طبقه‌بندی اقلیمی و تعیین مناطق مستعد کشت زعفران با استفاده از الگوریتم‌های داده‌کاوی در سطح استان خراسان رضوی

نوع مقاله: مقاله علمی پژوهشی

نویسندگان

1 استادیار گروه مرتع و آبخیزداری، دانشکده کشاورزی و منابع طبیعی، دانشگاه تربت‌حیدریه

2 استادیار گروه کامپیوتر و فناوری اطلاعات، دانشکده فنی و مهندسی، دانشگاه تربت حیدریه

3 استادیار گروه تولیدات گیاهی، دانشکده کشاورزی و منابع طبیعی، دانشگاه تربت حیدریه

4 مربی گروه مهندسی صنایع، دانشکده فنی و مهندسی، دانشگاه تربت حیدریه

چکیده

پیش­بینی عملکرد محصولات کشاورزی، نقش مهمی در برنامه­ریزی صادرات، واردات، خرید تضمینی، قیمت­گذاری، سود مطمئن و افزایش بهره­وری کشاورزی دارد. عملکرد محصولات، تابع پارامترهای متعددی از جمله اقلیم است. در این تحقیق، عملکرد زعفران در استان خراسان رضوی توسط الگوریتم‌های طبقه­بندی شامل شبکه­های عصبی مصنوعی، مدل‌های رگرسیونی، درخت خطی محلی، درخت تصمیم، آنالیز تشخیص، جنگل تصادفی، ماشین بردار پشتیبان و آنالیز نزدیک‌ترین همسایه با استفاده از 11 پارامتر اقلیمی طی دوره 20 ساله زراعی (88-1368) ارزیابی شد. نتایج نشان داد که تعداد کمی از پارامترهای اقلیمی، بر عملکرد زعفران تأثیر دارند. پارامترهای دمای حداقل، میانگین و حداکثر و بارش به ترتیب بیشترین همبستگی مثبت و پارامترهای رطوبت مطلق حداکثر، رطوبت نسبی ساعت 6:30، ساعات آفتابی، رطوبت نسبی ساعت 18:30، تبخیر، رطوبت نسبی ساعت 12:30 و رطوبت مطلق حداقل نیز به­ترتیب بیشترین همبستگی منفی را با مناطق کشت زعفران داشتند. همچنین در طبقه­بندی مناطق کشت زعفران، آنالیز تشخیص و ماشین بردار پشتیبان، از دقت بالاتری برخوردار بودند. بین مناطق کشت زعفران و میزان عملکرد محصول همبستگی نسبتاً مناسبی با ضریب همبستگی 38/0 به‌دست آمد. بین مناطق کشت و پارامترهای اقلیمی همبستگی بالایی برخوردار است و آنالیز نزدیک‌ترین همسایه با ضرایب تعیین برابر ۱ و 94/0 در مراحل آموزش و آزمون، با دقت بالایی مناطق کشت را طبقه­بندی نماید، اما در پیش­بینی میزان عملکرد محصول بر اساس پارامترهای اقلیمی، دقت مدل­ها نسبتاً پایین بود (متوسط ضریب تعیین برابر 48/0 و 05/0 در مراحل آموزش و آزمون) و آنالیز نزدیک‌ترین همسایه، بالاترین دقت پیش­بینی را در مراحل آموزش و آزمون (به ترتیب ضریب تعیین برابر ۱ و 17/0) نشان داد. طبق یافته­های تحقیق، می­توان با استفاده از پارامترهای اقلیمی و الگوریتم­های داده­کاوی، به‌طور مناسب اقدام به تفکیک مناطق کشت نمود و با شناسایی مناطقی که اقلیم آن‌ها مشابه مناطق با میزان عملکرد بالا است، مناطق مستعد کشت زعفران را شناسایی نمود.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Climatic zonation and land suitability determination for saffron in Khorasan-Razavi province using data mining algorithms

نویسندگان [English]

