AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Plant Phenomics Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access

Noninvasive Detection of Salt Stress in Cotton Seedlings by Combining Multicolor Fluorescence–Multispectral Reflectance Imaging with EfficientNet-OB2

Jiayi Li1,2,†, Haiyan Zeng1,2,†, Chenxin Huang1, Libin Wu1,2, Jie Ma1, Beibei Zhou3, Dapeng Ye1,2( ), Haiyong Weng1,2( )
College of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou 350002, China
Fujian Key Laboratory of Agricultural Information Sensoring Technology, College of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou, Fujian 350002, China
State Key Laboratory of Eco-hydraulics in Northwest Arid Region of China, Xi’an University of Technology, Xi’an 710048, Shaanxi, China

†These authors contributed equally to this work.

Show Author Information

Abstract

Salt stress is considered one of the primary threats to cotton production. Although cotton is found to have reasonable salt tolerance, it is sensitive to salt stress during the seedling stage. This research aimed to propose an effective method for rapidly detecting salt stress of cotton seedlings using multicolor fluorescence–multispectral reflectance imaging coupled with deep learning. A prototyping platform that can obtain multicolor fluorescence and multispectral reflectance images synchronously was developed to get different characteristics of each cotton seedling. The experiments revealed that salt stress harmed cotton seedlings with an increase in malondialdehyde and a decrease in chlorophyll content, superoxide dismutase, and catalase after 17 days of salt stress. The Relief algorithm and principal component analysis were introduced to reduce data dimension with the first 9 principal component images (PC1 to PC9) accounting for 95.2% of the original variations. An optimized EfficientNet-B2 (EfficientNet-OB2), purposely used for a fixed resource budget, was established to detect salt stress by optimizing a proportional number of convolution kernels assigned to the first convolution according to the corresponding contributions of PC1 to PC9 images. EfficientNet-OB2 achieved an accuracy of 84.80%, 91.18%, and 95.10% for 5, 10, and 17 days of salt stress, respectively, which outperformed EfficientNet-B2 and EfficientNet-OB4 with higher training speed and fewer parameters. The results demonstrate the potential of combining multicolor fluorescence–multispectral reflectance imaging with the deep learning model EfficientNet-OB2 for salt stress detection of cotton at the seedling stage, which can be further deployed in mobile platforms for high-throughput screening in the field.

References

1
Noreen S, Ahmad S, Fatima Z, Zakir I, Iqbal P, Nahar K, Hasanuzzaman M. Abiotic stresses mediated changes in morphophysiology of cotton plant. In: Ahmad S, Hasanuzzaman M, editors. Cotton production and uses: Agronomy, crop protection, and postharvest technologies. Singapore: Springer; 2020. p. 341–366.
Crossref
2

Xu P, Guo Q, Meng S, Zhang X, Xu Z, Guo W, Shen X. Genome-wide association analysis reveals genetic variations and candidate genes associated with salt tolerance related traits in Gossypium hirsutum. BMC Genomics. 2021;22(1):26.
Crossref Google Scholar
3

Jamil A, Riaz S, Ashraf M, Foolad MR. Gene expression profiling of plants under salt stress. CRC Rev Plant Sci. 2011;30(5):435–458.
Crossref Google Scholar
4

Munns R, Gilliham M. Salinity tolerance of crops—What is the cost? New Phytol. 2015;208(3):668–673.
Crossref Google Scholar
5

Zhang L, Zhang G, Wang Y, Zhou Z, Meng Y, Chen B. Effect of soil salinity on physiological characteristics of functional leaves of cotton plants. J Plant Res. 2013;126(2):293–304.
Crossref Google Scholar
6

Ma X, Dong H, Li W. Genetic improvement of cotton tolerance to salinity stress. Afr J Agric Res. 2011;6(33):6798–6803.
Crossref Google Scholar
7

Sun J, Li S, Guo H, Hou Z. Ion homeostasis and Na+ transport-related gene expression in two cotton (Gossypium hirsutum L.) varieties under saline, alkaline and saline-alkaline stresses. PLOS ONE. 2021;16(8):Article e0256000.
Crossref Google Scholar
8

Abdelraheem A, Esmaeili N, O’Connell M, Zhang J. Progress and perspective on drought and salt stress tolerance in cotton. Ind Crops Prod. 2019;130:118–129.
Crossref Google Scholar
9

Jiang X-H, Gao Y, Wang G-S, Zhou S, Zhang J-P. Examining effects of salt stress on leaf photosynthesis of cotton based on the FvCB model. J Appl Ecol. 2020;31:1653–1659.
Google Scholar
10

