Environmental Science Models and Artificial Intelligence

  • Sue Ellen Haupt
  • Valliappa Lakshmanan
  • Caren Marzban
  • Antonello Pasini
  • John K. Williams

Environmental science is one of the oldest scientific endeavors. Since the dawn of humanity, along with the ability to reason came the ability to observe and interpret the physical world. It is only natural that people would observe patterns then build basic mental models to predict a future state. For instance, records indicate that there has long been a version of the adage “Red at night, sailor's delight. Red in the morning, sailors take warning.”1 This saying is a simple predictive model based on generations of experience, and it often works. Over time people noted relationships between observations of the sky and subsequent conditions, formed this mental model, and used it to predict future behavior of the weather (Fig. 1.1).

The age of enlightenment following the Renaissance brought a more modern approach to science. Careful experimentation and observation led to uncovering the physics underlying natural phenomena. For instance, a modern understanding of “Red at night, sailor's delight” is based on the theory of Mie scattering. Light rays are scattered by large dry dust particles to the west in the setting sun. According to this theory, large particles tend to scatter the longer wavelength red light forward more than they do the other frequencies of visible light. The long trajectory of the solar beams through the atmosphere when the sun is at a very low zenith angle (such as at sunset or sunrise) compounds this effect. Thus, when light rays from the setting sun are scattered by large dry dust particles associated with a high pressure system to the west, more red light reaches the observer, and the sky appears red. Since prevailing winds in the mid latitudes (where this adage is common) blow from west to east, more Mie scattering at dusk implies that a dry weather pattern is approaching. “Red in the morning, sailors take warning,” refers to a similar process at dawn when the low zenith angle in the east would produce more scattering associated with a high pressure system that has already passed, thus suggesting the possibility that a low pressure system is now approaching and wet weather may follow. This example exemplifies the types of physical explanations of observed phenomena that developed in the environmental sciences.

Keywords

Fuzzy Logic Numerical Weather Prediction Cold Front Fuzzy Logic System Numerical Weather Prediction Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Baer, F., & Tribbia, J. J. (1977). On complete filtering of gravity modes through nonlinear initialization.Monthly Weather Review 1051536–1539CrossRefGoogle Scholar
  2. Branstator, G., & Haupt, S. E. (1998). An empirical model of barotropic atmospheric dynamics and its response to tropical forcing.Journal of Climate 112645–2667CrossRefGoogle Scholar
  3. Charney, J. G., Fjortoft, R., & von Neumann, J. (1950). Numerical integration of the barotropic vorticity equation.Tellus 2237–254CrossRefGoogle Scholar
  4. Cybenko, G. V. (1989). Approximation by superpositions of a sigmoidal function.Mathematics of Control, Signals and Systems 2303–314CrossRefGoogle Scholar
  5. Daley, R. (1991).Atmospheric data analysis(457 pp.). Cambridge: Cambridge University PressGoogle Scholar
  6. Einstein, A. (1922).Sidelights on relativity(56 pp.). London: Methuen & CoGoogle Scholar
  7. Glahn, H. R., & Lowry, D. A. (1972). The use of model output statistics (MOS) in objective weather forecasting.Journal of Applied Meteorology 111203–1211CrossRefGoogle Scholar
  8. Gleick, J. (1987).Chaos: Making a new science(352 pp.). New York: VikingGoogle Scholar
  9. Gneiting, T., & Raftery, A. E. (2005). Weather forecasting with ensemble methods.Science 310(5746), 248–249CrossRefGoogle Scholar
  10. Kalnay, E. (2005).Atmospheric modeling, data assimilation, and predictability(341 pp.). Cambridge, UK: Cambridge University PressGoogle Scholar
  11. Lorenz, E. N. (1963). Deterministic nonperiodic flow.Journal of the Atmospheric Sciences 20130–141CrossRefGoogle Scholar
  12. Lorenz, E. N. (1986). On the existence of a slow manifold.Journal of the Atmospheric Sciences 431547–1557CrossRefGoogle Scholar
  13. Lorenz, E. N. (1992). The slow manifold. What is it?.Journal of the Atmospheric Sciences 492449–2451CrossRefGoogle Scholar
  14. Lorenz, E. N. (2006). Reflections on the conception, birth, and childhood of numerical weather prediction.Annual Review of Earth and Planetery Sciences 3437–45CrossRefGoogle Scholar
  15. Lorenz, E. N., & Krishnamurthy, V. (1987). On the nonexistence of a slow manifold.Journal of the Atmospheric Sciences 442940–2950CrossRefGoogle Scholar
  16. Machenhauer, B. (1977). On the dynamics of gravity wave oscillations in a shallow water model with application to normal mode initialization.Beitr. Phys. Atmos. 50253– 271Google Scholar
  17. Pasini, A. (2005).From observations to simulations. A conceptual introduction to weather and climate modeling(201 pp.). Singapore: World Scientific PublishersGoogle Scholar
  18. Penland, C., & Matrosova, L. (1998). Prediction of tropical Atlantic sea surface temperatures using linear inverse modeling.Journal of Climate 11483–496CrossRefGoogle Scholar
  19. Reed, R. J. (1977). Bjerknes memorial lecture: The development and status of modern weather prediction.Bulletin American Meteorological Society 8390–399Google Scholar
  20. Richardson, L. F. (1922).Weather prediction by numerical process. Cambridge: Cambridge University PressGoogle Scholar
  21. Setiono, R., Leow, W. K., & Zurada, J. M. (2002). Extraction of rules from artificial neural networks for nonlinear regression.IEEE Transactions on Neural Networks 13564– 577CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V 2009

Authors and Affiliations

  • Sue Ellen Haupt
    • 1
  • Valliappa Lakshmanan
    • 2
  • Caren Marzban
    • 3
  • Antonello Pasini
    • 4
  • John K. Williams
    • 5
  1. 1.Applied Research Laboratory and Meteorology DepartmentThe Pennsylvania State UniversityUSA
  2. 2.Cooperative Institute of Mesoscale Meteorological Studies(CIMMS), University of Oklahoma and National Severe Storms Laboratory (NSSL)NormanUSA
  3. 3.Applied Physics Laboratory and the Department of StatisticsUniversity of WashingtonSeattleUSA
  4. 4.CNR — Institute of Atmospheric PollutionMonterotondo Stazione (Rome)Italy
  5. 5.Research Applications LaboratoryNational Center for Atmospheric ResearchBoulderUSA

Personalised recommendations