Hostname: page-component-586b7cd67f-gb8f7 Total loading time: 0 Render date: 2024-11-30T19:45:34.219Z Has data issue: false hasContentIssue false
  • English
  • Français

Feedforward Neural Network Estimation of a Crop Yield Response Function

Published online by Cambridge University Press:  28 April 2015

Wayne H. Joerding ,
Ying Li  and
Douglas L. Young
Wayne H. Joerding
Affiliation:
Department of Economics, Washington State University, Pullman, WA
Ying Li
Affiliation:
FannieMae, Washington DC
Douglas L. Young
Affiliation:
Department of Agricultural Economics, Washington State University, Pullman, WA
Get access Rights & Permissions [Opens in a new window]

Abstract

Feedforward networks have powerful approximation capabilities without the “explosion of parameters” problem faced by Fourier and polynomial expansions. This paper first introduces feedforward networks and describes their approximation capabilities, then we address several practical issues faced by applications of feedforward networks. First, we demonstrate networks can provide a reasonable estimate of a Bermudagrass hay fertilizer response function with the relatively sparse data often available from experiments. Second, we demonstrate that the estimated network with a practical number of hidden units provides reasonable flexibility. Third, we show how one can constrain feedforward networks to satisfy a priori information without losing their flexible functional form characteristic.

Keywords

neural networksbiological process modelsfeedforward networksproduction function
Type
Articles
Information
Journal of Agricultural and Applied Economics , Volume 26 , Issue 1 , July 1994 , pp. 252 - 263
Copyright
Copyright © Southern Agricultural Economics Association 1994

