Farklı Sulama Seviyeleri Altında Yetiştirilen Dolmalık Biberin Yaprak Alanının Tahmininde Makine Öğrenmesi Yaklaşımlarının Karşılaştırılması

Abstract

Yaprak Alanı (LA), bitki gelişiminin izlenmesi ve bitki su tüketimi tahmini için oldukça önemli bir parametredir. Bu çalışmada, dolmalık biberin LA değerlerini farklı makine öğrenmesi (ML) modelleri ile tahmin etmek ve farklı sulama düzeylerinin model performansına etkisini değerlendirmek amaçlanmıştır. ML algoritmaları olarak Rastgele Orman (RF), eXtreme Gradient Boosting (XGBoost), En Yakın Komşular (KNN) ve Çok Katmanlı Algılayıcı (MLP) kullanılmıştır. Geniş bir veri seti elde edebilmek için, dört farklı sulama düzeyinde yetiştirilen dolmalık biberin yaprak alanı değerlerinden yararlanılmış ve bu kapsamda 2 yıllık bir tarla denemesi yürütülmüştür. Birinci yıl (2017) elde edilen yaprak alanı değerleri (6757 örnek) model eğitiminde, ikinci yıl (2018) elde edilen değerler ise (6128 örnek) test verisi olarak kullanılmıştır. Elde edilen sonuçlara göre, kullanılan ML algoritmaları arasında en yüksek performansı MLP (R²=0.90, RMSE=0.20 cm² ve MAE=0.15 cm²) sergilerken; en düşük performans XGBoost (R²=0.90, RMSE=0.20 cm² ve MAE=0.15 cm²) tarafından gösterilmiştir. Ayrıca, farklı sulama düzeylerinden elde edilen yaprak alanı değerleri ayrı ayrı değerlendirildiğinde benzer performansların elde edildiği görülmüştür. Sonuçlar, ML yöntemlerinin yaprak alanını geleneksel yöntemlere alternatif olarak hızlı ve doğru şekilde tahmin edebildiğini ortaya koymaktadır.

Keywords

• Yaprak Alan İndeksi
• Makine Öğrenmesi
• Dolmalık Biber
• Sulama
• MLP

Project Number

PYO.ZRT.1904.19.001

Estimating Bell Pepper Leaf Area: A Comparative Study of Machine Learning Models Under Varying Irrigation Levels

Abstract

Leaf Area (LA) is a critical parameter for crop monitoring and evapotranspiration estimation. This study aimed to estimate bell pepper LA values using different machine learning (ML) models and to evaluate the effect of different irrigation levels on model performance. Random Forest (RF), eXtreme Gradient Boosting (XGBoost), K-Nearest Neighbors (KNN) and Multi-Layer Perceptron (MLP) were used as ML algorithms. In order to obtain a large data set, the LA values of bell pepper grown at four different irrigation levels were used. In this context, a 2-year field trial was conducted. LA values from the first year (2017) were used in the training of the models (6757 samples), while LA values from the second year (2018) (6128 samples) were used as test data. According to the results of this study, MLP (R2=0.9, RMSE=0.2 cm2 and MAE=0.15 cm2) showed the highest performance among used ML algorithms, while XGBoost (R2=0.9, RMSE=0.2 cm2 and MAE=0.15 cm2) showed the lowest performance. Moreover, similar performances were obtained when LA values obtained from different irrigation levels were evaluated separately. The results show that ML methods can estimate LA quickly and accurately as an alternative to traditional methods.

Keywords

• Leaf Area Estimation
• Machine Learning
• Bell Pepper
• Irrigation
• MLP

Supporting Institution

Ondokuz Mayıs University

Project Number

PYO.ZRT.1904.19.001

Ethical Statement

This study was supported by the Ondokuz Mayıs University (PYO.ZRT.1904.19.001).