Shen J, Chen D, Zhang X, Song L, Dong J, Xu Q, Hu M, Cheng Y, Shen F, Wang W. Mitigation of salt stress response in upland cotton (Gossypium hirsutum) by exogenous melatonin. J Plant Res. 2021;134(4):857–871.
Crossref Google Scholar
11

Abuduwaili J, Zhaoyong Z, Qing JF, Wei LD. The disastrous effects of salt dust deposition on cotton leaf photosynthesis and the cell physiological properties in the Ebinur Basin in Northwest China. PLOS ONE. 2015;10(5):Article e0124546.
Crossref Google Scholar
12

Guo H, Huang Z, Li M, Hou Z. Growth, ionic homeostasis, and physiological responses of cotton under different salt and alkali stresses. Sci Rep. 2020;10(1):Article 21844.
Crossref Google Scholar
13

Peng Z, He S, Sun J, Pan Z, Gong W, Lu Y, Du X. Na+ compartmentalization related to salinity stress tolerance in upland cotton (Gossypium hirsutum) seedlings. Sci Rep. 2016;6:Article 34548.
Crossref Google Scholar
14

Cao J-F, Huang J-Q, Liu X, Huang C-C, Zheng Z-S, Zhang X-F, Shangguan X-X, Wang L-J, Zhang Y-G, Wendel JF, et al. Genome-wide characterization of the GRF family and their roles in response to salt stress in Gossypium. BMC Genomics. 2020;21(1):575.
Crossref Google Scholar
15

Lu W, Chu X, Li Y, Wang C, Guo X. Cotton GhMKK1 induces the tolerance of salt and drought stress, and mediates defence responses to pathogen infection in transgenic Nicotiana benthamiana. PLOS ONE. 2013;8(7):Article e68503.
Crossref Google Scholar
16

Zhou B, Liang C, Chen X, Ye S, Peng Y, Yang L, Duan M, Wang X. Magnetically-treated brackish water affects soil water-salt distribution and the growth of cotton with film mulch drip irrigation in Xinjiang, China. Agric Water Manag. 2022;263:Article 107487.
Crossref Google Scholar
17

Zhou B, Yang L, Chen X, Ye S, Peng Y, Liang C. Effect of magnetic water irrigation on the improvement of salinized soil and cotton growth in Xinjiang. Agric Water Manag. 2021;248:Article 106784.
Crossref Google Scholar
18

Negrão S, Schmöckel SM, Tester M. Evaluating physiological responses of plants to salinity stress. Ann Bot. 2017;119(1):1–11.
Crossref Google Scholar
19

Mahlein A-K, Kuska MT, Behmann J, Polder G, Walter A. Hyperspectral sensors and imaging technologies in phytopathology: State of the art. Annu Rev Phytopathol. 2018;56:535–558.
Crossref Google Scholar
20

Sun D, Robbins K, Morales N, Shu Q, Cen H. Advances in optical phenotyping of cereal crops. Trends Plant Sci. 2022;27(2):191–208.
Crossref Google Scholar
21

Ollinger SV. Sources of variability in canopy reflectance and the convergent properties of plants. New Phytol. 2011;189(2):375–394.
Crossref Google Scholar
22

Xie WH, Ma SJ, Qi L, Zhang ZH, Bai XF. The mitigating effects of Na+ accumulation on the drought-induced damage to photosynthetic apparatus in cotton seedlings. Acta Ecol Sin. 2015;35(19):6549–6556.
Crossref Google Scholar
23

Calzone A, Cotrozzi L, Lorenzini G, Nali C, Pellegrini E. Hyperspectral detection and monitoring of salt stress in pomegranate cultivars. Agronomy. 2021;11(6):1038.
Crossref Google Scholar
24

Lazarević B, Kontek M, Carović-Stanko K, Clifton-Brown J, Al Hassan M, Trindade LM, Jurišić V. Multispectral image analysis detects differences in drought responses in novel seeded Miscanthus sinensis hybrids. GCB Bioenergy. 2022;14:1219–1234.
Crossref Google Scholar
25

Zushi K, Matsuzoe N. Using of chlorophyll a fluorescence OJIP transients for sensing salt stress in the leaves and fruits of tomato. Sci Hortic. 2017;219:216–221.
Crossref Google Scholar
26

