Investigaciones Geográficas Boletín del Instituto de Geografía,
Journal Year:
2023,
Volume and Issue:
112
Published: Oct. 19, 2023
En
esta
investigación
se
detectaron
con
imágenes
Worldview2
tres
jales
mineros
abandonados.
Su
localización
confirmó
multiespectrales
obtenidas
por
un
vehículo
aéreo
no
tripulado.
A
estos
jales,
y
otros
13
sitios
donde
reportó
actividad
minera,
les
realizó
una
cuantificación
de
los
siguientes
metales
pesados:
cadmio
(Cd)
plomo
(Pb),
así
como
del
metaloide
arsénico
(As),
mediante
espectrofotometría
absorción
atómica.
Para
analizar
la
distribución
espacial
elementos
generó
base
datos
mediciones
encontrados
más
22
reportados
centros
experimentación
Servicio
Geológico
Mexicano.
Con
información
generaron
mapas
interpolación
para
cada
elemento
encontró
que
valores
Pb
ubicados
en
el
poblado
son
mayores
a
2000
ppm,
patrón
similar
presentó
As
superiores
1500
mientras
Cd
fueron
menores
30
ppm.
Se
concluye
tanto
están
encima
NOM-147-SEMARNAT/SSA1-2004,
lo
tanto,
es
urgente
plan
remediación
esos
suelos,
principalmente
localizaron
dentro
las
inmediaciones
presa.
recomienda
fitoremediación
Dodonaea
viscosa
recientemente
ha
reportado
su
eficacia
retención
pesados
contenidos
suelos
minas
abandonadas.
Geoderma,
Journal Year:
2024,
Volume and Issue:
443, P. 116823 - 116823
Published: March 1, 2024
Soil
organic
matter
(SOM)
content
is
an
important
indicator
to
measure
the
degradation
degree
and
fertility
of
soil.
However,
most
current
SOM
prediction
methods
are
based
on
statistical
learning
theory,
overlooking
transmission
process
physical
mechanism
reflectance
spectra,
lacking
basis
soil
remote
sensing.
In
this
study,
a
method
for
estimating
spectral
indices
constructed
by
improved
Hapke
model
was
proposed,
which
started
from
radiative
transfer
spectra
used
converted
r
single
scattering
albedo
ω
as
means
construct
indices.
The
accuracy
these
with
sensitive
bands
selected
laboratory-measured
data
(Data1)
validated
using
field
high-spectral
(Data2),
potential
application
in
sensing
multispectral
(Data3).
As
expected,
exhibit
good
both
hyper-spectral
(TBI37:
R2P
73.88;
RPD
2.02)
(TBI17:
R2P,
67.19;
1.78).
comparative
results
indicate
that,
terms
stability,
outperform
those
reflectance.
This
study
reduces
complexity
calibration
effectively,
have
clear
meaning
fast
high
at
large
scales.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,
Journal Year:
2024,
Volume and Issue:
17, P. 15393 - 15406
Published: Jan. 1, 2024
In
recent
years,
deep
learning
algorithms,
particularly
convolutional
neural
networks
(CNNs),
have
significantly
improved
the
performance
of
hyperspectral
image
(HSI)
classification.
However,
due
to
high
dimensionality
HSI
and
limited
training
samples,
network
causes
model
overfitting.
Additionally,
considering
all
bands
datasets
equally
for
feature
being
unable
distinguish
between
edge
center
pixels
a
neighborhood
reduces
classification
accuracy.
Thus,
in
this
paper,
we
propose
an
end-to-end
spectral-spatial
residual
attention
(DSSpRAN)
motivated
by
mechanism
human
visual
system
The
DSSpRAN
considers
input
data
as
3-D
cube
instead
using
reduction
methods.
proposed
simultaneously
incorporates
spectral
spatial
features
(SRAN)
(SpRAN).
SRAN,
weights
are
assigned
learned
adaptively
select
essential
from
each
band.
SpRAN
enhances
importance
classifying
nearby
pixel
pixel.
It
assigns
same
label
that
surrounding
pixels,
thus
limiting
with
different
labels.
method
has
been
evaluated
on
five
prove
state-of-the-art
various
land
use
cover
scenarios.
A
comprehensive
qualitative
quantitative
analysis
results
shows
outperforms
other
Remote Sensing,
Journal Year:
2025,
Volume and Issue:
17(5), P. 882 - 882
Published: March 1, 2025
In
the
current
global
change
scenario,
valuable
tools
for
improving
soils
and
increasing
both
agricultural
productivity
food
security,
together
with
effective
actions
to
mitigate
impacts
of
ongoing
climate
trends,
are
priority
issues.
Soil
Organic
Carbon
(SOC)
acts
on
these
two
topics,
as
C
is
a
core
element
soil
organic
matter,
an
essential
driver
fertility,
becomes
problematic
when
disposed
in
atmosphere
its
gaseous
form.
Laboratory
methods
measure
SOC
expensive
time-consuming.
This
Systematic
Literature
Review
(SLR)
aims
identify
techniques
alternative
ways
estimate
using
Remote-Sensing
(RS)
spectral
data
computer
process
this
database.
SLR
was
conducted
Meta-Analysis
(PRISMA)
methodology,
highlighting
use
Deep
Learning
(DL),
traditional
neural
networks,
other
machine-learning
models,
input
were
used
SOC.
The
concludes
that
Sentinel
satellites,
particularly
Sentinel-2,
frequently
used.
Despite
limited
datasets,
DL
models
demonstrated
robust
performance
assessed
by
R2
RMSE.
Key
data,
such
vegetation
indices
(e.g.,
NDVI,
SAVI,
EVI)
digital
elevation
consistently
correlated
predictions.
These
findings
underscore
potential
combining
RS
advanced
artificial-intelligence
efficient
scalable
monitoring.