References

1. FAO, 2022. Value of Agricultural Production. https://www.fao.org/faostat/en/#data/qv.
2. Falodun, E., Obuo, O., 2024. Effect of plant spacing and fertilizer application on growth and yield of bell pepper (Capsicum annum) in experimental farm at Benin city, Edo state, Nigeria. Journal of Applied Sciences and Environmental Management, 28(3):929-935.
3. Novák, V., P. Šařec, O. Látal, 2024. Effect of Biostimulant, Manure Stabilizer, and Manure on Soil Physical Properties and Vegetation Status. Plants, 13(7):920.
4. Weraduwage, S.M., Chen, J., Anozie, F.C., Morales, A., Weise, S.E., Sharkey, T.D., 2015. The relationship between leaf area growth and biomass accumulation in Arabidopsis thaliana. Frontiers in Plant Science, 6, 167.
5. Cemek, B., Ünlükara, A., Kurunç, A., Küçüktopcu, E., 2020. Leaf area modeling of bell pepper (Capsicum annuum L.) grown under different stress conditions by soft computing approaches. Computers and Electronics in Agriculture, 174, 105514.
6. Demirsoy, H., 2009. Leaf area estimation in some species of fruit tree by using models as a non-destructive method. Fruits 64(1):45-51.
7. Öztürk, A., Cemek, B., Demirsoy, H., Küçüktopcu, E., 2019. Modelling of the leaf area for various pear cultivars using neuro computing approaches. Spanish Journal of Agricultural Research, 17(4):e0206-e0206.
8. Demirsoy, H., Küçüktopçu, E., Doğan, D.E., 2025. Novel Machine Learning Approaches for Accurate Leaf Area Estimation in Apples. Applied Fruit Science 67(2):1-10.

