پیش‌بینی عملکرد جو دیم و آبی (Hordeum vulgare L.) با استفاده از رهیافت شبکه عصبی مصنوعی (مطالعه موردی: استان کرمانشاه)

نوع مقاله: علمی - پژوهشی

نویسندگان

دانشگاه رازی

10.22067/jag.v10i2.61417

چکیده

نظر به اهمیت پیش‌بینی تولید محصولات کشاورزی، آزمایشی با هدف برآورد عملکرد محصول جو دیم و آبی (Hordeum vulgare L.) با استفاده از رهیافت شبکه عصبی مصنوعی، در استان کرمانشاه به اجرا درآمد. داده‌های مربوط به عملکرد 25 ساله (1370 تا 1394) جو دیم و آبی در شهرستان‌های استان و همچنین داده‌های خام و استاندارد شده هواشناسی (مجموع بارندگی سالیانه، متوسط درجه حرارت سالیانه، متوسط رطوبت سالیانه، مجموع ساعات آفتابی، میانگین تبخیر سالیانه و تعداد روزهای یخبندان) متناظر با این سال‌ها به‌عنوان داده‌های ورودی شبکه مورد استفاده قرار گرفتند. برای یافتن بهترین شبکه، انواع مختلف شبکه عصبی برای تخمین عملکرد، آزمایش شد. ارزیابی مدل‌ها نیز با استفاده از شاخص‌های آماری ضریب همبستگی (R)، ضریب تعیین (R2)، میانگین مربعات خطا (MSE) و ریشه میانگین مربعات خطا (RMSE) انجام شد. نتایج نشان داد که بهترین شبکه برای جو دیم شبکه‌های عصبی مودولار ساخته شده از داده‌های استاندارد و خام و با قانون یادگیری Momentum دارای ضریب همبستگی به‌ترتیب 96/0 و 92/0 بود. این در حالی بود که دقت شبکه عصبی در مورد جو آبی به‌اندازه کشت دیم نبود (ضریب همبستگی برای داده‌های ورودی استاندارد و خام به‌ترتیب 72/0 و 78/0). مقایسه شاخص‌های MSE و RMSE بین مدل‌های ذکر شده نیز مؤید این امر بود. به‌نظر می‌رسد در جو آبی انجام عملیات مدیریت داشت مانند آبیاری از تأثیر عوامل اقلیمی بر روی عملکرد آن کاسته است. از سوی دیگر، حساسیت شبکه عصبی مربوط به کشت جو دیم نسبت به متغیرهای ورودی مدل بسیار بیشتر از کشت آبی بود که در نهایت دقت بیشتر شبکه را به همراه داشت.

کلیدواژه‌ها


عنوان مقاله [English]

Predicting Yield of Rainfed and Irrigated Barley (Hordeum vulgare L.) in Kermanshah by Artificial Neural Network Approach (Case study Kermanshah, Iran)

نویسندگان [English]

  • Alireza Bagheri
  • Naser Sohrabi
Razi University
چکیده [English]

