Türkiye'de Pamuk Üretiminin Tahmini İçin Yapay Sinir Ağı Yöntemleri Uygulaması

Year 2021, Volume: 8 Issue: 4, 1018 - 1027, 24.10.2021

Nazire Mıkaıl , Mehmet Fırat Baran

https://doi.org/10.30910/turkjans.947978

Cited By: 1

Abstract

Yetiştiriciler bitkisel üretimde verimi etkileyen faktörleri hep merak etmişlerdir. Bu faktörlerin belirlenmesi ilerideki verim hakkında bilgi verebilir. Bilginin güvenilirliği iyi bir tahmin modeline bağlıdır. Çalışma sürecine göre yapay sinir ağları, insandaki sinir ağını taklit eder. Yapay sinir ağlarında insanların farklı deneyimlerden edindiği bilgileri birleştirerek mevcut duruma yönelik tahminler yapabilme yeteneği tasarlanmıştır. Bu nedenle karmaşık problemlerde yapay sinir ağlarına göre daha iyi sonuç verir. Bu çalışmada, pamuk üretimini modellemek için yapay sinir ağı yöntemi kullanılmıştır. Türkiye, Diyarbakır'da 73 işletmeyi kapsayan kapsamlı bir veri koleksiyonundan, ortalama pamuk üretimi 559,19 kg/da olarak hesaplanmıştır. Bu modele temel girdi olarak seçilen dört faktör vardır. Sonuç olarak, nihai YSA modeli, işletme durumları (pamuk alanı ve sulama periyodu), makine kullanımı ve gübre tüketimi gibi unsurlara dayanan pamuk üretimini gösterebilmektedir. Çalışma sonunda pamuk verimi %84 doğrulukla tahmin edilmiştir.

Keywords

Tarla ürünü, verim, pamuk, ANN, SVM, Türkiye

Application of Artificial Intelligence Methods to Predict Cotton Production in Turkey

Abstract

Farmers are always curious about the factors affecting yield in plant production. Determining these factors can give information about the yield in the future. Reliability of information is dependent on a good prediction model. According to the operating process artificial neural networks imitate the neural network in humans. The ability to make predictions for the current situation by combining the information people have gained from different experiences is designed in artificial neural networks. Therefore, in complex problems, it gives better results than conventional statistical methods.
In this study, artificial neural networks and support vector machines methods of artificial intelligence were used in order to predict the production of cotton. From a comprehensive data collection spanning 73 farms in Diyarbakır, Turkey, the mean cotton production was prevised at 559.19 kg da-1. There is four factors that picked as pivotal input into this model. As a result, the ultimate artificial neural network model is able to foreshow cotton production, which is built on elements like: farm states (cotton area and irrigation periodicity), machinery usage and fertilizer consumption. At the end of the study, cotton yield was estimated with %84 accuracy.

