JANUARY 2009 DE OLIVEIRA ET AL.

143

Neural Network Model to Predict a Storm Surge

MARILIA M. F. DE OLIVEIRA AND NELSON FRANCISCO F. EBECKEN

Instituto Alberto Luiz Coimbra de Pós-Graduacxão e Pesquisa de Engenharia, Universidade Federal do Rio de Janeiro,
Rio de Janeiro, Brazil

JORGE LUIZ FERNANDES DE OLIVEIRA

Departamento de Geografia, Instituto de Geocieˆncias, Universidade Federal Fluminense, Niterói, Brazil

ISIMAR DE AZEVEDO SANTOS

Departamento de Meteorologia, Instituto de Geocieˆncias, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil

(Manuscript received 30 October 2007, in final form 13 July 2008)

ABSTRACT

The southeastern coast of Brazil is frequently affected by meteorological disturbances such as cold fronts,
which are sometimes associated with intense extratropical cyclones. These disturbances cause oscillations on
the sea surface, generating low-frequency motions. The relationship of these meteorologically driven forces
in low frequency to the storm-surge event is investigated in this work. A method to predict coastal sea level
variations related to meteorological events that use a neural network model (NNM) is presented here.
Pressure and wind values from NCEP–NCAR reanalysis data and tide gauge time series from the Cananéia
reference station in São Paulo State, Brazil, were used to analyze the relationship between these variables
and to use them as input to the model. Meteorological influences in the sea level fluctuations can be verified
by filtering the astronomical tide frequencies for periods lower than tidal cycles (periods higher than 24 h).
Thus, a low-pass filter was applied in the tide gauge and meteorological time series for periods lower than
tides to identify more readily the interactions between coastal sea level response and atmospheric-driven
forces. Statistical analyses on time and frequency domain were used. Maxima correlations and coherence
between the low-frequency sea level and meteorological series could be defined using the time lag of the
NNM input variables. The model was tested for 6-, 12-, 18-, and 24-hourly forecasts, and the results were
compared with filtered sea level values. The results show that this model is able to capture the effects of
atmospheric and oceanic interactions. It can be considered to be an efficient model for predicting the
nontidal residuals and can effectively complement the standard constant harmonic analysis model. A case
study of a storm that impacted coastal areas of southeastern Brazil in March 1998 was analyzed and
indicates that the neural network model can be effectively utilized in the Cananéia region.

1. Introduction
Oscillations in sea level due to meteorological driving
forces related to wind and pressure occur at different
scales and frequencies in all coastal regions. Some
countries are affected by flooding, with serious damage.
Therefore, knowledge about the sea level height varia-
Corresponding author address: Marilia M. F. de Oliveira, Insti-
tuto Alberto Luiz Coimbra de Pós-Graduacxão e Pesquisa de En-
genharia—COPPE, UFRJ, Caixa Postal 68501, CEP 21945-970,
Rio de Janeiro, RJ, Brazil.
E-mail: marilia@coc.ufrj.br
tions is very important not only for marine services but
also for the protection of coastal residents, for moni-
toring the changes in marine ecosystems, and for de-
signing and constructing onshore and offshore struc-
tures. Interactions between meteorological (atmo-
spheric pressure, wind, sea surface temperature) and
oceanic (salinity and deep sea) variables affect the
regular tides and modify the sea level conditions in
coastal regions, mainly in restricted waters such as bays.
Tropical cyclones and extratropical storms are the
main cause of storm surges that can produce damage
through high waves and sprawling water over large
coastal areas in a single storm. The principal factors