Introduction
Predicting the yield of strategic crops such as wheat and barley can provide liquidity to purchase products from farmers, suitable space for storage, sufficient pricing, and estimating the import and export needs of the agricultural products. Crop yield forecasting can be estimated using different methods. Artificial neural network is one of the methods recently has been considered and has high accuracy in crop yield estimation. In this approach the relationship between independent and dependent variables as well as their complex interactions will be studied and hidden correlatioins between the variables is discovered. Crop yield, particularly in case of rain-fed crops, severely affected by climatic factors such as rainfall, humidity, temperature fluctuations and solar radiation during the growth season. On this basis, it seems that in case of relationships between climatic data (as independent variables) and crop yield (as dependent variable) it would be possible to predict agricultural production.
Materials and Methods
Considering the importance of forecasting agricultural production, an experiment was conducted in Kermanshah province, with the aim of estimating rainfed and irrigated barley yield using artificial neural network approach,. Barley yield data of 25 years (1991 to 2015) as well as raw and corresponding standardized meteorological data (total annual rainfall, average annual temperature, humidity annual average total sunshine hours, average annual evaporation and the number of frost days) were used as input data networks. To find the best network, performance of different types of neural networks was tested to barley yield evaluation. To evaluate models the statistics indices of correlation coefficient (R), coefficient of determination (R2), mean squared error (MSE) and root mean square error (RMSE) were used.
Results and Discussion
The results showed that the best neural network built for rainfed barley was Modular Neural Network with Momentum learning law. The network had a correlation coefficient of 0.96 and 0.92, and coefficient of determination of 0.85 and 0.92 for raw and standard data, respectively. The best neural network built for irrigated barley was also Modular Neural Network with Momentum learning law. The correlation coefficient for the raw and standard input data was 0.78 and 0.72 with coefficient of determination of 0.60 and 0.51, respectively. The results showed the less efficiency of artificial Neural Network in predicting irrigated compared to rainfed barley yield. Comparison of MSE and RMSE between the models also revealed that networks related to rainfed barely with more accuracy had more correlation coefficient compared to irrigated barely. It seems that the managing operations such as watering in irrigated barley has reduced the effect of climate factors on barley yield. So that the sensitivity of irrigated barley yield was much less than the rainfed barley. In fact, in irrigated cultivations, depending on the amount of available water, crops were irrigated regularly. This would be in addition to supplying the needed water of crops, also reduce the impact of other climatic factors such as temperature.
Conclusion
Generally based on the results of this study, the accuracy of Artificial Neural Network to predict the yield of rainfed barley was more acceptable than irrigated barley in Kermanshah province. Rainfed cultivation are more affected by climatic factors such as rainfall and temperature, which would be the reason of the achieved results. Hence, the accuracy of neural network for rainfed barley was more than irrigated barely, which represents more relationship between yield of rainfed barley with climatic factors as inputs of the model. So the sensitivity test of the yield to climatic factors revealed more sensitivity in rainfed than irrigated barley. Moreover, the accuracy of neural network showed that neural network was built for barley than wheat.

کلیدواژه‌ها [English]

