Advanced Predictive Analytics in Agriculture: Case Study on Wheat Kernel Weight

Year 2024, Volume: 14 Issue: 4, 1448 - 1460, 01.12.2024

Alperay Altıkat , Mehmet Hakkı Alma

https://doi.org/10.21597/jist.1526542

Abstract

This research, was aimed at modeling the thousand-grain weight of 13 different wheat varieties using five different input parameters. We used multiple linear regression (MLR), artificial neural networks (ANN), principal component analysis (PCA), and two different hybrid models consisting of PCA + MLR and PCA + ANN for this purpose. The MLR models were tested with various input configurations, demonstrating moderate explanatory power, with R² values ranging from 0.37 to 0.44. Increasing the number of independent variables increased prediction accuracy but also increased the risk of overlearning. ANN models showed significantly higher performance in prediction accuracy. The best performance was achieved in the ANN20 architecture with an R2 value of 0.866. In this architecture, a combination of the gradient descent training function, the hyperbolic tangent sigmoid transfer function, the linear transfer function, and 18 neurons were used. The PCA+MLR hybrid model was not effective in predicting thousand-grain weight. The fact that R² values obtained with different input configurations vary between 0.24 and 0.31 shows that the prediction accuracy of the model is low. In contrast, the PCA+ANN hybrid model significantly improved the prediction accuracy, and the best model achieved an R2 value of 0.981, an RMSE of 0.0829, and an MAE of 0.0359. The PCA+ANN model, which preserved the necessary variance by reducing the complexity of the input data, enabled the ANN to focus on the most critical components for accurate prediction. This study demonstrates that whereas ANN and PCA+ANN models give significantly increased accuracy in predicting wheat varieties' thousand-kernel weights, MLR models only offer moderate prediction capabilities.

Keywords

Thousand-kernel weight, wheat, multiple linear regression, principal component analysis, hybrid modeling

