I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
,
p
p
.
1
3
4
6
~
1
3
5
8
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v9
i
2
.
pp
1
3
4
6
-
1358
1346
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
P
a
ddy
f
i
e
l
d cl
a
s
s
i
f
i
c
a
ti
o
n
w
i
t
h M
OD
I
S
-
t
erra
m
ul
ti
-
tem
po
ra
l
i
m
a
g
e
tra
n
s
f
o
rm
a
ti
o
n u
s
i
n
g
ph
en
o
l
o
g
i
c
a
l
app
r
o
a
ch
i
n
J
a
v
a
I
s
l
a
nd
M
uh
a
mm
a
d Di
m
y
a
t
i
1
,
K
us
t
iy
o
2
,
Ra
t
ih De
w
a
nti
Di
m
y
a
t
i
3
1
De
p
a
rtme
n
t
o
f
G
e
o
g
r
a
p
h
y
,
Un
i
v
e
rsit
y
o
f
In
d
o
n
e
sia
,
I
n
d
o
n
e
sia
2
, 3
Re
m
o
te S
e
n
s
in
g
T
e
c
h
n
o
lo
g
y
a
n
d
Da
ta Ce
n
ter,
Na
ti
o
n
a
l
I
n
stit
u
te
o
f
A
e
ro
n
a
u
ti
c
s an
d
S
p
a
c
e
(LA
P
A
N),
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l
3
,
2
0
1
8
R
ev
i
s
ed
Sep
t
6
,
2
0
1
8
A
cc
ep
ted
Oct
11
,
2
0
1
8
T
h
is
p
a
p
e
r
p
re
se
n
ts
th
e
p
a
d
d
y
f
i
e
ld
c
las
sif
i
c
a
ti
o
n
m
o
d
e
l
u
sin
g
th
e
a
p
p
ro
a
c
h
b
a
se
d
o
n
p
e
ri
o
d
ic
p
lan
t
li
f
e
c
y
c
le
e
v
e
n
ts
a
n
d
h
o
w
th
e
se
e
le
v
a
ti
o
n
s
in
c
li
m
a
t
e
a
s
w
e
ll
a
s
h
a
b
it
a
t
f
a
c
to
rs,
su
c
h
a
s
e
lev
a
ti
o
n
.
T
h
e
d
a
ta
u
se
d
a
r
e
M
O
DIS
-
T
e
rra
tw
o
ti
les
o
f
H2
8
v
0
9
a
n
d
H
2
9
v
0
9
o
f
2
0
1
6
,
c
o
n
sist
o
f
4
6
se
ries
o
f
8
-
d
a
il
y
d
a
ta
,
w
it
h
5
0
0
m
e
ter
re
so
lu
ti
o
n
i
n
J
a
v
a
re
g
io
n
.
T
h
e
p
a
d
d
y
f
i
e
ld
c
las
sif
i
c
a
ti
o
n
m
e
th
o
d
b
a
se
d
o
n
th
e
p
h
e
n
o
l
o
g
ica
l
m
o
d
e
l
is
d
o
n
e
b
y
M
a
x
i
m
u
m
L
i
k
e
li
h
o
o
d
o
n
th
e
tran
sf
o
rm
e
d
a
n
n
u
a
l
m
u
lt
i
-
tem
p
o
ra
l
i
m
a
g
e
o
f
th
e
re
f
lec
tan
c
e
d
a
ta,
in
d
e
x
d
a
ta,
a
n
d
t
h
e
c
o
m
b
in
a
ti
o
n
o
f
re
fle
c
tan
c
e
a
n
d
in
d
e
x
d
a
ta.
T
h
e
re
s
u
lt
s
o
f
th
e
stu
d
y
sh
o
w
e
d
th
a
t,
w
it
h
th
e
re
fe
re
n
c
e
o
f
th
e
P
a
d
d
y
F
ield
M
a
p
f
ro
m
th
e
M
in
istry
o
f
Ag
ricu
lt
u
re
(M
o
A
),
th
e
o
v
e
ra
ll
a
c
c
u
ra
c
ies
o
f
th
e
p
a
d
d
y
f
ield
c
las
si
f
ica
ti
o
n
re
su
lt
s
u
sin
g
t
h
e
c
o
m
b
in
a
ti
o
n
o
f
re
f
lec
tan
c
e
a
n
d
i
n
d
e
x
d
a
ta
p
ro
v
id
e
th
e
h
ig
h
e
st
(8
5
.
4
%
)
a
m
o
n
g
th
e
re
f
l
e
c
tan
c
e
d
a
ta
(8
3
.
5
%
)
a
n
d
in
d
e
x
d
a
ta (8
1
.
7
%
).
T
h
e
a
c
c
u
ra
c
y
lev
e
ls
we
re
v
a
ried
;
th
e
se
d
e
p
e
n
d
o
n
t
h
e
slo
p
e
a
n
d
th
e
ty
p
e
s
o
f
p
a
d
d
y
f
ield
s.
P
a
d
d
y
f
ield
s
o
n
th
e
slo
p
e
s
o
f
0
-
2
%
c
o
u
ld
b
e
w
e
ll
id
e
n
ti
f
ied
b
y
M
OD
IS
-
T
e
rra
d
a
ta,
w
h
e
re
a
s
it
w
a
s
d
i
f
f
i
c
u
lt
to
i
d
e
n
ti
f
y
th
e
p
a
d
d
y
f
ield
s
o
n
th
e
slo
p
e
>
2
%
.
Ra
in
-
f
e
d
lo
w
lan
d
p
a
d
d
y
f
ield
ty
p
e
h
a
s
a
lo
w
e
r
u
se
r
a
c
c
u
ra
c
y
th
a
n
irri
g
a
ted
p
a
d
d
y
f
ield
s.
T
h
is
stu
d
y
a
lso
p
e
rf
o
r
m
e
d
c
o
rre
latio
n
(r
2
)
b
e
tw
e
e
n
th
e
a
n
a
ly
sis
re
su
lt
s
a
n
d
th
e
sta
ti
st
ic
a
l
d
a
t
a
b
a
se
d
o
n
d
istri
c
t
a
n
d
p
ro
v
i
n
c
ial
b
o
u
n
d
a
ries
w
e
re
>
0
.
8
5
a
n
d
>
0
.
9
9
re
sp
e
c
ti
v
e
l
y
.
T
h
e
s
e
c
o
rre
latio
n
s
w
e
re
m
u
c
h
h
ig
h
e
r
th
a
n
th
e
p
re
v
io
u
s
stu
d
y
re
su
lt
s,
w
h
ich
re
a
c
h
e
d
0
.
4
9
-
0
.
6
5
(h
il
ly
-
f
lat
a
re
a
s
o
f
c
o
u
n
ty
-
lev
e
l),
a
n
d
0
.
8
0
-
0
.
8
8
(h
il
ly
-
f
lat
a
re
a
s
o
f
p
ro
v
i
n
c
ial
lev
e
l)
f
o
r
Ch
i
n
a
,
a
n
d
re
a
c
h
e
d
0
.
4
4
f
o
r
I
n
d
o
n
e
sia
.
K
ey
w
o
r
d
s
:
C
las
s
i
f
icatio
n
Mu
lti
-
te
m
p
o
r
al
i
m
a
g
e
P
ad
d
y
f
ield
P
h
en
o
lo
g
ical
ap
p
r
o
ac
h
T
r
an
s
f
o
r
m
atio
n
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Mu
h
a
m
m
ad
Di
m
y
a
ti
,
Dep
ar
t
m
en
t o
f
Geo
g
r
ap
h
y
,
Un
i
v
er
s
it
y
o
f
I
n
d
o
n
e
s
ia,
Ka
m
p
u
s
UI
Dep
o
k
1
6
4
2
4
,
J
ak
ar
ta,
I
n
d
o
n
esia
.
E
m
ail:
m
u
h
.
d
i
m
y
at
i@
y
a
h
o
o
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
d
o
n
esia
w
it
h
a
p
o
p
u
latio
n
o
f
2
5
8
.
7
m
ill
io
n
p
eo
p
le
[
1
]
f
ac
es
m
aj
o
r
ch
allen
g
e
i
n
p
r
o
v
id
in
g
t
h
e
f
o
o
d
o
f
its
p
o
p
u
latio
n
.
P
o
licies
o
n
f
o
o
d
r
esil
ien
ce
a
n
d
f
o
o
d
in
d
ep
en
d
en
ce
ar
e
th
e
m
ai
n
is
s
u
e
s
an
d
ar
e
th
e
m
ai
n
f
o
cu
s
o
f
ag
r
ic
u
lt
u
r
al
d
ev
elo
p
m
en
t.
I
n
cr
ea
s
in
g
t
h
e
n
ee
d
a
n
d
th
e
i
n
d
ep
en
d
en
ce
o
f
f
o
o
d
an
d
e
m
p
lo
y
m
e
n
t
in
o
r
d
er
to
ea
r
n
a
d
ec
en
t
in
co
m
e
f
o
r
ac
ce
s
s
to
f
o
o
d
ar
e
th
e
t
w
o
m
ai
n
co
m
p
o
n
e
n
t
s
i
n
t
h
e
r
ea
lizatio
n
o
f
f
o
o
d
s
ec
u
r
it
y
[
2
]
.
