The usefulness of approaches combining fluorescence spectroscopic data and machine learning algorithms to distinguish between different hybrid varieties of tomatoes grown in a greenhouse

Vanya Slavova; Ewa Ropelewska; Muhammet Fatih Aslan; Kadir Sabanci; Todorka L. Dimitrova

Vanya Slavova, Ewa Ropelewska, Muhammet Fatih Aslan, Kadir Sabanci, Todorka L. Dimitrova

Abstract: The objective of this study was to discriminate different hybrid varieties of tomatoes, grown in a greenhouse, based on fluorescence spectroscopic data using models, developed with the use of machine learning algorithms belonging to groups of Meta, Trees, Bayes, Functions, Lazy, and Rules.
The combination of the fluorescence spectroscopic data and various machine learning algorithms is a great novelty in distinguishing the tomatoes grown in a greenhouse. The discriminant analysis including selected spectroscopic data was performed for all three samples and pairs of samples. In the case of discrimination of three samples, an average accuracy of 100%, TP (True Positive) Rate, Precision, MCC (Matthews Correlation Coefficient), ROC (Receiver Operating Characteristic) Area, PRC (Precision-Recall) Area, and F-Measure equal to 1.000, and FP (False Positive) Rate of 0.000 was determined for the Multi Class Classifier from the group of Meta, Bayes Net from the group of Bayes and Logistic from the group of Functions.
These results proved the complete differentiation of the samples in terms of selected spectroscopic data. Completely correct discriminations were also observed in the case of comparing some pairs of samples for the Multi Class Classifier, Bayes Net, Logistic, and kStar (Lazy) machine learning algorithms. The developed procedures can be used in practice to distinguish tomato samples in a non-destructive and objective way.

Keywords: discrimination; fluorescence spectroscopy; performance metrics; Tomato fruit

Citation: Slavova, V., Ropelewska, E., Aslan, M. F., Sabanci, K. & Dimitrova, T. L. (2026). The usefulness of approaches combining fluorescence spectroscopic data and machine learning algorithms to distinguish between different hybrid varieties of tomatoes grown in a greenhouse. Bulg. J. Agric. Sci., 32(1), 219–226

References: (click to open/close)