References

• Al-Adhaileh, M. H., & Aldhyani, T. H. H. (2022). Artificial intelligence framework for modeling and predicting crop yield to enhance food security in Saudi Arabia. PeerJ Comput Sci, 8, e1104. https://doi.org/10.7717/peerj-cs.1104
• Arigela, A., Kvs, R., & kumar, A. (2021). Study of Physical Properties of Zea mays in the Development of Seed Metering Unit. International Journal of Agriculture Environment and Biotechnology, 14, 159-163. https://doi.org/10.30954/0974-1712.02.2021.5
• Balda, E. B. A., & Mathar, R. (2018). An Information Theoretic View on Learning of Artificial Neural Networks. IEEE International Conference on Signal Processing and Communication Systems. https://doi.org/10.1109/ICSPCS.2018.8631758
• Dryha, V. V., Doronin, V. A., Kravchenko, Y. A., Doronin, V., & Orlov, S. D. (2022). The effect of the storage conditions on the quality of switchgrass seeds of different 1000-kernel weight. Scientific Papers of the Institute of Bioenergy Crops and Sugar Beet.
• Ferreira, A. S., Zucareli, C., Junior, A. A. B., Werner, F., & Coelho, A. E. (2017). Size, physiological quality, and green seed occurrence influenced by seeding rate in soybeans. Semina-ciencias Agrarias, 38, 595-606. Fonseca de Oliveira, G. R., Mastrangelo, C. B., Hirai, W. Y., Batista, T. B., Sudki, J. M., Petronilio, A. C. P., Crusciol, C. A.
• C., & Amaral da Silva, E. A. (2022). An Approach Using Emerging Optical Technologies and Artificial Intelligence Brings New Markers to Evaluate Peanut Seed Quality. Front Plant Sci, 13, 849986. https://doi.org/10.3389/fpls.2022.849986
• Gardner, M. W., & Dorling, S. R. (1998). Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmospheric Environment, 32(14), 2627-2636. https://doi.org/https://doi.org/10.1016/S1352-2310(97)00447-0
• Ghasemzadeh, H., Hillman, R. E., & Mehta, D. D. (2024). Toward Generalizable Machine Learning Models in Speech, Language, and Hearing Sciences: Estimating Sample Size and Reducing Overfitting. Journal of Speech, Language, and Hearing Research, 67(3), 753-781. https://doi.org/doi:10.1044/2023_JSLHR-23-00273
• Gierz, Ł., Kolankowska, E., Markowski, P., & Koszela, K. (2022). Measurements and Analysis of the Physical Properties of Cereal Seeds Depending on Their Moisture Content to Improve the Accuracy of DEM Simulation. Applied Sciences, 12(2), 549. https://www.mdpi.com/2076-3417/12/2/549
• Hankook, H., Lee, S., Kim, K., & Yoo, K. (1990). Comparison Analysis of single Multiplicative neuron with Conventional Neuron Models. Journal of Theoretical and Applied Information Technology. https://doi.org/10.1109/ICSPCS.2018.8631758
• Kaliniewicz, Z., Markowski, P., Anders, A., Jadwisieńczak, K., Żuk, Z., & Krzysiak, Z. (2019). Physical Properties of Seeds of Eleven Fir Species. Forests, 10(2), 142. https://www.mdpi.com/1999-4907/10/2/142
• Kandpal, P., & Mehta, A. (2019). Critical Analysis of Two Dimensional and Four-Dimensional Spiking Neuron Models. Journal of Computational and Theoretical Nanoscience. https://doi.org/10.1166/jctn.2019.8268
• Kheir, A., Mkuhlani, S., Mugo, J. W., Elnashar, A., Nangia, V., Deware, M., & Govind, A. (2023). Integrating APSIM model with machine learning to predict wheat yield spatial distribution. Agronomy Journal. https://doi.org/10.1002/agj2.21470
• Mamann, Â. T. W. D., Silva, J. G. d., Binelo, M. O., Scremin, O. B., Kraisig, A. R., Carvalho, I. R., Pereira, L. M., Berlezi, J. D., & Argenta, C. V. (2019). Artificial Intelligence Simulating Grain Productivity During the Wheat Development Considering Biological And Environmental Indicators. Journal of Agricultural Studies.
• Mittlböck, M., & Heinzl, H. (2002). MEASURES OF EXPLAINED VARIATION IN GAMMA REGRESSION MODELS. Communications in Statistics - Simulation and Computation, 31(1), 61-73. https://doi.org/10.1081/SAC-9687282
• Polishchuk, V., & Konovalov, D. V. (2023). The yield of conditioned winter wheat seeds depending on the cultivation technology. Advanced Agritechnologies.
• Saffariha, M., Jahani, A., & Potter, D. (2020). Seed germination prediction of Salvia limbata under ecological stresses in protected areas: an artificial intelligence modeling approach. BMC Ecol, 20(1), 48. https://doi.org/10.1186/s12898-020-00316-4
• Schielzeth, H. (2010). Simple means to improve the interpretability of regression coefficients. Methods in Ecology and Evolution, 1(2), 103-113. https://doi.org/https://doi.org/10.1111/j.2041-210X.2010.00012.x
• Shamsabadi, E. E. h., Sabouri, H., Soughi, H., & Sajadi, S. J. (2022). Using of Molecular Markers in Prediction of Wheat (Triticum aestivum L.) Hybrid Grain Yield Based on Artificial Intelligence Methods and Multivariate Statistics. Russian Journal of Genetics, 58, 603 - 611.
• Sieracka, D., Zaborowicz, M., & Frankowski, J. (2023). Identification of Characteristic Parameters in Seed Yielding of Selected Varieties of Industrial Hemp (Cannabis sativa L.) Using Artificial Intelligence Methods. Agriculture, 13(5), 1097. https://www.mdpi.com/2077-0472/13/5/1097
• Thangjam, U., & Sahoo, U. K. (2016). Effect of Seed Mass on Germination and Seedling Vigour of Parkia Timoriana (DC.) Merr. Current Agriculture Research Journal, 4, 171-178.
• Uyanık, G. K., & Güler, N. (2013). A Study on Multiple Linear Regression Analysis. Procedia - Social and Behavioral Sciences, 106, 234-240. https://doi.org/https://doi.org/10.1016/j.sbspro.2013.12.027
• Zhang, H., Ji, J., Ma, H., Guo, H., Liu, N., & Cui, H. (2023). Wheat Seed Phenotype Detection Device and Its Application. Agriculture, 13(3), 706. https://www.mdpi.com/2077-0472/13/3/706