R
ice
is
o
n
e
o
f
t
h
e
m
ai
n
s
u
p
p
o
r
ts
i
n
I
n
d
o
n
esia
's
f
o
o
d
s
ec
u
r
it
y
.
Mo
n
ito
r
in
g
t
h
e
e
x
te
n
t
o
f
p
ad
d
y
f
ield
,
in
o
r
d
er
to
i
m
p
r
o
v
e
t
h
e
ac
cu
r
ac
y
o
f
f
o
o
d
p
lan
n
in
g
an
d
s
el
f
-
s
u
f
f
icie
n
c
y
r
eq
u
ir
es
th
e
a
v
ailab
ilit
y
o
f
r
eg
u
lar
an
d
ac
c
u
r
ate
d
ata.
R
eg
u
lar
d
ata
av
ailab
il
it
y
to
m
o
n
ito
r
p
ad
d
y
f
ield
s
u
s
in
g
s
atellite
i
m
ag
er
y
,
s
u
ch
a
s
L
a
n
d
s
at,
SP
OT
,
an
d
lar
g
e
-
s
ca
le
s
atell
ite
i
m
ag
e
h
as
b
ee
n
w
id
el
y
u
s
ed
b
ec
au
s
e
o
f
t
h
e
p
o
s
iti
v
e
r
o
le
in
m
o
n
ito
r
in
g
.
Sate
ll
it
e
i
m
a
g
es
r
ec
o
r
d
ed
w
ith
v
er
y
h
ig
h
te
m
p
o
r
al
r
eso
lu
tio
n
,
alt
h
o
u
g
h
lo
w
s
p
atia
l
r
eso
lu
tio
n
s
u
c
h
as
Mo
d
er
ate
R
eso
l
u
tio
n
I
m
a
g
i
n
g
Sp
ec
tr
o
r
ad
io
m
eter
(
MO
DI
S)
o
n
N
A
S
A'
s
T
er
r
a
Satellite
s
h
o
o
tin
g
ca
n
h
elp
an
al
y
s
e
p
ad
d
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
P
a
d
d
y
field
cla
s
s
ifica
tio
n
w
ith
MODI
S
-
Ter
r
a
m
u
lti
-
temp
o
r
a
l
ima
g
e
tr
a
n
s
fo
r
ma
tio
n
…
(
Mu
h
a
mma
d
Dimya
ti
)
1347
f
ield
m
o
n
ito
r
in
g
f
as
ter
th
an
L
an
d
s
at,
SP
OT
,
an
d
o
th
er
lar
g
e
-
s
ca
le
s
ate
llit
es
[
3
]
,
[
4
]
.
T
er
r
a/A
q
u
a
MO
DI
S
d
ata
ar
e
s
atellite
i
m
ag
e
s
th
at
h
a
v
e
b
ec
o
m
e
p
u
b
lic
d
o
m
ai
n
,
h
a
v
e
th
e
s
p
atial
r
eso
l
u
tio
n
o
f
2
5
0
m
etr
es,
5
0
0
m
e
tr
es,
an
d
1
k
m
w
it
h
f
o
u
r
r
ec
o
r
d
in
g
ti
m
es
p
er
d
a
y
at
t
h
e
s
a
m
e
lo
ca
tio
n
o
n
ea
r
th
[
3
]
.
Ho
w
e
v
er
,
th
e
g
eo
g
r
ap
h
ic
co
n
d
itio
n
o
f
I
n
d
o
n
e
s
ia
in
t
h
e
t
r
o
p
ics
r
ed
u
ce
s
th
e
av
ailab
ilit
y
o
f
MO
DI
S
i
m
a
g
e
q
u
al
it
y
b
ec
a
u
s
e
t
h
e
ter
r
ito
r
y
o
f
I
n
d
o
n
esia is co
v
er
ed
b
y
MO
D
I
S i
m
a
g
e
w
h
ic
h
is
o
f
te
n
co
v
er
ed
b
y
clo
u
d
s
a
n
d
h
az
e.
Ma
n
y
r
esear
c
h
er
s
h
a
v
e
d
ev
el
o
p
ed
clo
u
d
ex
tr
ac
tio
n
tech
n
i
q
u
es
f
r
o
m
v
ar
io
u
s
s
atelli
te
i
m
ag
er
y
[
5
]
,
d
ev
elo
p
in
g
Mo
s
aic
P
ix
e
l
B
ased
f
o
r
L
an
d
s
at
d
ata
[
6
]
,
an
d
Mo
s
aic
T
ile
B
ased
o
f
L
an
d
s
at
-
8
to
o
b
tain
m
i
n
i
m
al
clo
u
d
co
v
er
[
7
]
.
T
h
e
U
n
iv
er
s
it
y
o
f
Ma
r
y
la
n
d
h
as
p
er
f
o
r
m
ed
ti
m
e
-
s
er
ie
s
tr
a
n
s
f
o
r
m
ati
o
n
o
f
MO
DI
S
an
d
L
a
n
d
s
a
t
d
ata
in
C
o
n
g
o
B
as
in
[
8
]
,
L
an
d
s
a
t
d
ata
f
r
o
m
1
9
8
5
to
2
0
1
2
in
E
aster
n
E
u
r
o
p
e’
s
[
9
]
.
I
m
a
g
e
tr
an
s
f
o
r
m
atio
n
is
d
o
n
e
b
y
h
i
s
to
g
r
a
m
-
b
ased
m
etr
ics
ap
p
r
o
ac
h
,
s
u
c
h
as
a
v
er
ag
e,
an
d
b
y
s
eq
u
e
n
tial
m
etr
ic
ap
p
r
o
ac
h
[
8]
-
[
1
0
]
.
T
h
e
co
llab
o
r
atio
n
s
a
m
o
n
g
L
A
P
A
N,
Mi
n
is
tr
y
o
f
E
n
v
ir
o
n
m
en
t
an
d
Fo
r
estr
y
(
ME
F),
a
n
d
W
o
r
ld
R
eso
u
r
ce
s
I
n
s
tit
u
te
(
W
R
I
)
h
av
e
tr
ied
to
tr
an
s
f
o
r
m
ti
m
e
-
s
er
ies
i
m
ag
e
s
w
it
h
MO
DI
S
-
T
er
r
a
an
d
L
an
d
s
a
t
-
8
OL
I
d
ata.
T
h
e
d
ata
u
s
ed
ar
e
MO
DI
S
f
r
o
m
2
0
0
0
to
2
0
1
7
,
an
d
L
a
n
d
s
at
f
r
o
m
2
0
1
5
to
2
0
1
7
.
T
h
e
ex
p
er
i
m
en
t
w
a
s
co
n
d
u
cted
w
i
t
h
h
is
to
g
r
a
m
-
b
ased
m
etr
ic
s
ap
p
r
o
ac
h
,
s
u
c
h
as
a
v
er
ag
e,
an
d
ti
m
e
-
s
eq
u
en
tia
l
m
etr
ic
s
ap
p
r
o
ac
h
,
s
u
ch
as
r
eg
r
es
s
io
n
.
Data
ti
m
e
-
s
er
ies
le
v
el
u
s
ed
is
s
in
g
le
i
m
a
g
e
tr
an
s
f
o
r
m
a
t
io
n
,
an
n
u
al
i
m
a
g
e
tr
an
s
f
o
r
m
atio
n
(
m
etr
ic
lev
el
-
1
)
,
an
d
in
ter
-
an
n
u
al
i
m
ag
e
tr
an
s
f
o
r
m
a
tio
n
(
m
etr
ic
le
v
el
-
2
)
.
T
h
e
r
es
u
lts
s
h
o
w
th
at
i
m
a
g
e
tr
an
s
f
o
r
m
atio
n
ca
n
b
e
u
s
ed
to
id
en
ti
f
y
ch
a
n
g
es i
n
f
o
r
est co
v
er
a
g
e,
w
it
h
o
u
t
h
a
v
i
n
g
to
an
al
y
s
e
i
n
d
i
v
id
u
a
l
ch
an
g
e
o
v
er
la
y
s
[
1
1
]
.
T
h
e
d
ev
elo
p
m
e
n
t
o
f
m
u
lti
-
te
m
p
o
r
al
i
m
ag
e
i
s
s
till
co
n
v
e
n
ti
o
n
all
y
d
o
n
e,
is
b
y
an
al
y
zi
n
g
an
n
u
al
d
ata
in
d
iv
id
u
all
y
b
ased
o
n
r
ef
lecta
n
ce
,
an
d
th
e
n
co
m
p
ar
ed
w
ith
th
e
an
n
u
al
d
ata
in
d
if
f
er
en
t
ti
m
e
to
o
b
tain
th
e
p
h
en
o
m
e
n
o
n
o
f
lan
d
u
s
e
ch
a
n
g
e.
T
r
en
d
o
r
lan
d
u
s
e
ch
a
n
g
e
an
al
y
s
is
u
s
in
g
t
h
ese
co
n
v
en
ti
o
n
al
m
et
h
o
d
s
tak
e
s
lo
n
g
er
an
d
r
eq
u
ir
es
s
p
ec
if
ic
ap
p
licatio
n
s
k
ills
.
T
h
e
u
s
e
o
f
th
e
i
m
a
g
e
tr
an
s
f
o
r
m
atio
n
ap
p
r
o
ac
h
to
an
al
y
s
i
n
g
p
ad
d
y
f
ield
m
ap
p
in
g
h
as
b
eg
u
n
to
b
e
u
s
ed
e
v
o
lu
ti
v
el
y
.
