Machine learning-enhanced GALDIT modeling for the Nile Delta aquifer vulnerability assessment in the Mediterranean region
Groundwater for Sustainable Development,
Год журнала:
2025,
Номер
28, С. 101403 - 101403
Опубликована: Янв. 7, 2025
Язык: Английский
An Improved Groundwater Vulnerability Evaluation Model Based on Random Forest Algorithm and Spatio-Temporal Change Prediction Method
Process Safety and Environmental Protection,
Год журнала:
2025,
Номер
unknown, С. 106781 - 106781
Опубликована: Янв. 1, 2025
Язык: Английский
Mapping Groundwater Potential Zones in the Widyan Basin, Al Qassim, KSA: Analytical Hierarchy Process-Based Analysis Using Sentinel-2, ASTER-DEM, and Conventional Data
Remote Sensing,
Год журнала:
2025,
Номер
17(5), С. 766 - 766
Опубликована: Фев. 22, 2025
Groundwater
availability
in
semi-arid
regions
like
the
Widyan
Basin,
Kingdom
of
Saudi
Arabia
(KSA),
is
a
critical
challenge
due
to
climatic,
topographic,
and
hydrological
variations.
The
accurate
identification
groundwater
zones
essential
for
sustainable
development.
Therefore,
this
study
combines
remote-sensing
datasets
(Sentinel-2
ASTER-DEM)
with
conventional
data
using
Geographic
Information
System
(GIS)
analytical
hierarchy
process
(AHP)
techniques
delineate
potential
(GWPZs).
basin’s
geology
includes
Pre-Cambrian
rock
units
Arabian
Shield
southwest
Cambrian–Ordovician
northeast,
Saq
Formation
serving
as
main
aquifer.
Six
soil
types
were
identified:
Haplic
Calcic
Yermosols,
Calcaric
Regosols,
Cambic
Arenosols,
Orthic
Solonchaks,
Lithosols.
topography
varies
from
steep
areas
northwest
nearly
flat
terrain
northeast.
Hydrologically,
basin
divided
into
28
sub-basins
four
stream
orders.
Using
GIS-based
AHP
weighted
overlay
methods,
GWPZs
mapped,
achieving
model
consistency
ratio
0.0956.
categorized
excellent
(15.21%),
good
(40.85%),
fair
(43.94%),
poor
(0%).
GWPZ
was
validated
by
analyzing
48
water
wells
distributed
area.
These
range
fresh
primary
saline
water,
depths
varying
between
13.98
130
m.
Nine
wells—with
an
average
total
dissolved
solids
(TDS)
value
597.2
mg/L—fall
within
zone,
twenty-one
are
fifteen
classified
remaining
fall
TDS
values
reaching
up
2177
mg/L.
results
indicate
that
central
zone
area
suitable
drilling
new
wells.
Язык: Английский
Advancing Deltaic Aquifer Vulnerability Mapping to Seawater Intrusion and Human Impacts in Eastern Nile Delta: Insights from Machine Learning and Hydrochemical Perspective
Earth Systems and Environment,
Год журнала:
2024,
Номер
unknown
Опубликована: Ноя. 16, 2024
Язык: Английский
Unveiling Groundwater Potential in Hangu District, Pakistan: A GIS-Driven Bivariate Modeling and Remote Sensing Approach for Achieving SDGs
Water,
Год журнала:
2024,
Номер
16(22), С. 3317 - 3317
Опубликована: Ноя. 18, 2024
Sustainable
groundwater
development
stands
out
as
a
contemporary
concern
for
growing
global
populations,
particularly
in
stressed
riverine
arid
and
semi-arid
regions.
This
study
integrated
satellite-based
(Sentinel-2,
ALOS-DEM,
CHIRPS
rainfall)
data
with
ancillary
lithology
infrastructure
datasets
using
Weight
of
Evidence
(WoE)
Frequency
Ratio
(FR)
models
to
delineate
Groundwater
Potential
Zones
(GWPZs)
the
Hangu
District,
hydrologically
region
northern
Pakistan,
support
Development
Goals
(SDGs).
