An Enhanced Artificial Neural Network for Air Temperature Prediction
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.
[1] W. R. Okie, G. L. Reighard, W. C. Newall, Jr., C. J. Graham, D. J.
Werner, A. Powell, G. Krewer, and T. G. Beckman, "Spring freeze
damage to the 1996 peach and nectarine crop in the southeastern United
States," HortTechnology, vol. 8, pp. 381-386, 1998.
[2] R. W. McClendon and G. Hoogenboom, "New non-insurance risk
management tools: Decision support for freeze protection using artificial
neural networks," presented at the USDA Agricultural Outlook Forum,
Arlington, VA, Feb. 24, 2005.
[3] C. Woods. (1998, Jan. 18). "New Florida Automated Weather Network
(FAWN) goes online today," [Press release, online]. Available:
http://www.napa.ufl.edu/98news/weather.htm (Verified July 15, 2005)
[4] G. Hoogenboom, "The Georgia automated environmental monitoring
network," in Preprints of the 24th Conference On Agricultural and
Forest Meteorology, American Meteorological Society, Boston, MA,
2000, pp. 24-25.
[5] A. Jain, R. W. McClendon, G. Hoogenboom, and R. Ramyaa,
"Prediction of frost for fruit protection using artificial neural networks,"
American Society of Agricultural Engineers, St. Joseph, MI, ASAE
Paper 03-3075, 2003.
[6] A. Jain, "Frost prediction using artificial neural networks: A temperature
prediction approach," M.S. thesis, Artificial Intelligence Center,
University of Georgia, Athens, GA, 2003.
[7] B. R. Temeyer, W. A. Gallus, Jr., K. A. Jungbluth, D. Burkheimer, and
D. McCauley, "Using an artificial neural network to predict parameters
for frost deposition on Iowa bridgeways," in Proceedings of the 2003
Mid-Continent Transportation Research Symposium, Iowa State
University, Ames, IA, 2003.
[8] Ramyaa, "Frost prediction using artificial neural networks: A
classification approach," M.S. thesis, Artificial Intelligence Center,
University of Georgia, Athens, GA, 2004.
[9] S. Haykin, Neural networks: a comprehensive foundation, 2nd edition.
Upper Saddle River, NJ: Prentice Hall, 1998.
[10] Manual of NeuroShell 2, Ward Systems Group, Frederick, MD, 1993.
[11] F. Salehi,, R. Lacroix, and K. M. Wade, "Effects of learning parameters
and data presentation on the performance of backpropagation networks
for milk yield prediction," Transactions of the ASAE, vol. 41, pp. 253-
259, 1998.
[1] W. R. Okie, G. L. Reighard, W. C. Newall, Jr., C. J. Graham, D. J.
Werner, A. Powell, G. Krewer, and T. G. Beckman, "Spring freeze
damage to the 1996 peach and nectarine crop in the southeastern United
States," HortTechnology, vol. 8, pp. 381-386, 1998.
[2] R. W. McClendon and G. Hoogenboom, "New non-insurance risk
management tools: Decision support for freeze protection using artificial
neural networks," presented at the USDA Agricultural Outlook Forum,
Arlington, VA, Feb. 24, 2005.
[3] C. Woods. (1998, Jan. 18). "New Florida Automated Weather Network
(FAWN) goes online today," [Press release, online]. Available:
http://www.napa.ufl.edu/98news/weather.htm (Verified July 15, 2005)
[4] G. Hoogenboom, "The Georgia automated environmental monitoring
network," in Preprints of the 24th Conference On Agricultural and
Forest Meteorology, American Meteorological Society, Boston, MA,
2000, pp. 24-25.
[5] A. Jain, R. W. McClendon, G. Hoogenboom, and R. Ramyaa,
"Prediction of frost for fruit protection using artificial neural networks,"
American Society of Agricultural Engineers, St. Joseph, MI, ASAE
Paper 03-3075, 2003.
[6] A. Jain, "Frost prediction using artificial neural networks: A temperature
prediction approach," M.S. thesis, Artificial Intelligence Center,
University of Georgia, Athens, GA, 2003.
[7] B. R. Temeyer, W. A. Gallus, Jr., K. A. Jungbluth, D. Burkheimer, and
D. McCauley, "Using an artificial neural network to predict parameters
for frost deposition on Iowa bridgeways," in Proceedings of the 2003
Mid-Continent Transportation Research Symposium, Iowa State
University, Ames, IA, 2003.
[8] Ramyaa, "Frost prediction using artificial neural networks: A
classification approach," M.S. thesis, Artificial Intelligence Center,
University of Georgia, Athens, GA, 2004.
[9] S. Haykin, Neural networks: a comprehensive foundation, 2nd edition.
Upper Saddle River, NJ: Prentice Hall, 1998.
[10] Manual of NeuroShell 2, Ward Systems Group, Frederick, MD, 1993.
[11] F. Salehi,, R. Lacroix, and K. M. Wade, "Effects of learning parameters
and data presentation on the performance of backpropagation networks
for milk yield prediction," Transactions of the ASAE, vol. 41, pp. 253-
259, 1998.
@article{"International Journal of Information, Control and Computer Sciences:53024", author = "Brian A. Smith and Ronald W. McClendon and Gerrit Hoogenboom", title = "An Enhanced Artificial Neural Network for Air Temperature Prediction", 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.
", keywords = "Time-series forecasting, weather modeling.", volume = "1", number = "7", pages = "1962-6", }