I
n
th
e
f
ir
s
t
g
en
er
atio
n
,
p
ad
d
y
f
ield
m
a
p
p
in
g
w
a
s
d
o
n
e
w
it
h
t
h
e
u
s
e
o
f
ca
teg
o
r
y
o
n
e
alg
o
r
ith
m
,
s
u
c
h
as
d
ata
r
e
f
lect
an
ce
an
d
i
m
a
g
e
s
ta
tis
tic
-
b
ase
d
ap
p
r
o
ac
h
es.
T
h
e
n
ex
t
d
ev
el
o
p
m
e
n
t
e
m
er
g
ed
a
s
th
e
s
ec
o
n
d
g
e
n
er
atio
n
u
s
i
n
g
v
eg
eta
tio
n
i
n
d
ex
a
n
d
en
h
a
n
c
ed
i
m
ag
e
s
tati
s
tic
-
b
ased
ap
p
r
o
ac
h
es.
I
n
t
h
e
t
h
ir
d
g
en
er
atio
n
d
ev
elo
p
m
e
n
t,
t
h
e
v
eg
eta
tio
n
i
n
d
ex
o
r
R
A
D
AR
b
ac
k
-
s
ca
tter
-
b
ased
te
m
p
o
r
al
an
al
y
s
i
s
is
u
s
ed
[
1
2
]
.
R
ec
en
t
d
ev
elo
p
m
e
n
t
s
b
eg
a
n
u
s
i
n
g
t
h
e
p
h
e
n
o
lo
g
ica
l
o
f
p
ad
d
y
th
r
o
u
g
h
r
e
m
o
te
s
e
n
s
i
n
g
r
ec
o
g
n
itio
n
o
f
k
e
y
g
r
o
w
t
h
ap
p
r
o
ac
h
p
h
ases
[
1
3
]
-
[
1
6
]
.
A
p
h
e
n
o
lo
g
ical
m
o
d
el
i
s
an
a
p
p
r
o
ac
h
b
ased
o
n
p
er
io
d
ic
p
lan
t
li
f
e
c
y
cle
ev
e
n
t
s
,
an
d
h
o
w
th
e
s
e
ar
e
in
f
lu
e
n
ce
d
b
y
s
ea
s
o
n
al
an
d
i
n
ter
-
a
n
n
u
al
v
ar
iatio
n
s
i
n
cl
i
m
ate,
as
w
e
ll
a
s
h
ab
itat
f
ac
to
r
s
,
s
u
c
h
as
e
lev
at
io
n
.
Var
iab
les
u
s
ed
f
o
r
p
ad
d
y
f
iel
d
class
if
icat
io
n
w
er
e
d
ev
elo
p
ed
f
r
o
m
d
ata
r
ef
lecta
n
ce
,
No
r
m
alize
d
Dif
f
er
e
n
ce
Veg
etatio
n
I
n
d
ex
(
N
DVI
)
an
d
E
n
h
a
n
ce
d
Veg
etat
io
n
I
n
d
e
x
(
E
VI
)
[
1
7
]
,
[
1
6
]
,
[
1
4
]
.
No
r
m
ali
s
ed
Dif
f
e
r
en
ce
W
ater
I
n
d
ex
(
NDW
I
)
[
1
8
]
-
[
2
0
]
,
an
d
L
a
n
d
S
u
r
f
ac
e
W
ater
I
n
d
ex
(
L
SW
I
)
[
1
7
]
,
[
1
9
]
.
T
h
e
u
s
e
o
f
v
e
g
etatio
n
in
d
ices
(
e.
g
.
N
DVI
,
E
VI
,
L
S
W
I
,
NDW
I
)
m
ak
e
th
e
ac
c
u
r
a
c
y
o
f
la
n
d
co
v
er
/
u
s
e
i
n
cr
ea
s
e
d
co
m
p
ar
ed
w
it
h
th
e
or
ig
in
al
r
e
f
lecta
n
ce
[
2
1
]
,
[
2
2
]
.
P
h
ases
o
f
d
ata
u
s
ed
w
er
e
d
ev
e
lo
p
ed
f
r
o
m
s
i
n
g
le
i
m
a
g
e
i
n
ea
r
l
y
g
r
o
w
i
n
g
s
ea
s
o
n
b
e
f
o
r
e
tr
an
s
p
la
n
ti
n
g
(
Fan
g
i
n
1
9
9
8
)
,
m
u
lti
-
i
m
a
g
es
f
r
o
m
s
ee
d
li
n
g
an
d
r
ip
e
n
in
g
s
tag
es
[
2
3
]
,
m
u
lt
i
i
m
a
g
es
i
n
g
r
o
w
i
n
g
s
ea
s
o
n
[
2
4
]
,
m
u
lti
i
m
ag
e
s
in
tr
an
s
p
lan
tin
g
an
d
till
er
in
g
s
tag
e
s
[
2
5
]
,
all
av
ailab
le
i
m
a
g
e
s
[
2
6
]
,
an
d
m
u
lti
i
m
ag
e
s
in
ea
r
l
y
r
ice
g
r
o
w
i
n
g
s
ea
s
o
n
[
2
7
]
.
Xian
g
m
in
g
Xiao
(
2
0
0
5
)
h
ad
s
t
u
d
ied
th
e
p
ad
d
y
f
ield
s
in
So
u
t
h
a
n
d
So
u
th
ea
s
t
Asi
a
u
s
in
g
m
u
lti
-
te
m
p
o
r
al
MO
DI
S
i
m
a
g
es.
H
e
h
ad
m
ap
p
ed
f
o
r
1
3
So
u
th
an
d
So
u
t
h
E
a
s
t
A
s
ia
n
co
u
n
tr
ies
w
ith
a
MO
DI
S
500
-
m
eter
s
p
atial
r
eso
lu
tio
n
o
v
er
8
-
d
a
y
d
ata
in
2
0
0
2
.
P
h
en
o
lo
g
ical
m
o
d
els
w
er
e
u
s
ed
in
t
h
e
s
tu
d
y
.
P
ad
d
y
r
ice
f
ield
s
w
er
e
c
h
ar
ac
ter
is
ed
b
y
a
n
in
itial
p
er
io
d
o
f
f
lo
o
d
in
g
a
n
d
tr
an
s
p
lan
ti
n
g
,
d
u
r
in
g
w
h
ic
h
a
m
i
x
tu
r
e
o
f
s
u
r
f
ac
e
w
ater
an
d
r
ice
s
ee
d
lin
g
s
e
x
i
s
ts
.
He
ap
p
lied
a
p
a
d
d
y
f
iel
d
m
ap
p
in
g
alg
o
r
it
h
m
th
at
u
s
es
a
ti
m
e
-
s
er
ies
o
f
MO
DI
S
-
d
er
i
v
ed
v
eg
eta
tio
n
i
n
d
ices
to
id
en
tify
t
h
e
i
n
itial
p
er
io
d
o
f
f
lo
o
d
in
g
an
d
tr
an
s
p
la
n
ti
n
g
i
n
p
ad
d
y
f
ield
s
,
b
ased
o
n
th
e
i
n
cr
ea
s
ed
s
u
r
f
ac
e
m
o
is
t
u
r
e.
T
h
e
r
esu
lta
n
t
M
ODI
S
-
d
er
iv
ed
p
ad
d
y
f
ield
m
a
p
w
as
co
m
p
ar
ed
to
n
atio
n
al
a
g
r
icu
l
tu
r
al
s
ta
tis
tica
l
d
ata
at
n
atio
n
al
an
d
s
u
b
n
atio
n
al
lev
el
s
.
T
h
e
r
esu
lts
s
h
o
w
a
s
i
m
ilar
it
y
w
i
th
t
h
e
lo
ca
tio
n
o
f
th
e
p
ad
d
y
f
ield
as
a
w
h
o
le,
b
u
t
th
er
e
ar
e
v
ar
iatio
n
s
in
s
o
m
e
o
f
th
e
lo
ca
tio
n
s
o
n
th
e
to
p
ic.
A
lt
h
o
u
g
h
th
e
r
es
u
lt
s
s
t
ill
n
ee
d
to
b
e
d
o
n
e
f
u
r
th
er
r
esear
c
h
,
t
h
e
m
et
h
o
d
an
d
u
s
e
o
f
MO
DI
S
d
ata
p
r
o
v
id
e
p
o
ten
tial [
1
6
]
,
[
1
5
]
,
[
1
4
]
.
Fro
m
th
e
v
ar
io
u
s
d
ev
elo
p
m
en
ts
o
f
t
h
e
ab
o
v
e
r
esear
c
h
,
p
ad
d
y
f
ield
m
ap
p
in
g
o
r
class
if
ica
tio
n
u
s
i
ng
p
h
en
o
lo
g
ical
ap
p
r
o
ac
h
r
esu
lt
i
n
g
f
r
o
m
i
m
ag
e
tr
a
n
s
f
o
r
m
atio
n
w
it
h
th
e
co
m
b
i
n
atio
n
o
f
r
ef
le
ctan
ce
an
d
MO
DI
S
-
T
er
r
a
an
n
u
al
m
u
lti
-
te
m
p
o
r
al
i
m
a
g
e
in
d
e
x
h
as
n
o
t
b
ee
n
d
o
n
e
y
et.
