Modeling Avocado Production in Mexico with Artificial Neural Networks
Downloads
An Artificial Neural Network (ANN) model was created in this research to estimate and predict the amount of avocado production in Mexico. In the development of the ANN model, the years that are time variable were used as the input parameter, and the avocado production amount (tons) was used as the output parameter. The research data includes avocado production in Mexico for 1961-2020 period. Mean Squared Error (MSE) and Mean Absolut Error (MAE) statistics were calculated using hyperbolic tangent activation function to determine the appropriate model. ANN model is a network architecture with 12 hidden layers, 12 process elements (12-12-1) and Levenberg-Marquardt back propagation algorithm. The amount of avocado production was estimated between 2021 and 2030 with the ANN. As a result of the prediction, it is expected that the amount of avocado production for the period 2021-2030 will be between 2,410,741-2,502,302 tons.
Brahmi, N., Sallem, S., Chaabene, M. 2010. ANN based parameters estimation of Weibull: Application to wind energy potential assessment of Sfax, Tunisia,” irec.cmerp.net, no.
, pp. 203–207.
Chen, Z., Shi, R., Zhang, S. 2013. An artificial neural network approach to estimate evapotranspiration from remote sensing and AmeriFlux data. Front. Earth Sci., 7(1): 103–111.
Çelik, Ç. 2019. Prediction of Mandarin Production in Turkey through Artificial Neural Networks and Time-Series Analysis. International Journal of Trend in Research and Development, 6(5): 85-90.
Çelik, Ş. 2020a. Modeling and forecasting of dry bean yield in Turkey using Artificial Neural Networks and Time Series Analysis. Research Inventy: International Journal of Engineering and Science, 10(10): 8–13.
Çelik, Ş. 2020b. Estimation Modelling of Tobacco Production in Turkey Comparative Analysis of Artificial Neural Networks and Multiplicative Decomposition Methods. International Journal of Trend in Research and Development, 7(4): 184–187.
Çelik, Ş. 2020c. Artificial Neural Network and Time Series Modeling of predicted future production with lentil production in Turkey and Analysis. Journal of Multidisciplinary Engineering Science Studies (JMESS), 6(11): 3564–3568.
Dahikar, S.S., Rode, S.V. 2014. Agricultural Crop Yield Prediction Using Artificial Neural Network Approach. International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control Engineering, 2(1): 683-686.
FAO, 2020. Crops and livestock products, crops primary. United Nations Food and Agriculture Organization. https://www.fao.org/faostat/en/#data (Accessed to: 12 July 2022). Kamilaris, A., Prenafeta, S.X. 2018. A review of the use of convolutional neural networks in agriculture. 156: 312-322. doi.org/10.1017/S0021859618000436.
Kaygısız, H. 2007. Amatör Meyvecilik. Hasad Yayıncılık Ltd. Şti., İstanbul-Türkiye.
Khamis, A., Abdullah, S.N.S.B. 2014. Forecasting Wheat Price Using Back propagation and NARX Neural Network, The International Journal of Engineering and Science (IJES). 3(11): 19-26
Khoshnevisan, B., Rafiee, S., Iqbal, J., Shamshirband, S., Omid, M., Anuar, N.B., Abdulwahab, A.W. 2015. A Comparative Study Between Artificial Neural Networks and Adaptive Neuro-Fuzzy Inference Systems for Modeling Energy Consumption in Greenhouse Tomato Production: A Case Study in Isfahan Province. The Journal of Agricultural Sicience, 17: 49-62.
Tatlı, A., Kahvecioğlu, S. 2016. Zaman Serilerinde NARX Sinir Ağları Modeliyle Uçuşa Elverişlilik Süresinin Kestirimi. 2016 Ulusal Elektrik, Elektronik ve Biyomedikal Mühendisliği Konferansı (ELECO), Bursa, 1-3 Aralık 2016, 130-134.
Yıldırım, H., Karaatlı, M. 2022. Yapay Sinir Ağları Narx Modeli ile elma üretim miktarının öngörülmesi. Süleyman Demirel Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 2022/1, 42: 1-29.
