Journal of Geophysical Research Atmospheres,
Journal Year:
2024,
Volume and Issue:
130(1)
Published: Dec. 26, 2024
Abstract
Arctic
sea
ice
prediction
is
critical
for
exploring
climate
change,
resource
extraction,
and
shipping
route
planning.
This
paper
introduces
a
novel
neural
network
model,
Ice
Graph
Attention
neTwork
(IceGAT),
that
trained
to
predict
concentration
(SIC)
from
number
of
atmospheric,
oceanic,
land
surface
measurements.
It
based
on
two
design
principles:
(a)
the
complex
spatial
interactions
in
weather
dynamics
are
captured
via
series
graphs
corresponding
different
resolutions
(b)
incorporation
physical
conservation
laws
moisture
potential
vorticity.
We
devise
main
variants
with
1
hr
24
temporal
resolution
determine
optimal
input
horizon
be
5
days.
IceGAT
features
leading
accuracy
(96.7%;
+2.4%
over
current
state‐of‐the‐art)
low
inference
time
(1/4
s,
single
GPU).
An
online
implementation
(based
data
ERA5)
alongside
supplementary
videos
our
shared
code
accessible
at:
https://lannwei.github.io/IceGAT/
.
Journal of Marine Science and Engineering,
Journal Year:
2024,
Volume and Issue:
12(2), P. 202 - 202
Published: Jan. 23, 2024
Ship
course-keeping
control
is
of
great
significance
to
both
navigation
efficiency
and
safety.
Nevertheless,
the
complex
navigational
conditions,
unknown
time-varying
environmental
disturbances,
dynamic
characteristics
ships
pose
difficulties
for
ship
course-keeping.
Thus,
a
PSO-based
predictive
PID-backstepping
(P-PB)
controller
proposed
in
this
paper
realize
efficient
rapid
ships.
The
takes
ship’s
target
course,
current
yawing
speed,
as
well
motion
parameters
into
consideration.
In
design
controller,
PID
improved
by
introducing
control.
Then,
combined
with
backstepping
balance
stability
Subsequently,
are
optimized
utilizing
Particle
Swarm
Optimization
(PSO),
which
can
adaptively
adjust
value
various
scenarios,
thus
further
increase
its
efficiency.
Finally,
validated
carrying
out
simulation
tests
scenarios.
results
show
that
it
improves
error
time-response
specification
4.19%
9.71%
on
average,
respectively,
efficiently
achieve
under
Scientific Reports,
Journal Year:
2024,
Volume and Issue:
14(1)
Published: Feb. 2, 2024
Abstract
Climate
change
has
been
inducing
a
continuous
increase
in
temperatures
within
the
Arctic
region,
consequently
leading
to
an
escalation
rates
of
ice
depletion.
These
changes
have
profound
implications
for
navigation
along
Northern
Sea
Route
(NSR).
However,
access
NSR
is
constrained
specific
temporal
intervals
when
sea
thickness
reaches
threshold
that
permits
safe
passage
ships.
This
research
employs
climate
model
simulations
and
Polar
Operational
Limit
Assessment
Risk
Indexing
System
framework
investigate
navigational
feasibility
diverse
ship
types
during
calendar
years
2030,
2040,
2050,
under
SSP2-4.5
SSP5-8.5
scenarios.
Different
categories
were
analyzed
context
these
two
Results
indicate
considerable
variation
navigability
different
across
scenarios
years.
In
general,
polar
ships
demonstrate
higher
potential
throughout
most
year,
while
pleasure
crafts
are
periods.
findings
bear
significant
future
shipping
NSR.
As
continues
melt,
anticipated
become
more
accessible
ships,
albeit
with
availability
remaining
contingent
on
category
seasonal
considerations.
Journal of Marine Science and Engineering,
Journal Year:
2024,
Volume and Issue:
12(3), P. 402 - 402
Published: Feb. 26, 2024
In
order
to
effectively
deal
with
collisions
in
various
encounter
situations
open
water
environments,
a
ship
collision
avoidance
model
was
established,
and
multiple
constraints
were
introduced
into
the
velocity
obstacle
method,
method
determine
domain
by
calculating
safe
distance
of
approach
proposed.
At
same
time,
based
on
is
analyzed,
relative
set
cone
obtained
solving
common
tangent
line
within
ellipse.
The
timing
starting
determined
risk,
for
ending
Finally,
comparing
simulation
experiments
improved
algorithm
those
traditional
actual
experiment
results
manual
maneuvering,
it
shown
that
can
avoid
distances
comply
navigation
experience
different
situations.
has
better
performance
behavior.
It
certain
feasibility
practical
applicability.
Sensors,
Journal Year:
2025,
Volume and Issue:
25(2), P. 326 - 326
Published: Jan. 8, 2025
The
retreat
of
Arctic
sea
ice
has
opened
new
maritime
routes,
offering
faster
shipping
opportunities;
however,
these
routes
present
significant
navigational
challenges
due
to
the
harsh
conditions.
To
address
challenges,
this
paper
proposes
a
deep
learning-based
risk
management
architecture
with
multiple
modules,
including
classification,
assessment,
floe
tracking,
and
load
calculations.
A
comprehensive
dataset
15,000
images
was
created
using
public
sources
contributions
from
Canadian
Coast
Guard,
it
used
support
development
evaluation
system.
performance
YOLOv8n-cls
model
assessed
for
classification
modules
its
fast
inference
speed,
making
suitable
resource-constrained
onboard
systems.
training
were
conducted
across
platforms,
Roboflow,
Google
Colab,
Compute
Canada,
allowing
detailed
comparison
their
capabilities
in
image
preprocessing,
training,
real-time
generation.
results
demonstrate
that
Image
Classification
Module
I
achieved
validation
accuracy
99.4%,
while
II
attained
98.6%.
Inference
times
found
be
less
than
1
s
Colab
under
3
on
stand-alone
system,
confirming
architecture's
efficiency
condition
monitoring.