T
h
e
s
u
cc
e
s
s
o
f
f
i
n
d
in
g
f
a
s
t,
p
r
ec
is
e
an
d
ac
cu
r
ate
p
r
o
ce
d
u
r
es
to
as
s
is
t
i
n
m
o
n
ito
r
i
n
g
a
la
n
d
ar
ea
an
d
r
ice
p
r
o
d
u
ctio
n
w
ill
g
r
ea
tl
y
a
s
s
is
t
in
th
e
p
lan
n
i
n
g
an
d
i
m
p
le
m
en
tatio
n
o
f
f
o
o
d
r
esil
ie
n
ce
an
d
in
d
ep
en
d
e
n
ce
p
r
o
g
r
a
m
s
[
2
8
]
,
[
2
]
.
T
h
e
J
av
a
I
s
lan
d
w
as
s
elec
ted
as
th
e
s
t
u
d
y
ar
ea
.
T
h
is
i
s
t
h
e
m
o
s
t
p
o
p
u
lo
u
s
i
s
lan
d
w
i
th
1
4
6
,
6
7
5
,
4
0
0
in
h
ab
ita
n
t
s
,
o
r
5
6
.
7
%
o
f
t
h
e
I
n
d
o
n
esia
to
tal
p
o
p
u
latio
n
o
f
2
5
8
,
7
0
4
,
9
0
0
in
2
0
1
6
.
T
h
is
i
s
lan
d
is
a
b
u
f
f
er
ar
ea
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il 2
0
1
9
:
1
3
4
6
-
1358
1348
r
ice
p
r
o
d
u
ctio
n
w
it
h
a
p
r
o
d
u
ctio
n
ca
p
ac
it
y
o
f
3
8
,
9
7
0
,
0
2
6
to
n
s
(
5
1
.
7
%)
o
f
al
l
r
ice
p
r
o
d
u
ctio
n
in
I
n
d
o
n
e
s
ia
(
7
5
,
3
9
7
,
8
4
1
t
o
n
s
)
b
y
2
0
1
5
.
T
h
e
ar
ea
o
f
p
ad
d
y
f
ield
s
i
n
J
av
a
is
lan
d
is
d
ec
r
ea
s
i
n
g
f
r
o
m
3
.
4
4
4
.
2
8
3
h
a
(
2
0
1
2
)
to
3
.
2
3
1
.
6
8
0
h
a
(
2
0
1
3
)
,
th
en
3
.
2
4
8
.
3
9
4
h
a
(
2
0
1
4
)
,
th
en
3
.
2
2
3
.
5
0
2
h
a
(
2
0
1
5
)
,
an
d
3
,
2
2
2
,
3
4
7
(
2
0
1
6
)
[
2
9
]
.
T
h
is
is
lan
d
is
th
e
m
o
s
t
d
y
n
a
m
ic
is
lan
d
a
m
o
n
g
lar
g
e
is
lan
d
s
in
I
n
d
o
n
esia,
d
u
e
to
p
o
p
u
latio
n
d
en
s
it
y
a
n
d
r
ap
id
d
ev
elo
p
m
en
t o
f
th
e
r
e
g
io
n
[
1
]
.
Fo
r
th
at,
th
e
ex
is
te
n
ce
o
f
a
g
o
o
d
m
o
n
i
to
r
in
g
to
o
l b
ec
o
m
es
m
o
r
e
n
ec
ess
ar
y
.
T
h
is
m
ai
n
o
b
j
ec
tiv
e
o
f
t
h
is
s
tu
d
y
i
s
to
tes
t
t
h
e
p
ad
d
y
f
iel
d
class
i
f
icatio
n
b
y
u
s
i
n
g
MO
DI
S
-
T
er
r
a
m
u
lti
-
te
m
p
o
r
al
i
m
a
g
e
w
it
h
a
co
m
b
i
n
atio
n
o
f
r
e
f
lec
tan
ce
(
R
ed
,
NI
R
,
SW
I
R
-
1
)
an
d
in
d
ex
(
NDVI
,
NOA
I
)
,
b
ased
o
n
p
h
en
o
lo
g
ical
ap
p
r
o
ac
h
.
T
h
is
r
esear
ch
is
d
if
f
er
en
t
f
r
o
m
w
h
at
h
as
b
ee
n
d
o
n
e
b
y
X
ian
g
m
i
n
g
Xiao
(
2
0
0
5
)
,
h
e
o
n
l
y
u
s
es
p
ar
a
m
e
ter
in
d
ex
(
NDVI
,
E
VI
,
a
n
d
NDW
I
)
.
T
h
e
s
i
m
ilar
it
y
w
ith
Xiao
Xia
n
g
m
i
n
g
'
s
r
esea
r
ch
is
th
e
u
s
e
o
f
ca
te
g
o
r
y
f
o
u
r
t
h
at
i
s
p
h
e
n
o
lo
g
ical
-
b
ase
d
m
o
d
els
th
r
o
u
g
h
r
e
m
o
te
s
e
n
s
in
g
r
ec
o
g
n
itio
n
o
f
k
e
y
g
r
o
w
th
p
h
a
s
es
w
it
h
t
h
e
an
n
u
al
p
er
io
d
.
T
h
e
p
h
en
o
lo
g
y
o
f
r
ice
p
lan
t
in
J
av
a
I
s
la
n
d
,
ch
ar
ac
ter
ized
b
y
a)
at
th
e
b
eg
i
n
n
in
g
o
f
p
lan
tin
g
al
wa
y
s
f
lo
o
d
ed
w
i
th
w
ater
,
b
)
ex
i
s
ten
ce
o
f
u
p
an
d
d
o
w
n
tr
en
d
i
n
v
e
g
etatio
n
in
d
ex
an
d
o
p
en
in
d
ex
ar
ea
,
an
d
c)
ch
an
g
e
o
f
d
y
n
a
m
ic
lan
d
co
v
e
r
ev
er
y
y
ea
r
,
w
ater
p
h
ase,
v
eg
etatio
n
a
n
d
f
allo
w
lan
d
is
s
h
o
w
n
b
y
th
e
v
ar
ian
ce
o
f
r
ef
lecta
n
ce
an
d
i
n
d
ex
v
al
u
e
s
.
2.
DATA AN
D
M
E
T
H
O
DS
2
.
1
.
Da
t
a
P
r
im
ar
y
d
ata
u
s
ed
i
n
t
h
is
r
ese
ar
ch
ar
e
th
e
8
-
d
a
y
's
r
e
f
lecta
n
ce
o
f
MO
DI
S
-
T
er
r
a
o
f
2
0
1
6
,
w
it
h
p
i
x
e
l
r
eso
lu
tio
n
5
0
0
m
eter
o
f
d
ata
f
r
o
m
N
AS
A's
L
a
n
d
P
r
o
ce
s
s
es
Dis
tr
ib
u
ted
A
cti
v
e
A
r
c
h
iv
e
C
en
tr
e
(
L
P
D
AAC).
T
h
is
d
ata
co
n
s
is
ts
o
f
4
6
s
er
ies
d
ata
o
f
p
ath
s
H2
8
v
0
9
an
d
H2
9
v
0
9
o
f
J
av
a
I
s
lan
d
,
co
v
er
s
b
an
d
R
ed
,
NI
R
,
an
d
SW
I
R
-
1
.
W
h
ile
t
h
e
t
w
o
t
y
p
es
o
f
s
ec
o
n
d
ar
y
d
ata
f
r
o
m
t
h
e
Min
i
s
tr
y
o
f
Ag
r
ic
u
lt
u
r
e
(
Mo
A
)
w
er
e
u
s
ed
,
in
th
e
f
o
r
m
o
f
P
ad
d
y
Field
Ma
p
i
n
2
0
1
2
as
s
h
o
w
n
in
Fi
g
u
r
e
1
a
n
d
p
ad
d
y
f
ie
ld
ar
ea
b
ase
o
n
d
is
tr
ict
a
n
d
p
r
o
v
in
c
e
s
tatis
t
ical
d
ata
r
ep
o
r
t
in
2
0
1
5
.
T
h
e
p
ad
d
y
f
ield
m
ap
o
b
tain
e
d
f
r
o
m
t
h
e
d
elin
ea
tio
n
o
f
h
i
g
h
-
r
eso
lu
tio
n
s
atel
lite
i
m
a
g
er
y
,
b
u
t t
h
e
an
n
u
al
s
tat
is
t
ical
r
ep
o
r
t f
r
o
m
f
ield
esti
m
atio
n
.
Fig
u
r
e
1
.
Ma
p
o
f
P
ad
d
y
Field
o
n
J
av
a
I
s
lan
d
in
2
0
1
2
So
u
r
ce
: P
u
s
d
ati
n
f
i
eld
d
ata
o
f
th
e
Mi
n
is
tr
y
o
f
Ag
r
icu
l
tu
r
e
2
.
2
.
M
et
ho
ds
2
.
2
.
1
.
I
m
a
g
e
cla
s
s
if
ica
t
io
n
T
h
e
m
eth
o
d
u
s
ed
i
n
p
ad
d
y
f
ield
m
ap
p
in
g
f
o
r
th
is
s
t
u
d
y
i
s
an
an
al
y
s
is
o
f
a
n
n
u
al
m
u
lti
-
te
m
p
o
r
a
l
i
m
a
g
er
y
w
it
h
a
p
h
en
o
lo
g
ical
ap
p
r
o
ac
h
.
