Science of Remote Sensing,
Год журнала:
2024,
Номер
10, С. 100146 - 100146
Опубликована: Июль 2, 2024
Combining
the
advantages
of
crop
growth
models
and
remote
sensing
observations,
data
assimilation
(DA)
has
emerged
as
a
vital
tool
for
monitoring
early-season
yield
forecasting.
As
an
increasing
number
related
studies
have
been
conducted,
systems
grown
increasingly
sophisticated.
However,
within
this
context,
research
on
algorithms,
core
component
system,
highly
need
investigating
potential.
In
review,
we
discuss
essential
differences
inherent
connections
various
algorithms
based
Bayes's
Theorem.
Building
upon
foundation,
review
application
progress
different
DA
models.
Additionally,
identify
challenges
limitations
faced
by
current
in
practical
applications
propose
potential
directions
future
study.
summary
entire
paper,
provide
recommendations
algorithm
choice
strategy
conjunction
with
specific
scenarios.
The Innovation,
Год журнала:
2024,
Номер
5(5), С. 100691 - 100691
Опубликована: Авг. 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
Reviews of Geophysics,
Год журнала:
2024,
Номер
62(1)
Опубликована: Фев. 11, 2024
Abstract
Lake
thermal
dynamics
have
been
considerably
impacted
by
climate
change,
with
potential
adverse
effects
on
aquatic
ecosystems.
To
better
understand
the
impacts
of
future
change
lake
and
related
processes,
use
mathematical
models
is
essential.
In
this
study,
we
provide
a
comprehensive
review
water
temperature
modeling.
We
begin
discussing
physical
concepts
that
regulate
in
lakes,
which
serve
as
primer
for
description
process‐based
models.
then
an
overview
different
sources
observational
data,
including
situ
monitoring
satellite
Earth
observations,
used
field
classify
various
available,
discuss
model
performance,
commonly
performance
metrics
optimization
methods.
Finally,
analyze
emerging
modeling
approaches,
forecasting,
digital
twins,
combining
deep
learning,
evaluating
structural
differences
through
ensemble
modeling,
adapted
management,
coupling
This
aimed
at
diverse
group
professionals
working
fields
limnology
hydrology,
ecologists,
biologists,
physicists,
engineers,
remote
sensing
researchers
from
private
public
sectors
who
are
interested
understanding
its
applications.
Annals of the American Association of Geographers,
Год журнала:
2024,
Номер
114(3), С. 499 - 519
Опубликована: Фев. 7, 2024
Spatial
statistics
is
an
important
methodology
for
geospatial
data
analysis.
It
has
evolved
to
handle
spatially
autocorrelated
and
(locally)
heterogeneous
data,
which
aim
capture
the
first
second
laws
of
geography,
respectively.
Examples
stratified
heterogeneity
(SSH)
include
climatic
zones
land-use
types.
Methods
such
are
relatively
underdeveloped
compared
two
properties.
The
presence
SSH
evidence
that
nature
lawful
structured
rather
than
purely
random.
This
induces
another
"layer"
causality
underlying
variations
observed
in
geographical
data.
In
this
article,
we
go
beyond
traditional
cluster-based
approaches
propose
a
unified
approach
provide
equation
SSH,
display
how
source
bias
spatial
sampling
confounding
modeling,
detect
nonlinear
stochastic
inherited
distribution,
quantify
general
interaction
identified
by
overlaying
distributions,
perform
prediction
based
on
develop
new
measure
goodness
fit,
enhance
global
modeling
integrating
them
with
q
statistic.
research
advances
statistical
theory
methods
dealing
thereby
offering
toolbox
Reviews of Geophysics,
Год журнала:
2024,
Номер
62(1)
Опубликована: Март 1, 2024
Abstract
Data
assimilation
plays
a
dual
role
in
advancing
the
“scientific”
understanding
and
serving
as
an
“engineering
tool”
for
Earth
system
sciences.
Land
data
(LDA)
has
evolved
into
distinct
discipline
within
geophysics,
facilitating
harmonization
of
theory
allowing
land
models
observations
to
complement
constrain
each
other.
Over
recent
decades,
substantial
progress
been
made
theory,
methodology,
application
LDA,
necessitating
holistic
in‐depth
exploration
its
full
spectrum.
Here,
we
present
thorough
review
elucidating
theoretical
methodological
developments
LDA
distinctive
features.
This
encompasses
breakthroughs
addressing
strong
nonlinearities
surface
processes,
exploring
potential
machine
learning
approaches
assimilation,
quantifying
uncertainties
arising
from
multiscale
spatial
correlation,
simultaneously
estimating
model
states
parameters.
proven
successful
enhancing
prediction
various
processes
(including
soil
moisture,
snow,
evapotranspiration,
streamflow,
groundwater,
irrigation
temperature),
particularly
realms
water
energy
cycles.
outlines
development
global,
regional,
catchment‐scale
systems
software
platforms,
proposing
grand
challenges
generating
reanalysis
coupled
land‒atmosphere
DA.
We
lastly
highlight
opportunities
expand
applications
pure
geophysical
natural
human
by
ingesting
deluge
observation
social
sensing
data.
The
paper
synthesizes
current
knowledge
provides
steppingstone
future
development,
promoting
driven
theory‐data
studies.
Abstract
Interpretable
Machine
Learning
(IML)
has
rapidly
advanced
in
recent
years,
offering
new
opportunities
to
improve
our
understanding
of
the
complex
Earth
system.
IML
goes
beyond
conventional
machine
learning
by
not
only
making
predictions
but
also
seeking
elucidate
reasoning
behind
those
predictions.
The
combination
predictive
power
and
enhanced
transparency
makes
a
promising
approach
for
uncovering
relationships
data
that
may
be
overlooked
traditional
analysis.
Despite
its
potential,
broader
implications
field
have
yet
fully
appreciated.
Meanwhile,
rapid
proliferation
IML,
still
early
stages,
been
accompanied
instances
careless
application.
In
response
these
challenges,
this
paper
focuses
on
how
can
effectively
appropriately
aid
geoscientists
advancing
process
understanding—areas
are
often
underexplored
more
technical
discussions
IML.
Specifically,
we
identify
pragmatic
application
scenarios
typical
geoscientific
studies,
such
as
quantifying
specific
contexts,
generating
hypotheses
about
potential
mechanisms,
evaluating
process‐based
models.
Moreover,
present
general
practical
workflow
using
address
research
questions.
particular,
several
critical
common
pitfalls
use
lead
misleading
conclusions,
propose
corresponding
good
practices.
Our
goal
is
facilitate
broader,
careful
thoughtful
integration
into
science
research,
positioning
it
valuable
tool
capable
enhancing
current
