Frontiers in Public Health,
Journal Year:
2022,
Volume and Issue:
10
Published: April 8, 2022
Shared
bicycles
are
currently
widely
welcomed
by
the
public
due
to
their
flexibility
and
convenience;
they
also
help
reduce
chemical
emissions
improve
health
encouraging
people
engage
in
physical
activities.
However,
during
development
process,
imbalance
between
supply
demand
of
shared
has
restricted
public's
willingness
use
them.
Thus,
it
is
necessary
forecast
for
different
urban
regions.
This
article
presents
a
prediction
model
called
QPSO-LSTM
origin
destination
(OD)
distribution
combining
long
short-term
memory
(LSTM)
quantum
particle
swarm
optimization
(QPSO).
LSTM
special
type
recurrent
neural
network
(RNN)
that
solves
long-term
dependence
problem
existing
general
RNN,
suitable
processing
predicting
important
events
with
very
intervals
delays
time
series.
QPSO
an
intelligence
algorithm
simulating
process
birds
searching
food.
In
model,
applied
predict
OD
numbers.
used
optimize
involving
large
number
hyperparameters,
optimal
combination
hyperparameters
quickly
determined.
Taking
Nanjing
as
example,
two
typical
areas,
needed
per
hour
future
day
predicted.
can
effectively
learn
cycle
regularity
change
bicycle
quantity.
Finally,
compared
autoregressive
integrated
moving
average
(ARIMA),
back
propagation
(BP),
networks
(RNNs).
shows
result
more
accurate.
The Innovation,
Journal Year:
2024,
Volume and Issue:
5(5), P. 100691 - 100691
Published: Aug. 23, 2024
Public
summary•What
does
AI
bring
to
geoscience?
has
been
accelerating
and
deepening
our
understanding
of
Earth
Systems
in
an
unprecedented
way,
including
the
atmosphere,
lithosphere,
hydrosphere,
cryosphere,
biosphere,
anthroposphere
interactions
between
spheres.•What
are
noteworthy
challenges
As
we
embrace
huge
potential
geoscience,
several
arise
reliability
interpretability,
ethical
issues,
data
security,
high
demand
cost.•What
is
future
The
synergy
traditional
principles
modern
AI-driven
techniques
holds
immense
promise
will
shape
trajectory
geoscience
upcoming
years.AbstractThis
paper
explores
evolution
geoscientific
inquiry,
tracing
progression
from
physics-based
models
data-driven
approaches
facilitated
by
significant
advancements
artificial
intelligence
(AI)
collection
techniques.
Traditional
models,
which
grounded
physical
numerical
frameworks,
provide
robust
explanations
explicitly
reconstructing
underlying
processes.
However,
their
limitations
comprehensively
capturing
Earth's
complexities
uncertainties
pose
optimization
real-world
applicability.
In
contrast,
contemporary
particularly
those
utilizing
machine
learning
(ML)
deep
(DL),
leverage
extensive
glean
insights
without
requiring
exhaustive
theoretical
knowledge.
ML
have
shown
addressing
science-related
questions.
Nevertheless,
such
as
scarcity,
computational
demands,
privacy
concerns,
"black-box"
nature
hinder
seamless
integration
into
geoscience.
methodologies
hybrid
presents
alternative
paradigm.
These
incorporate
domain
knowledge
guide
methodologies,
demonstrate
enhanced
efficiency
performance
with
reduced
training
requirements.
This
review
provides
a
comprehensive
overview
research
paradigms,
emphasizing
untapped
opportunities
at
intersection
advanced
It
examines
major
showcases
advances
large-scale
discusses
prospects
that
landscape
outlines
dynamic
field
ripe
possibilities,
poised
unlock
new
understandings
further
advance
exploration.Graphical
abstract
International Journal of Digital Earth,
Journal Year:
2023,
Volume and Issue:
16(1), P. 1022 - 1072
Published: March 23, 2023
The
concept
of
Digital
Earth
(DE)
was
formalized
by
Al
Gore
in
1998.
At
that
time
the
technologies
needed
for
its
implementation
were
an
embryonic
stage
and
quite
visionary.
Since
then
digital
have
progressed
significantly
their
speed
pervasiveness
generated
are
still
causing
transformation
our
society.
This
creates
new
opportunities
challenges
realization
DE.
‘What
is
DE
today?’,
could
be
future?’,
to
make
a
reality?’.
To
answer
these
questions
it
necessary
examine
considering
all
technological,
scientific,
social,
economic
aspects,
but
also
bearing
mind
principles
inspired
formulation.
By
understanding
lessons
learned
from
past,
becomes
possible
identify
remaining
scientific
technological
challenges,
actions
achieve
ultimate
goal
‘Digital
all’.
article
reviews
evolution
vision
multiple
definitions,
illustrates
what
has
been
achieved
so
far,
explains
impact
transformation,
vision,
concludes
with
future
scenarios
recommended
facilitate
full
implementation.
Science Bulletin,
Journal Year:
2023,
Volume and Issue:
68(7), P. 740 - 749
Published: March 8, 2023
Sustainable
development
goals
(SDGs)
in
the
United
Nations
2030
Agenda
call
for
action
by
all
nations
to
promote
economic
prosperity
while
protecting
planet.
Projection
of
future
land-use
change
under
SDG
scenarios
is
a
new
attempt
scientifically
achieve
SDGs.
Herein,
we
proposed
four
scenario
assumptions
based
on
SDGs,
including
sustainable
economy
(ECO),
grain
(GRA),
environment
(ENV),
and
reference
(REF)
scenarios.
We
forecasted
along
Silk
Road
(resolution:
300
m)
compared
impacts
urban
expansion
forest
conversion
terrestrial
carbon
pools.
There
were
significant
differences
land
use
stocks,
scenarios,
2030.
In
ENV
scenario,
trend
decreasing
was
mitigated,
stocks
China
increased
approximately
0.60%
2020.
GRA
rate
cultivated
area
has
slowed
down.
Cultivated
South
Southeast
Asia
only
shows
an
increasing
it
other
The
ECO
showed
highest
losses
associated
with
expansion.
study
enhances
our
understanding
how
SDGs
can
contribute
mitigate
environmental
degradation
via
accurate
simulations
that
be
applied
global
scale.
International Journal of Digital Earth,
Journal Year:
2022,
Volume and Issue:
15(1), P. 1855 - 1880
Published: Oct. 31, 2022
Geographic
simulation
models
can
be
used
to
explore
and
better
understand
the
geographical
environment.
Recent
advances
in
geographic
socio-environmental
research
have
led
a
dramatic
increase
number
of
for
this
purpose.
Some
model
repositories
provide
opportunities
users
apply
models,
but
few
general
evaluation
method
assessing
applicability
recognition
models.
In
study,
an
academic
impact
is
proposed.
Five
indices
are
designed
based
on
their
pertinence.
The
analytical
hierarchy
process
calculate
index
weights,
impacts
quantified
with
weighted
sum
method.
time
range
controlled
evaluate
life-term
annual
that
met
criteria
from
different
domains
then
evaluated.
results
show
proposed
method,
major
areas
identified.