Ten
key
variables,
including
elevation,
slope,
aspect,
distance
drainage
(DD),
rainfall,
land
use/land
cover,
Normalized
Difference
Vegetation
Index,
lithology,
road
proximity,
were
incorporated
into
Geographic
information
system
(GIS)
environment.
The
FR
model
outperformed
WoE
model,
achieving
success
prediction
rates
89%
93%,
compared
82%
86%.
GWPZs-FR
identified
23%
(317
km2)
high
potential,
located
highly
fractured
pediment
fans
below
550
m,
gentle
slopes
(<5
degrees),
DD
(within
200
m),
rainfall
areas
natural
trees
vegetation
on
valley
terrace
deposits.
research
findings
significantly
multiple
SDGs,
estimated
achievement
potentials
37.5%
SDG
6
(Clean
Water
Sanitation),
20%
13
(Climate
Action),
15%
8
(Decent
Work
Economic
Growth),
12.5%
9
(Industry,
Innovation,
Infrastructure),
notable
contributions
10%
2
5%
3.
approach
provides
valuable
insights
policymakers,
offering
framework
managing
resources
advancing
sustainable
practices
similar
Язык: Английский
Advancing Agricultural Land Suitability in Urbanized Semi-Arid Environments: Insights from Geospatial and Machine Learning Approaches
ISPRS International Journal of Geo-Information,
Год журнала:
2024,
Номер
13(12), С. 436 - 436
Опубликована: Дек. 3, 2024
Rising
food
demands
are
increasingly
threatened
by
declining
crop
yields
in
urbanizing
riverine
regions
of
Southern
Asia,
exacerbated
erratic
weather
patterns.
Optimizing
agricultural
land
suitability
(AgLS)
offers
a
viable
solution
for
sustainable
productivity
such
challenging
environments.
This
study
integrates
remote
sensing
and
field-based
geospatial
data
with
five
machine
learning
(ML)
algorithms—Naïve
Bayes
(NB),
extra
trees
classifier
(ETC),
random
forest
(RF),
K-nearest
neighbors
(KNN),
support
vector
machines
(SVM)—alongside
land-use/land-cover
(LULC)
considerations
the
food-insecure
Dharmapuri
district,
India.
A
grid
searches
optimized
hyperparameters
using
factors
as
slope,
rainfall,
temperature,
texture,
pH,
electrical
conductivity,
organic
carbon,
available
nitrogen,
phosphorus,
potassium,
calcium
carbonate.
The
tuned
ETC
model
showed
lowest
root
mean
squared
error
(RMSE
=
0.15),
outperforming
RF
0.18),
NB
0.20),
SVM
0.22),
KNN
0.23).
AgLS-ETC
map
identified
29.09%
area
highly
suitable
(S1),
19.06%
moderately
(S2),
16.11%
marginally
(S3),
15.93%
currently
unsuitable
(N1),
19.21%
permanently
(N2).
By
incorporating
Landsat-8
derived
LULC
to
exclude
forests,
water
bodies,
settlements,
these
estimates
were
adjusted
19.08%
14.45%
11.40%
10.48%
9.58%
Focusing
on
model,
followed
land-use
analysis,
provides
robust
framework
optimizing
planning,
ensuring
protection
ecological
social
developing
countries.
Язык: Английский
Machine learning-based monitoring and design of managed aquifer rechargers for sustainable groundwater management: scope and challenges
Environmental Science and Pollution Research,
Год журнала:
2024,
Номер
unknown
Опубликована: Ноя. 25, 2024
Abstract
Managed
aquifer
recharge
(MAR)
replenishes
groundwater
by
artificially
entering
water
into
subsurface
aquifers.
This
technology
improves
storage,
reduces
over-extraction,
and
ensures
security
in
water-scarce
or
variable
environments.
MAR
systems
are
complex,
encompassing
various
components
such
as
soil,
meteorological
factors,
management
(GWM),
receiving
bodies.
Over
the
past
decade,
utilization
of
machine
learning
(ML)
methodologies
for
modeling
prediction
has
increased
significantly.
review
evaluates
all
supervised,
semi-supervised,
unsupervised,
ensemble
ML
models
employed
to
predict
factors
parameters,
rendering
it
most
comprehensive
contemporary
on
this
subject.
study
presents
a
concise
integrated
overview
MAR’s
effective
approaches,
focusing
design,
suitability
quality
(WQ)
applications,
GWM.