DOI: 10.1175/2008JAMC1907.1

Ó 2009 American Meteorological Society

144 JOURNAL OF APPLIED METEOROLOGY AND CLIMATOLOGY
involved in the generation and modification of storm
surge are the action of wind stresses on the surface
water, reduction of atmospheric pressure (inverted ba-
rometer effect), waves and swells in the shallow water
area, coastline configuration, and bathymetry (Pore
1964).
Frontal systems associated with extratropical cy-
clones introduce variations that are observed in the tide
records and sometimes result in storm surges (Pugh
1987, 2005). These storms differ with respect to size and
intensity, and the associated storm surges have charac-
teristics consistent with these differences. The different
characteristics of these types of storms in particular
concern wind speeds and spatial scale of the storm
(Storch and Worth 2008).
In the South Atlantic Ocean, along the Brazilian
coastline, there are few tide gauge records with long
series to analyze and predict surge events. Characteris-
tics of the meteorological tide variations along the
southeast coast of Brazil have been studied by Marone
and Camargo (1994). Castro and Lee (1995) presented
a study of sea level fluctuations due to wind-driven
forces in the southeast continental shelf. Ribeiro (1997)
investigated a surge caused by the passage of a cyclone
along the Rio de Janeiro coastline that raised the sea
level 0.60 m above the mean sea level datum, causing
damage to coastal communities along the Guanabara
Bay. Netto and Lana (1997) studied the superficial sedi-
ment characteristics of tidal flats in Paranaguá Bay. De
Mesquita (2008a,b) verified a similar behavior of the
mean sea level oscillations along this area of the Bra-
zilian coastline. Mantovanelli et al. (2004) verified the
tidal velocity and duration as a determinant of water
transport and residual flow in Paranaguá Bay estuary.
Dalazoana et al. (2005) studied the mean sea level
variations using longer tide gauge temporal series from
Cananéia and Fiscal Island (state of Rio de Janeiro)
tide gauge and satellite altimetry to establish analysis
methods applicable to Brazilian vertical datum regions.
The classical method of harmonic analysis is used to
predict the astronomical tides. Tidal curves appear as
periodic oscillations and can be described in terms of
amplitude, period, or frequency. The harmonic analysis
is based in tidal variations represented by N harmonic
constituents of the tide (Doodson and Warburg 1944).
Normally, 365 days of hourly data at a point are needed
to extract the constituents with adequate separation of
closely spaced constituents using the least squares
method. These constituents can then be used to provide
reliable predictions for future tides at the respective
point (Franco 1981).
Predictions for reference stations are prepared from
VOLUME 48
the astronomical arguments using local constituents de-
termined by previous analysis and do not take into ac-
count meteorological influences. Thus, the observed
and predicted values of the sea level are normally dif-
ferent. Numerical models developed to predict surges
are still considered to be insufficient because of the
complexity of the nonlinear processes involved. These
models require a large amount of tidal and meteoro-
logical data, collecting many factors such as central
pressure, speed of the cyclone, rainfall, and coastal to-
pography (Lee 2006).
Nowadays, the neural network model (NNM) has
been widely applied to modeling nonlinear dynamic
systems using time series that translate the physical re-
lations between the input variables (predictors) and the
phenomenon that will be modeled (predictand). Elsner
and Tsonis (1992) developed some methods for making
short-term predictions of nonlinear time series data us-
ing a neural network model. These authors discuss the
implications of these methods for the study of weather
and climate.
The NNM has some important characteristics such as
generalization, parallelism, nonlinearity, adaptability,
and robustness (Haykin 2001). These models have been
used in some fields of science and engineering. Szto-
bryn (2003) applied NNM in hydrological forecasting
where the variation of water level is only wind gener-
ated. The results were successfully compared with ob-
served sea level and other routine methods. Lee (2006)
applied an NNM for forecasting storm surge in Taiwan
related to the passage of three typhoons over the re-
gion. The results indicate that NNM is efficiently ca-
pable of learning and predicting from these events.
Tseng et al. (2007) used a typhoon-surge forecasting
model developed with a backpropagation neural net-
work in coastal northeastern Taiwan. To determine the
better forecasting model, four models were applied and
tested under different compositions of the input vari-
ables. For coastal and harbor engineering applications,
Chang and Lin (2006) simulated tides at multipoints
considering tide-generating forces. The NNM proposed
is applicable for multipoint tidal prediction in which the
tidal type is similar to that of the original point.
The southeast coast of Brazil is sufficiently affected
