Derin Öğrenme ve Çeşitli Işık Spektrumları Kullanılarak Domates Bitkisi Verimliliğinin Artırılması

Öz

Dünya nüfusu her geçen gün artmakta, buna karşın tarım alanları azalmaktadır. Bu nedenle tarımsal ürünlerde verimliliğin artırılması büyük önem taşımaktadır. Işık, bitki büyümesi ve gelişimini önemli ölçüde etkileyen kritik bir faktördür. Bitkiler, cins ve türlerine bağlı olarak farklı ışık yoğunluklarına uyum sağlamıştır. Işık yoğunluğu değiştiğinde bitkilerin büyüme, gelişme ve üreme fonksiyonları etkilenmektedir. Domates bitkisinin verimliliği, fide, çiçeklenme ve ürün aşamalarında farklı ışık dalga boylarına göre değişiklik göstermektedir. Bu çalışma, derin öğrenme ve farklı ışık dalga boylarını kullanarak domates bitkilerinin verimliliğini artırmayı amaçlamaktadır. Domates bitkisinin fide, çiçeklenme ve ürün aşamalarını belirlemek amacıyla bir sınıflandırma çalışması yapılmıştır. Sınıflandırma, derin öğrenmede kullanılan dört farklı mimari ile gerçekleştirilmiştir. En yüksek doğruluk oranı %99,85 ile VGGNet mimarisinde elde edilmiştir. Geliştirilen gerçek zamanlı sistem ile domates bitkisinin ışık dalga boyları, derin öğrenme sonuçlarına göre otomatik olarak ayarlanmıştır. Araştırma sonucunda, domates bitkilerinde %4,10 oranında daha erken ürün elde edilmiş ve verimde %9,85 artış sağlanmıştır. Elde edilen bulgulara göre, derin öğrenme ve farklı ışık yoğunluklarının kullanımı domates bitkilerinin verimliliğini etkili bir şekilde artırmıştır.

Anahtar Kelimeler

• Derin öğrenme
• VGGNet
• verimlilik
• evrişimli sinir ağı
• ışığın farklı dalga boyları.

Enhancing Tomato Plant Productivity Using Deep Learning and Varied Light Spectra

Öz

The world population is increasing daily, while agricultural lands are decreasing. Therefore, increasing productivity in agricultural products is crucial. Light is a critical factor that significantly affects plant growth and development. Plants have adapted to different light intensities depending on their genus and species. When the light intensity changes, the growth, development, and reproductive functions of these plants are affected. The productivity of tomato plants varies with different light wavelengths during the seedling, flowering, and crop stages. This study aims to increase the productivity of tomato plants by using deep learning and different light wavelengths. A classification study was conducted to determine the seedling, flowering, and yield stages of the tomato plant. The classification was performed using four different deep learning architectures. The highest accuracy rate of 99.85% was achieved with the VGGNet architecture. With the real-time system developed, the light wavelengths for the tomato plant were automatically adjusted according to the deep learning results. As a result of the research, tomato plants yielded crops 4.10% earlier and achieved a 9.85% increase in yield. According to the findings, the use of deep learning and different light intensities effectively improved the productivity of tomato plants.

Anahtar Kelimeler

• Deep learning
• VGGNet
• productivity
• convolutional neural network
• different wavelengths of light.