9. Kandiannan, K., Parthasarathy, U., Krishnamurthy, K.S., Thankamani, C.K., Srinivasan, V., 2009. Modeling individual leaf area of ginger (Zingiber officinale Roscoe) using leaf length and width. Scientia Horticulturae, 120(4):532-537.
10. Jordan, M.I., Mitchell, T.M., 2015. Machine learning: Trends, perspectives and prospects. Science 349(6245):255-260.
11. İrik, H.A., Ropelewska, E., Çetin, N., 2024. Using spectral vegetation indices and machine learning models for predicting the yield of sugar beet (Beta vulgaris L.) under different irrigation treatments. Computers and Electronics in Agriculture 221:109019.
12. Huang, F., Zhang, Y., Zhang, Y., Nourani, V., Li, Q., Li, L., Shangguan, W., 2023. Towards interpreting machine learning models for predicting soil moisture droughts. Environmental Research Letters, 18(7):074002.
13. Yıldırım, D., Küçüktopcu, E., Cemek, B., Simsek, H., 2023. Comparison of machine learning techniques and spatial distribution of daily reference evapotranspiration in Türkiye. Applied Water Science, 13(4):107.
14. Vazquez-Cruz, M.A., Luna-Rubio, R., Contreras-Medina, L.M., Torres-Pacheco, I., Guevara-Gonzalez, R.G., 2012. Estimating the response of tomato (Solanum lycopersicum) leaf area to changes in climate and salicylic acid applications by means of artificial neural networks. Biosystems Engineering, 112(4):319-327.
15. Sankar, V., Sakthivel, T., Karunakaran, G., Tripathi, P.C., 2017. Non-destructive estimation of leaf area of durian (Durio zibethinus)-An artificial neural network approach. Scientia Horticulturae, 219, 319-325.
16. Lee, J., Moon, T., Park, K.S., Son, J.E., 2018. Estimation of leaf area in Paprika based on leaf length, leaf width, and node number using regression models and an artificial neural network. Horticultural Science and Technology, 36(2):183-192.
17. Kıymaz, S., U. Karadavut, A. Ertek, 2018. A comparison of artificial neural networks and some nonlinear models of leaf area estimation of sugar beet at different nitrogen levels. Türk Tarım ve Doğa Bilimleri Dergisi, 5(3): p. 303-309.
18. Odabas, M., Ergun, E., Oner, F., 2013. Artificial neural network approach for the predication of the corn (Zea mays L.) leaf area. Bulgarian Journal of Agricultural Science, 19(4):766-769.
19. Aboukarima, A., Elsoury, H., Menyawi, M., 2015. Artificial neural network model for the prediction of the cotton crop leaf area. Int. J. Plant Soil Sci., 8:1-13.
20. Sabouri, H., Sajadi, S.J., Jafarzadeh, M.R., Rezaei, M., Ghaffari, S., Bakhtiari, S., 2021. Image processing and prediction of leaf area in cereals: A comparison of artificial neural networks, an adaptive neuro‐fuzzy inference system, and regression methods. Crop Science, 61(2):1013-1029.
21. Rahimikhoob, H., M. Delshad, R. Habibi, 2023. Leaf area estimation in lettuce: Comparison of artificial intelligence-based methods with image analysis technique. Measurement, 222:113636.
22. Amiri, M.J., Shabani, A., 2017. Application of an adaptive neural-based fuzzy inference system model for predicting leaf area. Communications in Soil Science and Plant Analysis 48(14):1669-1683.
23. Sabouri, A., Bakhshipour, A., Poornoori, M., Abouzari, A., 2022. Application of image processing and soft computing strategies for non-destructive estimation of plum leaf area. PlosOne, 17(7):e0271201.
24. Tunca, E., Köksal, E.S., 2022. Bell pepper yield estimation using time series unmanned air vehicle multispectral vegetation indexes and canopy volume. Journal of Applied Remote Sensing, 16(2):022202-022202.
25. Küçüktopçu, E., B. Cemek, H. Simsek, 2024. Comparative analysis of single and hybrid machine learning models for daily solar radiation. Energy Reports, 11:3256-3266.
26. Küçüktopcu, E., Cemek, E., Cemek, B., Simsek, H., 2023. Hybrid statistical and machine learning methods for daily evapotranspiration modeling. Sustainability, 15(7):5689.
27. Tunca, E., Köksal, E.S., Öztürk, E., Akay, H., Taner, S.Ç., 2024. Accurate leaf area index estimation in sorghum using high-resolution UAV data and machine learning models. Physics and Chemistry of the Earth, Parts A/B/C, 133, 103537.
28. Novák, V., Šařec, P., Křížová, K., Novák, P., Látal, O., 2021. Soil physical properties and crop status under cattle manure and Z’Fix in Haplic Chernozem. Plant, Soil & Environment, 67(7).
29. Zong, Y., Nian, Y., Zhang, C., Tang, X., Wang, L., Zhang, L., 2025. Hybrid Grid Search and Bayesian optimization-based random forest regression for predicting material compression pressure in manufacturing processes. Engineering Applications of Artificial Intelligence, 141, 109580.
30. Velarde, G., Sudhir, A., Deshmane, S., Deshmunkh, A., Sharma, K., Joshi, V., 2023. Evaluating XGBoost for balanced and imbalanced data: application to fraud detection. arXiv preprint arXiv:2303.15218.
31. Pan, Z., Pan, Y., Wang, Y., Wang, W., 2021. A new globally adaptive k-nearest neighbor classifier based on local mean optimization. Soft Computing-A Fusion of Foundations, Methodologies & Applications, 25(3).
32. Gong, C., Su, Z.G., Zhang, X., You, Y., 2023. Adaptive evidential K-NN classification: Integrating neighborhood search and feature weighting. Information Sciences, 648, 119620.
33. Padrón, R.A.R., Lopes, S.J., Swarowsky, A., Cerquera, R.R., Nogueira, C.U., Maffei, M., 2016. Non-destructive models to estimate leaf area on bell pepper crop. Ciência Rural, 46(11):1938-1944.
34. Moon, T., Kim, D., Kwon, S., Ahn, T.I., Son, J.E., 2022. Non-destructive monitoring of crop fresh weight and leaf area with a simple formula and a convolutional neural network. Sensors, 22(20):7728.
35. Mohammadi, V., Minaei, S., Mahdavian, A.R., Khoshtaghaza, M.H., Gouton, P., 2021. Estimation of leaf area in bell pepper plant using image processing techniques and artificial neural networks. In 2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA) pp:173-178, IEEE.
36. Cemek, B., A. Ünlükara, A. Kurunc, 2011. Nondestructive leaf-area estimation and validation for green pepper (Capsicum annuum L.) grown under different stress conditions. Photosynthetica, 49:98-106.
37. Giang, T.T.H., Ryoo, Y.J., 2024. Sweet Pepper Leaf Area Estimation Using Semantic 3D Point Clouds Based on Semantic Segmentation Neural Network. Agri Engineering, 6(1):645-656.