Keywords

Crop fields, yield, cotton, ANN, SVM, Turkey

References

• Anonym 2020a, Diyarbakır ve Şanlıurfa illerinde pamuk sektörü Envanteri, Access link: https://www.karacadag.gov.tr/Dokuman/Dosya/www.karacadag.org.tr_8_WH3D93PC_Diyarbakir_ve_Sanliurfa_illerinde_pamuk_sektoru_envanterinin_hazirlanmasi_projesi.pdf, Access date: 21.01.2020
• Anonym, 2020b, Cotton production report, April 2019, Access Link: https://ticaret.gov.tr/data/5d41e59913b87639ac9e02e8/d0e2b9c79234684ad29baf256a0e7dce.pdf , Access date: 02.05.2020
• Anonym 2020c, Cotton report, 2018 Access Link: http://www.zmo.org.tr/genel/bizden_detay.php?kod=30467&tipi=17&sube=0, Access date: 21.01.2020
• Anonym 2020d, Cotton, Access link, https://arastirma.tarimorman.gov.tr/tepge/Belgeler/PDF%20Tar%C4%B1m%20%C3%9Cr%C3%BCnleri%20Piyasalar%C4%B1/2019Ocak%20Tar%C4%B1m%20%C3%9Cr%C3%BCnleri%20Raporu/2019-Ocak%20Pamuk.pdf, Access date: 21.01.2020
• Anonym, 2020e. Diyarbakır ili coğrafyası. http://www.diyarbakirkulturturizm.gov.tr/TR-56881/cografya.html, Erişim tarihi: 01.05.2020 (In Turkish)
• Bozkurt, Y., Aydogan, T., Tuzun, C.G., Mikail, N., Varban, S., Dogan, C., Tatlı, M. (2015). Some applications of artificial neural networks used beef cattle production, 4th International Congress New Perspectives and Challenges of Sustainable Livestock Production, 07-09 EKİM 2015, Belgrade, Sırbistan.
• Çiçek, A., Erkan, O. (1996). Tarım Ekonomisinde Araştırma ve Örnekleme Yöntemleri. Gaziosmanpaşa Üniversitesi, Ziraat Fakültesi Yayınları No: 12, Ders Notları Serisi No: 6, Tokat.
• Farooq, A., Sarwar, M. I., Ashraf, M. A., Iqbal, D., Hussain, A., & Malik, S. (2018). Predicting Cotton Fibre Maturity by Using Artificial Neural Network. Autex Research Journal. https://doi.org/10.1515/aut-2018-0024
• Karademir, E , Karademir, C , Ekinci, R , Sevilmis, U. (2015). İleri Generasyondaki Pamuk (Gossypium hirsutum L.) Hatlarında Verim ve Lif Kalite Özelliklerinin Belirlenmesi. Türkiye Tarımsal Araştırmalar Dergisi, 2 (2) , 100-107 . DOI: 10.19159/tutad.60964 (In Turkish)
• Khoshnevisan, B., Rafiee, S., Omid, M., Mousazadeh, H., & Sefeedpari, P. (2013a). Prognostication of environmental indices in potato production using artificial neural networks. Journal of Cleaner Production. https://doi.org/10.1016/j.jclepro.2013.03.028
• Khoshnevisan, B., Rafiee, S., Omid, M., Yousefi, M., & Movahedi, M. (2013b). Modeling of energy consumption and GHG (greenhouse gas) emissions in wheat production in Esfahan province of Iran using artificial neural networks. Energy. https://doi.org/10.1016/j.energy.2013.01.028
• Khoshroo, A., Emrouznejad, A., Ghaffarizadeh, A., Kasraei, M., & Omid, M. (2018). Sensitivity analysis of energy inputs in crop production using artificial neural networks. Journal of Cleaner Production. https://doi.org/10.1016/j.jclepro.2018.05.249
• Konishi, S. (2014). Introduction to multivariate analysis: Linear and nonlinear modeling. In Introduction to Multivar. Analysis: Linear and Nonlinear Modeling. https://doi.org/10.1201/b17077
• Mammadova, N., & Keskin, I. (2013). Application of the support vector machine to predict subclinical mastitis in dairy cattle. The Scientific World Journal, 2013, 603897. http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3886278&tool=pmcentrez&rendertype=abstract
• Mammadova, N. M., & Keskin, I. (2015). Application of neural network and adaptive neuro-fuzzy inference system to predict subclinical mastitis in dairy cattle. Indian Journal of Animal Research, 49(5). https://doi.org/10.18805/ijar.5581
• Mathworks (2009). MATLAB - Mathworks - MATLAB & Simulink. http://doi.org/2016-11-26 Mikail, N., Altay, Y., Keskin, İ. (2013). A Sample Model Prediction of 305-Day Milk Yield of Holstein Cows Using Artificial Neural Networks, VIth International Balkan Animal Conference, BALNIMALCON, Tekirdağ, Turkey, 03-05 EKİM, 2013.
