Modeling in Nutrient Sensing for Agricultural and Environmental Applications

  • Won Suk Lee
  • Ismail Bogrekci
  • Min Min
Part of the Springer Optimization and Its Applications book series (SOIA, volume 25)


This chapter describes applications of modeling in nutrient prediction, such as nitrogen (N) for citrus production and phosphorus (P) for agricultural and environmental purposes. Heavy reliance on agricultural chemicals has raised many environmental and economic concerns. Some of the environmental concerns include the presence of agricultural chemicals in groundwater and eutrophication in lakes due to excessive nutrients. To prevent groundwater contamination or eutrophication in lakes, excess use of chemicals should be avoided. Timely and efficient supplies of nutrients for agricultural production are also essential for high yield and profit.

Nitrogen is an essential nutrient for growing crops and is also a concern in maintaining a healthy environment. It is well-known that excess P entering a lake from surrounding agricultural fields causes many problems, such as periodic algal blooms and displacement of native ecosystems. Currently, N and P concentrations are measured from samples obtained in agricultural fields through standard laboratory analysis procedures, which are very time consuming, costly, and labor intensive.

Real-time sensing systems using N and P prediction models will enable cost-effective nutrient detection, which will greatly decrease the time and labor required for monitoring nutrient levels in crops and in tributaries of lakes. Citrus tissue samples are acquired from commercial groves at different times of the year and at different stages of growth. Soil samples are obtained from different locations in drainage basins of lakes. Reflectance spectra of samples are measured in the ultraviolet, visible, and near-infrared regions. Nutrient concentrations in the samples are correlated with the absorbance of the same samples.

Prediction models are developed using different statistical methods, such as stepwise multiple linear regression (SMLR) and partial least squares (PLS) regression. Then, N and P concentrations in unknown samples are determined nondestructively from reflectance spectra of the samples. Such prediction could be used to better assess the effectiveness of best management practices for fertilizers. The sensor systems are combined with a differential Global Positioning System (DGPS) receiver, and they can generate a nutrient concentration map of the entire citrus grove or lake drainage basin under investigation.


Partial Little Square Partial Little Square Regression Stepwise Multiple Linear Regression Partial Little Square Analysis Differential Global Position System 


