{"title":"An Enhanced Artificial Neural Network for Air Temperature Prediction","authors":"Brian A. Smith, Ronald W. McClendon, Gerrit Hoogenboom","volume":7,"journal":"International Journal of Computer and Information Engineering","pagesStart":2166,"pagesEnd":2172,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/3911","abstract":"
The mitigation of crop loss due to damaging freezes requires accurate air temperature prediction models. An improved model for temperature prediction in Georgia was developed by including information on seasonality and modifying parameters of an existing artificial neural network model. Alternative models were compared by instantiating and training multiple networks for each model. The inclusion of up to 24 hours of prior weather information and inputs reflecting the day of year were among improvements that reduced average four-hour prediction error by 0.18°C compared to the prior model. Results strongly suggest model developers should instantiate and train multiple networks with different initial weights to establish appropriate model parameters.<\/p>\r\n","references":"[1] W. R. Okie, G. L. Reighard, W. C. Newall, Jr., C. J. Graham, D. J.\r\nWerner, A. Powell, G. Krewer, and T. G. Beckman, \"Spring freeze\r\ndamage to the 1996 peach and nectarine crop in the southeastern United\r\nStates,\" HortTechnology, vol. 8, pp. 381-386, 1998.\r\n[2] R. W. McClendon and G. Hoogenboom, \"New non-insurance risk\r\nmanagement tools: Decision support for freeze protection using artificial\r\nneural networks,\" presented at the USDA Agricultural Outlook Forum,\r\nArlington, VA, Feb. 24, 2005.\r\n[3] C. Woods. (1998, Jan. 18). \"New Florida Automated Weather Network\r\n(FAWN) goes online today,\" [Press release, online]. Available:\r\nhttp:\/\/www.napa.ufl.edu\/98news\/weather.htm (Verified July 15, 2005)\r\n[4] G. Hoogenboom, \"The Georgia automated environmental monitoring\r\nnetwork,\" in Preprints of the 24th Conference On Agricultural and\r\nForest Meteorology, American Meteorological Society, Boston, MA,\r\n2000, pp. 24-25.\r\n[5] A. Jain, R. W. McClendon, G. Hoogenboom, and R. Ramyaa,\r\n\"Prediction of frost for fruit protection using artificial neural networks,\"\r\nAmerican Society of Agricultural Engineers, St. Joseph, MI, ASAE\r\nPaper 03-3075, 2003.\r\n[6] A. Jain, \"Frost prediction using artificial neural networks: A temperature\r\nprediction approach,\" M.S. thesis, Artificial Intelligence Center,\r\nUniversity of Georgia, Athens, GA, 2003.\r\n[7] B. R. Temeyer, W. A. Gallus, Jr., K. A. Jungbluth, D. Burkheimer, and\r\nD. McCauley, \"Using an artificial neural network to predict parameters\r\nfor frost deposition on Iowa bridgeways,\" in Proceedings of the 2003\r\nMid-Continent Transportation Research Symposium, Iowa State\r\nUniversity, Ames, IA, 2003.\r\n[8] Ramyaa, \"Frost prediction using artificial neural networks: A\r\nclassification approach,\" M.S. thesis, Artificial Intelligence Center,\r\nUniversity of Georgia, Athens, GA, 2004.\r\n[9] S. Haykin, Neural networks: a comprehensive foundation, 2nd edition.\r\nUpper Saddle River, NJ: Prentice Hall, 1998.\r\n[10] Manual of NeuroShell 2, Ward Systems Group, Frederick, MD, 1993.\r\n[11] F. Salehi,, R. Lacroix, and K. M. Wade, \"Effects of learning parameters\r\nand data presentation on the performance of backpropagation networks\r\nfor milk yield prediction,\" Transactions of the ASAE, vol. 41, pp. 253-\r\n259, 1998.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 7, 2007"}