Abstract
The potential of combining artificial neural networks (ANNs) and image processing for assessing leaf relative water content (RWC) and water content (WC) was addressed. Spathiphyllum wallisii was employed as model species, because it has broad leaves and very responsive stomata. In the course of desiccation, leaves were periodically weighted (to calculate RWC and WC conventionally) and imaged. Image acquisition was performed by a scanner, and was, thus, independent of ambient light environment. Color feature extraction was performed in three color spaces (RGB, HSI, and CIELAB), while six texture statistical features were calculated for each of the (nine) computed color channels. Prior to model development via ANNs, the obtained feature vector underwent feature reduction using principal component analysis. The presented methodology yielded very precise estimations of leaf RWC and WC (correlation coefficient > 0.95). Therefore, the technique under study was proven to be very promising for non-invasive in situ measurements of leaf water status.
Similar content being viewed by others
Abbreviations
- ANN:
-
Artificial neural network
- B:
-
Blue
- CIE:
-
International Commission on Illumination
- CIE L*a*b* or CIELAB:
-
CIE lightness: redness and yellowness
- e :
-
Entropy
- G:
-
Green
- HSI:
-
Hue: saturation and intensity
- m :
-
Mean
- MAE:
-
Mean absolute error
- MLP:
-
Multi-layer perceptron
- MSE:
-
Mean square errors
- PCA:
-
Principal component analysis
- R:
-
Red
- RGB:
-
Red: green and blue
- R :
-
Smoothness
- R 2 :
-
Coefficient of determination
- R-value:
-
Pearson’s correlation coefficient
- RMSE:
-
Root mean square error
- RWC:
-
Relative water content
- U :
-
Uniformity
- WC:
-
Water content
- δ :
-
Standard deviation
- μ 3 :
-
Third moment
References
Ali MM, Al-Ani A, Eamus D, Tan DK (2012) A new image-processing-based technique for measuring leaf dimensions. Am Eurasian Am Agric Environ Sci 12:1588–1594
Azevedo AM, Andrade Júnior VC, Pedrosa CE, Oliveira CM, Dornas MFS, Cruz CD, Valadares NR (2015) Application of artificial neural networks in indirect selection: a case study on the breeding of lettuce. Bragantia 74:1–7
Baldacci L, Pagano M, Masini L, Toncelli A, Carelli G, Storchi P (2017) Non-invasive absolute measurement of leaf water content using terahertz quantum cascade lasers. Plant Methods 13:51
Brasileiro BP, Marinho CD, Costa PMA, Cruz CD, Peternelli LA, Barbosa MHP (2015) Selection in sugarcane families with artificial neural networks. Crop Breed Appl Biotechnol 15:72–78
Carvalho DRA, Koning-Boucoiran CFS, Fanourakis D, Vasconcelos MW, Carvalho SMP, Heuvelink E, Krens FA, Maliepaard C (2015) QTL analysis for stomatal functioning in tetraploid Rosa × hybrida grown at high relative air humidity and its implications on postharvest longevity. Mol Breeding 35:172
Carvalho DRA, Fanourakis D, Correia MJ, Monteiro JA, Araújo-Alves JPL, Vasconcelos MW, Almeida DPF, Heuvelink E, Carvalho SMP (2016) Root-to-shoot ABA signaling does not contribute to genotypic variation in stomatal functioning induced by high relative air humidity. Environ Exp Bot 123:13–21
Dadshani S, Kurakin A, Amanov S, Hein B, Rongen H, Cranstone S, Blievernicht U, Menzel E, Léon J, Klein N, Ballvora A (2015) Non-invasive assessment of leaf water status using a dual-mode microwave resonator. Plant Methods 11:8
Devi MJ, Reddy VR (2018) Transpiration response of cotton to vapor pressure deficit and its relationship with stomatal traits. Front Plant Sci 9:1572
Dóka O, Ficzek G, Luterotti S, Bicanic D, Spruijt R, Buijnsters JG, Szalay L, Végvári G (2013) Simple and rapid quantification of total carotenoids in lyophilized apricots (Prunus armeniaca L.) by means of reflectance colorimetry and photoacoustic spectroscopy. Food Technol Biotechnol 51:453–459
