The application of artificial neural network models to forecast wheat production through time series analysis in key countries

Authors

  • Wafaa Benayad University of Abu Bakr Belkaid - Tlemcen, Algeria
  • Fettouhi Khadidja University of Abu Bakr Belkaid - Tlemcen, Algeria

Keywords:

Artificial Neural Network Models, Time Series Analysis, Wheat Production

Abstract

This study aims to analyze wheat production data from five major countries (Australia, India, United States, Canada, Canada, and Russia) for the period 1992 to 2022, using machine learning techniques to predict wheat production based on historical patterns. Three neural network models were developed: Multilayer Perceptron (MLP) with two hidden layers, Recurrent Neural Network (RNN) with SimpleRNN layer, and Long Short Term Memory (LSTM). Dropout of 0.3 was used in all models to minimize overfitting. The prediction results showed that the RNN model achieved the lowest values for the mean absolute error and the square root of the mean error, demonstrating its high ability to accurately predict. While the LSTM model provided excellent results in countries such as Australia and India, the MLP model showed poor performance overall, indicating its challenges in accurate prediction. The study highlights the importance of using machine learning techniques to improve the accuracy of predicting the production of strategic crops, and reflects the need to adopt innovative agricultural strategies to address environmental challenges.

References

Reynolds, C. A. (2000). Estimating crop yields and pro- duction by integrating the FAO Crop Specific Water Balance model with real-time satellite data and ground-based ancillary datav. International Journal of Remote Sensing , 21(18). doi:https://doi.org/10.1080/014311600750037516

Demirel, M. H., Z. S., Baran, M. F., & Gokdogan, O. (2024). Effect of Input Usage on Wheat Yield: An Application of Artificial Neural Networks (ANN). Journal of Agricultural Science and Technology, 26(2). doi:10.22034/JAST.26.2.233

Fischer, R. A. (2015). Definitions and determination of crop yield, yield gaps, and of rates of change. . Field Crops Research,.

Hara, P., & M. P. (2023). Prediction of Pea (Pisum sativum L.) Seeds Yield Using Artificial Neural Networks. Agriculture, 13(3). doi:https://doi.org/10.3390/agriculture13030661

J.A. Marchant, C. O. (2002 ). Comparison of Bayesian classifier with multilayer feed-forward neural network using example of plant/weed/soil discrimination, Computers and Electronics in Agriculture 39 (2002) 3-22. Computers and Electronics in Agriculture , 39.

Kaur, K. (2023). Artifcial Neural Network Model to Forecast Energy Consumption in Wheat Production in India. Journal of Statistical Theory and Applications, 22. Retrieved from https://link.springer.com/article/10.1007/s44199-023-00052-w

K.-C. Ke and M.-S. Huang. (2020). "Quality prediction for injection molding by using a multilayer perceptron neural network," Polymers, vol. 12, no. 8, p. 1812, 2020. Polymers, 12(8).

Kadaja, J. S. (2009). Probabilistic Yield Forecast Based on Aproduction Process Model. Computer and Computing Technologies in Agriculture II, 1( 487–494. doi: https://doi.org/10.1007/978-1-4419-0209-2_50). doi:https://doi.org/10.1007/978-1-4419-0209-2_50

Lobell, D. B.-R. (2011). Climate Trends and Global Crop Production Since 1980. Science, 333 (6042), 616–620. doi: https://doi.org/10.1126/science.1204531. Science, 333 ( 6042). doi:https://doi.org/10.1126/science.1204531

M.M. Rahman, B. B. (2010). Modelling of jute production using artificial neural networks . Biosystems Engineering , 105.

Morales, A., & Villalobos, F. J. (2023). Using machine learning for crop yield prediction in the past or the future. Frontiers in Plant Scienc, 14. doi:https://doi.org/10.3389/fpls.2023.1128388

Mustapha, F. M. (2023). A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU. doi:DOI: 10.13140/RG.2.2.11938.81609

Nandram, B. B. (2013). A hierarchical Bayesian model for forecasting state-level corn yield. Environmental and Ecological Statistics, 21 (3), 507–530. doi: https://doi.org/10.1007/s10651-013-0266-z. Environmental and Ecological Statistics, 21 (3), 507–530. doi: https://doi.org/10.1007/s10651-013-0266-z, 21(3). doi:https://doi.org/10.1007/s10651-013-0266-z

Obaid Zaffar, S. K. (2024). Forecasting of wheat production, productivity and cultivated area in India using artificial neural networks. International Journal of Statistics and Applied Mathematics, 9(1). doi: https://dx.doi.org/10.22271/maths

Phalan, B. G. (2014). Closing yield gaps: perils and possibilities for biodiversity conservation. PhilosophicalTransactions of the Royal Society B: Biological Sciences,, 369(1639). doi:doi: https://doi.org/10.1098

Puma, M. J. (2015). Assessing the evolving fragility of the global food system. Environmental Research Letters , 10(2).

R. Linker, I. S. (2004). Greenhouse temperature modelling: A comparison between sigmoid neural networks and hybrid models, Mathematics and Computers in Simulation 65 (2004) 19-29. Mathematics and Computers in Simulation , 65.

S. RAY, & A. M. G. AL KHATIB, B. K. (2023). Forecasting cash crop production with statistical and neural network model. Journal of Crop and Weed, 19(1). doi:10.22271/09746315.2023.v19.i1.1679

Sadenova, M., Beisekenov, N., Varbanov, P. S., & Pan, T. (2023). Application of Machine Learning and Neural Networks to Predict the Yield of Cereals, Legumes, Oilseeds and Forage Crops in Kazakhstan. Agriculture, 13(6). doi: https://doi.org/10.3390/agriculture13061195

Siti Khairunniza-Bejo, S. M. (2014). Application of Artificial Neural Network in Predicting Crop Yield: A Review. Journal of Food Science and Engineering 4 , 1(9).

T. Morimoto, Y. O. (2007). Dynamic optimization of watering Satsuma mandarin using neural networks and genetic algorithms,93 (2007) 1-10. Agricultural Water Management, 93, 1-10.

T.R. Green, J. S. (2007). Relating crop yield to topographic attributes using spatial analysis neural network and regression (Vol. 139). Geoderma.

Y. Chtioui, S. P.-5. (1999). A generalized regression neural network and its application for leaf wetness prediction to forecast plant disease. Chemometrics and Intelligent Laboratory Systems , 48.

Ying Wang, W. S., & Wen, T. (2023). Prediction of winter wheat yield and dry matter in North China Plain using machine learning algorithms for optimal water and nitrogen application. Agricultural Water Management, 277. doi:https://doi.org/10.1016/j.agwat.2023.108140

W. Fang, Y. C. (2021). Survey on research of RNN-based spatio-temporal sequence prediction algorithms,. Journal on Big Data, vol. 3, no. 3, p. 97, 2021., 3(3).

Published

2024-10-23

How to Cite

Benayad, W., & Khadidja, F. (2024). The application of artificial neural network models to forecast wheat production through time series analysis in key countries. International Journal of Economic Perspectives, 18(10), 1810–1826. Retrieved from https://ijeponline.org/index.php/journal/article/view/683

Issue

Section

Peer Review Articles