by cold fronts over 3–5-day periods. An important
event that sometimes occurs because of the combina-
tion of tides and surges is the rising of the sea level with
waves that reached the coastline. There are few NNM
applications to predict the variability of sea level along
the Brazilian coastline that are focused on the surge
events. The relationships describing the response of the
coastal sea level to the influence of cold fronts were
JANUARY 2009 DE OLIVEIRA ET AL.
FIG. 1. Storm surge, observed, and predicted water level at
Cananéia tide gauge station in March 1998. Storm tide can be
verified through the observed tide curve.
analyzed using cross correlations and spectral density
between the tide gauge series and meteorological vari-
ables. Maximum values and time lags of both analyses
were proposed as inputs of the sea level forecast model.
This paper presents a method to predict coastal sea
level variations and surge using an NNM.
Although drastic storm surge typically does not occur
along the coastal waters of Brazil, these events can
cause some damage to coastal regions. A strong storm
surge occurred along the southeast coast of Brazil in
March of 1998, causing severe flooding in these coastal
areas and destroying some coastline constructs. Figure
1 shows the curves related to water level over a 6-day
period at the Cananéia tide gauge station in São Paulo,
Brazil. The storm surge revealed can be compared with
other series. In this case, the curves are water levels
referenced to mean low water (MLW), that is, refer-
enced to a fixed level or station datum (tide gauge
benchmark near a gauge, to which the gauge zero is
referred) for the convenience of plotting with mostly
positive numbers. In this paper, we demonstrate the
application of the NNM for this study case.
Operational forecasting of high sea levels (storm
surges) might be important in the southeast coast of
Brazil, where there are registered sea level variations
above the astronomical tide predictions that can con-
sistently impact coastal zones in this area. The aim of
this study is to develop an empirical prediction of storm
surge by determining the relationship of the wind and
pressure fields to storm surge. This proposed model can
be used to complement the standard constant harmonic
model to improve the prediction of sea level variations.
2. Study area
The study area lies within the Cananéia Estuary
(248509–258059S and 478459–488009W), in the southeast
145
coastal region of Brazil in São Paulo State (Fig. 2). This
region is located on the continental shelf, which is wider
than the shelf of the northern coast. The average width
and declivity near Cananéia city in São Paulo State are
about 218 km and 46 cm km21, respectively (Filippo
2003). The isobaths are oriented from southwest to
northeast, parallel to the coastline with 458 northern
direction (Trucculo 1998). It has wide coastal plains,
long beach barriers, and large estuaries (Angulo and
Lessa 1997). The Cananéia Estuary is an important bio-
logical reserve and contains federal and state environ-
mentally protected areas (SMA 1990, 1996). This estua-
rine system covers an area of 135 km2 and is sur-
rounded by a large mangrove area with high
concentrations of nutrients (Besnard 1950; Shaeffer-
Novelli et al. 1990).
The astronomical tide pattern at Cananéia station is
semidiurnal, with the greatest amplitude H for the con-
stituents M2 (principal lunar) and S2 (principal solar).
The diurnal constituents O1 (principal lunar) and K1
(declinational lunisolar) are also present, as well as the
shallow-water constituents M3 and M4 (third and quar-
ter diurnal lunar, respectively), which indicate the in-
fluence of the propagation of the tide wave in the con-
tinental shelf (Fig. 3).
Surges that are verified in the tide gauge records nor-
mally are related to the same extreme events—the pas-
sage of cold fronts over this region (de Mesquita
2000a,b). Figure 4 shows the maximum recorded at the
Cananéia gauge (3.13 m) during a storm on 25–28
March 1998.
Climatological description of the region
The South American continent is affected by both
tropical and extratropical weather systems. The most
severe weather systems in South America are cold
fronts, intense extratropical cyclones near the east coast
that cause intense winds, upper-level cyclonic vortices
(ULCV; in some cases responsible for cyclogenesis and
frontogenesis), the South Atlantic convergence zone,
squall lines, mesoscale convective complexes, and the
low-level jet. This region is influenced by persistent
high pressure over the South Atlantic Ocean that en-
hances northeast flow across the area. This circulation
is periodically disturbed by the passage of frontal sys-
tems caused by migrating anticyclones that move from
the southwest across the northeast in the southeast
coast of Brazil. In this region the presence of strong
cyclogenesis activity is verified (Gan and Rao 1991; Se-
luchi 1995) that is associated with ULCV that reach
through the South American west coast and cause in-
stability in the east and northeast sector. Gan and Rao
146 JOURNAL OF APPLIED METEOROLOGY AND CLIMATOLOGY VOLUME 48