Kaynakça

1. Kim T, Lee D.H, Kim K.C, Choi T, Yu J.M. Tomato maturity estimation using deep neural network. Appl Sci 2023; 13(1): 42. https://doi.org/10.3390/app13010412
2. Rodrigues C, Pinho J, Monteiro O, Can P. Lycopene be considered an effective protection against cardiovascular disease? Food Chem 2018; 245: 1148–1153. https://doi.org/10.1016/j.foodchem.2017.11.055
3. Tarek H, Aly H, Eisa S, Abul-Soud M. Optimized deep learning algorithms for tomato leaf disease detection with hardware deployment. Electronics 2022; 11(1): 140. https://doi.org/10.3390/electronics11010140
4. Liu W, Liu K, Chen D, Zhang Z, Li B, El-Mogy M.M, Tian S, Chen T. Solanum lycopersicum, a model plant for developmental biology, stress biology and food science. Foods 2022; 11(16): 1–15. https://doi.org/10.3390/foods11162402
5. Knapp S, Peralta I.E, Causse J.G.M, Mondher B, Mohamed Z. The tomato (Solanum lycopersicum L., Solanaceae) and its botanical relatives. The Tomato Genome. Springer, Berlin, Heidelberg; 2016. pp. 7–21. https://doi.org/10.1007/978-3-662-53389-5_2
6. Samarah N.H, Bany Hani M.M.I, Makhadmeh I.M. Effect of magnetic treatment of water or seeds on germination and productivity of tomato plants under salinity stress. Horticulturae 2022; 7(8): 220. https://doi.org/10.3390/horticulturae7080220
7. Hanyu H, Shoji K. Acceleration of growth in spinach by short-term exposure to red and blue light at the beginning and end of the daily dark period. Acta Hortic 2002; 580: 145–150. https://doi.org/10.17660/ActaHortic.2002.580.17
8. Liu J, van Iersel M.W. Photosynthetic physiology of blue, green, and red light: light intensity effects and underlying mechanisms. Front Plant Sci 2021; 12: 328. https://doi.org/10.3389/fpls.2021.619987