• Mikail, N., Keskin, İ., Altay, Y. (2014). Siyah Alaca ineklerin süt verimi tahmininde yapay sinir ağları ve destek vektör makineleri yöntemlerinin kullanımı, Uluslararası Mezopotamya Tarım Kongresi, 22-25 EYLÜL 2014, Diyarbakır, Türkiye.
• Mikail, N., Keskin, İ. (2015). Application of neural network and adaptive neuro-fuzzy inference system to predict subclinical mastitis in dairy cattle. Indian J. Anim. Res., 49 (5) 2015 : 671-679.
• Mikail, N., Keskin, İ., Altay, Y., Dağ, B. (2016). A sample model prediction of milk yield in Akkaraman ewes using artificial neural networks. International Human and Nature Sciences: Problems and Solution Seeking Congress, 07-09 EKİM 2016, Bosna Hersek.
• Nabavi-Pelesaraei, A., Rafiee, S., Hosseinzadeh-Bandbafha, H., & Shamshirband, S. (2016). Modeling energy consumption and greenhouse gas emissions for kiwifruit production using artificial neural networks. Journal of Cleaner Production. https://doi.org/10.1016/j.jclepro.2016.05.188
• Nguyen, H. (2019). Support vector regression approach with different kernel functions for predicting blast-induced ground vibration: a case study in an open-pit coal mine of Vietnam. SN Applied Sciences, 1(4). https://doi.org/10.1007/s42452-019-0295-9
• Rostami, S., Choobin, S., Samani, B. H., Esmaeili, Z., & Zareiforoush, H. (2017). Analysis and Modeling of Yield, CO2 Emissions, and Energy for Basil Production in Iran using Artificial Neural Networks.
• Safa, M., & Samarasinghe, S. (2011). Determination and modelling of energy consumption in wheat production using neural networks: “A case study in Canterbury province, New Zealand.” Energy. https://doi.org/10.1016/j.energy.2011.06.016
• Safa, M., Samarasinghe, S., & Nejat, M. (2015). Prediction of wheat production using artificial neural networks and investigating indirect factors affecting it: Case study in canterbury province, New Zealand. Journal of Agricultural Science and Technology.
• Saltuk, B., Mikail, N. (2019). Prediction of indoor temperature in a greenhouse: Siirt sample. Fresen. Environ. Bull. 28(4A), 3577-3585.
• Samarasinghe, S. (2006). Neural Networks for Applied Sciences and Engineering. In Neural Networks for Applied Sciences and Engineering. https://doi.org/10.1201/9781420013061
• Spiegel, M. R., Schiller, J. J., & Srinivasan, R. A. (2009). Probability and statistics. In Schaum’s outlines.
• Taki, M., Ajabshirchi, Y., & Mahmoudi, A. (2012). Prediction of output energy for wheat production using artificial neural networks in Esfahan province of Iran. International Journal of Agricultural Technology, 8, 1229-1242.
• Taki, M., Rohani, A., Soheili-Fard, F., & Abdeshahi, A. (2016). Assessment of energy consumption and modeling of output energy for wheat production by neural network (MLP and RBF) and Gaussian process regression (GPR) models. Journal of Cleaner Production. https://doi.org/10.1016/j.jclepro.2017.11.107
• Vapnik, V. (1996). The Nature of Statistical Learning Theory. Springer, New York.
• Vapnik, V. (1998). Statistical Learning Theory. Wiley, New York.
• Willmott, C.J. and Matsuura, K. (2005). Advantages of the Mean Absolute Error (MAE) over the Root Mean Square Error (RMSE) in Assessing Average Model Performance. Climate Research, 30, 79-82. http://dx.doi.org/10.3354/cr030079
• Yamane, T. (1967). Statistics: And Introductory Analysis, 2nd Ed., : In Scottish Journal of Arts, Social Sciences and Scientific Studies.
• Yingli, L. V., Le, Q. T., Bui, H. B., Bui, X. N., Nguyen, H., Nguyen-Thoi, T., Dou, J., & Song, X. (2020). A comparative study of different machine learning algorithms in predicting the content of ilmenite in titanium placer. Applied Sciences (Switzerland), 10(2). https://doi.org/10.3390/app10020635