Abstract
Identifying and quantifying the number and size of stomata on leaf surfaces is useful for a wide range of plant ecophysiological studies, specifically those related to water-use efficiency of different plant species or agricultural crops. The time-consuming nature of manually counting and measuring stomata have limited the utility of manual methods for large-scale precision agriculture applications. A deep learning segmentation network was developed to automate the analysis of stomatal density and size and to distinguish between open and closed stomata using citrus trees grafted on different rootstocks as a model system. A novel method was developed utilizing the Mask-RCNN algorithm, which allows identification, quantification, and characterization of stomata from leaf epidermal peel microscopic images with an accuracy of up to 99%. Moreover, this method permits the differentiation of open and closed stomata with 98% precision and measurement of individual stomata size. In the citrus model system, significant differences in the size and density of stomata and diurnal regulation patterns were detected that were associated with the rootstock cultivar on which the trees were grafted. Nearly 9000 individual stomata were analyzed, which would have been impractical using manual methods. The novel automated method presented here is not only accurate, but also rapid and low-cost, and can be applied to a variety of crop and non-crop plant species.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Albrecht, U., Tripathi, I., & Bowman, K. D. (2020). Rootstock influences the metabolic response to Candidatus Liberibacter asiaticus in grafted sweet orange trees. Trees, 34, 405–431. https://doi.org/10.1007/s00468-019-01925-3.
Albrecht, U., Tripathi, I., Kim, H., & Bowman, K. D. (2018). Rootstock effects on metabolite composition in leaves and roots of young navel orange (Citrus sinensis L. Osbeck) and pummelo (C. grandis L. Osbeck) trees. Trees, 33, 243–265. https://doi.org/10.1007/s00468-018-1773-1.
Ampatzidis, Y., & Partel, V. (2019). UAV-based high throughput phenotyping in citrus utilizing multispectral imaging and artificial intelligence. Remote Sensing, 11(4), 410. https://doi.org/10.3390/rs11040410.
Ampatzidis, Y., Partel, V., & Costa, L. (2020). Agroview: Cloud-based application to process, analyze and visualize UAV-collected data for precision agriculture applications utilizing artificial intelligence. Computers and Electronics in Agriculture, 174, 105–157. https://doi.org/10.1016/j.compag.2020.105457.
Ampatzidis, Y., Partel, V., Meyering, B., & Albrecht, U. (2019). Citrus rootstock evaluation utilizing UAV-based remote sensing and artificial intelligence. Computers and Electronics in Agriculture, 164, 104900. https://doi.org/10.1016/j.compag.2019.104900.
Banuls, J., & Primo-Millo, E. (1995). Effects of salinity on some citrus scion-rootstock combinations. Annals of Botany, 76(1), 97–102. https://doi.org/10.1006/anbo.1995.1083.
Bertolino, L. T., Caine, R. S., & Gray, J. E. (2019). Impact of stomatal density and morphology on water-use efficiency in a changing world. Frontiers in Plant Science. https://doi.org/10.3389/fpls.2019.00225.
Bhugra, S., Mishra, D., Anupama, A., Chaudhury, S., Lall, B., Chugh, A., & Chinnusamy, V. (2018). Deep convolutional neural networks based framework for estimation of stomata density and structure from microscopic images. In Proceedings of the European conference on computer vision (ECCV). https://doi.org/10.1007/978-3-030-11024-6_31.
Bowman, K. D., & Joubert, J. (2020). Citrus rootstocks. In M. Talon, M. Caruso, & F. G. Gmitter (Eds.), The genus citrus (pp. 105–127). Cambridge, MA: Woodhead Publishing. https://doi.org/10.1016/B978-0-12-812163-4.00006-1.
Cao, Z., Long, M., Wang, J., & Jordan, M. I. (2018). Partial transfer learning with selective adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2724–2732).
Cruz, A., Ampatzidis, Y., Pierro, R., Materazzi, A., Panattoni, A., De Bellis, L., & Luvisi, A. (2019). Detection of grapevine yellows symptoms in vitis vinifera L. with artificial intelligence. Computers and Electronics in Agriculture, 157, 63–76.
Cruz, A. C., Luvisi, A., De Bellis, L., & Ampatzidis, Y. (2017). X-FIDO: An effective application for detecting olive quick decline syndrome with novel deep learning methods. Frontiers in Plant Science. https://doi.org/10.3389/fpls.2017.01741.
Doheny-Adams, T., Hunt, L., Franks, P. J., Beerling, D. J., & Gray, J. E. (2012). Genetic manipulation of stomatal density influences stomatal size, plant growth and tolerance to restricted water supply across a growth carbon dioxide gradient. Philosophical Transactions of the Royal Society B, 367(1588), 547–555. https://doi.org/10.1098/rstb.2011.0272.