9. Naznin M.T, Lefsrud M, Gravel V, Azad M.O.K. Blue light added with red LEDs enhance growth characteristics, pigment content, and antioxidant capacity in lettuce, spinach, kale, basil, and sweet pepper in a controlled environment. Plants 2019; 8(4): 93. https://doi.org/10.3390/plants8040093
10. Zhen S, Haidekker M, van Iersel M.W. Far-red light enhances photochemical efficiency in a wavelength-dependent manner. Physiol Plant 2019; 167(1): 21–33. https://doi.org/10.1111/ppl.12834
11. Alrifai O, Hao X, Marcone M.F, Tsao R. Current Review of the Modulatory effects of LED lights on photosynthesis of secondary metabolites and future perspectives of microgreen vegetables. J Agric Food Chem 2019; 67(22): 6075–6090. https://doi.org/10.1021/acs.jafc.9b00819
12. Bartucca M.L, Guiducci M, Falcinelli B, Del Buono D, Benincasa P. Blue:red LED light proportion affects vegetative parameters, pigment content, and oxidative status of einkorn wheatgrass. J Agric Food Chem 2020; 68(33): 8757–8763. https://doi.org/10.1021/acs.jafc.0c03851
13. He R, Zhang Y.T, Song S.W, Su W, Hao Y.W, Liu H.C. UV-A and FR irradiation improves growth and nutritional properties of lettuce grown in an artificial light plant factory. Food Chem 2021; 345: 128768. https://doi.org/10.1016/j.foodchem.2020.128727
14. Li R, Huang W, Wang X, Liu X, Xu Z. Effects of yellow, green, and different blue spectra on growth of potato plantlets in vitro. HortScience 2018; 53: 541–546. https://doi.org/10.21273/HORTSCI12848-18
15. Bantis F, Smirnakou S, Ouzounis T, Koukounaras A, Ntagkas N, Radoglou K. Current status and recent achievements in horticulture with the use of LEDs. Sci Hortic 2018; 235: 437–451. https://doi.org/10.1016/j.scienta.2018.02.058
16. Wang C, Zhang B.B, Song L.P, Li P.Y, Hao Y, Zhang J.F. Assessment of different blanching strategies on quality and bioactive constituents of Toona sinensis. LWT–Food Sci Technol 2020; 130: 109647. https://doi.org/10.1016/j.lwt.2020.109549
17. Yang W.X, Cadwallader K.R, Liu Y.P, Huang M.Q, Sun B.G. Characterization of potent odorants in raw and cooked Toona sinensis by instrumental-sensory analysis. Food Chem 2019; 282: 153–163. https://doi.org/10.1016/j.foodchem.2018.12.112
18. Spaninks K, van Lieshout J, van Ieperen W, Offringa R. Regulation of early plant development by red and blue light: a comparative analysis between Arabidopsis thaliana and Solanum lycopersicum. Front Plant Sci 2020; 11: 599982. https://doi.org/10.3389/fpls.2020.599982
19. Vasilean I, Cîrciumaru A, Garnai M, Patrascu L. The influence of light wavelength on the germination performance of legumes. Ann Univ Dunarea de Jos Galati, Fascicle VI–Food Technol 2018; 42(2): 95–108.
20. Ratner K, Joshi N.C, Yadav D, Many Y, Kamara I, Esquira I, Achiam M, Gilad Z, Charuvi D. Application of LED-interlighting for improving yield of passive tunnel-grown bell pepper. In: Proc XI Int Symp Protected Cultivation in Mild Winter Climates and I Int Symp on Nettings; 2019. pp. 19–26.
21. Sanoubar R, Calone R, Noli E, Barbanti L. Data on seed germination using LED versus fluorescent light under growth chamber conditions. Data Brief 2018; 19: 594–600. https://doi.org/10.1016/j.dib.2018.05.040
22. Zhai X.T, Granvogl M. Elucidation of the impact of different drying methods on key odorants of Toona sinensis using the sensomics approach. J Agric Food Chem 2020; 68(29): 7697–7709. https://doi.org/10.1021/acs.jafc.0c02144
23. Zhang X.Y, Bian Z.H, Yuan X.X, Chen X, Lu C.G. A review on the effects of LED light on the nutrients of sprouts and microgreens. Trends Food Sci Technol 2020; 99: 203–216. https://doi.org/10.1016/j.tifs.2020.02.031
24. Arslan, C., and Kaya, V., “Classification of Plant Species from Microscopic Plant Cell Images Using Machine Learning Methods,” International Research Journal of Engineering and Technology (IRJET), vol. 11, no. 5, pp. 853–858, May 2024.
25. Pendhari, H., Virkar, R., and Jadhav, A., “A comparative study on algorithms for plant disease detection using transfer learning,” in Proc. 5th International Conference on Inventive Research in Computing Applications (ICIRCA), Aug. 2023, pp. 1–6, https://doi.org/10.1109/ICIRCA57980.2023.10220597
26. Paz M, Fisher P.R, Gómez C. Minimum light requirements for indoor gardening of lettuce. Urban Agric Reg Food Syst 2019; 4(1): 1–10. https://doi.org/10.2134/urbanag2019.03.0001
27. Swan B, Bugbee B. Increasing blue light from LEDs reduces growth of lettuce. SAE Tech Pap 2017; 23: 1–12.
