Artificial intelligence for modeling and understanding extreme weather and climate events
Nature Communications,
Год журнала:
2025,
Номер
16(1)
Опубликована: Фев. 24, 2025
In
recent
years,
artificial
intelligence
(AI)
has
deeply
impacted
various
fields,
including
Earth
system
sciences,
by
improving
weather
forecasting,
model
emulation,
parameter
estimation,
and
the
prediction
of
extreme
events.
The
latter
comes
with
specific
challenges,
such
as
developing
accurate
predictors
from
noisy,
heterogeneous,
small
sample
sizes
data
limited
annotations.
This
paper
reviews
how
AI
is
being
used
to
analyze
climate
events
(like
floods,
droughts,
wildfires,
heatwaves),
highlighting
importance
creating
accurate,
transparent,
reliable
models.
We
discuss
hurdles
dealing
data,
integrating
real-time
information,
deploying
understandable
models,
all
crucial
steps
for
gaining
stakeholder
trust
meeting
regulatory
needs.
provide
an
overview
can
help
identify
explain
more
effectively,
disaster
response
communication.
emphasize
need
collaboration
across
different
fields
create
solutions
that
are
practical,
understandable,
trustworthy
enhance
readiness
risk
reduction.
Artificial
Intelligence
transforming
study
like
helping
overcome
challenges
integration.
review
article
highlights
models
improve
response,
communication
trust.
Язык: Английский
A Performance Comparison Study on Climate Prediction in Weifang City Using Different Deep Learning Models
Water,
Год журнала:
2024,
Номер
16(19), С. 2870 - 2870
Опубликована: Окт. 9, 2024
Climate
change
affects
the
water
cycle,
resource
management,
and
sustainable
socio-economic
development.
In
order
to
accurately
predict
climate
in
Weifang
City,
China,
this
study
utilizes
multiple
data-driven
deep
learning
models.
The
data
for
73
years
include
monthly
average
air
temperature
(MAAT),
minimum
(MAMINAT),
maximum
(MAMAXAT),
total
precipitation
(MP).
different
models
artificial
neural
network
(ANN),
recurrent
NN
(RNN),
gate
unit
(GRU),
long
short-term
memory
(LSTM),
convolutional
(CNN),
hybrid
CNN-GRU,
CNN-LSTM,
CNN-LSTM-GRU.
CNN-LSTM-GRU
MAAT
prediction
is
best-performing
model
compared
other
with
highest
correlation
coefficient
(R
=
0.9879)
lowest
root
mean
square
error
(RMSE
1.5347)
absolute
(MAE
1.1830).
These
results
indicate
that
method
a
suitable
model.
This
can
also
be
used
surface
modeling.
will
help
flood
control
management.
Язык: Английский
Predicting Atlantic and Benguela Niño events with deep learning
Science Advances,
Год журнала:
2025,
Номер
11(14)
Опубликована: Апрель 2, 2025
Atlantic
and
Benguela
Niño
events
substantially
affect
the
tropical
region,
with
far-reaching
consequences
on
local
marine
ecosystems,
African
climates,
El
Southern
Oscillation.
While
accurate
forecasts
of
these
are
invaluable,
state-of-the-art
dynamic
forecasting
systems
have
shown
limited
predictive
capabilities.
Thus,
extent
to
which
variability
is
predictable
remains
an
open
question.
This
study
explores
potential
deep
learning
in
this
context.
Using
a
simple
convolutional
neural
network
architecture,
we
show
that
Atlantic/Benguela
Niños
can
be
predicted
up
3
4
months
ahead.
Our
model
excels
peak-season
remarkable
accuracy
extending
lead
time
5
months.
Detailed
analysis
reveals
our
model’s
ability
exploit
known
physical
precursors,
such
as
long-wave
ocean
dynamics,
for
predictions
events.
challenges
perception
unpredictable
highlights
learning’s
advance
understanding
critical
climate
Язык: Английский
Contributions of Atmospheric Ridging and Low Soil Moisture to the Record‐Breaking June 2023 Mexico‐Texas Heatwave
Geophysical Research Letters,
Год журнала:
2025,
Номер
52(5)
Опубликована: Фев. 27, 2025
Abstract
June
2023
witnessed
the
hottest,
largest,
and
longest‐lasting
heatwave
across
Mexico
Texas
between
1940
2023.
We
apply
constructed
analogs
with
multiple
linear
regression
models
to
quantify
contribution
of
different
drivers
daily
temperature
anomalies
during
this
heatwave.
On
hottest
day
(20
June),
circulation,
soil
moisture,
their
interaction
explained
3.82°C
(90%
CI:
2.72–4.91°C)
5.42°C
observed
anomaly
most
residual
attributed
thermodynamic
effects
long‐term
warming.