Horaczek T, Dąbrowski P, Kalaji HM, Baczewska-Dąbrowska AH, Pietkiewicz S, Stępień W, Gozdowski D. JIP-test as a tool for early detection of the macronutrients deficiency in Miscanthus plants. Photosynthetica. 2020;58(S1):322–332.
Crossref Google Scholar
27

Tian Y, Xie L, Wu M, Yang B, Ishimwe C, Ye D, Weng H. Multicolor fluorescence imaging for the early detection of salt stress in Arabidopsis. Agronomy. 2021;11(12):2577.
Crossref Google Scholar
28

Yao J, Sun D, Cen H, Xu H, Weng H, Yuan F, He Y. Phenotyping of Arabidopsis drought stress response using kinetic chlorophyll fluorescence and multicolor fluorescence imaging. Front Plant Sci. 2018;9:603.
Crossref Google Scholar
29

Silva EA, Gouveia-Neto AS, Oliveira RA, Moura DS, Cunha PC, Costa EB, Câmara TJR, Willadino LG. Water deficit and salt stress diagnosis through LED induced chlorophyll fluorescence analysis in Jatropha curcas L. J Fluoresc. 2012;22(2):623–630.
Crossref Google Scholar
30

Kumar P, Eriksen RL, Simko I, Mou B. Molecular mapping of water-stress responsive genomic loci in lettuce (Lactuca spp.) using kinetics chlorophyll fluorescence, hyperspectral imaging and machine learning. Front Genet. 2021;12:Article 634554.
Crossref Google Scholar
31

Houle D. Numbering the hairs on our heads: The shared challenge and promise of phenomics. Proc Natl Acad Sci U S A. 2010;107(Suppl 1):1793–1799.
Crossref Google Scholar
32

Mishra KB, Mishra A, Klem K, Govindjee. Plant phenotyping: A perspective. Indian J Plant Physiol. 2016;21(4):514–527.
Crossref Google Scholar
33

Homolová L, Malenovský Z, Clevers JGPW, García-Santos G, Schaepman ME. Review of optical-based remote sensing for plant trait mapping. Ecol Complex. 2013;15:1–16.
Crossref Google Scholar
34

Li L, Zhang Q, Huang D. A review of imaging techniques for plant phenotyping. Sensors. 2014;14(11):20078–20111.
Crossref Google Scholar
35

Pineda M, Gáspár L, Morales F, Szigeti Z, Barón M. Multicolor fluorescence imaging of leaves—A useful tool for visualizing systemic viral infections in plants. Photochem Photobiol. 2008;84:1048–1060.
Crossref Google Scholar
36

Behmann J, Steinrücken J, Plümer L. Detection of early plant stress responses in hyperspectral images. ISPRS J Photogramm Remote Sens. 2014;93:98–111.
Crossref Google Scholar
37

Buschmann C, Lichtenthaler HK. Principles and characteristics of multi-colour fluorescence imaging of plants. J Plant Physiol. 1998;152(2–3):297–314.
Crossref Google Scholar
38

Merzlyak MN, Gitelson AA, Chivkunova OB, Rakitin VY. Non-destructive optical detection of pigment changes during leaf senescence and fruit ripening. Physiol Plant. 1999;106:135–141.
Crossref Google Scholar
39
Rouse JW, Haas RH, Deering DW, Schell JA, Harlan JC. Monitoring the vernal advancement and retrogradation (green wave effect) of natural vegetation. NASA/GSFCT Type Ⅲ Final Report, 371. NASA; 1974.
40

Urbanowicz RJ, Meeker M, La Cava W, Olson RS, Moore JH. Relief-based feature selection: Introduction and review. J Biomed Inform. 2018;85:189–203.
Crossref Google Scholar
41

Bilgili A, Bilgili AV, Tenekeci ME, Karadağ K. Spectral characterization and classification of two different crown root rot and vascular wilt diseases (Fusarium oxysporum f. sp. radicis lycopersici and Fusarium solani) in tomato plants using different machine learning algorithms. Eur J Plant Pathol. 2023;165:271–286.
Crossref Google Scholar
42

Osco LP, Ramos APM, Moriya ÉAS, Bavaresco LG, de Lima BC, Estrabis N, Pereira DR, Creste JE, Júnior JM, Gonçalves WN, et al. Modeling hyperspectral response of water-stress induced lettuce plants using artificial neural networks. Remote Sens. 2019;11(23):2797.
Crossref Google Scholar
43

Koutanaei FN, Sajedi H, Khanbabaei M. A hybrid data mining model of feature selection algorithms and ensemble learning classifiers for credit scoring. J Retail Consum Serv. 2015;27:11–23.
Crossref Google Scholar
44

