Meteorolojik Parametreler Kullanılarak Yapay Sinir Ağları ile Toprak Sıcaklığının Tahmini

Bu çalışmanın amacı, Devlet Meteoroloji İşleri Genel Müdürlüğü'nden alınan 1970-2011 yılları arasındaki Türkiye'deki illere ait 88 istasyonda ölçülen aylık ortalama değerlere sahip bazı meteorolojik parametreleri kullanarak bir sonraki yılın aylık ortalama toprak sıcaklıklarını tahmin eden bir model geliştirmektir. Beş, on, yirmi, elli ve yüz santimetre olmak üzere beş farklı derinlikteki toprak sıcaklıkları için ileri beslemeli ve levenberg marquardt algoritmalı olan beş ayrı yapay sinir ağı (YSA) modeli geliştirilmiştir. Yapay sinir ağını eğitmek için kullanılan veriler lineer regresyon modeline uygulanarak, yapay sinir ağı modelleri ile regresyon modellerinin performansları belirlilik katsayısı (R2), ortalama karesel hata (OKH) ve ortalama mutlak yüzde hata (MAPE) gibi kriterlere göre kıyaslanmıştır. Bu kriterlere göre yapay sinir ağı modellerindeki tahmin sonuçlarının regresyon modellerindeki tahmin sonuçlarından çok daha iyi olduğu ve yapay sinir ağı modellerindeki tahmin sonuçlarının ölçülen gerçek toprak sıcaklıklarına çok daha yakın olduğu belirlenmiştir

Estimating Soil Temperature With Artificial Neural Networks Using Meteorological Parameters

The aim of this study is to develop a model which estimates monthly average soil temperature in the coming year by using some meteorological parameters that cover monthly average values measured by Turkish State Meteorological Service in 88 stations in Turkey between 1970 and 2011 years. Five different artificial neural network estimation models that are feed forward neural networks and algorithm of levenberg marquardt networks have been developed for soil temperature in different depths such as five, ten, twenty, fifty and a hundred centimeters. These models have been applied to lineer regression models and the productivity of artificial neural network models and regression models has been compared in regard to criteria like R2, MSE and MAPE according to the criteria, it has been determined that estimations with artificial neural network models are much more better than the ones with regression models, and estimations with artificial neural network models are so close to the real soil temperatures

___

  • Zheng, D., Raymond Hunt, E., Running, S., " A Daily Soil Temperature Model Based on Air Temperature and Precipitation for Continental Applications", Climate Research, 2, 183-191, 1993.
  • Bond-Lamberty, B., Wang, C., Gower, S., "Spatiotemporal Measurement and Modeling of Stand- Level Boreal Forest Soil Temperatures", Agriculture and Forest Meteorology, 131, 27-40, 2005.
  • Yang, C, C., Prasher, S.O., Mehuys, G.R., Patni, N.K., "Application of Artificial Neural Networks for Simulation of Soil Temperature", Transactions of the ASABE, Vol: 40(3), 649-656, 1997.
  • Bilgili, M., Şimşek, E., Şahin, B., "Ege Bölgesi'ndeki Toprak Sıcaklıklarının Yapay Sinir Ağları Yöntemi İle Belirlenmesi", Isı Bilimi ve Tekniği Dergisi, 30(1), 121- 132, 2010.
  • Bilgili, M., "The Use of Artificial Neural Networks for Forecasting the Monthly Mean Soil Temperatures in Adana, Turkey", Tubitak Journal of Agriculture and Forestry, Vol:35, 83-93, 2011.
  • Mavi, B., Günoğlu, İ., Akkurt, İ., "Yapay Sinir Ağı Kullanarak Toprak Sıcaklığı Tahmini", Journal of New World Sciences Academy, 6-2 (2011), 30-36, 2011.
  • Omaima, N. A., Shalla, A., "Nonlineer Autoregresivve Neural Network for Estimation Soil Temperature: A Comparison of Different Optimization Neural Network Algorithms", Special Issue of ICIT 2011 Conference, 2011.
  • Öztürk, M., Salman, O., Koç, M., "Artificial Neural Network Model for Estimating the Soil Temperature", Canadian Journal of Soil Science, 91, 551-562, 2011.
  • Jebamalar, A, S., Roja, A,T., Bai, J,S., "Prediction of Annual and Seasonal Soil Temperature Variation Using Artificil Neural Network", Indian Journal of Radio&Space Physics, Vol:41, 48-57, 2012. 19.
  • Tabari, H., Sabziparvar, A. A., Ahmadi, M., "Comparison of Artificial Neural Network and Multivariate Linear Regression Methods for Estimation of Daily Soil Temperature in an Arid Region", Meteorology and tmospheric Physics, Vol:110, 135-142, 2011.
  • Bilgili, M., Şahin, B., Songun, L., "Estimating Soil Temperature Using Neighboring Station Data Via Multi- Nonlinear Regression and Artificial Neural Network Models", Environmental Monitoring and Assessment, DOI 10,1007/s10661-012-2557-5, 2012.
  • Trippi, R. and Turban, E., Neural Networks in Finance and Investing. Chicago:Irwin Publishing, 1996.
  • Tsaukalas, L. H. and Uhrig, R. E., Fuzzy and Neural Approaches in Engineering. New York: Wiley, 1997.
  • Kaastra, I., Boyd, M., "Designing a Neural Network for Forecasting Financial and Economic Time Series", Neurocomputing, 10, 215-236, 1996.
  • Levenberg, K., "A Method for the Solution of Certain Problems in Last Squares", Quart. Appl. Math. 2, 164- 168, 1944.
  • Marquardt, D., "An Algorithm for Least Squares Estimation of Nonlinear Parameters", SIAMJ. Appl. Math. 11, 431-441, 1963.
  • Hagan, M. T., Menhaj, M., "Training Feedforward Networks with the Marquardt Algorithm", IEEE Transactions on Neural Networks, 5(6), 989-993, 1994.
  • Charalambous, C., "Conjugate Gradient Algorithm for Efficient Training of Artificial Neural Networks", IEEE Proceedings, 139 (3), 301-310, 1992.
  • Devilliers, J., Bernard, E., "Backpropagation Neural Networks with One and Two Hidden Layers", IEEE, 4 (1), 136-141, 1993.
  • Çelik, B., "Yapay Sinir Ağları Metedolojisi ile Zaman Serisi Analizi: Teori ve Uygulama", Marmara Üniversitesi, Sosyal Bilimler Enstitüsü, Yüksek Lisans Tezi. 2008.
  • Öztemel, E. "Yapay Sinir Ağları", Papatya Yayıncılık, İstanbul, 2003.
  • Baily, D., Thomson, D., "Developing Neural Network Application". AI Expert, 33-41, 1990.
  • Katz, J. O., "Developing Neural Network Forecasters for Trading", Commodities, 58-70, 1992.
  • Doig, G., "Severity of Illness Scoring in the Intensive Care Unit: A Comparison of Logistic Regression and Artificial Neural Networks", PhD , The University of Western Ontario, 1999.
  • Ünver, Ö., Uygulamalı İstatistik Yöntemler. (İkinci Baskı). Ankara: Siyasal Kitabevi, 1996.
  • Witt, S. F. and Witt, C. A., Modeling and Forecasting Demand in Tourism. Londra: Academic Press., 1992.
  • Lewis, C. D., Industrial and Business Forecasting Methods. Londra: Butterworths Publishing, 1982.