FIG. 2. Map of the study area with the localization of Cananéia Estuary and the tide gauge station.

(1991) have verified two regions of persistent cyclogen-
esis over South America; one over the San Matias Gulf
in Argentina (42.58S, 62.58W) and another over Uru-
guay (31.58S, 558W). The climate is subtropical humid,
and during the El Niño–South Oscillation (ENSO) phe-
nomenon great climatic disturbances occur in this re-
gion, leading to abundant rain.
ENSO strongly influences rainfall patterns mainly in
southern Brazil that tend to be above the median from

FIG. 3. Tidal cycles at Cananéia station in March 1998 by the FIG. 4. Observed and predicted tide at Cananéia station in
M2, S2, O1, and K1 constituents, including shallow-water terms. March 1998.
JANUARY 2009 DE OLIVEIRA ET AL.
FIG. 5. Map showing the shape of the southeastern coastal region of Brazil and the local-
ization of the tide gauge station and reanalysis points (chart modified from one provided by
CHM).
November to February (Rao and Rada 1990). The El
Niño event in 1997–98 was considered, by some mea-
sures, to be the strongest on record, causing major cli-
matic impacts around the world (McPhaden 1999).
During the 1997–98 El Niño event, the sea level in the
Cananéia region was significantly affected by a storm
surge, which is analyzed in this work.
3. Meteorological and sea level dataset
Hourly sea level records for the period 1997–98 were
obtained from the tide gauge station installed at
Cananéia Estuary at latitude 258019S and longitude
478559W. The equipment has been operated and main-
tained by the Instituto Oceanográfico/Universidade de
São Paulo, and data were available (http://ilikai.soest.
hawaii.edu/UHSLC/jasl.html) through the Joint Ar-
chive for Sea Level program of the University of Ha-
waii Sea Level Center. Atmospheric pressure and wind
from the National Centers for Environmental Predic-
tion–National Center for Atmospheric Research re-
analysis data (Kistler et al. 2001) at 0000, 0600, 1200,
and 1800 UTC between 258009 and 278309S and from
the coastline up to 458009W at 2.58 3 2.58 and 1.9058 3
1.8758 grid points—latitude and longitude, respec-
tively—were used for studying the local influences
caused by the passage of cold fronts. Meteorological
analysis and forecasts from the forecast daily bulletins
transmitted by the Centro de Hidrografia da Marinha
147
do Brasil (CHM) during this period were also used.
Figure 5 shows the location of the Cananéia Estuary
tide gauge and the reanalysis grid points.
4. Statistical analysis
The atmospheric pressure, wind, and tide gauge time
series were analyzed statistically by estimating the cen-
ter of the distribution (mean and median), variances,
standard deviation, asymmetry, and kurtosis. From the
percentiles analyses, a few outliers in the sea level
record could be identified from box plots. They were
replaced by the average values between the previous
and following hourly data. Before fitting, both series
were used for the period from January 1997 to Decem-
ber 1998 to study the coastal sea level response related
to the meteorological conditions as well as the behavior
of the coastal sea level in this Brazilian region.
a. Filtering data using a low-pass filter
This study was focused on the oscillations in sea level
caused by frequency lower than astronomically driven
forces that is related to the passage of frontal systems
that have periods around 3–5 days. Tides and inertial
motions usually cause a high-frequency noise in sea
level records used to analyze low-frequency motion in
the ocean (Thompson 1983). To eliminate diurnal and
shorter-period tide oscillations from the input dataset,
the Thompson low-pass filter, a symmetric digital filter,
148 JOURNAL OF APPLIED METEOROLOGY AND CLIMATOLOGY
was used. This filter is defined by the following expres-
sions:
Yt 5 å
n
wk xt1k ; wk 5 wk ; ð1Þ
k 5 n
where Yt is the filtered time series, w2k and wk are the
symmetric weights (n 5 2120 to 1120 with a total of
241 weights, including 0), and xt1k are the input data.
The symmetry is imposed to preserve phase informa-
8
1 w , V1
< 
>
pðw  V1 Þ
LðwÞ 5 1 2 1 1 cos
= for
>
: V2  V1
0 V2 , w
where V1 and V2 are cutoff frequencies chosen within a
definite range. The cutoff frequencies used in this study
were V1 5 6.48 h21 and V2 5 11.28 h21, with periods of
56.25 and 32.14 h, respectively. The Thompson filter
uses 15 harmonic components and local inertial fre-
quency (Coriolis parameter: 2V sinu, where u is lati-
tude) to calculate the weights that will be used for fil-
tering by convolution of the hourly dataset.
Hourly observed sea level records were then filtered
to remove the oscillations or noises related to tidal fre-
quencies. For the reanalysis dataset, the same filter was
used, considering the 6-hourly intervals. After filtering,
the hourly sea level series was replaced at 6-hourly in-
tervals as the reanalysis data so that both datasets could
be compared for the same time interval and frequencies.
b. Series analysis in the time and frequency domain
Storm surge is usually considered to be driven by two
processes: the extreme wind stress and atmospheric
pressure. Therefore, cross correlations among the fil-
tered sea level, atmospheric pressure, and zonal and
meridional wind stresses were calculated. The zonal
wind stress (zws) and meridional wind stress (mws)
were calculated using the following equations:
T x 5 rCd jW jU and ð4Þ
T y 5 rCd jW jV; ð5Þ
23
where r 5 1.22 kg m (air density), W 5 intensity of
the wind (m s21) calculated from zonal (U) and merid-
ional (V) wind components of the reanalysis dataset,
and Cd 5 1.1 1 0.053W [coefficient of drag for the
southeast Brazil coast (Stech and Lorenzzetti 1992)].
The units used for wind stress are newtons per meter
squared, where 1 hPa is equal to 102 N m22.
VOLUME 48
tion, and, to pass low frequencies correctly, a constraint
is considered (Thompson 1983):
n
å
k 5 n
wk 5 1: ð2Þ
The digital filter response is near unity at low frequen-
cies but is near zero at high frequencies, mainly at in-
ertial frequency (w 5 w0) and tidal frequencies (w 5 wt).
An example of a function that has a desirable shape
for this filter is

V1 , w , V2 ; ð3Þ
Spectral analyses of filtered meteorological data and
filtered sea level records were carried out, using fast
Fourier transform. Cross-spectral analyses were ob-
tained to identify the frequency characteristics of the
local and remote meteorological events that have an
influence on the variation of the sea level at the
Cananéia tide gauge station. The coherence between
the peaks of the meteorological and sea level time se-
ries was analyzed to verify the linear correlation be-
tween the components of the bivaried process.
5. Neural network modeling
The progress of neurobiology allowed several re-
searchers to develop this model to emulate the cerebral
capacity of learning in the attempt to solve problems of
a complex nature. It has the capability of abstraction in
representing the characteristics of the phenomenon
through the information from a large database. To de-
termine the best linear approach to a dataset, Rumel-
hart et al. (1986) has developed the backpropagation
learning algorithm, which is widely used in the mul-
tiple-layers model.
An NNM receives a set of inputs Xi that is multiplied
by a weight Wi and added, consisting of a linear com-
bination. It is expressed as
U5 åi X iW i: ð6Þ
The backpropagation learning is used for supervised
learning with multilayer feed-forward networks. This
algorithm repeats the application of a chain rule to
compute each weight in the model with respect to an
error function. The topology of a multiple-layer per-
ceptron (MLP) is specified by the number of layers and
JANUARY 2009 DE OLIVEIRA ET AL. 149