  • mehdi Bashiri 1
  • Ali Maroosi 2
  • Amir Salari 3
  • Mohammad Ghodoosi 4
1 Assistant Professor, Department of Range and Watershed Management, Faculty of Agriculture and Natural Resources, University of Torbat Heydarieh
2 Assistant Professor, Department of Computer Engineering and Information Technology, Faculty of Technical and Engineering, University of Torbat Heydarieh
3 Assistant Professor, Department of Plant Production, Faculty of Agriculture and Natural Resources, University of Torbat Heydarieh
4 Lecturer, Department of Industrial Engineering, Faculty of Technical and Engineering, University of Torbat Heydarieh
چکیده [English]

Yield prediction for agricultural crops plays an important role in export-import planning, purchase guarantees, pricing, secure profits and increasing in agricultural productivity. Crop yield is affected by several parameters especially climate. In this study, the saffron yield in the Khorasan-Razavi province was evaluated by different classification algorithms including artificial neural networks, regression models, local linear trees, decision trees, discriminant analysis, random forest, support vector machine and nearest neighbor analysis. These algorithms analyzed data for 20 years (1989-2009) including 11 climatological parameters. The results showed that a few numbers of climatological parameters affect the saffron yield. The minimum, mean and maximum of temperature, had the highest positive correlations and the relative humidity of 6.5h, sunny hours, relative humidity of 18.5h, evaporation, relative humidity of 12.5h and absolute humidity had the highest negative correlations with saffron cultivation areas, respectively. In addition, in classification of saffron cultivation areas, the discriminant analysis and support vector machine had higher accuracies. The correlation between saffron cultivation area and saffron yield values was relatively high (r=0.38). The nearest neighbor analysis had the best prediction accuracy for classification of cultivation areas. For this algorithm the coefficients of determination were 1 and 0.944 for training and testing stages, respectively. However, the algorithms accuracy for prediction of crop yield from climatological parameters was low (the average coefficients of determination equal to 0.48 and 0.05 for training and testing stages). The best algorithm i.e. nearest neighbor analysis had coefficients of determination equal to 1 and 0.177 for saffron yield prediction. Results showed that, using climatological parameters and data mining algorithms can classify cultivation areas. By this way it is possible to identify areas that have similar climate to prone areas and recognize suitable areas for cultivation.

کلیدواژه‌ها [English]

  • Separation
  • singulation
  • saffron flower
  • aligning

Abraham, A. 2005. Artificial neural networks, Presented in book: Handbook of Measuring System Design, Oklahoma State University, Stillwater, USA. pp. 902-908.

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 (2): 70-77.

Ashrafi, S. 2010. Precipitation classification of northwest of Iran using cluster analysis and discriminate analysis. Journal of Climate Research 1 (3-4): 27-44. (In Persian).

Assaleh, K., Shanableh, T., and Kheil, Y.A. 2013. Group method of data handling for modeling magnetorheological dampers. Intelligent Control and Automation 4: 70-79.

Azadeh, A., Ghaderi, S.F., Anvari, M., and Saberi, M. 2006. Measuring performance electric power generations using artificial neural networks and fuzzy clustering. Proceedings of the 32nd Annual Conference of the IEEE Industrial Electronics Society (IECON’06), Conservatoire National des Arts and Metiers, Paris, France.

Bagheri, S., Gheysari, M., Ayoubi, Sh., and Lavaee, N. 2012. Silage maize yield prediction using artificial neural networks. Journal of Plant Production 19 (4): 77-96. (In Persian).

Bashiri, M., and Salari, A. 2016. Using geostatistics for zoning prone areas of saffron cultivation in Razavi-Khorasan province based on climatological parameters. Journal of Saffron Agronomy and Technology 4 (2): 155-167. (In Persian).

Bashiri, M., Seyedi, S.M., and Tosan, M. 2014. The effect of sunny hours numbers on saffron yield in Khorasan-Razavi province. 3rd National Congress on Saffron Scientific-Research Achievements, Torbat Heydarieh, 26-27 November 2014, 3pp. (In Persian).