Fahlgren N, Gehan MA, Baxter I (2015) Lights, camera, action: high-throughput plant phenotyping is ready for a close-up. Curr Opin Plant Biol 24:93–99
Fanourakis D, Briese C, Max J, Kleinen S, Putz A, Fiorani F, Ulbrich A, Schurr U (2014) Rapid determination of leaf area and plant height by using light curtain arrays in four species with contrasting shoot architecture. Plant Methods 10:9
Fanourakis D, Giday H, Milla R, Pieruschka R, Kjaer KH, Bolger M, Vasilevski A, Nunes-Nesi A, Fiorani F, Ottosen CO (2015) Pore size regulates operating stomatal conductance, while stomatal densities drive the partitioning of conductance between leaf sides. Ann Bot 115:555–565
Fanourakis D, Giday H, Li T, Kambourakis E, Ligoxigakis EK, Papadimitriou M, Strataridaki A, Bouranis D, Fiorani F, Heuvelink E, Ottosen CO (2016) Antitranspirant compounds alleviate the mild-desiccation-induced reduction of vase life in cut roses. Postharvest Biol Technol 117:110–117
Fanourakis D, Hyldgaard B, Giday H, Bouranis D, Körner O, Nielsen KL, Ottosen CO (2017) Differential effects of elevated air humidity on stomatal closing ability of Kalanchoë blossfeldiana between the C3 and CAM states. Environ Exp Bot 143:115–124
Fanourakis D, Giday H, Hyldgaard B, Bouranis D, Körner O, Ottosen C-O (2019a) Low air humidity during growth promotes stomatal closure ability in roses. Eur J Hortic Sci 84:245–252
Fanourakis D, Hyldgaard B, Giday H, Aulik I, Bouranis D, Körner O, Ottosen CO (2019b) Stomatal anatomy and closing ability is affected by supplementary light intensity in rose (Rosa hybrida L.). Hort Sci 46:81–89
Fanourakis D, Aliniaeifard S, Sellin A, Giday H, Körner O, Rezaei Nejad A, Delis C, Bouranis D, Koubouris G, Kambourakis E, Nikoloudakis N, Tsaniklidis G (2020a) Stomatal behavior following mid- or long-term exposure to high relative air humidity: a review. Plant Physiol Biochem 153:92–105
Fanourakis D, Bouranis D, Tsaniklidis G, Rezaei Nejad A, Ottosen CO, Woltering EJ (2020b) Genotypic and phenotypic differences in fresh weight partitioning of cut rose stems: implications for water loss. Acta Physiol Plant 42:48
Fanourakis D, Nikoloudakis N, Pappi P, Markakis E, Doupis G, Charova S, Delis C, Tsaniklidis G (2020c) The role of proteases in determining stomatal development and tuning pore aperture: A review. Plants 9:340
Fiorani F, Schurr U (2013) Future scenarios for plant phenotyping. Annu Rev Plant Biol 64:267–291
Giday H, Fanourakis D, Kjaer KH, Fomsgaard IS, Ottosen CO (2013) Foliar abscisic acid content underlies genotypic variation in stomatal responsiveness after growth at high relative air humidity. Ann Bot 112:1857–1867
Giday H, Kjaer KH, Ottosen CO, Fanourakis D (2015) Cultivar differences in plant transpiration rate at high relative air humidity are not related to genotypic variation in stomatal responsiveness. Acta Hort 1064:99–106
Hassanvand F, Rezaei Nejad A, Fanourakis D (2019) Morphological and physiological components mediating the silicon-induced enhancement of geranium essential oil yield under saline conditions. Ind Crops Prod 134:19–25
Huang KY (2007) Application of artificial neural network for detecting phalaenopsis seedling diseases using color and texture features. Comput Electron Agric 57:3–11
Koman VB, Lew TT, Wong MH, Kwak S-Y, Giraldo JP, Strano MS (2017) Persistent drought monitoring using a microfluidic-printed electro-mechanical sensor of stomata in planta. Lab Chip 17:4015–4024
Kovar M, Brestic M, Sytar O, Barek V, Hauptvogel P, Zivcak M (2019) Evaluation of hyperspectral reflectance parameters to assess the leaf water content in soybean. Water 11:443
Li L, Zhang Q, Huang D (2014) A review of imaging techniques for plant phenotyping. Sensors 14:20078–20111
