TY - JOUR
T1 - Nonlinear analysis and forecasting of a brackish karstic spring
AU - Lambrakis, N.
AU - Andreou, A. S.
AU - Polydoropoulos, P.
AU - Georgopoulos, E.
AU - Bountis, T.
N1 - Copyright:
Copyright 2004 Elsevier Science B.V., Amsterdam. All rights reserved.
PY - 2000
Y1 - 2000
N2 - Nonlinear methods and artificial neural network techniques are applied to the study of the regime and the possibility of short-term forecasting of discharges of the spring of Almyros, Iraklion, Crete. Questions regarding the nonlinearity and chaotic characteristics of the system necessitate the examination of dynamical properties. Toward this objective the time series of daily average discharges is analyzed in detail. First, the dimensionality of the dynamics in the reconstructed phase space is found to be quite low, ~3-4. Then several tests are applied to examine the nonlinearity and the presence of noise in the data. Using the surrogate time series test, a high degree of nonlinearity and a deterministic nature are revealed, while the differentiation test showed that the presence of high-frequency noise in the series of the discharge is not dynamically important. These suggest that an attempt to forecast the short-term future behavior of this time series may turn out to be quite successful. Nonlinear methods, such as Farmer's algorithm and artificial neural networks, were employed and found to exhibit a very satisfactory predictive ability, with neural networks achieving a slightly better performance.
AB - Nonlinear methods and artificial neural network techniques are applied to the study of the regime and the possibility of short-term forecasting of discharges of the spring of Almyros, Iraklion, Crete. Questions regarding the nonlinearity and chaotic characteristics of the system necessitate the examination of dynamical properties. Toward this objective the time series of daily average discharges is analyzed in detail. First, the dimensionality of the dynamics in the reconstructed phase space is found to be quite low, ~3-4. Then several tests are applied to examine the nonlinearity and the presence of noise in the data. Using the surrogate time series test, a high degree of nonlinearity and a deterministic nature are revealed, while the differentiation test showed that the presence of high-frequency noise in the series of the discharge is not dynamically important. These suggest that an attempt to forecast the short-term future behavior of this time series may turn out to be quite successful. Nonlinear methods, such as Farmer's algorithm and artificial neural networks, were employed and found to exhibit a very satisfactory predictive ability, with neural networks achieving a slightly better performance.
UR - http://www.scopus.com/inward/record.url?scp=0034069973&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0034069973&partnerID=8YFLogxK
U2 - 10.1029/1999WR900353
DO - 10.1029/1999WR900353
M3 - Article
AN - SCOPUS:0034069973
VL - 36
SP - 875
EP - 884
JO - Water Resources Research
JF - Water Resources Research
SN - 0043-1397
IS - 4
ER -