FIG. 6. Oscillations of observed and filtered sea level time series from Cananéia tide gauge
station using the Thompson low-pass filter.

the number of nodes per layer. The layers are denoted

by the input, hidden, and output layers. A basic ele-
ment of this model is the activation function (linear,
logic, and sigmoid) that computes the activation level
across the NNM. The output signal is given by

Y k 5 uðuk 1 bk Þ; ð7Þ

where u(uk) is the activation function and bk 5 bias

(controller over the activation function).
The first step of the NNM approach to design specific
network architecture includes a number of layers, each
layer consisting of a specific number of neurons. The
size and structure of the model need to be a match for
the nature of the problem. This stage is usually not well
known, and therefore it is not an easy task, often in-
volving a trial-and-error approach according to the
characteristics of the application domain. The network
is then subjected to the training stage. In that phase,
neurons apply an iterative process to the input variables
to adjust the weights of the NNM to optimally predict
the data on which the training is performed. In this way,
the error for each output unit is calculated and is used
to update the weights. As a consequence, one could say
that the model attained the optimum architecture or
found a fit to when the error between the desired out-
put and the target is reduced. The NNM needs three
datasets of input such as training, testing, and validation
series. After learning, another new dataset is used to
test or verify the performance of the trained neural
network. Training and test series are used for calibrat-
ing the model. Validation series verify the generaliza-
tion of the model comparing the output data (predic-
tions) with the actual ones (Fu 1994).
In this paper, different training methods were ap-
FIG. 7. Peaks of the cross correlation between the meteorologi-
plied to find the best performance: radial basis func-
cal variables and low-frequency sea level response: (a) pressure
tions (RBF), a network particularly adapted to approxi- (point 1), (b) zws (point 2), and (c) mws (point 2). The k lags for
mation function in which the hidden layer is defined by points 1 and 2 are 6-hourly. Therefore, the x values must be mul-
radial basis functions and the learning fits a nonlinear tiplied by 6.
150 JOURNAL OF APPLIED METEOROLOGY AND CLIMATOLOGY VOLUME 48

FIG. 8. Fourier analysis of the sea level variation (meteorological tide) related to
meteorologically driven forces at Cananéia Estuary: (a) pressure, (b) zws, and (c) mws.

