Non-destructive Photosynthetic Pigments Prediction using Multispectral Imagery and 2D-CNN
Keywords:Convolutional Neural Network, Multispectral Image, Non-Destructive, Photosynthetic Pigments
Rapid assessment of plant photosynthetic pigments content is an essential issue in precise management farming. Such an assessment can represent the status of plants in their stages of growth. We have developed a new 2 Dimensional-Convolutional Neural Network (2D-CNN) architecture, the P3MNet. This architecture simultaneously predicts the content of 3 main photosynthetic pigments of a plant leaf in a non-destructive and real-time manner using multispectral images. Those pigments are chlorophyll, carotenoid, and anthocyanin. By illuminating with visible light, the reflectance of individual plant leaf at 10 different wavelengths – 350, 400, 450, 500, 550, 600, 650, 700, 750, and 800 nm – was captured in a form of 10 digital images. It was then used as the 2D-CNN input. Here, our result suggested that P3MNet outperformed AlexNet and VGG-9. After undergoing a training process using Adadelta optimization method for 1000 epochs, P3MNet has achieved superior MAE (Mean Absolute Error) in the average of 0.000778 ± 0.0001 for training and 0.000817 ± 0.0007 for validation (data range 0-1).
R. Esteban, O. Barrutia, U. Artetxe, B. Fernández-Marín, A. Hernández, J.I. García-Plazaola, “Internal and external factors affecting photosynthetic pigment composition in plants: a meta-analytical approach,” New Phytologist, vol. 206, issue 1, pp. 268–280, 2015. https://doi.org/10.1111/nph.13186.
A. Jabeen, T.V. Kiran, D. Subrahmanyam, D.L. Lakshmi, G. Bhagyanarayana, D. Khrisnaveni, “Variations in chlorophyll and carotenoid contents in tungro infected rice plants,” Journal of Research and Development, vol. 5, issue 1, pp. 2311-3278, 2017.
H. Croft, J.M. Chen, Leaf Pigment Content, in: S. Liang, X. Xiong, J.J. Butler (Eds.), Comprehensive Remote Sensing, Elsevier Inc, 2018, pp. 117-142. https://doi.org/10.1016/B978-0-12-409548-9.10547-0.
A. Gitelson, Non-destructive Estimation of Foliar Pigment (Chlorophylls, Carotenoids and Anthocyanins) Contents: Espousing a Semi-Analytical Three-Band Model, in: Thenkabail, P.S., Lyon, J.G., Huete, A. (Eds.), Hyperspectral Remote Sensing of Vegetation. Taylor and Francis, 2011, pp. 141–162.
A. Gitelson, A. Solovchenko, “Generic algorithm for estimating foliar pigment content,” Geophysical Research Letter, vol. 44, issue 18, pp. 9293-9298, 2017. https://doi.org/10.1002/2017GL074799.
A. Gitelson, A. Solovchenko, “Non-invasive quantification of foliar pigments: Possibilities and limitations of reflectance and absorbance-based approaches,” Journal of Photochemistry and Photobiology B: Biology, vol. 178, issue January, pp. 537–544, 2018. https://doi.org/10.1016/j.jphotobiol.2017.11.023.
D. Inácio, R. Rieder, “Computer vision and artificial intelligence in precision agriculture for grain crops: a systematic review,” Computer and Electronics in Agriculture, vol. 153, issue October, pp. 69–81, 2018. https://doi.org/10.1016/j.compag.2018.08.001.
Y. Peng, Y. Wang, “Prediction of the chlorophyll content in pomegranate leaves based on digital image processing technology and stacked sparse autoencoder,” International Journal of Food Properties, vol. 22, issue 1, pp. 1720-1732, 2019. https://doi.org/10.1080/10942912.2019.1675692.
M. Perez-Patricio, J. Camas-Anzueto, A. Sánchez-Alegría, A. Aguilar-González, F. Gutiérrez-Miceli, “Optical method for estimating the chlorophyll contents in plant leaves,” Sensors, vol. 18, issue 650, pp. 1-12, 2018. https://doi.org/10.3390/s18020650.
M. Tanska, M Ambrosewicz-Walacik, K. Jankowski, D. Rotkiewicz, “Possibility use of digital image analysis for the estimation of the rapeseed maturity stage,” International Journal of Food Properties, vol. 20, issue 3, pp. S2379-S2394, 2018. https://doi.org/10.1080/10942912.2017.1371188.
A. Gitelson, M.N. Merzlyak, “Non-destructive assessment of chlorophyll, carotenoid and anthocyanin content in higher plant leaves: Principle and algorithms, in: S. Stamatiadis, J.M. Lynch, J.S. Schepers (Eds), Remote Sensing for Agriculture and the environment, Greece, Ella, 2004, pp. 78-94
K.R. Prilianti, I.C. Onggara, M.A.S. Adiwibhawa, T.H.P. Brotosudarmo, “Multispectral imaging and convolutional neural network for photosynthetic pigments prediction,” Proceedings of the 5th International Conference on Electrical Engineering Computer Science and Informatics (EECSI), Malang, Indonesia, August 31 – September 1, 2018, pp. 554–559. https://doi.org/10.1109/EECSI.2018.8752649.
J.I. Arribas, G.V. Sanchez-Ferrero, G. Ruiz-Ruiz, and J. Gomez-Gil, “Leaf classification in sunflower crops by computer vision and neural networks,” Computer and Electronics in Agriculture, vol. 78, issue 1, pp. 9-18, 2011. https://doi.org/10.1016/j.compag.2011.05.007.
