Improving Air Temperature Prediction with Artificial Neural Networks
The mitigation of crop loss due to damaging freezes
requires accurate air temperature prediction models. Previous work
established that the Ward-style artificial neural network (ANN) is a
suitable tool for developing such models. The current research
focused on developing ANN models with reduced average prediction
error by increasing the number of distinct observations used in
training, adding additional input terms that describe the date of an
observation, increasing the duration of prior weather data included in
each observation, and reexamining the number of hidden nodes used
in the network. Models were created to predict air temperature at
hourly intervals from one to 12 hours ahead. Each ANN model,
consisting of a network architecture and set of associated parameters,
was evaluated by instantiating and training 30 networks and
calculating the mean absolute error (MAE) of the resulting networks
for some set of input patterns. The inclusion of seasonal input terms,
up to 24 hours of prior weather information, and a larger number of
processing nodes were some of the improvements that reduced
average prediction error compared to previous research across all
horizons. For example, the four-hour MAE of 1.40°C was 0.20°C, or
12.5%, less than the previous model. Prediction MAEs eight and 12
hours ahead improved by 0.17°C and 0.16°C, respectively,
improvements of 7.4% and 5.9% over the existing model at these
horizons. Networks instantiating the same model but with different
initial random weights often led to different prediction errors. These
results strongly suggest that ANN model developers should consider
instantiating and training multiple networks with different initial
weights to establish preferred 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] 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.
[3] 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, 2003,
ASAE Paper 03-3075.
[4] A. Jain, "Frost prediction using artificial neural networks: A temperature
prediction approach," M.S. thesis, Artificial Intelligence Center,
University of Georgia, Athens, GA, 2003.
[5] Ramyaa, "Frost prediction using artificial neural networks: A
classification approach," M.S. thesis, Artificial Intelligence Center,
University of Georgia, Athens, GA, 2004.
[6] 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.
[7] S. Haykin, Neural networks: a comprehensive foundation, 2nd edition.
Upper Saddle River, NJ: Prentice Hall, 1998, pp. 161-175.
[8] Manual of NeuroShell 2, Ward Systems Group, Frederick, MD, 1993.
[9] 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] 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.
[3] 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, 2003,
ASAE Paper 03-3075.
[4] A. Jain, "Frost prediction using artificial neural networks: A temperature
prediction approach," M.S. thesis, Artificial Intelligence Center,
University of Georgia, Athens, GA, 2003.
[5] Ramyaa, "Frost prediction using artificial neural networks: A
classification approach," M.S. thesis, Artificial Intelligence Center,
University of Georgia, Athens, GA, 2004.
[6] 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.
[7] S. Haykin, Neural networks: a comprehensive foundation, 2nd edition.
Upper Saddle River, NJ: Prentice Hall, 1998, pp. 161-175.
[8] Manual of NeuroShell 2, Ward Systems Group, Frederick, MD, 1993.
[9] 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:59411", author = "Brian A. Smith and Ronald W. McClendon and Gerrit Hoogenboom", title = "Improving Air Temperature Prediction with Artificial Neural Networks", abstract = "The mitigation of crop loss due to damaging freezes
requires accurate air temperature prediction models. Previous work
established that the Ward-style artificial neural network (ANN) is a
suitable tool for developing such models. The current research
focused on developing ANN models with reduced average prediction
error by increasing the number of distinct observations used in
training, adding additional input terms that describe the date of an
observation, increasing the duration of prior weather data included in
each observation, and reexamining the number of hidden nodes used
in the network. Models were created to predict air temperature at
hourly intervals from one to 12 hours ahead. Each ANN model,
consisting of a network architecture and set of associated parameters,
was evaluated by instantiating and training 30 networks and
calculating the mean absolute error (MAE) of the resulting networks
for some set of input patterns. The inclusion of seasonal input terms,
up to 24 hours of prior weather information, and a larger number of
processing nodes were some of the improvements that reduced
average prediction error compared to previous research across all
horizons. For example, the four-hour MAE of 1.40°C was 0.20°C, or
12.5%, less than the previous model. Prediction MAEs eight and 12
hours ahead improved by 0.17°C and 0.16°C, respectively,
improvements of 7.4% and 5.9% over the existing model at these
horizons. Networks instantiating the same model but with different
initial random weights often led to different prediction errors. These
results strongly suggest that ANN model developers should consider
instantiating and training multiple networks with different initial
weights to establish preferred model parameters.", keywords = "Decision support systems, frost protection, fruit,time-series prediction, weather modeling", volume = "1", number = "10", pages = "3200-8", }