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Aarts, E. and Korst, J.. Simulated Annealing and Boltzmann Machines. New York: John Wiley and Sons, 1989.Google Scholar
Andrews, D.W.K. “Asymptotic Normality of Series Estimators for Nonparametric and Semiparametric Regression Models.” Econometrica, 59(1991):307–345.CrossRefGoogle Scholar
Beattie, B. R., and Taylor, C.R.. The Economics of Production. New York: John Wiley and Sons, 1985.Google Scholar
Barron, A.R. “Universal Approximation Bounds for Superpositions of a Sigmoidal Function.” Manuscript, Department of Statistics, University of Illinois, IL 61820, 1991.Google Scholar
Brokken, R.F. “The Case of a Queer Isoquant: Increasing Marginal Rates of Substitution of Grain Roughage in Cattle Finishing.” West. J. Agr. Econ., 1(1977):221–24.Google Scholar
Carroll, B.W. and Dickinson, B.D.. “Construction of Neural Net Using the Radon Transform.” '89IJCNN Proceedings, I(1989):607–611.Google Scholar
Chambers, Robert G.Applied Production Analysis: A Dual Approach. New York: Cambridge U. Press, 1988.Google Scholar
Cybenko, G. “Approximation by Superpositions of a Sigmoidal Function.” Mathematical Control Signal Systems, 2(1989):303–314.CrossRefGoogle Scholar
Dillon, Carl R., Mjelde, James W., and McCarl, Bruce A.. “Recommendations on the Implementation and Development of Biophysical Simulation Models in Agricultural Economics Research.” Monograph. Dept. of Agr. Econ., Texas A & M U., College Station, 1989.Google Scholar
Engibous, J.C., and Young, D.L.. “Economics of Fertilizer Use.” Ch. 10 in The Fertilizer Handbook. The Fertilizer Inst., Washington, DC, 1982.Google Scholar
Gallant, A.R. “On the Bias in Flexible Functional Forms and an Essentially Unbiased Form.” Journal of Econometrics, 15(1981):211–245.CrossRefGoogle Scholar
Gallant, A.R. “Unbiased Determination of Production Technologies.” Journal of Econometrics, 20(1982):285–323.CrossRefGoogle Scholar
Gallant, A.R. and Golub, G.H.. “Imposing Curvature Restrictions on Flexible Functional Forms.” Journal of Econometrics, 26(1984):295–321.CrossRefGoogle Scholar
Golub, G.H. and Loan, C. F. Van. Matrix Computations. Baltimore: Johns Hopkins University Press, 1989.Google Scholar
Heady, Earl O., and Dillon, John L.. Agricultural Production Functions. Ames: Iowa State U. Press, 1961.Google Scholar
Hornik, K., Stinchcombe, M., and White, H.. “Multilayer Feedforward Networks are Universal Approximators.” Journal of Neural Networks, 2(1989):359–366.CrossRefGoogle Scholar
Hornik, K., Stinchcombe, M., and White, H.. “Universal Approximation of an Unknown Mapping and Its Derivatives Using Multilayer Feedforward Networks.” Journal of Neural Networks, 3(1990):551–560.CrossRefGoogle Scholar
Ito, Y. “Approximation of Functions on a Compact Set by Finite Sums of a Sigmoid Functions Without Scaling.” Journal of Neural Networks, 4(1991):817–826.CrossRefGoogle Scholar
Ito, Y. “Approximation of Continuous Functions on R d by Linear Combinations of Shifted Rotations of a Sigmoid Function With and Without Scaling.” Journal of Neural Networks, 5(1992): 105–116.CrossRefGoogle Scholar
Joerding, W.H. and Li, Y.. “Global Training with A Priori Constraints.” Manuscript, Department of Economics, Washington State University, Pullman, WA, 99164, 1992.Google Scholar
Joerding, W.H. and Li, Y., Hu, S., and Meador, J.. “Approximating Production Technologies with Feedforward Neural Networks.” Forthcoming Advances in Artificial Intelligence in Economics, Finance, and Management. Greenwich: AI Press, 1992.Google Scholar
Joerding, W.H. and Meador, J.L.. “Encoding A Priori Information in Feedforward Networks.” Journal of Neural Networks, 4(1991):847–856.CrossRefGoogle Scholar
Kunkel, K.E. “Operational Soil Moisture Estimation for the Midwestern United States.” J. Appi. Meteorology, Notes and Correspondence, 29(11):1158–66, 1990.2.0.CO;2>CrossRefGoogle Scholar
Li, Y., Joerding, W. H. and Genz, A. “A Hybrid LS/Simulated Annealing Training Algorithm for Feedforward Networks.” Manuscript, Department of Economics, Washington State University, Pullman, WA, 99164, 1992.Google Scholar
McClelland, J. and Rumelhart, D.. Parallel Distributed Processing. Cambridge: The MIT Press, 1988.Google Scholar
Mitscherlich, E.A. “Das Gesetz des Minimums und das Gesetz des Abnehmenden Bodenertrages.” Landw. Jahrb., 38(1909):537–52.Google Scholar
Musser, W., and Tew, B.. “Use of Biophysical Simulation in Production Economics.” So. J. Agr. Econ., 16(1984):77–86.Google Scholar
Spillman, W.J. “Applications of the Law of Diminishing Returns to Some Fertilizer and Feed Data.” J. Farm Econ., 5(1923):36–52.CrossRefGoogle Scholar
Stackle, Claudio O. “Simulation Models in Agriculture: From Cellular Level to Field Scale.” Proceedings of the 1989 Summer Computer Simulation Conf., Austin, TX, July 24-27, 1989.Google Scholar
Thai, C.N. and Shewfelt, R.L.. “Modeling Sensory Color Quality of Tomato and Peach: Neural Networks and Statistical Regression.” Transactions of the ASAE, 34(1991):950–955.CrossRefGoogle Scholar
Theil, H.Principles of Econometrics. New York: John Wiley & Sons, Inc., 1971.Google Scholar
Uhrig, J. W., and Botkin, C.J.. “An Application of Neural Networks in Predicting Planted Acreage of Corn and Wheat in the United States.” Paper presented at the Amer. Agr. Econ. Assoc. annual meeting, Vancouver, BC, Aug. 4-8, 1990.Google Scholar
Uhrig, J. W., Engel, B. A., and Baker, W.L.. “An Application of Neural Networks: Predicting Corn Yields.” Paper presented at the Fourth International Congress for Computer Technology in Agriculture, Paris-Versailles, France, June 1-3, 1992.Google Scholar
Wasserman, P.D.Neural Computing: Theory and Practice. New York: Van Nostrand Reinhold, 1989.Google Scholar