infested by weed indicated a high probability of a negative impact on sugarcane productivity. It is recommended that the adequacy of CNN’s algorithm for Remotely Piloted Aircraft (RPA) images be carried out, aiming at the differentiation between weed species, as well as its application in the detection in areas with different culture crops

Downloads

Download data is not yet available.

References

V. N. T. Le, S. Ahderom, and K. Alameh, “Performances of the lbp based algorithm over cnn models for detecting crops and weeds with similar morphologies,” Sensors, vol. 20, no. 8, 2020. [Online]. Available: https://www.mdpi.com/1424-8220/20/8/2193 DOI: https://doi.org/10.3390/s20082193

T. Burks, S. Shearer, J. Heath, and K. Donohue, “Evaluation of neural-network classifiers for weed species discrimination,” Biosystems Engineering, vol. 91, no. 3, pp. 293–304, 2005. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1537511004002302 DOI: https://doi.org/10.1016/j.biosystemseng.2004.12.012

M. A. M. Espinoza, C. Z. Le, A. Raheja, and S. Bhandari, “Weed identification and removal using machine learning techniques and unmanned ground vehicles,” in Autonomous Air and Ground Sensing Systems for Agricultural Optimization and Phenotyping V, J. A. Thomasson and A. F. Torres-Rua, Eds., vol. 11414, International Society for Optics and Photonics. SPIE, 2020, pp. 109 – 118. [Online]. Available: https://doi.org/10.1117/12.2557625 DOI: https://doi.org/10.1117/12.2557625

R. Ferreira, E. Contato, M. Kuva, A. Ferraudo, P. Alves, F. Magario, and T. Salgado, “Organizacão das comunidades infestantes de plantas daninhas na cultura da cana-de-açúcar em agrupamentos-padrão,” Planta Daninha, vol. 29, no. 2, pp. 363–371, Jun. 2011. [Online]. Available: https://doi.org/10.1590/s0100-83582011000200014 DOI: https://doi.org/10.1590/S0100-83582011000200014

M. A. Haq, “Cnn based automated weed detection system using uav imagery,” Computer Systems Science and Engineering, vol. 42, no. 2, pp. 837–849, 2022. [Online]. Available: http://www.techscience.com/csse/v42n2/46130 DOI: https://doi.org/10.32604/csse.2022.023016

S. Haykin, Redes Neurais - 2ed. Bookman, 05, 2022.

H. Jiang, C. Zhang, Y. Qiao, Z. Zhang, W. Zhang, and C. Song, “Cnn feature based graph convolutional network for weed and crop recognition in smart farming,” Computers and Electronics in Agriculture, vol. 174, p. 105450, 2020. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0168169919321349 DOI: https://doi.org/10.1016/j.compag.2020.105450

X. Jin, Y. Sun, J. Che, M. Bagavathiannan, J. Yu, and Y. Chen, “A novel deep scplearning-based/scp method for detection of weeds in vegetables,” Pest Management Science, vol. 78, no. 5, pp. 1861–1869, Feb. 2022. [Online]. Available: https://doi.org/10.1002/ps.6804 DOI: https://doi.org/10.1002/ps.6804

A. Kamilaris and F. X. Prenafeta-Boldu ́, “A review of the use of con- volutional neural networks in agriculture,” The Journal of Agricultural Science, vol. 156, no. 3, p. 312–322, 2018. DOI: https://doi.org/10.1017/S0021859618000436

J. R. Landis and G. G. Koch, “An application of hierarchical kappa-type statistics in the assessment of majority agreement among multiple observers,” Biometrics, vol. 33, no. 2, pp. 363–374, 1977. [Online]. Available: http://www.jstor.org/stable/2529786 DOI: https://doi.org/10.2307/2529786

W. C. Liang, Y. J. Yang, and C. M. Chao, “Low-cost weed identification system using drones,” in 2019 Seventh International Symposium on Computing and Networking Workshops (CANDARW), 2019, pp. 260– 263. DOI: https://doi.org/10.1109/CANDARW.2019.00052

P. D. S. Oliveira, “Uso de aprendizagem de máquina e redes neurais convolucionais profundas para a classificação de áreas queimadas em imagens de alta resolução espacial,” Dissertação (Mestrado em Geografia), Jun. 2019.