The
paper
examines
performance
measures,
input
specifications,
variety
functions
GWM,
highlights
prospects.
It
also
offers
suggestions
utilizing
MAR,
addressing
issues
related
physical
aspects,
technical
advancements,
case
studies.
Additionally,
previous
research
ML-based
data-driven
soft
sensing
techniques
is
critically
evaluated.
concludes
that
integrating
holds
significant
promise
optimizing
WQ
enhancing
efficiency
replenishment
strategies.
Язык: Английский
Resolving challenges of groundwater flow modelling for improved water resources management: a narrative review
International Journal of Hydrology,
Год журнала:
2024,
Номер
8(5), С. 175 - 193
Опубликована: Янв. 1, 2024
Groundwater
flow
modelling
is
critical
for
managing
groundwater
resources,
particularly
amid
climate
change
and
rising
water
demand.
This
narrative
review
examines
the
role
of
models
in
sustainable
resource
management,
focusing
on
challenges
solutions
to
enhance
model
reliability.
A
key
challenge
data
limitation—especially
regions
like
sub-Saharan
Africa
South
Asia,
where
scarce
hydrogeological
hinders
accurate
calibration.
The
complexity
aquifer
systems,
such
as
karst
aquifers
North
America
fractured-rock
India,
further
complicates
development,
requiring
detailed
geological
complex
simulations.
Additionally,
uncertainties
arise
from
limited
knowledge
properties,
variable
boundary
conditions,
sparse
monitoring
networks,
which
can
reduce
predictability.
Despite
these
obstacles,
are
essential
simulating
behaviour
response
altered
precipitation
patterns,
increasing
extraction
rates,
extreme
events
droughts.
For
instance,
predictive
has
helped
assess
potential
depletion
risks
California’s
Central
Valley
contamination
industrial
zones
East
guiding
strategies
assessments.
To
improve
reliability,
this
emphasizes
need
enhanced
collection,
integration
advanced
technologies—such
artificial
intelligence
machine
learning
accuracy—and
adoption
multidisciplinary
approaches.
These
advancements,
improved
sensor
regional
data-sharing
initiatives
reducing
precision.
Ultimately,
improvements
will
support
adaptation
efforts
promote
management
global
benefiting
managers
policy
makers.
Язык: Английский
Study on the Spatiotemporal Evolution of Habitat Quality in Highly Urbanized Areas Based on Bayesian Networks: A Case Study from Shenzhen, China
Sustainability,
Год журнала:
2024,
Номер
16(24), С. 10993 - 10993
Опубликована: Дек. 15, 2024
Rapid
urbanization
presents
significant
challenges
to
biodiversity
through
habitat
degradation,
fragmentation,
and
loss.
This
study
focuses
on
Shenzhen,
China,
a
highly
urbanized
region
experiencing
substantial
land
use
changes
facing
considerable
risk
of
decline,
investigate
the
dynamics
quality
over
two
critical
periods:
2010–2015
2015–2020.
Using
InVEST
(Integrated
Valuation
Ecosystem
Services
Trade-offs)
model
for
assessment
Bayesian
networks
analyze
causal
relationships,
this
research
offers
an
innovative
comparison
between
recovery
degradation
across
these
phases.
Results
indicate
that
from
2010
2015,
localized
was
achieved
0.53%
area
due
restoration
policies,
yet
overall
trend
remained
negative.
During
2015–2020
period,
intensified
(7.19%)
compared
(5.7%);
notably,
70.6%
areas
had
been
previously
restored
are
now
once
again.
re-degradation
highlights
instability
earlier
efforts
under
ongoing
urban
pressure.
By
integrating
spatial
analysis
with
network
modeling,
provides
nuanced
understanding
where
why
initial
were
unsuccessful,
identifying
susceptible
persistent
degradation.
The
emphasizes
expansion—particularly
development
construction
land,
primary
driver
while
ecological
sensitivity
played
crucial
role
in
determining
long-term
success
efforts.
approach
valuable
insights
designing
more
effective,
sustainable
conservation
strategies
rapidly
urbanizing
regions.
Язык: Английский