T
h
e
an
al
y
s
i
s
p
r
o
ce
s
s
in
c
lu
d
es
t
w
o
s
ta
g
es:
a)
th
e
s
t
ep
s
to
ex
tr
ac
t
th
e
8
-
d
a
y
’
s
MO
DI
S
d
ata
in
to
m
u
l
ti
-
te
m
p
o
r
al
f
ea
t
u
r
e
in
f
o
r
m
atio
n
i
m
a
g
e,
p
er
f
o
r
m
ed
u
s
in
g
i
m
a
g
e
tr
an
s
f
o
r
m
a
tio
n
,
an
d
b
)
th
e
s
tep
to
class
if
y
t
h
e
tr
an
s
f
o
r
m
ed
m
u
l
ti
-
te
m
p
o
r
al
f
ea
tu
r
e
i
m
a
g
e
w
ith
t
h
e
M
ax
i
m
u
m
L
i
k
eli
h
o
o
d
C
las
s
i
f
icatio
n
(
M
L
C
)
ap
p
r
o
ac
h
[
3
0
]
.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
o
f
MO
DI
S
i
m
a
g
e
i
s
e
x
ec
u
te
d
b
ef
o
r
e
a
m
u
lti
-
te
m
p
o
r
al
tr
an
s
f
o
r
m
a
tio
n
,
w
h
ic
h
i
n
clu
d
e
s
clo
u
d
m
as
k
i
n
g
,
ti
m
e
-
s
er
ies
f
ilter
in
g
,
a
n
d
in
ter
p
o
latio
n
o
f
b
la
n
k
d
ata
d
u
e
to
th
e
clo
u
d
.
P
r
e
-
p
r
o
c
ess
i
n
g
i
s
d
o
n
e
to
m
i
n
i
m
iz
e
th
e
i
m
ag
e
o
f
th
e
clo
u
d
co
v
er
[
3
1
]
,
[
3
2
]
.
Diag
r
a
m
m
a
ticall
y
,
t
h
e
i
llu
s
tr
a
tio
n
o
f
t
h
e
p
ad
d
y
f
ie
ld
clas
s
i
f
icatio
n
m
o
d
el
w
i
th
a
p
h
en
o
lo
g
ical
m
o
d
el
u
s
in
g
MO
DI
S
-
T
er
r
a
m
u
lt
i
-
te
m
p
o
r
al
i
m
a
g
e
tr
an
s
f
o
r
m
a
tio
n
i
s
illu
s
tr
ated
in
Fig
u
r
e
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
P
a
d
d
y
field
cla
s
s
ifica
tio
n
w
ith
MODI
S
-
Ter
r
a
m
u
lti
-
temp
o
r
a
l
ima
g
e
tr
a
n
s
fo
r
ma
tio
n
…
(
Mu
h
a
mma
d
Dimya
ti
)
1349
Fig
u
r
e
2
.
I
llu
s
tr
ati
v
e
d
iag
r
a
m
o
f
p
ad
d
y
f
ield
cla
s
s
i
f
ica
tio
n
m
o
d
el
w
ith
p
h
en
o
lo
g
ical
ap
p
r
o
a
ch
u
s
in
g
t
h
e
MO
DI
S
-
T
er
r
a
m
u
lt
ite
m
p
o
r
al
i
m
ag
e
tr
a
n
s
f
o
r
m
at
io
n
2
.
2
.
2
.
I
m
a
g
e
t
ra
ns
f
o
r
m
a
t
io
n
T
h
er
e
ar
e
th
r
ee
ty
p
es
o
f
r
ef
lecta
n
ce
i
m
ag
e
s
w
it
h
t
h
e
MO
DI
S
-
T
er
r
a
m
u
lt
i
-
te
m
p
o
r
al
i
m
a
g
e
tr
an
s
f
o
r
m
atio
n
p
r
o
ce
s
s
ed
in
th
is
s
t
u
d
y
,
th
o
s
e
ar
e
th
r
ee
r
e
f
lec
tan
ce
i
m
a
g
es
o
f
SW
I
R
-
1
,
NI
R
,
an
d
R
ed
;
a
n
d
t
w
o
in
d
ex
i
m
a
g
es,
n
a
m
el
y
No
r
m
a
lized
Dif
f
er
en
ce
Ve
g
etatio
n
I
n
d
ex
(
ND
VI
)
,
an
d
No
r
m
alize
d
Op
en
A
r
ea
I
n
d
e
x
(
NOA
I
)
,
w
it
h
t
h
e
f
o
llo
w
i
n
g
f
o
r
m
u
las.
T
h
e
s
elec
tio
n
o
f
i
n
d
ex
f
o
r
m
u
la
th
at
i
s
t
h
e
m
in
i
m
u
m
o
f
r
e
f
lecta
n
ce
o
f
NI
R
a
n
d
th
e
m
in
i
m
u
m
r
e
f
le
ctan
ce
SW
I
R
-
1
d
o
n
e
to
h
ig
h
lig
h
t
p
ad
d
y
f
ield
w
h
e
n
f
lo
o
d
ed
at
th
e
ti
m
e
o
f
p
lan
tin
g
.
T
h
e
u
p
s
an
d
d
o
w
n
s
o
f
NDVI
in
d
icate
t
h
e
p
h
e
n
o
lo
g
y
t
h
at
d
u
r
in
g
t
h
e
r
ice
g
r
o
w
i
n
g
p
er
io
d
,
th
e
NDVI
v
alu
e
w
il
l
i
n
cr
ea
s
e
d
u
r
in
g
f
lo
o
d
in
g
to
th
e
v
eg
etat
iv
e
s
ta
g
e,
w
h
i
le
at
th
e
m
at
u
r
atio
n
s
ta
g
e
o
f
t
h
e
p
ad
d
y
,
th
e
v
alu
e
o
f
NDVI
w
ill d
ec
r
ea
s
e.
R
ed
=
Red
(
1
)
NI
R
=
N
I
R
(
2
)
SW
I
R
_
1
=
S
W
IR_1
(
3
)
NDVI
=
(
N
I
R
-
Red
)
/(
N
IR
+
Red
)
(
4
)
NO
A
I
=
(
S
W
I
R_1
-
N
IR
)
/(
S
W
IR_1
+
N
I
R
)
(
5
)
w
h
er
e
S
W
IR_1,
N
I
R
an
d
red
ar
e
r
ef
lecta
n
ce
i
n
s
h
o
r
t
w
av
e
i
n
f
r
ar
ed
1
,
n
ea
r
in
f
r
ar
ed
an
d
r
ed
,
r
esp
ec
tiv
el
y
.
T
h
e
th
r
ee
r
ef
lecta
n
ce
i
m
a
g
e
s
an
d
t
w
o
in
d
e
x
i
m
a
g
es
ar
e
th
en
tr
an
s
f
o
r
m
ed
b
y
ten
alg
o
r
ith
m
s
.
T
h
e
r
esu
lt
o
f
a
m
u
l
ti
-
te
m
p
o
r
al
i
m
a
g
e
tr
a
n
s
f
o
r
m
atio
n
i
n
t
h
e
f
o
r
m
o
f
t
h
e
n
e
w
i
m
ag
e
is
ca
lled
m
etr
ic
i
m
a
g
e.
An
ex
tr
ac
tio
n
al
g
o
r
ith
m
f
o
r
o
b
tain
in
g
m
etr
ic
i
m
ag
e
ca
n
b
e
ca
lcu
lated
b
ased
o
n
th
e
s
tati
s
t
ic
v
al
u
e,
r
eg
ar
d
less
o
f
r
ec
o
r
d
in
g
ti
m
e
o
r
w
i
th
r
esp
ec
t to
r
ec
o
r
d
in
g
ti
m
e
s
eq
u
e
n
ce
.
I
m
a
g
e
m
etr
ic
i
s
a
n
i
m
a
g
e
(
f
e
atu
r
e)
t
h
at
co
n
tain
s
in
f
o
r
m
atio
n
in
ac
co
r
d
an
ce
w
i
th
t
h
e
n
ee
d
s
o
f
th
e
ap
p
licatio
n
.
T
h
er
e
ar
e
ten
t
y
p
es
o
f
al
g
o
r
ith
m
f
o
r
m
u
la
to
o
b
tain
i
m
a
g
e
f
ea
t
u
r
e
m
etr
ic,
th
at
is
:
1)
Av
er
ag
e
all
clea
r
p
ix
e
ls
̅
∑
(
6
)
2)
Dev
iatio
n
s
ta
n
d
ar
d
all
clea
r
p
i
x
els
∑
̅
(
7
)
MO
DI
S
-
Te
r
r
a
8
-
da
y
r
e
f
l
e
c
t
a
nc
e
da
t
a
of
H
28v09
a
nd
H
29v09
of
2016
C
l
oud
M
a
s
ki
ng
T
i
m
e
S
e
r
i
e
s
F
i
l
t
e
r
i
ng
I
nt
e
r
pol
a
t
i
on
of
C
l
oud
C
ove
r
ND
VI
,
NOAI
RED
,
N
I
R,
SW
I
R
-
1
TRA
NS
F
ORM
A
TI
ON
1)
a
ve
r
a
ge
a
l
l
c
l
e
a
r
pi
xe
l
s
,
2)
de
vi
a
t
i
on
s
t
a
nda
r
d
a
l
l
c
l
e
a
r
pi
xe
l
s
,
3)
m
i
ni
m
um
of
a
l
l
c
l
e
a
r
pi
xe
l
s
,
4)
m
a
xi
m
um
of
a
l
l
c
l
e
a
r
pi
xe
l
s
,
5)
a
ve
r
a
ge
of
70%
c
l
e
a
r
pi
xe
l
s
,
6)
de
vi
a
t
i
on
s
t
a
nda
r
d
of
70%
c
l
e
a
r
pi
xe
l
s
,
7)
m
i
ni
m
um
of
70%
c
l
e
a
r
pi
xe
l
s
,
8)
m
a
xi
m
um
of
70%
c
l
e
a
r
pi
xe
l
s
,
9)
a
m
pl
i
t
ude
up,
a
nd
10
)
a
m
pl
i
t
ude
dow
n.
