Geo-spatial Information Science,
Год журнала:
2024,
Номер
unknown, С. 1 - 21
Опубликована: Окт. 18, 2024
Reservoir
characterization
is
a
vital
task
within
the
oil
and
gas
industry,
with
identification
of
lithofacies
in
subsurface
formations
being
fundamental
aspect
this
process.
However,
complex
geological
environments
high
dimensions,
such
as
Lower
Indus
Basin
Pakistan,
poses
notable
challenge,
especially
when
dealing
limited
data.
To
address
issue,
we
propose
four
common
data-driven
machine
learning
approaches:
multi-resolution
graph-based
clustering
(MRGC),
artificial
neural
networks
(ANN),
K-nearest
neighbors
(KNN),
self-organizing
map
(SOM).
We
utilized
these
proposed
approaches
to
assess
their
performance
scenarios
varying
core
sample
availability,
specifically
evaluating
effectiveness
identifying
Goru
formation
middle
Basin.
The
study
reveals
that
number
samples,
MRGC
preferred
choice,
while
KNN
or
more
suitable
for
larger
datasets.
results
demonstrate
superior
specified
environment,
SOM
following
closely
behind,
ANN
exhibiting
comparatively
lower
efficacy.
accurate
from
selected
model
complemented
by
application
truncated
Gaussian
simulation
method
facies
modeling.
Comparative
confirm
excellent
agreement
between
well
logs
electro-facies
obtained
volume.
This
highlights
crucial
role
selecting
right
approach
precise
modeling
environments.
comparative
analysis
provides
practitioners
petroleum
industry
insights
into
strengths
limitations
each
method,
enhancing
existing
knowledge.
In
conclusion,
research
emphasizes
significance
comprehensive
selection
advancing
diverse
areas,
ultimately
benefiting
broader
field
industry.
Geocarto International,
Год журнала:
2023,
Номер
38(1)
Опубликована: Май 2, 2023
The
majority
of
people
living
on
earth
rely
groundwater
as
their
primary
supply
water
for
daily
needs.
However,
human
activities
continuously
threaten
this
natural
resource.
In
an
attempt
to
unravel
the
extent
impact
human-related
physicochemical
characteristics
in
Nnewi
and
Awka
urban
clusters
(Nigeria),
several
techniques
were
integrated
study.
Groundwater
samples
warm
acidic
nature.
Concentrations
SO42-,
NO3-,
PO43-,
Cl-,
HCO3-,
Ca2+,
Mg2+,
Na+
K+
within
set
benchmarks.
nutrient
pollution
index
(ranging
from
0.060
0.745),
nitrate
(varying
between
−0.999
−0.790)
0.057
0.630)
estimated
anthropogenic
contamination
showed
low
characteristics.
health
risks
due
ingestion
skin
absorption
nitrate-contaminated
computed
six
age
groups
(6–12
months,
5–10
years,
10–15
15–20
20–60
years
>60
years)
risk
values
that
<
1,
implying
chronic
humans.
cumulative
total
hazard
ranged
0.006
0.787
with
a
mean
value
0.167.
Chemometric
analyses
geochemical
plots
revealed
relationships
variables
sources.
Chadha's
plot
55%
Ca2+-Mg2+-Cl-
waters,
predominating
over
Na+-Cl-
Ca2+-Mg2+-HCO3-
waters.
Bivariate
multivariate
also
indicated
impact.
Furthermore,
principal
component
analysis
R-type
hierarchical
clustering
confirmed
chemistry
quality
mostly
influenced
by
geogenic
processes
than
acts.
Conclusively,
influence
is
low.
These
findings
would
be
useful
future
monitoring
both
clusters.
Water,
Год журнала:
2023,
Номер
15(3), С. 558 - 558
Опубликована: Янв. 31, 2023
Flood,
a
distinctive
natural
calamity,
has
occurred
more
frequently
in
the
last
few
decades
all
over
world,
which
is
often
an
unexpected
and
inevitable
hazard,
but
losses
damages
can
be
managed
controlled
by
adopting
effective
measures.
In
recent
times,
flood
hazard
susceptibility
mapping
become
prime
concern
minimizing
worst
impact
of
this
global
threat;
nonlinear
relationship
between
several
causative
factors
dynamicity
risk
levels
makes
it
complicated
confronted
with
substantial
challenges
to
reliable
assessment.
Therefore,
we
have
considered
SVM,
RF,
ANN—three
ML
algorithms
GIS
platform—to
delineate
zones
subtropical
Kangsabati
river
basin,
West
Bengal,
India;
experienced
frequent
events
because
intense
rainfall
throughout
monsoon
season.
our
study,
adopted
are
efficient
solving
non-linear
problems
assessment;
multi-collinearity
analysis
Pearson’s
correlation
coefficient
techniques
been
used
identify
collinearity
issues
among
fifteen
factors.
research,
predicted
results
evaluated
through
six
prominent
statistical
(“AUC-ROC,
specificity,
sensitivity,
PPV,
NPV,
F-score”)
one
graphical
(Taylor
diagram)
technique
shows
that
ANN
most
modeling
approach
followed
RF
SVM
models.
The
values
AUC
model
for
training
validation
datasets
0.901
0.891,
respectively.
derived
result
states
about
7.54%
10.41%
areas
accordingly
lie
under
high
extremely
danger
zones.
Thus,
study
help
decision-makers
constructing
proper
strategy
at
regional
national
mitigate
particular
region.
This
type
information
may
helpful
various
authorities
implement
outcome
spheres
decision
making.
Apart
from
this,
future
researchers
also
able
conduct
their
research
byconsidering
methodology
