Scientific Reports,
Год журнала:
2024,
Номер
14(1)
Опубликована: Фев. 6, 2024
Abstract
An
accurate
assessment
of
nitrate
leaching
is
important
for
efficient
fertiliser
utilisation
and
groundwater
pollution
reduction.
However,
past
studies
could
not
efficiently
model
due
to
conventional
algorithms.
To
address
the
issue,
current
research
employed
advanced
machine
learning
algorithms,
viz.,
Support
Vector
Machine,
Artificial
Neural
Network,
Random
Forest,
M5
Tree
(M5P),
Reduced
Error
Pruning
(REPTree)
Response
Surface
Methodology
(RSM)
predict
optimize
leaching.
In
this
study,
Urea
Super
Granules
(USG)
with
three
different
coatings
were
used
experiment
in
soil
columns,
containing
1
kg
placed
between.
Statistical
parameters,
namely
correlation
coefficient,
Mean
Absolute
Error,
Willmott
index,
Root
Square
Nash–Sutcliffe
efficiency
evaluate
performance
ML
techniques.
addition,
a
comparison
was
made
test
set
among
models
which,
RSM
outperformed
rest
irrespective
coating
type.
Neem
oil/
Acacia
oil(ml):
clay/sulfer
(g):
age
(days)
minimum
found
be
2.61:
1.67:
2.4
USG
bentonite
clay
neem
oil
without
heating,
2.18:
2:
heating
1.69:
1.64:
2.18
sulfer
acacia
oil.
The
would
provide
guidelines
researchers
policymakers
select
appropriate
tool
precise
prediction
leaching,
which
optimise
yield
benefit–cost
ratio.
Journal of Hydrology,
Год журнала:
2024,
Номер
633, С. 130968 - 130968
Опубликована: Фев. 28, 2024
Water
availability
for
agricultural
practices
is
dynamically
influenced
by
climatic
variables,
particularly
droughts.
Consequently,
the
assessment
of
drought
events
directly
related
to
strategic
water
management
in
sector.
The
application
machine
learning
(ML)
algorithms
different
scenarios
variables
a
new
approach
that
needs
be
evaluated.
In
this
context,
current
research
aims
forecast
short-term
i.e.,
SPI-3
from
predictors
under
historical
(1901–2020)
and
future
(2021–2100)
employing
(bagging
(BG),
random
forest
(RF),
decision
table
(DT),
M5P)
Hungary,
Central
Europe.
Three
meteorological
stations
namely,
Budapest
(BD)
(central
Hungary),
Szeged
(SZ)
(east
south
Szombathely
(SzO)
(west
Hungary)
were
selected
agriculture
Standardized
Precipitation
Index
(SPI-3)
long
run.
For
purpose,
ensemble
means
three
global
circulation
models
GCMs
CMIP6
are
being
used
get
projected
time
series
indicators
(i.e.,
rainfall
R,
mean
temperature
T,
maximum
Tmax,
minimum
Tmin
two
socioeconomic
pathways
(SSP2-4.5
SSP4-6.0).
results
study
revealed
more
severe
extreme
past
decades,
which
increase
near
(2021–2040).
Man-Kendall
test
(Tau)
along
with
Sen's
slope
(SS)
also
an
increasing
trend
period
Tau
=
−0.2,
SS
−0.05,
−0.12,
−0.09
SSP2-4.5
−0.1,
−0.08
SSP4-6.0.
Implementation
ML
scenarios:
SC1
(R
+
T
Tmax
Tmin),
SC2
(R),
SC3
T))
at
BD
station
RF-SC3
lowest
RMSE
RFSC3-TR
0.33,
highest
NSE
0.89
performed
best
forecasting
on
dataset.
Hence,
was
implemented
remaining
(SZ
SzO)
1901
2100
Interestingly,
forecasted
SSP2-4.5,
0.34
0.88
SZ
0.87
SzO
SSP2-4.5.
our
findings
recommend
using
provide
accurate
predictions
R
projections.
This
could
foster
gradual
shift
towards
sustainability
improve
resources.
However,
concrete
plans
still
needed
mitigate
negative
impacts
2028,
2030,
2031,
2034.
Finally,
validation
RF
prediction
large
dataset
makes
it
significant
use
other
studies
facilitates
making
disaster
strategies.
Water,
Год журнала:
2024,
Номер
16(13), С. 1904 - 1904
Опубликована: Июль 3, 2024
Machine
learning
(ML)
applications
in
hydrology
are
revolutionizing
our
understanding
and
prediction
of
hydrological
processes,
driven
by
advancements
artificial
intelligence
the
availability
large,
high-quality
datasets.
This
review
explores
current
state
ML
hydrology,
emphasizing
utilization
extensive
datasets
such
as
CAMELS,
Caravan,
GRDC,
CHIRPS,
NLDAS,
GLDAS,
PERSIANN,
GRACE.
These
provide
critical
data
for
modeling
various
parameters,
including
streamflow,
precipitation,
groundwater
levels,
flood
frequency,
particularly
data-scarce
regions.
We
discuss
type
methods
used
significant
successes
achieved
through
those
models,
highlighting
their
enhanced
predictive
accuracy
integration
diverse
sources.
The
also
addresses
challenges
inherent
applications,
heterogeneity,
spatial
temporal
inconsistencies,
issues
regarding
downscaling
LSH,
need
incorporating
human
activities.
In
addition
to
discussing
limitations,
this
article
highlights
benefits
utilizing
high-resolution
compared
traditional
ones.
Additionally,
we
examine
emerging
trends
future
directions,
real-time
quantification
uncertainties
improve
model
reliability.
place
a
strong
emphasis
on
citizen
science
IoT
collection
hydrology.
By
synthesizing
latest
research,
paper
aims
guide
efforts
leveraging
large
techniques
advance
enhance
water
resource
management
practices.