S
a
m
pl
i
ng
f
or
M
L
C
M
a
p
of
P
a
ddy
F
i
e
l
d
of
J
a
va
I
s
l
a
nd
of
2012
M
a
xi
m
um
L
i
ke
l
i
hood
C
l
a
s
s
i
f
i
c
a
t
i
on
F
i
na
l
M
O
D
I
S
i
m
a
ge
of
P
a
ddy
F
i
e
l
d
ba
s
e
d
on
P
he
nol
ogy
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il 2
0
1
9
:
1
3
4
6
-
1358
1350
3
)
Min
i
m
u
m
o
f
all
clea
r
p
ix
els
(
8
)
4)
Ma
x
i
m
u
m
o
f
al
l c
lear
p
ix
els
(
9
)
5
)
An
av
er
a
g
e
o
f
7
0
% c
lear
p
ix
el
s
̅
∑
(
1
0
)
6)
A
d
ev
iatio
n
s
tan
d
ar
d
o
f
7
0
% c
lear
p
ix
els
∑
(
1
1
)
7
)
Min
i
m
u
m
o
f
7
0
% c
lear
p
ix
els
(
1
2
)
8)
Ma
x
i
m
u
m
o
f
7
0
% c
lear
p
ix
el
s
(
1
3
)
9
)
Am
p
lit
u
d
e
u
p
(
)
(
1
4
)
10)
Am
p
lit
u
d
e
d
o
w
n
(
)
(
1
5
)
w
h
er
e
x
a
v
er
a
g
e
x
i
th
e
v
a
lu
e
o
f
t
h
e
it
h
s
a
m
p
le
;
〖
sx
〗
_
i=
th
e
v
a
lu
e
o
f
th
e
it
h
s
a
m
p
le
a
f
ter
b
ein
g
s
o
r
ted
f
r
o
m
s
m
a
ll to
lar
g
e
; n
=
n
u
m
b
e
r
o
f
s
a
m
p
les
δ
=
d
ev
iatio
n
s
ta
n
d
ar
d
;
Fig
u
r
e
3
.
Featu
r
e
tr
an
s
f
o
r
m
a
ti
o
n
alg
o
r
ith
m
m
etr
ics o
f
s
tati
s
ti
cs b
ased
Ho
w
e
v
er
,
in
th
i
s
s
tu
d
y
o
n
l
y
f
ea
tu
r
e
m
etr
ic
alg
o
r
it
h
m
co
r
r
elate
d
w
it
h
p
ad
d
y
f
ield
g
r
o
w
t
h
p
h
en
o
lo
g
y
in
J
av
a
ar
e
s
elec
ted
,
th
at
is
1
)
av
er
ag
e
o
f
7
0
%
clea
r
p
ix
els,
2
)
s
tan
d
ar
d
d
ev
iatio
n
o
f
7
0
%
clea
r
p
ix
els,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
P
a
d
d
y
field
cla
s
s
ifica
tio
n
w
ith
MODI
S
-
Ter
r
a
m
u
lti
-
temp
o
r
a
l
ima
g
e
tr
a
n
s
fo
r
ma
tio
n
…
(
Mu
h
a
mma
d
Dimya
ti
)
1351
3
)
m
in
i
m
u
m
o
f
7
0
%
c
lear
p
ix
els,
4
)
m
a
x
i
m
u
m
o
f
7
0
%
clea
r
p
ix
els,
5
)
a
m
p
l
itu
d
e
u
p
,
an
d
6
)
am
p
li
tu
d
e
d
o
w
n
.
T
h
e
p
r
o
ce
s
s
o
f
i
m
a
g
e
tr
a
n
s
f
o
r
m
atio
n
a
n
d
it
s
alg
o
r
it
h
m
ic
r
ep
r
esen
tatio
n
is
s
h
o
w
n
i
n
Fi
g
u
r
e
3
an
d
Fi
g
u
r
e
4
.
T
h
e
s
a
m
p
le
s
elec
tio
n
o
f
p
ad
d
y
f
ield
clas
s
i
f
icatio
n
f
o
r
ML
C
w
a
s
d
o
n
e
o
n
3
0
m
u
lti
-
te
m
p
o
r
al
r
ef
lecta
n
ce
i
m
a
g
e
tr
an
s
f
o
r
m
atio
n
r
esu
lt
s
(
m
etr
ic
)
w
h
ic
h
r
ef
er
to
th
e
P
ad
d
y
Field
Ma
p
o
f
J
av
a
I
s
lan
d
o
f
2
0
1
2
o
b
tain
ed
f
r
o
m
th
e
Mo
A
.
T
h
ese
3
0
m
etr
ics
r
ep
r
esen
t
th
e
m
u
lt
ip
licatio
n
o
f
3
r
e
f
lecta
n
ce
i
m
a
g
es,
2
i
n
d
ex
i
m
a
g
es,
a
n
d
6
f
ea
tu
r
e
m
etr
ic
al
g
o
r
ith
m
s
.
T
h
e
r
ef
lecta
n
ce
i
m
a
g
e
o
f
b
an
d
R
ed
,
NI
R
,
a
n
d
SW
I
R
-
1
ar
e
class
i
f
ied
b
y
M
L
C
to
o
b
tain
th
e
d
is
tr
ib
u
tio
n
o
f
p
ad
d
y
(
r
ice
f
ie
ld
)
an
d
n
o
n
-
p
ad
d
y
(
n
o
n
-
r
ice
f
ield
)
f
ield
.
W
h
ile
th
e
in
d
e
x
im
ag
e
s
o
f
NDVI
an
d
NO
A
I
ar
e
also
cla
s
s
i
f
ied
with
M
L
C
to
o
b
tain
t
h
e
d
is
t
r
ib
u
tio
n
o
f
p
ad
d
y
f
ield
an
d
n
o
n
-
p
ad
d
y
f
ield
.
T
h
e
co
m
b
in
atio
n
o
f
r
ef
lecta
n
c
e
i
m
ag
e
s
o
f
b
an
d
R
ed
,
NI
R
,
SW
I
R
-
1
an
d
th
e
in
d
ex
i
m
a
g
es
o
f
NDVI
an
d
NOA
I
ar
e
also
class
i
f
ied
w
i
th
M
L
C
t
o
o
b
tain
th
e
d
is
tr
ib
u
tio
n
o
f
p
ad
d
y
f
ield
an
d
n
o
n
-
p
ad
d
y
f
ield
.
T
h
e
r
esu
lts
o
f
t
h
e
th
r
ee
clas
s
i
f
icatio
n
s
w
i
th
t
h
e
i
n
p
u
t
o
f
m
etr
ic
r
e
f
lecta
n
ce
i
m
a
g
e,
m
etr
ic
i
n
d
ex
i
m
a
g
e,
a
n
d
al
s
o
th
e
co
m
b
in
a
tio
n
o
f
r
ef
lecta
n
ce
i
m
a
g
e
an
d
in
d
e
x
i
m
a
g
e
w
er
e
ca
lcu
lated
b
y
its
ca
teg
o
r
ies
an
d
co
m
p
ar
ed
its
ac
cu
r
ac
y
w
ith
t
h
e
r
ef
er
en
ce
o
f
P
ad
d
y
Field
Ma
p
o
f
J
av
a
I
s
lan
d
i
n
2
0
1
2
f
r
o
m
t
h
e
Mo
A
.
Fig
u
r
e
4
.
T
r
an
s
f
o
r
m
atio
n
i
m
a
g
e
o
f
m
u
l
ti
-
te
m
p
o
r
al
MO
DI
S
-
T
er
r
a
3.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
NS
3
.
1
.
Ana
ly
s
is
o
f
t
he
im
a
g
e
t
ra
ns
f
o
r
m
a
t
io
n r
esu
lt
T
h
er
e
ar
e
s
ev
er
al
ex
a
m
p
les
o
f
th
e
a
n
n
u
al
m
etr
ic
r
ef
lec
tan
ce
i
m
a
g
e
a
n
d
th
e
a
n
n
u
al
m
etr
ic
in
d
e
x
i
m
a
g
e
o
f
MO
DI
S
-
T
er
r
a
m
u
lti
-
te
m
p
o
r
al
i
m
ag
e
tr
a
n
s
f
o
r
m
atio
n
r
esu
lt
s
in
2
0
1
6
.