M. A. Ponti and G. B. P. da Costa, “Como funciona o deep learning,” Tópicos em Gerenciamento de Dados e Informações, 2018. [Online]. Available: https://arxiv.org/abs/1806.07908

L. Quan, H. Feng, Y. Lv, Q. Wang, C. Zhang, J. Liu, and Z. Yuan, “Maize seedling detection under different growth stages and complex field environments based on an improved faster r–cnn,” Biosystems Engineering, vol. 184, pp. 1–23, 2019. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1537511019300327 DOI: https://doi.org/10.1016/j.biosystemseng.2019.05.002

N. R. Rao, “Development of a crop‐specific spectral library and discrimination of various agricultural crop varieties using hyperspectral imagery”, International Journal of Remote Sensing, v. 29, n. 1, p. 131–144, 2008. DOI: https://doi.org/10.1080/01431160701241779

L. R. Sartori, M. L. B. T. Galo, and N. N. Imai, “Mapeamento de plantas daninhas em cultura de café a partir de imagens multiespectrais de escalas grandes usando redes neurais artificiais,” Revista Brasileira de Cartografia, no. 61, pp. 165–175, 2009.

T. M. Shah, D. P. B. Nasika, and R. Otterpohl, “Plant and weed identifier robot as an agroecological tool using artificial neural networks for image identification,” Agriculture, vol. 11, no. 3, 2021. [Online]. Available: https://www.mdpi.com/2077-0472/11/3/222 DOI: https://doi.org/10.3390/agriculture11030222

J. Useya, S. Chen, “Exploring the Potential of Mapping Cropping Patterns on Smallholder Scale Croplands Using Sentinel-1 SAR Data”. Chinese Geographical Science, v. 29, n. 4, p. 626–639, 2019. DOI: https://doi.org/10.1007/s11769-019-1060-0

M. Weis, C. Gutjahr, V. R. Ayala, R. Gerhards, C. Ritter, and F. Scho ̈lderle, “Precision farming for weed management: techniques,” Gesunde Pflanzen, vol. 60, no. 4, pp. 171–181, Nov. 2008. [Online]. Available: https://doi.org/10.1007/s10343-008-0195-1 DOI: https://doi.org/10.1007/s10343-008-0195-1

K. Xu, Y. Zhu, W. Cao, X. Jiang, Z. Jiang, S. Li, and J. Ni, “Multi-modal deep learning for weeds detection in wheat field based on rgb-d images,” Frontiers in Plant Science, vol. 12, 2021. [Online]. Available: https://www.frontiersin.org/article/10.3389/fpls.2021.732968 DOI: https://doi.org/10.3389/fpls.2021.732968

I. H. Yano, “Mapeamento de infestac ̧o ̃es de plantas daninhas em lavoura decana-de-ac ̧u ́carporaeronaveremotamentepilotadas(rpa),”Tesede Doutorado (Doutor em Engenharia Agricola), 2018.

J. Yu, S. M. Sharpe, A. W. Schumann, and N. S. Boyd, “Detection of broadleaf weeds growing in turfgrass with convolutional neural networks,” Pest Management Science, vol. 75, no. 8, pp. 2211–2218, Mar. 2019. [Online]. Available: https://doi.org/10.1002/ps.5349 DOI: https://doi.org/10.1002/ps.5349

M. Weiss; F. Jacob; G. Duveiller, “Remote sensing for agricultural applications: A meta-review”. Remote Sensing of Environment, v. 236, p. 111402, 2020. DOI: https://doi.org/10.1016/j.rse.2019.111402

Q. Zhang et al., “Missing data reconstruction in remote sensing image with a unified spatial–temporal–spectral deep convolutional neural network”. IEEE Transactions on Geoscience and Remote Sensing (TGRS), China, v. 56, n. 8, p. 4274-4288, 14 mar. 2018.Cristo, H. S. de, Filho, A. S. N., Marinho de Aragão, J. W., & Saba, H. (2022). Media Bios and Artificial Intelligence: The dark side of Fake News. International Journal for Innovation Education and Research, 10(4), 23–33. https://doi.org/10.31686/ijier.vol10.iss4.3701 DOI: https://doi.org/10.1109/TGRS.2018.2810208