  • Artificial Intelligence
  • barley
  • Predictive variables
  • Yield prediction
  1. Alvarez, R. 2009. Predicting average regional yield and production of wheat in the argentine pampas by an artificial neural network approach. European Journal of Agronomy 30: 70-77.
  2. Amari, S.., Murata, N., Muller, K.., Finke, M., and Yang, H.H. 1997. Asymptotic statistical theory of overtraining and cross-validation. IEEE Transactions on Neural Networks 8: 985-996.
  3. Anonymous, 2015. Agricultural Statistics, Agricultural Year of 2014-2015. First Volume, the Crops. Iranian Ministry of Agriculture 9-11.
  4. Anysz, H., Zbiciak, A., and Ibadov, N. 2016. The influence of input data standardization method on prediction accuracy of artificial neural networks. Procedia Engineering 153: 66-70.
  5. Azizi, G., and Safarkhani, E. 2002. Evaluation of drought and its impact on rainfed wheat yield in ilam province, with an emphasis on recent drought (1998-2000). Modarres 6: 61-79.
  6. Crasta, O., and Cox, W. 1996. Temperature and soil water effects on maize growth, development yield, and forage quality. Crop Science 36: 341-348.
  7. Drummond, S.T., Sudduth, K.A., Joshi, A., Birrell, S.J., and Kitchen, N.R. 2003. Statistical and neural methods for site–specific yield prediction. Transactions of the ASAE 46: 5.
  8. Eghbali, L., Haghighi, R.S., Rad, H.M., and Bagheri, A. 2005. Seed identification of Amaranthus spp. using machine vision and artificial neural network. Journal of Seed Science and Technology 2: 74-85.
  9. Elizondo, D., McClendon, R., and Hoogenboom, G. 1994. Neural network models for predicting flowering and physiological maturity of soybean. Transactions of the ASAE 37: 981-988.
  10. Haykin, S., and Lippmann, R. 1994. Neural networks, a comprehensive foundation. International Journal of Neural Systems 5: 363-364.
  11. Hosaini, M.T., Siosemarde, A., Fathi, P., and Siosemarde, M. 2007. Application of artificial neural network (ann) and multiple regression for estimating assessing the performance of dry farming wheat yield in Ghorveh region, Kurdistan Province. Agricultural Research: Water, Soil and Crop 7: 41-54.
  12. Ji, B., Sun, Y., Yang, S., and Wan, J. 2007. Artificial neural networks for rice yield prediction in mountainous regions. The Journal of Agricultural Science 145: 249-261.
  13. Joergensen, S.E., and Bendoricchio, G. 2001. Fundamentals of Ecological Modelling. Elsevier, Oxford, UK.
  14. Kaul, M., Hill, R.L., and Walthall, C. 2005. Artificial neural networks for corn and soybean yield prediction. Agricultural Systems 85: 1-18.
  15. Landeras, G., Ortiz-Barredo, A., and Lopez, J.J. 2009. Forecasting weekly evapotranspiration with arima and artificial neural network models. Journal of Irrigation and Drainage Engineering 135: 323-334.
  16. Liangzhi, Y., Stanley, W., and Rosegrant, M. 2005. Impact of global warming on chinese wheat productivity. International Food Policy Research Institute, Discussion paper, pp. 143-158.
  17. Lingireddy, S., and Brion, G.M. 2005. Artificial Neural Networks in Water Supply Engineering. ASCE Publications.
  18. Lobell, D.B., and Asner, G.P. 2003. Climate and management contributions to recent trends in U.S agricultural yields. Science 299: 1032-1032.
  19. Melesse, A.M., and Hanley, R.S. 2005. Artificial neural network application for multi-ecosystem carbon flux simulation. Ecological Modelling 189: 305-314.
  20. Nemes, A., Schaap, M., and Wösten, J. 2003. Functional evaluation of pedotransfer functions derived from different scales of data collection. Soil Science Society of America Journal 67: 1093-1102.
  21. Peng, S., Huang, J., Sheehy, J.E., Laza, R.C., Visperas, R.M., Zhong, X., Centeno, G.S., Khush, G.S., and Cassman, K.G. 2004. Rice yields decline with higher night temperature from global warming. Proceedings of the National Academy of Sciences of the United States of America 101: 9971-9975.
  22. Rahmani, L., Liaghat, A., and Khalili, A. 2008. Estimates barley yield in east azerbaijan using meteorological parameters and drought indices by artificial neural network method. Iranian Journal of Soil and Water Research 39: 47-56. (In Persian with English Summary)
  23. Rahmani, M., Jami Al-Ahmadi, M., Shahidi, A., and Hadizadeh Azghandi, M. 2016. Effects of climate change on length of growth stages and water requirement of wheat (Triticum aestivum L.) and barley (Hordeum vulgare L.) (Case study: Birjand plain). Journal of Agroecology 7: 443-460.
  24. Rao, V., and Rao, H. 1995. C++ Neural Networks and Fuzzy Logic. MIS: Press, Dehle, India.
  25. Shokoohi, M., and Sanaei Nejhad, S.H. 2014 The relationship between weather conditions and crop production for rainfed barley (Case Study: East Azerbaijan). Journal of Agroecology 6: 634-644. (In Persian with English Summary)
  26. Somaratne, S., Seneviratne, G., and Coomaraswamy, U. 2005. Prediction of soil organic carbon across different land-use patterns. Soil Science Society of America Journal 69: 1580-1589.
  27. Talliee, A.A., and Bahramy, N. 2003. The effect of rainfall and temprature on the yield of dryland wheat in Kermanshah province. Journal of Soil and Water Science 17: 106-112. (In Persian with English Summary)
  28. Talliee, A.A., and Sayadian, K. 2000. Effect of supplementary irrigation and nutrition requirement of chick-pea in dry land conditions. Iranian Journal of Crop Science 2: 63-70. (In Persian with English Summary)
  29. Wu, F.Y., and Yen, K.K. 1992. Applications of neural network in regression analysis. Computers and Industrial Engineering 23: 93-95.
  30. Zarakani, F., Kamali, G., and Chizari, A. 2014. Impact of climate change on the economy of rainfed wheat (Case study: Northern Khorasan). Journal of Agroecology 6: 301-310. (In Persian with English Summary)