Fro
m
th
e
R
GB
co
lo
r
co
m
p
o
s
ite
o
f
t
h
e
tr
a
n
s
f
o
r
m
ed
r
ef
lect
an
ce
i
m
a
g
e
a
n
al
y
s
i
s
i
n
Fi
g
u
r
e
5
i
t
is
k
n
o
w
n
th
at
t
h
e
b
lu
e
i
n
Fi
g
u
r
e
5
(
a)
s
h
o
w
s
t
h
e
d
o
m
i
n
a
n
ce
o
f
t
h
e
w
ater
co
n
te
n
t
f
o
r
a
y
ea
r
i
n
th
e
m
u
lti
-
te
m
p
o
r
al
im
a
g
e.
W
h
ile
t
h
e
b
lu
e
i
n
Fi
g
u
r
e
5
(
b
)
s
h
o
w
s
th
e
d
o
m
i
n
a
n
ce
o
f
p
ad
d
y
f
iel
d
s
w
h
e
n
i
n
u
n
d
ated
i
n
t
h
e
m
u
lti
-
te
m
p
o
r
al
i
m
ag
e.
W
h
ile
f
r
o
m
t
h
e
a
n
al
y
s
i
s
t
h
e
tr
an
s
f
o
r
m
ed
i
n
d
ex
i
m
ag
e
i
n
F
ig
u
r
e
5
(
c)
,
it
i
s
k
n
o
w
n
t
h
at
t
h
e
g
r
ee
n
s
h
o
w
s
t
h
e
i
n
cr
ea
s
e
o
f
NO
A
I
i
n
d
ex
,
w
h
il
e
th
e
r
ed
v
alu
e
i
n
d
icate
s
th
e
d
e
cr
ea
s
e
o
f
NO
A
I
in
d
e
x
v
al
u
e,
an
d
th
e
y
ello
w
in
d
icate
s
th
e
r
i
s
in
g
an
d
t
h
e
f
a
l
li
n
g
v
alu
e
at
d
i
f
f
er
e
n
t
lo
ca
ti
o
n
s
.
Fro
m
t
h
e
I
m
a
g
e
in
Fi
g
u
r
e
5
(
d
)
s
h
o
w
s
t
h
at
th
e
r
ed
in
d
icate
s
a
h
ig
h
v
ar
iatio
n
i
n
NDVI
i
n
d
ex
v
al
u
e,
w
h
ic
h
m
ea
n
s
th
at
la
n
d
co
v
er
c
h
an
g
e
s
in
o
n
e
-
y
ea
r
in
ter
v
als
ar
e
li
k
el
y
ca
u
s
ed
b
y
t
h
e
ch
an
g
es i
n
la
n
d
co
v
er
d
u
r
in
g
p
ad
d
y
cu
lt
iv
at
io
n
.
T
h
e
r
esu
lt
o
f
class
i
f
icatio
n
o
f
th
e
r
ef
lecta
n
ce
i
m
ag
e
u
s
i
n
g
b
an
d
s
R
ed
,
NI
R
,
an
d
SW
I
R
-
1
b
y
ML
C
to
o
b
tain
th
e
d
is
tr
ib
u
tio
n
o
f
p
ad
d
y
f
ie
ld
an
d
n
o
n
-
p
ad
d
y
f
ie
ld
is
s
h
o
w
n
in
T
h
e
I
m
a
g
e
in
Fig
u
r
e
6
(
a)
.
T
h
e
r
esu
lt
o
f
class
i
f
icatio
n
w
i
th
t
h
e
i
n
d
ex
i
m
a
g
e
i
n
p
u
t
o
f
NDVI
an
d
N
OA
I
is
p
r
e
s
en
ted
in
T
h
e
I
m
a
g
e
i
n
Fi
g
u
r
e
6
(
b
)
.
W
h
ile
th
e
clas
s
i
f
icatio
n
r
es
u
lt
w
it
h
t
h
e
co
m
b
in
atio
n
o
f
i
m
a
g
e
r
ef
lecta
n
ce
b
an
d
R
ed
,
NI
R
,
SW
I
R
-
1
an
d
NDVI
an
d
NO
A
I
in
d
ex
i
m
a
g
es i
s
p
r
e
s
en
ted
i
n
T
h
e
I
m
a
g
e
i
n
Fi
g
u
r
e
6
(
c)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il 2
0
1
9
:
1
3
4
6
-
1358
1352
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
5
.
(
a)
R
GB
,
C
o
m
p
o
s
ite
o
f
Me
tr
ics I
m
a
g
e,
No
te
:
R
ed
i
s
av
er
ag
e
o
f
SW
I
R
-
1
o
f
7
0
% o
f
clo
u
d
-
f
r
ee
d
ata;
Gr
ee
n
is
a
n
av
er
ag
e
o
f
NI
R
o
f
7
0
% o
f
clo
u
d
-
f
r
ee
d
ata;
B
lu
e
is
av
er
ag
e
o
f
R
ed
o
f
7
0
p
er
ce
n
t o
f
clo
u
d
-
f
r
ee
d
ata.
T
h
e
b
lu
e
co
lo
r
s
h
o
w
s
th
e
d
o
m
i
n
a
n
ce
o
f
w
ater
f
o
r
a
y
ea
r
,
(
b
)
R
GB
,
C
o
m
p
o
s
ite
o
f
Me
tr
ics I
m
a
g
e
,
No
te
:
R
ed
is
m
i
n
i
m
u
m
o
f
SW
I
R
-
1
o
f
7
0
% o
f
clo
u
d
-
f
r
ee
d
ata;
Gr
ee
n
is
a
m
in
i
m
u
m
o
f
NI
R
o
f
7
0
% o
f
clo
u
d
-
f
r
ee
d
ata;
B
lu
e
is
m
i
n
i
m
u
m
o
f
R
ed
o
f
7
0
% c
lo
u
d
-
f
r
ee
d
ata.
T
h
e
b
lu
e
co
lo
r
s
h
o
w
s
th
e
i
n
u
n
d
ate
d
o
f
p
ad
d
y
f
ield
,
(
c)
R
GB
,
C
o
m
p
o
s
i
te
o
f
Me
tr
ic
s
I
m
a
g
e
,
No
te:
R
ed
is
NO
A
I
o
f
a
m
a
x
i
m
u
m
o
f
a
m
p
lit
u
d
e
u
p
;
Gr
ee
n
is
NO
A
I
o
f
m
a
x
i
m
u
m
a
m
p
lit
u
d
e
d
o
w
n
.
T
h
e
g
r
ee
n
co
lo
r
in
d
icate
s
an
i
n
cr
ea
s
e
o
f
NO
A
I
,
w
h
ile
t
h
e
r
ed
v
alu
e
i
n
d
icate
s
th
e
d
ec
r
ea
s
e
o
f
NO
A
I
,
t
h
e
y
ell
o
w
co
lo
r
in
d
icate
s
b
o
th
,
(
d
)
R
GB
,
C
o
m
p
o
s
ite
o
f
Me
tr
ics I
m
ag
e
,
No
te:
R
ed
is
th
e
s
ta
n
d
ar
d
d
ev
iatio
n
o
f
ND
VI
; G
r
ee
n
is
t
h
e
av
er
ag
e
7
0
%
o
f
NDVI
.
R
ed
co
lo
r
in
d
icate
s
a
h
ig
h
v
ar
ia
tio
n
i
n
NDVI
v
al
u
es,
i
n
d
icatin
g
a
ch
a
n
g
e
i
n
la
n
d
co
v
er
w
i
th
i
n
1
-
y
ea
r
in
ter
v
al
s
th
at
m
a
y
b
e
ca
u
s
ed
b
y
c
h
an
g
e
s
in
lan
d
co
v
er
d
u
r
in
g
p
ad
d
y
c
u
lti
v
atio
n
(
a)
(
b)
(
c)
Fig
u
r
e
6
.
(
a)
T
h
e
R
esu
lt o
f
C
l
ass
i
f
icatio
n
u
s
in
g
b
an
d
s
R
ed
,
NI
R
,
an
d
SW
I
R
-
1
,
No
te
:
i
n
p
u
t
th
e
r
ef
lecta
n
ce
i
m
a
g
es o
f
b
an
d
s
R
ed
,
NI
R
,
an
d
SW
I
R
-
1
,
(
b
)
T
h
e
R
esu
lt o
f
C
las
s
i
f
icatio
n
o
f
in
d
e
x
i
m
a
g
e
i
n
p
u
t o
f
N
DVI
a
n
d
NO
A
I
,
No
te:
in
p
u
t t
h
e
i
n
d
ex
i
m
ag
e
s
o
f
ND
VI
an
d
NO
A
I
,
(
c)
T
h
e
R
es
u
lt o
f
C
las
s
i
f
icatio
n
w
it
h
t
h
e
co
m
b
i
n
atio
n
o
f
i
m
ag
e
r
e
f
lecta
n
ce
b
an
d
s
R
ed
,
NI
R
,
SW
I
R
-
1
an
d
NDVI
an
d
NO
A
I
in
d
e
x
i
m
ag
e
s
,
No
te:
in
p
u
t
th
e
co
m
b
i
n
atio
n
o
f
r
ef
lecta
n
ce
i
m
ag
e
s
o
f
R
ed
,
NI
R
,
SW
I
R
-
1
,
an
d
th
e
in
d
e
x
i
m
a
g
e
s
o
f
ND
VI
an
d
NOA
I
3
.