Fetter, K. C., Eberhardt, S., Barclay, R. S., Wing, S., & Keller, S. R. (2019). StomataCounter: A neural network for automatic stomata identification and counting. New Phytologist, 223(3), 1671–1681. https://doi.org/10.1111/nph.15892.
Franks, P. J., & Beerling, D. J. (2009). Maximum leaf conductance driven by CO2 effects on stomatal size and density over geologic time. Proceedings of the National Academy of Sciences of the United States of America, 106, 10343–10347. https://doi.org/10.1073/pnas.0904209106.
Franks, P. J., Doheny-Adams, T. W., Britton-Harper, Z. J., & Gray, J. E. (2015). Increasing water-use efficiency directly through genetic manipulation of stomatal density. New Phytologist, 207(1), 188–195. https://doi.org/10.1111/nph.13347.
Gan, H., Lee, W. S., Alchanatis, V., Ehsani, R., & Schueller, J. K. (2018). Immature green citrus fruit detection using color and thermal images. Computers and Electronics in Agriculture, 152, 117–125. https://doi.org/10.1016/j.compag.2018.07.011.
Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 1440–1448). https://doi.org/10.1109/ICCV.2015.169.
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 580–587). https://doi.org/10.1109/CVPR.2014.81.
Graham, J. H., Gottwald, T. R., Riley, T. D., & Achor, D. (1992). Penetration through leaf stomata and growth of strains of Xanthomonas campestris in citrus cultivars varying in susceptibility to bacterial diseases. Phytopathology, 82, 1319–1325. https://doi.org/10.1094/Phyto-82-1319.
He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 2961–2969). https://doi.org/10.1109/ICCV.2017.322.
Hepworth, C., Doheny-Adams, T., Hunt, L., Cameron, D. D., & Gray, J. E. (2015). Manipulating stomatal density enhances drought tolerance without deleterious effect on nutrient uptake. New Phytologist, 207(2), 336–341. https://doi.org/10.1111/nph.13598.
Hirano, E. (1931). Relative abundance of stomata in citrus and some related genera. Botanical Gazette, 92(3), 296–310. https://doi.org/10.1086/334198.
Hubel, D. H., & Wiesel, T. N. (1959). Receptive fields of single neurones in the Cat’s striate cortex. The Journal of Physiology, 148(3), 574–591. https://doi.org/10.1113/jphysiol.1959.sp006308.
Igboabuchi, N. A., & Ilodibia, C. V. (2017). A study on the anatomy of Zanthoxylum macrophylla (L.) Sarg. (Rutaceae). Asian Journal of Botany, 3(4), 1–6. https://doi.org/10.9734/AJOB/2017/36104.
Jones, H. G. (2012). How do rootstocks control shoot water relations. New Phytologist, 194(2), 301–303. https://doi.org/10.1111/j.1469-8137.2012.04114.x.
Kitrungrotsakul, T., Iwamoto, Y., Han, X. H., Takemoto, S., Yokota, H., Ipponjima, S., & Chen, Y. W. (2019). A cascade of CNN and LSTM network with 3D anchors for mitotic cell detection in 4D microscopic image. In ICASSP 2019–2019 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 1239–1243). IEEE. https://doi.org/https://doi.org/10.1109/ICASSP.2019.8682326.
Koen, B. (1988). Toward a definition of the engineering method. European Journal of Engineering Education, 13(3), 307–315. https://doi.org/10.1080/03043798808939429.
Korner, C. (1988). Does global increase of CO2 alter stomatal density? Flora, 181, 253–257. https://doi.org/10.1016/S0367-2530(17)33116-X.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems. https://doi.org/10.1145/3065386.
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989). Backpropagation applied to handwritten zip code recognition. Neural Computation, 1(4), 541–551. https://doi.org/10.1162/neco.1989.1.4.541.
Li, W., Fu, H., Yu, L., & Cracknell, A. (2017). Deep learning based oil palm tree detection and counting for high-resolution remote sensing images. Remote Sensing, 9(1), 22. https://doi.org/10.3390/rs9010022.
Liu, C., He, N., Zhang, J., Li, Y., Wang, Q., Sack, L., & Yu, G. (2018). Variation of stomatal traits from cold temperate to tropical forests and association with water use efficiency. Functional Ecology, 32(1), 20–28. https://doi.org/10.1111/1365-2435.12973.
Martínez-Alcántara, B., Rodriguez-Gamir, J., Martínez-Cuenca, M. R., Iglesias, D. J., Primo-Millo, E., & Forner-Giner, M. A. (2013). Relationship between hydraulic conductance and citrus dwarfing by the Flying Dragon rootstock (Poncirus trifoliata L. Raft var. monstruosa). Trees, 27, 629–638. https://doi.org/10.1007/s00468-012-0817-1.