Basu, J.K., Bhattacharyya, D., and Kim, T.H. 2010. Use of artificial neural network in pattern recognition. International Journal of Software Engineering and its Applications 4 (2): 23-34.

Breiman, L. 2001. Random forests. Machine Learning Journal 45 (1): 5-32.

Christopher, J., and Burges, C.A. 1998. Tutorial on support vector machines for pattern recognition. Journal of Data Mining and Knowledge Discovery 2: 121-167.

Coppersmith, D., Hong, S.J., and Hosking, J.R. 1999. Partitioning nominal attributes in decision trees. Journal of Data Mining and Knowledge Discovery 3 (2): 197–217.

Coulibaly, P., Anctil, F., Aravena, R., and Bobee, B. 2001. Artificial neural networks modelling of water table depth fluctuations. Water Resources Research 37 (4): 885-896.

Damangir, H. 2001. Training artificial neural network dynamics and its application in real time prediction of floods. M.Sc thesis, Shiraz University. (In Persian).

Ebrahimkhani, S., Afzali, M., and Shokoohi, A. 2012. Weather and road accidents factors using data mining algorithms. Zanjan Law Students Journal 1 (1): 112-125. (In Persian).

 Golabi, M.R., Akhondali, A.M., and Radmanesh, F. 2013. Comparison of the performance of different neural networks algorithm functions in simulation of seasonal precipitation, Case study:  Selected stations of Khuzestan province. Journal of Geographical Sciences 13 (30): 151-169. (In Persian).

Hajian, A., Zomorrodian, H., Styles, P., Greco, F., and Lucas, C. 2012. Depth estimation of cavities from microgravity data using a new approach: the local linear model tree (LOLIMOT). Near Surface Geophysics Journal 10 (3): 221-234.

Hartmann, B., Ebert, T., Fischer, T., Belz, J., Kampmann, G., and Nelles, O. 2012a. LMNtool - Toolbox zum automatischen Trainieren lokaler Modellnetze. 22nd Workshop of Computational Intelligence, Dortmund, Germany, p. 341-355.

Hartmann, B., Ebert, T., Fischer, T., Belz, J., Kampmann, G., and Nelles, O. 2012b. LMN-Tool: Matlab-Toolbox for Local Model Networks. Siegen University, Deutschland.

Hosseini, M., Mollafilabi, A., and Nassiri, M. 2008. Spatial and temporal patterns in Saffron (Crocus sativus L.) yield of Khorasan province and their relationship with long term weather variation. Journal of Iranian Field Crop Research 6 (1): 79-88. (In Persian).

Imrie, C.E., Dean, S., and Korre, A. 2000. River flow using artificial neural network: generalization beyond the calibration range. Journal of Hydrology 233 (1-4): 138-153.

Islam, S., and Kothart, R. 2000. Artificial neural networks in remote sensing of hydrologic processes. Journal of Hydrologic Engineering 5 (2): 138-144.

Johnson, R.A., and Wichern, W.D. 2008. Applied multivariate statistical analysis (6th Edition), Upper Saddle River, NJ, USA, 800 p.

Kalantari, K.h. 2008. Processing and analysis of data on socio-economic research using SPSS software. Tehran, Saba Farhang, 388 p. (In Persian).

Kaul, M., Hill, R.L., and Walthall, C. 2005. Artificial neural networks for corn and soybean yield prediction. Journal of Agricultural System 85 (1): 1-18.

Khoshgoftaar, T.M., Golawala, M., and Van Hulse, J. 2007. An empirical study of learning from imbalanced data using random forest. Proceedings of the 19th IEEE Conference on Tools with Artificial Intelligence 2: 310-317.

Landeras, G., Ortiz-Barredo, A., and Lopez, J.J. 2009. Forecasting weekly evapotranspiration with ARIMA and artificial neural network models. Irrigation and Drainage Engineering, American Society of Civil Engineers 135 (3): 323-334.

Loh, W.Y. 2011. Classification and regression trees. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 1 (1):14-23.