J.C. Pyo, H. Duan, S. Baek, M.S. Kim, T. Jeon, Y.S. Kwon, H. Lee, K.H. Cho, “A convolutional neural network regression for quantifying cyanobacteria using hyperspectral imagery,” Remote Sensing of Environment, vol. 233, Issue November, pp. 111350, 2019. https://doi.org/10.1016/j.rse.2019.111350.
J. Gu, Z. Wang, J. Kuen, L. Ma, A. Shahroudy, B. Shuai, T. Liu, X. Wang, L. Wang, G. Wang, J. Cai, T. Chen, “Recent advances in convolutional neural networks,” Pattern Recognition, vol. 77, issue May, pp. 354–377, 2018. https://doi.org/10.1016/j.patcog.2017.10.013.
Y.L. Cun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436-444, 2015. https://doi.org/10.1038/nature14539.
K.R. Prilianti, S. Anam, A. Suryanto, “Deep chemometrics for nondestructive photosynthetic pigments prediction using leaf reflectance spectra,” Information Processing in Agriculture, vol. 8, issue 1, pp. 194-204 2021. https://doi.org/10.1016/j.inpa.2020.02.001.
H.K., Lichtenthaler, “Chlorophyll and carotenoids: pigments of photosynthetic biomembranes,” Methods Enzymology, vol. 148, pp. 350-382, 1987. https://doi.org/10.1016/0076-6879(87)48036-1.
D.A. Sims, J.A. Gamon, “Relationships between leaf pigment content and spectral reflectance across a wide range of species, leaf structures and developmental stages,” Remote Sensing of Environment, vol. 81, issue 2-3, pp. 337-354, 2002. https://doi.org/10.1016/S0034-4257(02)00010-X.
P. Toulis, T. Horel, E.M. Airoldi, “Stable Robbins-Monro approximations through stochastic proximal updates,” arXiv preprint arXiv:1510.00967 v3, 2018.
J. Duchi, E. Hazan, Y. Singer, “Adaptive subgradient methods for online learning and stochastic optimization,” Journal of Machine Learning Research, vol. 12, issue July, pp. 2121-2159, 2011.
M.D. Zeiler, “ADADELTA: an adaptive learning rate method,” arXiv:1212. 5701, 2012.
G. Hinton, N. Srivastava, K. Swersky, “Overview of mini batch gradient descent,” Computer Science Department, University of Toronto, 2015.
D.P. Kingma, J.L. Ba, “Adam: a method for stochastic optimization,” Proceedings of the International Conference on Learning Representations, San Diego, USA, May 7-9, 2015, pp. 1-15.
T. Dozat, “Incorporating Nesterov momentum into adam,” Proceedings of the International Conference on Learning Representation, San Juan, Puerto Rico, May 2-4, 2016, pp. 1-4.
A.L. Maas, A.Y. Hannun, A.Y. Ng, “Rectifiers nonlinearities improve neural network acoustic models,” Proceedings of 30th International Conference on Machine Learning, Atlanta, USA, June 16-21, 2013, pp. 1-4.
B. Gaonkar, D. Hovda, N.A. Martin, L. Macyszyn, “Deep learning in the small sample size setting: cascaded feedforward neural networks for medical image segmentation,” Proceedings of the SPIE Medical Imaging, San Diego, USA, February 27 – March 3, 2016, pp. 1-8. https://doi.org/10.1117/12.2216555.
R. Keshari, M. Vatsa, R. Singh, A. Noore, “Learning structure and strength of CNN filters for small sample size training,” arXiv:1803.11405, 2018. https://doi.org/10.1109/CVPR.2018.00974.
N.M.R, Aquino, M. Gutoski, L. Hattori, H.S. Lopes, “The effect of data augmentation on the performance of convolutional neural networks,” Proceedings of the Brazilian Society of Computational Intelligence, Rio de Janeiro, Brazil, October, 2017, pp. 1-12. https://doi.org/10.21528/CBIC2017-51.
K.R., Prilianti, T.H.P. Brotosudarmo, S. Anam, A. Suryanto, “Performance comparison of the convolutional neural network optimizer for photosynthetic pigments prediction on plant digital image,” Proceedings of the Symposium on Biomathematics, Depok, Indonesia, August 31 – September 1, 2018, pp. 020020-1 – 020020-8. https://doi.org/10.1063/1.5094284.
T.D. Truong, V.T. Nguyen, M.T. Tran, “Lightweight deep convolutional network for tiny object recognition,” Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods, Funchal, Portugal, January 16-18, 2018. pp. 675-682. https://doi.org/10.5220/0006752006750682.
A.A. Gitelson, M.N. Merzlyak, Non-destructive assessment of chlorophyll, carotenoid and anthocyanin content in higher plant leaves: principles and algorithm, in: S. Stamatiadis, J.M. Lynch, J.S. Schepers (Eds.), Remote Sensing for Agriculture and the Environment. Greece, Ella, 2004, pp. 78–94.
W.D. Huang, K.H. Lin, M.H. Hsu, M.Y. Huang, Z.W. Yang, P.Y. Chao, C.M. Yang, “Eliminating interference by anthocyanin in chlorophyll estimation of sweet potato (Ipomoea batatas L.) leaves,” Botanical Study, vol. 55, issue 11, pp. 1–10, 2014. https://doi.org/10.1186/1999-3110-55-11.
How to Cite
LicenseInternational Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:
• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.