McElwain, J. C., & Chaloner, W. G. (1995). Stomatal density and index of fossil plants track atmospheric carbon dioxide in the palaeozoic. Annals of Botany, 76(4), 389–395. https://doi.org/10.1006/anbo.1995.1112.
Moradiamin, M., Memari, A., Samadzadehaghdam, N., Kermani, S., & Talebi, A. (2016). Computer aided detection and classification of acute lymphoblastic leukemia cell subtypes based on microscopic image analysis. Microscopy Research and Technique, 79(10), 908–916. https://doi.org/10.1002/jemt.22718.
Obiremi, E. O., & Oladele, F. A. (2001). Water conserving stomatal systems in selected Citrus species. South African Journal of Botany, 67, 258–206. https://doi.org/10.1016/S0254-6299(15)31127-3.
Partel, V., Kakarla, S. C., & Ampatzidis, Y. (2019). Development and evaluation of a low-cost and smart technology for precision weed management utilizing artificial intelligence. Computers and Electronics in Agriculture, 157, 339–350. https://doi.org/10.1016/j.compag.2018.12.048.
Partel, V., Nunes, L., Stansley, P., & Ampatzidis, Y. (2019). Automated Vision-based system for monitoring Asian citrus psyllid in orchards utilizing artificial intelligence. Computers and Electronics in Agriculture, 162, 328–336. https://doi.org/10.1016/j.compag.2019.04.022.
Patel, N., & Mishra, A. (2015). Automated leukaemia detection using microscopic images. Procedia Computer Science, 58, 635–642. https://doi.org/10.1016/j.procs.2015.08.082.
Penuelas, J., & Matamala, R. (1990). Changes in N and S leaf content, stomatal density and specific leaf area of 14 plant species during the last three centuries of CO2 increase. Journal of Experimental Botany, 41(9), 1119–1124. https://doi.org/10.1093/jxb/41.9.1119.
R Core Team. (2019). R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing.
Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems. https://doi.org/10.1109/TPAMI.2016.2577031.
Rodriguez-Gamir, J., Primo-Millo, E., Forner, J. B., & Forner-Giner, M. A. (2010). Citrus rootstock responses to water stress. Scientia Horticulturae, 126(2), 95–102. https://doi.org/10.1016/j.scienta.2010.06.015.
Sa, I., Ge, Z., Dayoub, F., Upcroft, B., Perez, T., & McCool, C. (2016). Deepfruits: A fruit detection system using deep neural networks. Sensors, 16(8), 1222. https://doi.org/10.3390/s16081222.
Sharma, R., & Kaur, S. (2019). Convolution neural network based several orange leave disease detection and identification methods: A review. In 2019 international conference on smart systems and inventive technology (ICSSIT) (pp. 196–201). https://doi.org/10.1109/ICSSIT46314.2019.8987744.
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. In Thirty-first AAAI conference on artificial intelligence.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818–2826). https://doi.org/10.1109/CVPR.2016.308.
Szegedy, C., Wei, L., Yangqing, J., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1–9). https://doi.org/10.1109/CVPR.2015.7298594.
Tanaka, Y., Sugano, S. S., Shimada, T., & Hara-Nishimura, I. (2013). Enhancement of leaf photosynthetic capacity through increased stomatal density in Arabidopsis. New Phytologist, 198(3), 757–764.
Wang, C., Lee, W. S., Zou, X., Choi, D., Gan, H., & Diamond, J. (2018). Detection and counting of immature green citrus fruit based on the local binary patterns (LBP) feature using illumination-normalized images. Precision Agriculture, 19, 1062. https://doi.org/10.1007/s11119-018-9574-5.
Wu, Y., Kirillov, A., Massa, F., Lo, W., & Girshick, R. (2019). Detectron2. Github repository. https://github.com/facebookresearch/detectron2
Xu, Z., & Zhou, G. (2008). Responses of leaf stomatal density to water status and its relationship with photosynthesis in a grass. Journal of Experimental Botany, 59(12), 3317–3325. https://doi.org/10.1093/jxb/ern185.
Yang, Z., Salakhutdinov, R., & Cohen, W. W. (2017). Transfer learning for sequence tagging with hierarchical recurrent networks. arXiv preprint. http://arxiv.org/abs/1703.06345.
Acknowledgements
This material was made possible, in part, by a Cooperative Agreement from the U.S. Department of Agriculture’s (USDA) Animal and Plant Health Inspection Service (APHIS) and USDA-NIFA-SCRI (#2019-70016-29096). Its contents are solely the responsibility of the authors and do not necessarily represent the official views of the USDA.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Costa, L., Archer, L., Ampatzidis, Y. et al. Determining leaf stomatal properties in citrus trees utilizing machine vision and artificial intelligence. Precision Agric 22, 1107–1119 (2021). https://doi.org/10.1007/s11119-020-09771-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11119-020-09771-x