Using
CESM2‐LENS2,
we
find
that
2023‐like
patterns
are
not
projected
increase
in
frequency
but
will
become
1.9°C
hotter
by
mid‐21st
century
under
SSP3‐7.0.
The
simulated
these
could
produce
temperatures
>50°C
(122°F)
south
Texas,
representing
a
low‐likelihood
yet
physically
plausible
worst‐case
scenario
inform
disaster
preparedness
adaptation
planning.
Язык: Английский
Carbon price prediction research based on CEEMDAN-VMD secondary decomposition and BiLSTM
Environmental Science and Pollution Research,
Год журнала:
2025,
Номер
unknown
Опубликована: Март 17, 2025
Язык: Английский
Attributing climate and weather extremes to Northern Hemisphere sea ice and terrestrial snow: progress, challenges and ways forward
npj Climate and Atmospheric Science,
Год журнала:
2025,
Номер
8(1)
Опубликована: Май 3, 2025
Abstract
Sea
ice
and
snow
are
crucial
components
of
the
cryosphere
climate
system.
Both
sea
spring
in
Northern
Hemisphere
(NH)
have
been
decreasing
at
an
alarming
rate
a
changing
climate.
Changes
NH
linked
with
variety
weather
extremes
including
cold
spells,
heatwaves,
droughts
wildfires.
Understanding
these
linkages
will
benefit
predictions
extremes.
However,
existing
work
on
this
has
largely
fragmented
is
subject
to
large
uncertainties
physical
pathways
methodologies.
This
prevented
further
substantial
progress
attributing
change,
potentially
risk
loss
critical
window
for
effective
change
mitigation.
In
review,
we
synthesize
current
by
evaluating
observed
linkages,
their
pathways,
suggesting
ways
forward
future
research
efforts.
By
adopting
same
framework
both
snow,
highlight
combined
influence
cryospheric
feedback
We
suggest
that
from
improving
observational
networks,
addressing
causality
complexity
using
multiple
lines
evidence,
large-ensemble
approaches
artificial
intelligence,
achieving
synergy
between
different
methodologies/disciplines,
widening
context,
coordinated
international
collaboration.
Язык: Английский
Linking European Temperature Variations to Atmospheric Circulation With a Neural Network: A Pilot Study in a Climate Model
Geophysical Research Letters,
Год журнала:
2025,
Номер
52(9)
Опубликована: Май 8, 2025
Abstract
In
Europe,
temperature
variations
are
mainly
driven
by
the
North
Atlantic
atmospheric
circulation.
Here,
with
data
from
MIROC6
large
ensemble,
we
investigate
a
convolutional
neural
network
(a
UNET)
for
reconstructing
daily
anomalies
in
Europe
Sea
Level
Pressure
(SLP)
as
proxy
of
circulation,
and
compare
results
traditional
analogs
approach.
We
show
an
excellent
ability
UNET
to
estimate
given
information
SLP
only.
This
novel
method
outperforms
method,
at
both
inter‐annual
time
scales.
Our
study
also
shows
that
during
training,
learns
such
seasonal
cycle
relationship
between
sea‐level
pressure
anomalies,
which
could
explain
part
its
scores.
exploratory
work
opens
up
promising
prospects
estimating
contribution
variability
observed
variations.
Язык: Английский
Extreme precipitation, exacerbated by anthropogenic climate change, drove Peru's record-breaking 2023 dengue outbreak
Опубликована: Окт. 23, 2024
Anthropogenic
forcing
is
increasing
the
likelihood
and
severity
of
certain
extreme
weather
events,
which
may
catalyze
outbreaks
climate-sensitive
infectious
diseases.
Extreme
precipitation
events
can
promote
spread
mosquito-borne
illnesses
by
creating
vector
habitat,
destroying
infrastructure,
impeding
control.
Here,
we
focus
on
Cyclone
Yaku,
caused
heavy
rainfall
in
northwestern
Peru
from
March
7th
-
20th,
2023
was
followed
worst
dengue
outbreak
Peru's
history.
We
apply
generalized
synthetic
control
methods
to
account
for
baseline
climate
variation
unobserved
confounders
when
estimating
causal
effect
Yaku
cases
across
56
districts
with
greatest
anomalies.
estimate
that
67
(95%
CI:
30
87)
%
cyclone-affected
were
attributable
Yaku.
The
cyclone
significantly
increased
over
six
months,
causing
38,209
17,454
49,928)
out
57,246
cases.
largest
increases
incidence
due
occurred
a
large
share
low-quality
roofs
walls
residences,
greater
flood
risk,
warmer
temperatures
above
24°
Язык: Английский