Nascimento M, Peternelli LA, Cruz CD, Nascimento ACC, Ferreira RP, Bhering LP, Salgado CC (2013) Artificial neural networks for adaptability and stability evaluation in alfalfa genotypes. Crop Breed Appl Biotechno 13:152–156
Nouraki A, Akhavan S, Rezaei Y (2017) Predicting the relative water content of sunflower plant using RGB reflectance. Researcher 9:1–5
Perez-Sanz F, Navarro PJ, Egea-Cortines M (2017) Plant phenomics: an overview of image acquisition technologies and image data analysis algorithms. GigaScience 6:1–18
Pound MP, Burgess AJ, Wilson MH, Atkinson JA, Griffiths M, Jackson AS, Bulat A, Tzimiropoulos G, Wells DM, Murchie EH, Pridmore TP, French AP (2016) Deep machine learning provides state-of-the-art performance in image-based plant phenotyping. Gigascience 6:1–10
Rayagopal R, Ulvskov P, Marcusen J, Andersen JM, Allerup S (1987) Hormonal and phenolic changes accompanying and following UV-C induced stress in Spathiphyllum leaves. J Plant Physiol 130:291–306
Sarabi B, Fresneau C, Ghaderi N, Bolandnazar S, Streb P, Badeck F-W, Citerne S, Tangama M, David A, Ghashghaie J (2019) Stomatal and non-stomatal limitations are responsible in down-regulation of photosynthesis in melon plants grown under the saline condition: application of carbon isotope discrimination as a reliable proxy. Plant Physiol Biochem 141:1–19
Seif M, Aliniaeifard S, Arab M, Mehrjerdi MZ, Shomali A, Fanourakis D, Li T, Woltering E (2021) Monochromatic red light during plant growth decreases the size and improves the functionality of stomata in chrysanthemum. Funct Plant Biol. https://doi.org/10.1071/FP20280
Seroczyńska A, Korzeniewska A, Sztangret-Wiśniewska J, Niemirowicz-Szczytt K, Gajewski M (2006) Relationship between carotenoids content and flower or fruit flesh colour of winter squash (Cucurbita máxima). Folia Hortic 18:51–61
Singh A, Ganapathysubramanian B, Singh AK, Sarkar S (2015) Machine learning for highthroughput stress phenotyping in plants. Trends Plant Sci 21:110–112
Smart RE, Bingham GE (1974) Rapid estimates of relative water content. Plant Physiol 53:258–260
Sørensen HK, Fanourakis D, Tsaniklidis G, Bouranis D, Rezaei Nejad A, Ottosen CO (2020) Using artificial lighting based on electricity price without a negative impact on growth, visual quality or stomatal closing response in Passiflora. Scientia Hortic 267:109354
Turner NC (1981) Techniques and experimental approaches for the measurement of plant water status. Plant Soil 58:339–366
Wang Z, Li H, Zhu Y, Xu TF (2016) Review of plant identification based on image processing. Arch Comput Methods Eng 24:637–654
Zakaluk R, Ranjan R (2008) Predicting the leaf water potential of potato plants using RGB reflectance. Can Biosyste Eng 50:7.1-7.12
Zhao ZQ, Ma LH, Cheung Y-ming WuX, Tang Y, Chen CLP (2015) ApLeaf: an efficient android-based plant leaf identification system. Neurocomputing 151:1112–1119
Acknowledgements
This research was financed by grants from the Lorestan University (Iran). We thank the laboratory staff for their contributions, continued diligence, and dedication to their craft. The authors also wish to express their gratitude to Dr Amy Kaleita for her constructive recommendations and invaluable assistance. The valuable comments of the editor and two anonymous reviewers are greatly acknowledged.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by B. Zheng.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Taheri-Garavand, A., Rezaei Nejad, A., Fanourakis, D. et al. Employment of artificial neural networks for non-invasive estimation of leaf water status using color features: a case study in Spathiphyllum wallisii. Acta Physiol Plant 43, 78 (2021). https://doi.org/10.1007/s11738-021-03244-y
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11738-021-03244-y