Beckles, D. M. (2012). Factors affecting the postharvest soluble solids and sugar content of tomato (Solanum lycopersicum L.) fruit. Postharvest Biology Technology, 63(1), 129 - 140.
Bouckaert, R. R., Frank, E., Hall, M., Kirkby, R., Reutemann, P., Seewald, A. & Scuse, D. (2016). WEKA manual for version 3-9-1. University of Waikato, Hamilton, New Zealand.
Bureau, S., Boas, A. A. d. C. V., Giovinazzo, R., Jaillais, B. & Page, D. (2020). Toward the implementation of mid-infrared spectroscopy along the processing chain to improve quality of the tomato based products. LWT, 130, 109518.
Csendes, B. & Mucsi, L. (2016). Identification and spectral evaluation of agricultural crops on hyperspectral airborne data. Journal of Environmental Geography, 9(3-4), 49 - 53.
de Brito, A. A., Campos, F., dos Reis Nascimento, A., de Carvalho Corrêa, G., da Silva, F. A., de Almeida Teixeira, G. H. & Júnior, L. C. C. (2021). Determination of soluble solid content in market tomatoes using near-infrared spectroscopy. Food Control, 126, 108068.
De Clercq, M., Vats, A. & Biel, A. (2018). Agriculture 4.0: The future of farming technology. Proceedings of the World Government Summit, Dubai, UAE, 11 - 13.
de Oliveira, A. N., Bolognini, S. R. F., Navarro, L. C., Delafiori, J., Sales, G. M., de Oliveira, D. N. & Catharino, R. R. (2023). Tomato classification using mass spectrometry-machine learning technique: A food safety-enhancing platform. Food Chemistry, 398, 133870.
Eibe, F., Hall, M. A. & Witten, I. H. (2016). The WEKA workbench. Online appendix for data mining: practical machine learning tools and techniques. In: Morgan Kaufmann: Morgan Kaufmann Publishers, 24 – 93.
El-Sitiny, M. F., Omar, H. M., El-Shehawi, A. M., Elseehy, M. M., El-Tahan, A. M., El-Saadony, M. T. & Selem, G. S. (2022). Biochemical and molecular diagnosis of different tomato cultivars susceptible and resistant to Tuta absoluta (Meyrick) infestation. Saudi Journal of Biological Sciences, 29(4), 2904 - 2910.
Gerszberg, A., Hnatuszko-Konka, K., Kowalczyk, T. & Kononowicz, A. K. (2015). Tomato (Solanum lycopersicum L.) in the service of biotechnology. Plant Cell., Tissue Organ. Culture, 120(3), 881 - 902.
Huang, Y., Lu, R. & Chen, K. (2018a). Assessment of tomato soluble solids content and pH by spatially-resolved and conventional Vis/NIR spectroscopy. Journal of Food Engineering, 236, 19 - 28.
Huang, Y., Lu, R. & Chen, K. (2018b). Prediction of firmness parameters of tomatoes by portable visible and near-infrared spectroscopy. Journal of Food Engineering, 222, 185 - 198.
Huang, Y., Lu, R., Xu, Y. & Chen, K. (2018). Prediction of tomato firmness using spatially-resolved spectroscopy. Postharvest Biology and Technology, 140, 18 - 26.
Huynh, D. P., Van Vo, M., Van Dang, N. & Truong, T. Q. (2021). Classifying maturity of cherry tomatoes using Deep Transfer Learning techniques. In: IOP Conference Series: Materials Science and Engineering, 1109, 012058. IOP Publishing.
Kaur, S., Girdhar, A. & Gill, J. (2018). Computer vision-based tomato grading and sorting. In: Springer, Advances in data and information sciences, 75 - 84.
Kwak, G.-H. & Park, N.-W. (2019). Impact of texture information on crop classification with machine learning and UAV images. Applied Sciences, 9(4), 643.
Li, X., Tsuta, M., Hayakawa, F., Nakano, Y., Kazami, Y. & Ikehata, A. (2021). Estimating the sensory qualities of tomatoes using visible and near-infrared spectroscopy and interpretation based on gas chromatography–mass spectrometry metabolomics. Food Chemistry, 343, 128470.
Nassiri, S. M., Tahavoor, A. & Jafari, A. (2021). Fuzzy logic classification of mature tomatoes based on physical properties fusion. Information Processing in Agriculture, 9(4), 547 - 555.
Pavithra, V., Pounroja, R. & Bama, B. S. (2015). Machine vision based automatic sorting of cherry tomatoes. In: 2015 2nd International Conference on Electronics and Communication Systems (ICECS), 271 - 275, IEEE.
Ropelewska, E. (2022). Distinguishing lacto-fermented and fresh carrot slice images using the Multilayer Perceptron neural network and other machine learning algorithms from the groups of Functions, Meta, Trees, Lazy, Bayes and Rules. European Food Research and Technology, 1-9.
Ropelewska, E. & Piecko, J. (2022). Discrimination of tomato seeds belonging to different cultivars using machine learning. European Food Research Technology, 248(3), 685 - 705.
Ropelewska, E., Sabanci, K. & Aslan, M. F. (2022). Authentication of tomato (Solanum lycopersicum L.) cultivars using discriminative models based on texture parameters of flesh and skin images. European Food Research Technology, 1-18.
Ropelewska, E., Slavova, V., Sabanci, K., Aslan, M. F., Cai, X. & Genova, S. (2022a). Discrimination of onion subjected to drought and normal watering mode based on fluorescence spectroscopic data. Computers and Electronics in Agriculture, 196, 106916.
Ropelewska, E., Slavova, V., Sabanci, K., Aslan, M. F., Cai, X. & Genova, S. (2022b). Discrimination of onion subjected to drought and normal watering mode based on fluorescence spectroscopic data. Computers Electronics in Agriculture, 196, 106916.
Ropelewska, E. & Szwejda‐Grzybowska, J. (2021). A comparative analysis of the discrimination of pepper (Capsicum annuum L.) based on the cross‐section and seed textures determined using image processing. Journal of Food Process Engineering, 44(6), e13694.
Senesi, G. S., De Pascale, O., Marangoni, B. S., Caires, A. R. L., Nicolodelli, G., Pantaleo, V. & Leonetti, P. (2022). Chlorophyll fluorescence imaging (CFI) and laser-induced breakdown spectroscopy (LIBS) applied to investigate tomato plants infected by the root knot nematode (RKN) Meloidogyne incognita and tobacco plants infected by Cymbidium ringspot virus. In: Photonics, 9, 627. MDPI.
Sheng, R., Cheng, W., Li, H., Ali, S., Agyekum, A. A. & Chen, Q. (2019). Model development for soluble solids and lycopene contents of cherry tomato at different temperatures using near-infrared spectroscopy. Postharvest Biology and Technology, 156, 110952.
Trebolazabala, J., Maguregui, M., Morillas, H., de Diego, A. & Madariaga, J. M. (2017). Portable Raman spectroscopy for an in-situ monitoring the ripening of tomato (Solanum lycopersicum) fruits. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 180, 138 - 143.
Wan, P., Toudeshki, A., Tan, H. & Ehsani, R. (2018). A methodology for fresh tomato maturity detection using computer vision. Computers electronics in agriculture, 146, 43 - 50.
Witten, I. H., Frank, E., Hall, M. A. & Pal, C. J. (2005). Practical machine learning tools and techniques. In: Data Mining, 2(4), 403 - 413.
Zhong, L., Gong, P. & Biging, G. S. (2014). Efficient corn and soybean mapping with temporal extendability: A multi-year experiment using Landsat imagery. Remote Sensing of Environment, 140, 1 - 13.
Zhou, X., Zhao, C., Sun, J., Cao, Y., Yao, K. & Xu, M. (2023). A deep learning method for predicting lead content in oilseed rape leaves using fluorescence hyperspectral imaging. Food Chemistry, 409, 135251.

Date published: 2026-02-25

Download full text