Research activities of Martin C. Casdagli at SFI September 1989--May 1991
My research over this period has focused on the theory and application of non-linear time series forecasting. The purpose of time series forecasting is to predict apparently random behavior about which we have little or no knowledge. A time series is a set of values that change in time, for example, daily stock market prices for a given set of firms, or the volume of the polar ice caps over the last two million years. Recent developments in the understanding of chaotic dynamical systems have stimulated new approaches to time series analysis. These results raise the possibility that apparently random behavior may essentially be the consequence of chaotic behavior of deterministic equations with a small number of variables. My main research effort has been to develop a theory of nonlinear time series forecasting which applies to chaotic time series with low levels of observational noise. I have also developed a new algorithm for analyzing experimental time series data in order to determine whether a nonlinear deterministic, as opposed to nonlinear stochastic model is an appropriate description of the data, and have applied this algorithm to a wide range of time series data. In addition to involvement in these and other research activities, I have helped organize a conference on nonlinear modeling and forecasting, jointly sponsored by NATO and SFI. I describe the above projects in more detail in the following paragraphs. Several of these projects benefited greatly fro the excellent computer facilities available at SFI.
- Research Organization:
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Santa Fe Inst., NM (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- W-7405-ENG-36
- OSTI ID:
- 10116969
- Report Number(s):
- LA-SUB-93-223; ON: DE94005655
- Resource Relation:
- Other Information: PBD: [1993]
- Country of Publication:
- United States
- Language:
- English
Similar Records
Detecting nonlinearity and chaos in epidemic data
Phenomenological Model of Nonlinear Dynamics and Deterministic Chaotic Gas Migration in Bentonite: Experimental Evidence and Diagnostic Parameters