surface according to some stochastic criteria (Wasser- technique, given only a training set (Cigizoglu and Alp
man 1993); the generalized regression neural network 2006); and NNM feed forward–MLP, which used the
(GRNN), a method for estimating the joint probability supervised learning and backpropagation algorithm.
density function of x and y as in the standard regression All samples were used with intervals of 6 h (LT)
JANUARY 2009 DE OLIVEIRA ET AL.
between the observations, and this dataset was selected
with 50% for training, 25% for testing, and 25% for
validation. The input variables for the NNM training
were atmospheric variables, filtered sea level series of
previous hours, and observed wind for the actual time.
6. Results of the statistical analysis
The filtered records generated the time series of the
sea level response in low frequency related with the
meteorological systems that were used in the NNM
(Fig. 6). Figures 7a–c show the peaks of the cross cor-
relation between the low-frequency sea level at the
Cananéia gauge station and pressure, zws, and mws
from one and two reanalysis grid points. The greatest
values of the cross correlations for the sea level re-
sponse and pressure, zws, and mws components were
48, 30, and 0 h, respectively, with percentages around
32%, 35%, and 47%.
To verify the intercorrelations of the sea level re-
sponse and meteorological variables in the same fre-
quency, values of cross-spectral densities and coher-
ence between the series were analyzed. It was found
that peaks of energy and high coherence for periods
from 5 to 3 days were related to passages of cold fronts
over the region.
Figures 8a and 8b show the maximum peaks around
2.9 days for pressure and 1.7 days for zws. Another
peak is also verified around 4.6 days for pressure and
2.8 days for zws. In Fig. 8c, peaks can be observed for
periods around 6.2–2.8 days for mws. These values in-
dicate a correlation of sea level variation and meteoro-
logical events such as cold fronts that can be identified
in low-frequency motions. Similar results were found
by Paiva (1993) and Castro and Lee (1995) with respect
to the effect of waves in the continental shelf of the
Brazilian southeast coastline. High coherence values
around 75% also were verified between the meteoro-
logical variables and the low-frequency sea level varia-
tion to periods from 5 to 3 days (Fig. 9).
7. NNM performances
The maximum values of cross correlations described
previously were used as input to the model. Then, a
time lag was considered with respect to the sea level
response and the meteorological variables. Autocorre-
lations of the low-frequency sea level and wind speed
for the current time were also used. Therefore, pres-
sure, zws, mws, 18-, 12-, and 6-hourly filtered sea level,
and wind speed predictors were input vectors. The fil-
tered sea level relating to 6-hours after was used as the
output variable (predictand).
151
FIG. 9. Coherence between the meteorological variables and
low-frequency sea level at Cananéia Estuary.
The filtering dataset from January 1997 to December
1998 for predicting sea level variations was used, and
the results were compared with actual and predicted
values. Table 1 shows the best performances of the
NNM with the correlation coefficients r. The MLP with
7–14–1 layers produced the best results.
The backpropagation algorithm was used for the
NNM training. The activation function used in the hid-
den and output units was the hyperbolic tangent func-
tion. The software Statistica Neural Networks for Win-
dows was employed in this work.
Table 2 shows the correlation coefficients to the se-
lected pairs for training, testing, and validation for 6-,
12-, 18-, and 24-hourly simulations. In both of the
stages, a high correlation was observed.
The MLP (7–14–1) for forecasting the sea level varia-
tions for 6-hourly time lags presents accurate results.
The performance of the NNM in forecasting the sea
level variations was satisfactory enough (r 5 0.999) for
6-hourly time lags. Figure 10 shows the comparison be-
tween NNM generalization (validation) to predict the
variations of the low-frequency sea level and the target
(filtering dataset). It is observed that the two curves are
very similar, being in accordance with the statistical
results shown in Table 2.
Figure 11 shows the evolution for training and vali-
dation of the MLP model to reach the error conver-
gence. Learning rate and momentum parameters affect
the speed of the convergence of the backpropagation
algorithm. The stopping criterion was based on the er-
TABLE 1. Correlation coefficients r.
NNM Training Validation
RBF 0.9536 0.9363
GRNN 0.9818 0.9765
MLP (7–9–1) 0.9573 0.9383
MLP (7–11–1) 0.9581 0.9417
MLP (7–14–1) 0.9990 0.9987
152 JOURNAL OF APPLIED METEOROLOGY AND CLIMATOLOGY
TABLE 2. Correlation coefficients for 6-, 12-, 18-, and 24-hourly
simulations.
Time lag (h) Training Testing Validation
6 0.9991 0.9988 0.9987
12 0.9898 0.9875 0.9844
18 0.9549 0.9432 0.9364
24 0.8819 0.8506 0.8308
ror to be minimized to improve the performance of the
network. The model attained the best performance for
700 epochs in which the training error is 0.008 276 and
validation error is 0.008 531 with learning rate of 0.01
and momentum of 0.9. After 700 epochs, the process
was stabilized as shown in Fig. 11.
The scatterplots shown in Fig. 12 have a small dis-
parity, illustrating that NNM has a smaller error in the
learning stage than in the validation stage according to
the correlation coefficients in Table 2. This is a common
result in establishing an NNM. The simulation perfor-
mance of predictors is normally evaluated by the root-
mean-square (RMS) or the square of correlation coef-
ficient (R2), which is called the coefficient of determi-
nation. Small RMS and large R2 values indicate that the
simulation performance is good (Chang and Lin 2006).
The left column of this figure shows the target and
desired output simulated by NNM in the training stage
for 1997. This column indicates that there is little dis-
parity between filtered and simulated values for 6- and
12-hourly training, for which R2 is 0.9981 and 0.9803,
respectively. The R2 values for 18- and 24-hourly are
around 0.912 and 0.7767, respectively, showing that the
NNM preserves the influences of the physical process,
such as pressure and wind, in the sea level variations.
The right column shows the scatterplots for 1998 in the
validation stage. Small differences between the two
stages are verified. The R2 values for 6-, 12-, and 18-
hourly present similar results with the learning stage.
For 24-hourly forecasting, the R2 presented values
FIG. 10. Oscillations of the low-frequency sea level (target) and
simulated curve by the MLP.
VOLUME 48
FIG. 11. Performance of the MLP model for training and vali-
dation stages, showing the convergence of the error and the sta-
bilization of the process.
lower than for the testing stage. It can be related to the
correlation between the predictors and predictand.
Strong (;15 m s21) southwesterly (1908–2608) winds
blowing for 3–5 days, over the ocean parallel to the
coastline, are the most conducive wind vectors for pro-
ducing storm surge along the southeast Brazilian coast.
Figure 13 shows the curves of the sea level variation
related to the storm surge that occurred on 26–28
March 1998 in southeast coastal Brazil. The value of the
peak of the high water level on 26 March was 3.13 m,
and the predicted tide with the harmonic model (HM)
was 2.53 m. The difference between the maximum
peaks was around 0.60 m, characterizing the occurrence
of a surge in this region. The value predicted by NNM
was around 0.63 m. Therefore, the value obtained with
both models (HM 1 NNM) was around 3.16 m. It can
also be verified in the figure that some peaks of the high
water predicted with both models are above the ob-
served sea level. The values of the low water level are
very similar.
8. Conclusions
Conventional numerical models developed to predict
surges are still considered insufficient because of the
complexity of the nonlinear processes involved. In this
paper, an alternative method based on the structure of
the neural network model to predict coastal sea level
variations related to meteorological events was pro-
posed.
Preprocessing of the data series in the time and fre-
quency domain allowed definition of the input of the
neural network model. Maximum correlations in the
physical process could determine the time lag between
the meteorological variables and the sea level response.
The results indicate that the MLP architecture of the
network developed in this work could generalize satis-
factorily the nonlinear behavior of the sea level fluc-
tuations due to the interactions of ocean and atmo-
JANUARY 2009 DE OLIVEIRA ET AL. 153