28. Ouzounis T, Heuvelink E, Ji Y, Schouten H, Visser R, Marcelis L. Blue and red LED lighting effects on plant biomass, stomatal conductance, and metabolite content in nine tomato genotypes. Acta Hortic 2016; 1134: 251–258. https://doi.org/10.17660/ActaHortic.2016.1134.34
29. Kusuma P, Pattison P.M, Bugbee B. From physics to fixtures to food: current and potential LED efficacy. Hortic Res 2020; 7: 56. https://doi.org/10.1038/s41438-020-0283-7
30. Kong Y, Zheng Y. Phototropin involvement in blue-light-mediated stem elongation, flower initiation, and leaf expansion in Arabidopsis. Environ Exp Bot 2020; 171: 103967. https://doi.org/10.1016/j.envexpbot.2019.103967
31. Mishra S, Khurana J.P. Emerging roles and new paradigms in signaling mechanisms of plant cryptochromes. Crit Rev Plant Sci 2017; 36: 89–115. https://doi.org/10.1080/07352689.2017.1348725
32. Meng Q, Kelly N, Runkle E.S. Substituting green or far-red radiation for blue radiation induces shade avoidance and promotes growth in lettuce and kale. Environ Exp Bot 2019; 162: 383–391. https://doi.org/10.1016/j.envexpbot.2019.03.016
33. Mahnaz M, Bo-Sen W, Philip W.A, Sarah M, Mark L. Growth responses of tomato plants to different wavelength ratios of amber, red, and blue light. Sci Hortic 2023; 322: 112459. https://doi.org/10.1016/j.scienta.2023.112459
34. Ya-ting Z, Yu-qi Z, Qi-chang Y, Tao L. Overhead supplemental far-red light stimulates tomato growth under intra-canopy lighting with LEDs. J Integr Agric 2019; 18: 62–69. https://doi.org/10.1016/S2095-3119(18)62130-6
35. Nuri Ç, Can E. The effects of different wavelength LED lights on the development of green leafy plants. J Agric Mach Sci 2018; 14(2): 105–114.
36. Nezihe K, Meral İ, Ahmet T. Effects of LED lighting on plant development of tomato. Res J Agric Sci 2013; 6(2): 71–75.
37. Kumar A, Desai S.V, Balasubramanian V.N, Rajalakshmi P, Guo W, Naik B.B, Balram M, Desai U.B. Efficient maize tassel-detection method using UAV-based remote sensing. Remote Sens Appl 2021; 23: 100549. https://doi.org/10.1109/IGARSS39084.2020.9323266
38. Zhang Y, Li M, Ma X, Wu X, Wang Y. High-precision wheat head detection model based on one-stage network and GAN model. Front Plant Sci 2022; 13: 1730. https://doi.org/10.3389/fpls.2022.787852
39. Zang H, Wang Y, Ru L, Zhou M, Chen D, Zhao Q, Zhang J, Li G, Zheng G. Detection method of wheat spike improved YOLOv5s based on the attention mechanism. Front Plant Sci 2022; 13: 3577. https://doi.org/10.3389/fpls.2022.993244
40. Xiong H, Cao Z, Lu H, Madec S, Liu L, Shen C. TasselNetv2: in-field counting of wheat spikes with context-augmented local regression networks. Plant Methods 2019; 15: 1–14. https://doi.org/10.1186/s13007-019-0537-2
41. Li J, Li C, Fei S, Ma C, Chen W, Ding F, Wang Y, Li Y, Shi J, Xiao Z. Wheat ear recognition based on RetinaNet and transfer learning. Sensors 2021; 21: 4845. https://doi.org/10.3390/s21144845
42. Gong B, Ergu D, Cai Y, Ma B. Real-time detection for wheat head applying deep neural network. Sensors 2020; 21(1): 191. https://doi.org/10.3390/s21010191
43. Yang B, Gao Z, Gao Y, Zhu Y. Rapid detection and counting of wheat ears in the field using YOLOv4 with attention module. Agronomy 2021; 11(6): 1202. https://doi.org/10.3390/agronomy11061202
44. Qiu R, He Y, Zhang M. Automatic detection and counting of wheat spikelet using semi-automatic labeling and deep learning. Front Plant Sci 2022; 13: 1507. https://doi.org/10.3389/fpls.2022.872555
45. Ullah E, Ullah M, Sajjad M, Alaya Cheikh F. Deep learning-based wheat ears count in robot images for wheat phenotyping. Electron Imaging 2022; 34(6): IRIACV-264. https://doi.org/10.2352/EI.2022.34.6.IRIACV-264
46. Datta M.N, Rathi Y, Eliazer M. Wheat heads detection using deep learning algorithms. Ann Rom Soc Cell Biol 2021; 25: 5641–5654.
47. Madec S, Jin X, Lu H, De Solan B, Liu S, Duyme F, Heritier E, Baret F. Ear density estimation from high resolution RGB imagery using deep learning technique. Agric For Meteorol 2019; 264: 225–234. https://doi.org/10.1016/j.agrformet.2018.10.013
48. Gunturu S, Munir A, Ullah H, Welch S, Flippo D. A spatial AI-based agricultural robotic platform for wheat detection and collision avoidance. AI 2022; 3(3): 719–738. https://doi.org/10.3390/ai3030042
49. Wan L, Zhang G. Super-resolution reconstruction of unmanned aerial vehicle image based on deep learning. J Phys Conf Ser 2021; 1948: 012028. https://doi.org/10.1088/1742-6596/1948/1/012028