Madala, H.R., and Ivakhnenko, A.G. 1974. Inductive learning algorithms for complex system modeling. Boca Raton: CRC, 373 pp.

Meng, X., Zhang, Z., and Xu, X. 2014. A novel K-Nearest neighbor algorithm based on I-Divergence with application to soil moisture estimation in maize field. Journal of Software 9 (4): 841-846.

Merdun, H., Çınar, O., Meral, R., and Apan, M. 2006. Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity. Soil and Tillage Research 90 (1-2): 108-116.

Moradkhani, H., Hsu, K.L., Gupta, H.V., and Sorooshian, S. 2004. Improved streamflow forecasting using self-organizing radial basis function artificial neural networks. Journal of Hydrology 295 (1-4): 246-262.

Mubiru, J. 2008. Predicting total solar irradiation values using artificial neural networks. Renewable Energy journal 33 (10): 2329-2332.

Mukerji, A., Chatterjee, C., and Raghuwanshi, N.S. 2009. Flood forecasting using ANN, Neuro-fuzzy and Neuro-GA models. Journal of Hydrologic Engineering. American Society of Civil Engineers 14 (6): 647-652.

Pardoe, I., Yin, X., and Cook, R.D. 2007. Graphical tools for quadratic discriminant analysis. Technometrics Journal 49 (2): 172-183.

Pinto, U., Maheshwar, B., Shrestha, S., and Morris, C. 2012. Modeling eutrophication and microbial risks in peri-urban river systems using discriminant function analysis. Water Research Journal 4 (6): 6476- 6488.

Piri, J., Amin, S., Moghaddamnia, A., Keshavarz, A., Han, D., and Remesan, R. 2009. Daily pan evaporation modeling in a hot and dry climate. Journal of Hydrologic Engineering, American Society of Civil Engineers 14 (8): 803-811.

Platt, J. 1998. Sequential minimal optimization: A fast algorithm for training support vector machines. Microsoft Research TechReport, Number MSR-TR-98-14: p. 21.

Rajagopalan, B., and Lall, U. 1999. A k-nearest neighbor simulator for daily precipitation and other variables. Water Resources Research 35 (10): 3089–3101.

Samsudin, R., Saad, P., and Shabri, A. 2008. The GMDH model and its application to forecasting of rice yields. Journal Teknologi Maklumat 20 (4): 113-124.

Shirdeli, A., and Tawassoli, A. 2015. Predicting yield and water use efficiency in saffron using models of artificial neural network based on climate factors and water. Saffron Agronomy and Technology 3 (2): 121-131. (In Persian).

Siemsen, E., Roth, A., and Oliveira, P. 2010. Common method bias in regression models with linear, quadratic, and interaction effects. Organizational Research Methods 13 (3): 456-476.

Smith, B.A., Hoogenboom, G., and McClendon, R.W. 2009. Artificial neural networks for automated year-round temperature prediction. Computers and Electronics in Agriculture 68 (1): 52-61.

Tamura, H., and Kondo, T. 1980. Heuristics free group method of data handling algorithm of generating optimal partial polynomials with application to air pollution prediction. International Journal of Systems Science 11 (9): 1095-1111.

Tauser, J., and Buryan, P. 2011. Exchange Rate Predictions in International Financial Management by Enhanced GMDH Algorithm. Prague Economic Papers 20 (3): 232-249.

Toloei Ashlaghi, A., Poorebrahimi, A., Ebrahimi, M., and Ghasemahmad, L. 2013. Using data mining techniques for prediction breast cancer recurrence. Iranian Journal of Breast Diseases 5 (4): 23-34. (In Persian).

Zealand, C.M., Bum, D.H., and Simonovic, S.P. 1999. Short term stream flow forecasting using Artificial Neural Networks. Journal of Hydrology 214 (1-4): 32-48.

Zhan, Y., Chen, H., and Zhang, G.C. 2006. An optimization algorithm of K-NN classification. IEEE International Conference on Machine Learning and Cybernetics, Dalian, China, pp. 2246-2251.