  1. 1.
    Allen, L., Jr. 1987. Dairy-sitting criteria and other options for waste water management on high-table soils. Soil & Crop Science Society 47: 108–127.Google Scholar
  2. 2.
    Bausch, W.C., Diker, K., Goetz, A. F. H., Curtis, B. 1998. Hyperspectral characteristics of nitrogen deficient corn. ASAE Paper No. 983061. St. Joseph, MI: ASAE.Google Scholar
  3. 3.
    Beal, D.J. 2005. SAS code to select the best multiple linear regression model for multivariate data using information criteria. In: Proceedings of Southeast SAS Users Group Conference.Google Scholar
  4. 4.
    Björkström, A., Sundberg, R. 1999. A generalized view on continuum regression. Scandinavian Journal of Statistics 26: 17–30.MATHCrossRefGoogle Scholar
  5. 5.
    Blackmer, T.M., Schepers, J.S., Varvel, G.E. 1994. Light reflectance compared with other nitrogen stress measurements in corn leaves. Agronomy Journal 86: 934–938.CrossRefGoogle Scholar
  6. 6.
    Bogrekci, I., Lee, W.S., Herrera, J. 2003. Assessment of P-concentrations in the Lake Okeechobee drainage basins with spectroscopic reflectance of VIS and NIR. ASAE paper No. 031139. St. Joseph, MI: ASAE.Google Scholar
  7. 7.
    Bogrekci, I., Lee, W.S., Herrera, J.P. 2004. Spectral signatures for the Lake Okeechobee soils using UV-VIS-NIR spectroscopy and prediction phosphorus concentrations. ASAE Paper No. 041076. St. Joseph, MI: ASAE.Google Scholar
  8. 8.
    Bogrekci, I., Lee, W.S. 2005. Spectral phosphorus mapping using diffuse reflectance of soils and grass. Biosystems Engineering 91(3): 305–312.CrossRefGoogle Scholar
  9. 9.
    Card, D.H., Peterson, D.L., Matson, P.A., Aber, J.D. 1988. Prediction of leaf chemistry by the use of visible and near infrared reflectance spectroscopy. Remote Sensing of Environment 26: 123–147.CrossRefGoogle Scholar
  10. 10.
    Esbensen, K.H. 2002. Multivariabte Data Analysis in Practice. 5th ed. Woodbridge, NJ: CAMO Technologies.Google Scholar
  11. 11.
    Federico, A., Dickson, K., Kratzer, C., Davis, F. 1981. Lake Okeechobee water quality studies and eutrophication assessment. Tech. Publ. 81-2. S. Florida Water Management District., West Palm Beach, FL.Google Scholar
  12. 12.
    Gain, S. 1997. An optimized network for phosphorus load monitoring for Lake Okeechobee, Florida. USGS Report 97-4011.Google Scholar
  13. 13.
    Geladi, P., Kowalski, B.R. 1986. Partial least squares regression: a tutorial. Analytica Chimica Acta 185: 1–17.CrossRefGoogle Scholar
  14. 14.
    Harper, D. 1992. Eutrophication of Freshwater. Principles, Problems and Restoration. New York: Chapman and Hall.Google Scholar
  15. 15.
    Helland, I.S. 2001. Some theoretical aspects of partial least squares regression. Chemometrics and Intelligent Laboratory Systems 58: 97–107.CrossRefGoogle Scholar
  16. 16.
    Herrera, J.P., Lee, W.S., Bogrekci, I. 2004. Spectral based phosphorus sensing in the Lake Okeechobee basin. ASAE paper No. 041077. St. Joseph, MI: ASAE.Google Scholar
  17. 17.
    Lingærde, O.L., Christophersen, N. 2000. Shrinkage structure of partial least squares. Scandinavian Journal of Statistics 27: 459–473.CrossRefGoogle Scholar
  18. 18.
    Martens, H. 2001. Reliable and relevant modeling of real world data: a personal account of the development of PLS regression. Chemometrics and Intelligent Laboratory Systems 58: 85–95.CrossRefGoogle Scholar
  19. 19.
    Martens, H., Næs, T. 1989. Multivariate Calibration. Chichester, England: John Wiley & Sons.MATHGoogle Scholar
  20. 20.
    Min, M., Lee, W.S. 2003. Spectral-based nitrogen sensing for citrus. ASAE paper No. 031137. St. Joseph, MI: ASAE.Google Scholar
  21. 21.
    Min, M., Lee, W.S. 2005. Determination of significant wavelengths and prediction of nitrogen content for citrus. Translation ASAE 48(2): 455–461.Google Scholar
  22. 22.
    Mueller, D.K., Helsel, D.R. 1996. Nutrients in the nation's waters – Too much of a good thing? U.S. Geological Survey Circular 1136, p. 24.Google Scholar
  23. 23.
    Nair, V., Graetz, D., Portier, K. 1995. Forms of phosphorus in soil profiles from dairies of south Florida. Soil Science Society of America 59: 1244–1249.CrossRefGoogle Scholar
  24. 24.
    SAS Institute Inc. 1999. SAS/STAT Users Guide. The PLS Procedure. Version 8. Cary, NC: SAS Institute, pp. 2691–2734.Google Scholar
  25. 25.
    Sharpley, A. 1999. Agricultural phosphorus and eutrophication. Environmental Quality 24: 947–951.CrossRefGoogle Scholar
  26. 26.
    South Florida Water Management District (SFWMD). 2003. Lake Okeechobee. Available at: Accessed August 2003.
  27. 27.
    Stafford, J.V., Weaving, G.S., Lowe, J.C. 1989a. A portable infra-red moisture meter for agricultural and food materials: Part 1, Instrument development. Journal of Agricultural Engineering Research 43: 45–56.Google Scholar
  28. 28.
    Stafford, J.V., Bull, C.R., Weaving, G.S. 1989b. A portable infra-red moisture meter for agricultural and food materials: Part 2, Field evaluation on grass. Journal of Agricultural Engineering Research 43: 57–66.CrossRefGoogle Scholar
  29. 29.
    Stoica, P., Söderström, T. 1998. Partial least squares: a first-order analysis. Scandinavian Journal of Statistics 25:17–24.MATHCrossRefGoogle Scholar
  30. 30.
    Sudduth, K.A., Hummel, J.W. 1996. Geographic operating range evaluation of a NIR soil sensor. Translation ASAE 39(5): 1599–1604.Google Scholar
  31. 31.
    Sundberg, R. 1999. Multivariate calibration – Direct and indirect regression methodology. Scandinavian Journal of Statistics 26: 161–207.MathSciNetMATHCrossRefGoogle Scholar
  32. 32.
    Thomas, J.R., Oerther, G.F. 1972. Estimating nitrogen content of sweet pepper leaves by reflectance measurements. Agronomy Journal 64: 11–13.CrossRefGoogle Scholar
  33. 33.
    Tobias, R.D. 2000. TS-509: An introduction to partial least squares regression. Cary, NC: SAS Institute Inc.Google Scholar
  34. 34.
    U.S. EPA. 1994. National water quality inventory. 1992 Report to Congress. US EPA 841-R-94-001. Office of Water. Washington, DC: U.S. Government Printing Office.Google Scholar
  35. 35.
    U.S. EPA. 2006. List of drinking water contaminants & MCLs. Available at: Accessed 15 August 2006.
  36. 36.
    Wang, N., Zhang, N., Peterson, D.E., Dowell, F.E. 2000. Testing of a spectral-based weed sensor. ASAE Paper No. 003127. St. Joseph, MI: ASAE.Google Scholar
  37. 37.
    Williams, P., Norris, K. 2001. Near-Infrared Technology in the Agricultural and Food Industries. 2nd ed. St. Paul, MI: American Association of Cereal Chemists, Inc.Google Scholar
  38. 38.
    Wold, H. 1975. Soft modeling by latent variables: the nonlinear iterative partial least squares approach. In Perspectives in Probability and Statistics. Papers in Honor of M.S. Barlett. J. Gani, ed. New York: Academic Press.Google Scholar
  39. 39.
    Wold, S., Martens, H., Wold, H. 1983. The multivariate calibration method in chemistry solved by the PLS method. In: Proceedings of the Conference in Matrix Pencils. A. Ruhe and B. Kagstrom, eds. Heidelberg, Germany: Springer-Verlag.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  • Won Suk Lee
    • 1
  • Ismail Bogrekci
  • Min Min
  1. 1.Department of Agricultural and Biological EngineeringUniversity of FloridaGainesvilleUSA

Personalised recommendations