FUDMA Journal of Sciences,
Journal Year:
2024,
Volume and Issue:
8(6), P. 503 - 513
Published: Dec. 31, 2024
Tidal
analysis
involves
the
computation
of
tidal
constants
(phase
lag
(g)
and
amplitude
(H))
constituents
at
a
location.
This
study
focuses
on
assessment
stability
g
H
for
Bonny
port
which
is
only
standard
in
Nigeria.
Monthly
observations
was
carried
out
with
1980,
1994
2018
year’s
data
using
Least
Squares
Method
(LSM)
Harmonic
Analysis
MATLAB
programming
codes.
The
observation
equation
technique
LSM
adopted;
dimension
Normal
(N)
matrix
equations
obtained
monthly
72
56
i.e.
rows,
columns.
N
inverted
gave
results
mean
sea
level
(MSL)
28
primary
tide.
Four
major
tide
(M2,
S2,
K1
O1)
remain
stable
throughout
analysis.
each
year
observed
to
be
almost
equal
from
three-year
data.
maximum
residuals
spreads
computed
over
period
show
that
are
accurately
analyze
one-month
can
employed
prediction
several
years.
Therefore,
it
concluded
M2,
O1
type
(F)
semidiurnal
since
F
0.16
0.25.
Environmental Monitoring and Assessment,
Journal Year:
2025,
Volume and Issue:
197(3)
Published: Feb. 18, 2025
Abstract
Solar
radiation
plays
a
critical
role
in
the
carbon
sequestration
processes
of
terrestrial
ecosystems,
making
it
key
factor
environmental
sustainability
among
various
renewable
energy
sources.
This
study
integrates
two
advanced
signal
processing
techniques—empirical
mode
decomposition
(EMD)
and
ensemble
empirical
(EEMD)—with
machine
learning
(ML)
algorithms,
including
multilayer
perceptron
(MLP),
random
forest
regression
(RFR),
support
vector
(SVR),
ridge
regression,
to
forecast
long-term
solar
radiation.
Meteorological
data
spanning
13
years
(2000–2012)
from
seven
locations
across
India
(Bhubaneswar,
Chennai,
Delhi,
Hyderabad,
Nagpur,
Patna,
Trivandrum)
were
used
for
training
testing.
The
optimal
model
was
identified
based
on
performance
metrics,
highest
linear
correlation
coefficient
(
R
),
lowest
mean
absolute
error
(MAE)
root
square
(RMSE).
results
indicate
that
EEMD
integrated
with
ML
algorithms
consistently
outperformed
EMD-based
approaches.
Among
models
evaluated,
MLP
achieved
best
all
locations,
RMSE
=
0.332,
MAE
0.26,
2
0.99.
Furthermore,
comparative
analysis
previous
studies
demonstrated
proposed
approach
provides
superior
accuracy,
underscoring
its
efficacy
forecasting.
Ocean Modelling,
Journal Year:
2024,
Volume and Issue:
190, P. 102384 - 102384
Published: May 17, 2024
This
paper
proposes
a
new
model
to
study
future
coastal
maritime
climate
under
change
context.
combines
statistical
analysis,
Monte
Carlo
simulations
and
Artificial
Neural
Networks
(ANNs).
Statistical
analysis
are
used
extrapolate
wave
context
at
regional
level
ANNs
propagate
these
projected
sea
states
obtained
in
deep
water
the
coast.
The
use
of
allows
for
utilization
large
amounts
data
very
low
computational
cost,
enables
generation
projections
level.
combination
two
methodologies
results
accurate
(MSE
0.02
m
1
s)
computationally
inexpensive
hybrid
that
considering
change.
methodology
has
been
validated
applied
Western
Mediterranean
long-term
regime
extreme
events,
obtaining
increases
events
up
1.5
height
1.8
s
period
by
2050.