Zhang S, Cheng D, Deng Z, Zong M, Deng X. A novel kNN algorithm with data-driven k parameter computation. Pattern Recogn Lett. 2018;109:44–54.
Crossref Google Scholar
45

Hasanlou M, Samadzadegan F, Homayouni S. SVM-based hyperspectral image classification using intrinsic dimension. Arab J Geosci. 2015;8:477–487.
Crossref Google Scholar
46

Breiman L. Random forests. Mach Learn. 2001;45:5–32.
Crossref Google Scholar
47
Ramesh S, Hebbar R, Niveditha M, Pooja R, Prasad Bhat N, Shashank N, Vinod PV. Plant disease detection using machine learning. In: 2018 International Conference on Design Innovations for 3Cs Compute Communicate Control (ICDI3C). IEEE: 2018. p. 41–45.
Crossref
48

Singh A, Ganapathysubramanian B, Singh AK, Sarkar S. Machine learning for high-throughput stress phenotyping in plants. Trends Plant Sci. 2016;21(2):110–124.
Crossref Google Scholar
49

Ubbens JR, Stavness I. Corrigendum: Deep plant phenomics: A deep learning platform for complex plant phenotyping tasks. Front Plant Sci. 2018;8:2245.
Crossref Google Scholar
50
Tan M, Le Q. EfficientNet: Rethinking model scaling for convolutional neural networks. In: Proceedings of the 36th International Conference on Machine Learning, PMLR. 2019. p. 6105–6114.
51

Azarmi F, Mozafari V, Abbaszadeh Dahaji P, Hamidpour M. Biochemical, physiological and antioxidant enzymatic activity responses of pistachio seedlings treated with plant growth promoting rhizobacteria and Zn to salinity stress. Acta Physiol Plant. 2016;38:Article 21.
Crossref Google Scholar
52

Guo H, Hu Z, Zhang H, Min W, Hou Z. Comparative effects of salt and alkali stress on antioxidant system in cotton (Gossypium hirsutum L.) leaves. Open Chemistry. 2019;1352–1360.
Crossref Google Scholar
53

Zafar MM, Shakeel A, Haroon M, Manan A, Sahar A, Shoukat A, Mo H, Farooq MA, Ren M. Effects of salinity stress on some growth, physiological, and biochemical parameters in cotton (Gossypium hirsutum L.) germplasm. J Nat Fibers. 2022;19(14):8854–8886.
Crossref Google Scholar
54

Munawar W, Hameed A, Khan MKR. Differential morphophysiological and biochemical responses of cotton genotypes under various salinity stress levels during early growth stage. Front Plant Sci. 2021;12:Article 622309.
Crossref Google Scholar
55

Kent LM, Läuchli A. Germination and seedling growth of cotton: Salinity-calcium interactions. Plant Cell Environ. 1985;8(2):155–159.
Crossref Google Scholar
56

Zhang L, Zhou Z, Zhang G, Meng Y, Chen B, Wang Y. Monitoring the leaf water content and specific leaf weight of cotton (Gossypium hirsutum L.) in saline soil using leaf spectral reflectance. Eur J Agron. 2012;41:103–117.
Crossref Google Scholar
57

Anderegg J, Yu K, Aasen H, Walter A, Liebisch F, Hund A. Spectral vegetation indices to track senescence dynamics in diverse wheat germplasm. Front Plant Sci. 2020;10:Article 1749.
Crossref Google Scholar
58

Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D. Grad-CAM: Visual explanations from deep networks via gradient-based localization. Int J Comp Vis. 2020;128:336–359.
Crossref Google Scholar
Plant Phenomics
Volume 5,
2023
Article number: 0125
DOI: 10.34133/plantphenomics.0125
Cite this article:
Li J, Zeng H, Huang C, et al. Noninvasive Detection of Salt Stress in Cotton Seedlings by Combining Multicolor Fluorescence–Multispectral Reflectance Imaging with EfficientNet-OB2. Plant Phenomics, 2023, 5: 0125. https://doi.org/10.34133/plantphenomics.0125

140

Views

5

Crossref

5

Web of Science

6

Scopus

0

CSCD

Altmetrics
Received: 03 July 2023
Accepted: 18 November 2023
Published: 08 December 2023
© 2023 Jiayi Li et al. Exclusive licensee Nanjing Agricultural University. No claim to original U.S. Government Works.

Distributed under a Creative Commons Attribution License 4.0 (CC BY 4.0).
Return