FIG. 12. Scatterplots of simulated and filtered sea level data in the training stage for 1997
and the validation stage for 1998.

sphere at the Cananéia tide gauge station. This model shown in Fig. 13. The results obtained for 24-hourly
presented the best performance, with a correlation co- time-lag simulations of approximately 0.83 for the cor-
efficient around 0.99 for the 6-hourly time-lag simula- relation coefficient suggest that this model could still be
tion, and it can be efficient to forecast storm surge, as used for forecasting the low-frequency sea level at this

FIG. 13. Comparison between observed and predicted coastal sea level with both models. It
is verified that the HM undervalues the prediction for a storm surge on 26–28 Mar 1998.
154 JOURNAL OF APPLIED METEOROLOGY AND CLIMATOLOGY
time lag with good performance. Forecasting for peri-
ods larger than 24-hours could be improved by consid-
ering hydrodynamic variables such as river discharges.
The results indicate that the NNM can also be useful
as a complement to the standard harmonic model and
thus to improve the sea level forecast. Also, the pro-
posed NNM for predicting the surge level can be fur-
ther applied to other locations along the Brazilian coast
or in other sites in the world. In addition, this NNM
could be developed in conjunction with a numerical
ocean model (e.g., Princeton Ocean Model) to improve
forecasting water levels at the key locations.
Acknowledgments. We are thankful to CHM for sup-
plying the tide gauge records and the meteorological
information. Appreciation and thanks are also given to
three anonymous reviewers for their constructive com-
ments and suggestions to improve the manuscript.
REFERENCES
Angulo, R. J., and G. C. Lessa, 1997: The Brazilian sea-level
curves: A critical review emphasis on curves from Paranaguá
and Cananéia regions. Mar. Geol., 140, 141–166.
Besnard, W., 1950: General aspects about the Cananéia-Iguape
region-1. Inst. Paulista Oceanogr., 1, 9–26.
Castro, B. M., and T. N. Lee, 1995: Wind-forced sea level vari-
ability on the southeast Brazilian shelf. J. Geophys. Res., 100,
16 045–16 056.
Chang, H.-K., and L.-C. Lin, 2006: Multi-point tidal prediction
using artificial neural network with tide-generating forces.
Coastal Eng., 53, 857–864.
Cigizoglu, H. R., and M. Alp, 2006: Generalized regression neural
network in modelling river sediment yield. Adv. Eng. Soft-
ware, 37, 63–68.
Dalazoana, R., R. T. Luz, and S. R. C. de Freitas, 2005: Mean sea
level studies from tide gauge and satellite altimetry time se-
ries looking for the integration of Brazilian Network to
SIRGAS. Rev. Bras. Cartogr., 57, 140–153.
de Mesquita, A. R., cited 2008a: Marés, Circulac xão e Nı́vel do mar
na Costa Sudeste do Brasil (Tides, circulation and sea level in
the southeastern coast of Brazil). [Available online at http://
www.mares.io.usp.br/sudeste/sudeste.html.]
——, cited 2008b: Sea level variations along the Brazilian coast: A
short review. Brazilian Symp. on Sandy Beaches. [Available
online at http://www.mares.io.usp.br/praias/praias.html.]
Doodson, A. T., and H. D. Warburg, 1944: Manual de Mare´s do
Almirantado (Manual of Tides of the Admiralty). 2nd ed.
Brazilian Navy, 372 pp.
Elsner, J. B., and A. A. Tsonis, 1992: Nonlinear prediction, chaos,
and noise. Bull. Amer. Meteor. Soc., 73, 49–60.
Filippo, A. M., 2003: Variabilidade do nı́vel do mar em func xão de
eventos meteorológicos de baixa freqüência (Variability of
sea level as a function of meteorological events of low fre-
quency). Ph.D. thesis, Fuminense Federal University, Ni-
terói, Rio de Janeiro State, , Brazil, 100 pp.
Franco, A. S., 1981: Tides: Fundamentals Analysis and Prediction.
IPT, 232 pp.
Fu, L.-M., 1994: Neural Networks in Computer Intelligence.
McGraw-Hill, 460 pp.
VOLUME 48
Gan, M. A., and V. B. Rao, 1991: Surface cyclogenesis over South
America. Mon. Wea. Rev., 119, 1293–1302.
Haykin, S., 2001: Redes Neurais: Princı´pios e Prática (Neural Net-
works: Principle and Practice). 2nd ed. Bookman, 900 pp.
Kistler, R., and Coauthors, 2001: The NCEP–NCAR 50-Year Re-
analysis: Monthly means CD-ROM and documentation. Bull.
Amer. Meteor. Soc., 82, 247–267.
Lee, T. L., 2006: Neural network prediction of a storm surge.
Ocean Eng., 33, 483–494.
Mantovanelli, A., and Coauthors, 2004: Combined tidal velocity
and duration asymmetries as a determinant of water trans-
port and residual flow in Paranaguá Bay estuary. Estuarine
Coastal Shelf Sci., 59, 523–537.
Marone, E., and R. Camargo, 1994: Marés meteorológicas no lito-
ral do estado do Paraná: o evento de 18 de agosto de 1993
(Meteorological tides in the coast of the state of Paraná: The
event of 18 August 1993). Nerı´tica, 8, 1–2.
McPhaden, M., 1999: El Niño: The child prodigy of 1997–98. Na-
ture, 398, 559–562.
Netto, S. A., and P. C. Lana, 1997: Influence of Spartina Alterni-
flora on superficial sediment characteristics of tidal flats in
Paranaguá Bay (South-eastern, Brazil). Estuarine Coastal Shelf
Sci., 44, 641–648.
Paiva, A. M., 1993: Estudo das variac xões do nı́vel do mar em
Arraial do Cabo-RJ (Study of sea level variations in Arraial
do Cabo, Rio de Janeiro). Instituto Alberto Luiz Coimbra de
Pós-Graduacxão e Pesquisa de Engenharia Research Rep.,
COPPE, Universidade Federal do Rio de Janeiro.
Pore, N. A., 1964: The relation of wind and pressure to extratrop-
ical storm surge at Atlantic City. J. Appl. Meteor., 3, 155–163.
Pugh, D. T., 1987: Tides, Surges and Mean Sea Level. John Wiley
and Sons, 472 pp.
——, 2005: Changing Sea Levels: Effects of Tides, Weather and
Climate. Cambridge University Press, 265 pp.
Rao, V. B., and K. Rada, 1990: Characteristics of rainfall over
Brazil: Annual variations and connections with the southern
oscillation. Theor. Appl. Climatol., 42, 81–91.
Ribeiro, C. E. P., 1997: Uma nova técnica adaptativa para análise
direcional de ondas (A new adaptive technique for direction-
al analysis of waves). Anais do II Encontro de Ondas e Marés.
Instituto de Estudos do Mar Almirante Paulo Moreira, 182–
193.
Rumelhart, D. E., G. E. Hinton, and R. J. Willians, 1986: Learn-
ing internal representations by error propagation, parallel
distributed processing. Exploration in the Microstructures of
Cognition, Vol. 1, D. E. Rumelhart and J. L. McClelland,
Eds., MIT Press, 318–362.
Seluchi, M. E., 1995: Diagnóstico y prognóstico de situaciones
sinópticas conducentes a ciclogênesis sobre el este de Su-
damerica (Diagnostics and prognostics of synoptic situations
conducive to cyclogenesis on the east of South America).
Geofis. Int., 34, 171–186.
Shaeffer-Novelli, Y., H. S. L. Mesquita, and G. Cintrón-Molero,
1990: The Cananéia lagoon estuarine system. Estuaries, 13,
193–203.
SMA, 1990: Macrozoning of the Cananéia-Iguape estuary:
Coastal management planning. Secretaria do Meio Ambiente
do Estado de São Paulo, 41 pp.
——, 1996: Regulation of the Cananéia-Iguape-Peruı́be-
environment protected area (EPA): Action planning. Insti-
tuto Brasileiro do Meio Ambiente e dos Recursos Naturais
Renováveis (IBAMA), 64 pp.
Stech, J. L., and J. A. Lorenzzetti, 1992: The response of the South
JANUARY 2009 DE OLIVEIRA ET AL.
Brazil Bight to the passage of wintertime cold fronts. J. Geo-
phys. Res., 97, 9507–9520.
Storch, H., and K. Worth, 2008: Storm surges, perspectives and
options. Sustainability Sci., 3, 33–43.
Sztobryn, M., 2003: Forecast of storm surge by means of artificial
neural network. J. Sea Res., 49, 317–322.
Thompson, R. O. R. Y., 1983: Low-pass filters to suppress inertial
and tidal frequencies. J. Phys. Oceanogr., 13, 1077–1083.
Truccolo, E. C., 1998: Maré meteorológica e forc xantes atmos-
155
féricas locais em São Francisco do Sul-SC (Meteorological
tides and local atmospheric forcing in São Francisco do Sul,
Santa Catarina). M.S. thesis, Federal University of Santa
Catarina, Florianópolis, Santa Catarina State, Brazil, 115 pp.
Tseng, C. M., C. D. Jan, J. S. Wang, and C. M. Wang, 2007: Ap-
plication of artificial neural network in typhoon surge fore-
casting. Ocean Eng., 34, 1757–1768.
Wasserman, P. D., 1993: Advanced Methods in Neural Computing.
John Wiley and Sons, 250 pp.