2
.
P
a
dd
y
f
ield a
re
a
a
nd
a
c
cura
cy
a
s
s
ess
m
e
nt
T
h
e
th
r
ee
class
if
ied
i
m
a
g
es
w
it
h
M
L
C
ap
p
r
o
ac
h
w
er
e
t
h
en
ca
lcu
la
ted
b
y
t
h
eir
ca
te
g
o
r
ies
an
d
co
m
p
ar
ed
th
eir
ac
cu
r
ac
ie
s
to
th
e
P
ad
d
y
Field
Ma
p
f
r
o
m
th
e
Mo
A
o
f
2
0
1
2
.
C
o
m
p
ar
is
o
n
o
f
class
i
f
icat
io
n
i
m
a
g
es
w
i
th
r
e
f
lecta
n
ce
i
n
p
u
ts
,
in
d
e
x
i
n
p
u
ts
,
a
n
d
t
h
e
co
m
b
in
at
io
n
s
o
f
r
ef
lecta
n
ce
a
n
d
in
d
ex
i
n
p
u
t
s
ar
e
p
r
esen
ted
in
T
ab
le
1
,
T
ab
le
2
an
d
T
a
b
le
3
.
Fro
m
t
h
e
tab
le,
it
ca
n
b
e
s
ee
n
t
h
at
th
e
c
o
r
r
ec
tn
ess
o
f
M
L
C
class
i
f
icatio
n
w
it
h
th
e
in
p
u
ts
o
f
r
ef
lecta
n
ce
i
m
ag
e
s
o
f
b
an
d
s
R
ed
,
NI
R
,
SW
I
R
-
1
s
h
o
w
s
th
at
th
e
p
ad
d
y
f
ield
i
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
P
a
d
d
y
field
cla
s
s
ifica
tio
n
w
ith
MODI
S
-
Ter
r
a
m
u
lti
-
temp
o
r
a
l
ima
g
e
tr
a
n
s
fo
r
ma
tio
n
…
(
Mu
h
a
mma
d
Dimya
ti
)
1353
q
u
ite
h
i
g
h
(
2
0
.
6
6
%),
an
d
h
ig
h
er
th
an
th
e
cla
s
s
i
f
icatio
n
w
it
h
in
p
u
ts
o
f
th
e
co
m
b
i
n
atio
n
o
f
r
ef
lecta
n
ce
i
m
a
g
es
R
ed
,
NI
R
,
SW
I
R
-
1
an
d
i
n
d
ex
i
m
a
g
es o
f
N
DVI
an
d
NO
A
I
(
1
9
.
9
2
%).
T
h
e
ac
cu
r
ac
y
o
f
th
e
clas
s
i
f
ic
atio
n
an
al
y
s
i
s
r
esu
lts
w
it
h
M
L
C
o
n
th
e
t
h
r
ee
in
p
u
t
s
is
ca
l
cu
lated
an
d
p
r
esen
ted
in
T
ab
le
4
.
Fro
m
th
e
an
al
y
s
is
r
es
u
lt
s
,
it c
an
b
e
s
ee
n
th
at
t
h
e
u
s
e
o
f
t
h
e
co
m
b
in
a
tio
n
o
f
r
ef
lec
tan
ce
o
f
b
an
d
R
ed
,
NI
R
,
SW
IR
-
1
,
NDVI
,
an
d
NOA
I
i
m
a
g
e
s
g
i
v
e
s
h
i
g
h
er
ac
cu
r
ac
y
o
f
8
5
.
4
3
%
(
p
r
o
d
u
ce
r
ac
cu
r
ac
y
9
3
.
4
0
%),
c
o
m
p
ar
ed
to
t
h
e
u
s
e
o
f
o
n
l
y
r
ef
lec
tan
ce
i
m
a
g
e
s
o
f
b
a
n
d
R
ed
,
NI
R
,
SW
I
R
-
1
,
th
at
i
s
8
3
.
5
0
%
(
p
r
o
d
u
ce
r
ac
cu
r
ac
y
8
6
.
4
3
%).
T
h
e
v
al
u
e
o
f
p
r
o
d
u
ce
r
ac
cu
r
ac
y
i
n
d
icate
s
t
h
at
t
h
e
p
a
d
d
y
f
iel
d
th
at
is
d
etec
ted
b
y
MO
DI
S
-
T
er
r
a
m
u
l
ti
-
te
m
p
o
r
al
i
m
a
g
e
h
a
s
h
ig
h
ac
c
u
r
ac
y
.
W
h
i
le
th
e
u
s
er
ac
c
u
r
ac
y
v
al
u
e
i
n
d
icate
s
th
a
t t
h
er
e
ar
e
s
till
m
a
n
y
u
n
id
en
ti
f
ied
p
ad
d
y
f
ield
s
u
s
i
n
g
MO
DI
S
-
T
er
r
a
d
ata.
As
a
n
ex
a
m
p
le,
t
h
er
e
i
s
s
til
l
3
9
.
0
9
%
o
f
p
ad
d
y
f
ield
w
h
ich
co
u
ld
n
o
t
b
e
id
en
ti
f
ied
u
s
in
g
i
n
p
u
t
r
e
f
lecta
n
c
e
o
r
3
6
.
1
8
%
o
f
p
ad
d
y
f
ield
ca
n
n
o
t
b
e
id
en
ti
f
ied
u
s
i
n
g
in
p
u
t
in
d
ex
,
an
d
3
9
.
7
8
%
o
f
p
ad
d
y
f
ield
ca
n
n
o
t
b
e
id
en
tifie
d
u
s
i
n
g
t
h
e
in
p
u
t
o
f
t
h
e
co
m
b
in
at
io
n
s
o
f
r
ef
lecta
n
ce
a
n
d
in
d
e
x
.
T
h
e
er
r
o
r
o
f
class
i
f
icatio
n
wh
ich
s
h
o
u
ld
b
e
class
i
f
ied
as
t
h
e
p
ad
d
y
f
ield
,
b
u
t
i
s
id
en
ti
f
i
ed
as
n
o
n
-
p
ad
d
y
f
ield
s
,
w
h
ic
h
ar
e
3
.
2
4
%
f
o
r
cla
s
s
i
f
icat
io
n
w
i
th
r
ef
le
ctan
ce
i
m
a
g
e
i
n
p
u
t
an
d
1
.
4
1
%
in
th
e
c
lass
if
icatio
n
w
it
h
in
d
e
x
i
m
a
g
e
i
n
p
u
t.
T
h
e
t
y
p
e
o
f
p
ad
d
y
f
ield
a
f
f
ec
ted
c
lass
i
f
icatio
n
ac
c
u
r
ac
y
,
in
ad
d
itio
n
to
to
p
o
g
r
ap
h
y
f
ac
to
r
.
Su
p
er
i
m
p
o
s
e
clas
s
i
f
icatio
n
r
esu
lt
s
w
it
h
r
ef
lecta
n
ce
in
p
u
ts
,
in
d
ex
i
n
p
u
ts
,
t
h
e
co
m
b
i
n
atio
n
s
o
f
r
ef
lecta
n
ce
a
n
d
i
n
d
ex
,
is
s
h
o
w
n
i
n
Fi
g
u
r
e
7
.
Fro
m
th
a
t
f
ig
u
r
e,
w
h
er
e
t
h
e
clas
s
i
f
icatio
n
o
f
p
ad
d
y
f
ie
ld
s
u
s
i
n
g
r
ef
lecta
n
ce
in
p
u
t
(
i
n
d
icate
d
b
y
R
ed
)
,
i
n
d
ex
i
n
p
u
t
s
(
i
n
d
icate
d
b
y
B
l
u
e)
,
th
e
co
m
b
in
a
tio
n
s
o
f
r
ef
lec
tan
ce
a
n
d
in
d
ex
(
i
n
d
icate
d
b
y
Gr
ee
n
)
.
T
h
e
ar
ea
o
f
p
ad
d
y
f
ield
u
s
i
n
g
r
ef
lecta
n
ce
in
p
u
t
is
7
6
.
1
0
%,
th
e
ar
ea
u
s
in
g
i
n
d
ex
in
p
u
t i
s
7
8
.
6
7
%,
an
d
th
e
ar
ea
u
s
i
n
g
th
e
co
m
b
i
n
atio
n
o
f
r
ef
le
ctan
ce
an
d
t
h
e
in
d
e
x
is
7
1
.
8
9
%.
T
h
e
ca
u
s
es
o
f
th
e
lo
w
u
s
er
a
cc
u
r
ac
y
a
n
d
t
h
e
n
u
m
b
er
o
f
p
ad
d
y
f
ield
s
u
n
id
e
n
ti
f
ied
b
y
th
e
MO
DI
S
-
T
er
r
a
im
a
g
e
ar
e
s
lo
p
e
an
d
th
e
t
y
p
es
o
f
p
ad
d
y
f
ield
s
,
t
h
e
h
i
g
h
er
th
e
s
lo
p
e
t
h
e
lo
w
er
th
e
ac
c
u
r
ac
y
.
B
esid
es,
t
h
e
r
ain
-
f
ed
f
ield
s
h
a
v
e
lo
w
er
ac
c
u
r
ac
y
t
h
a
n
ir
r
ig
a
ted
p
ad
d
y
f
ie
ld
s
.
T
h
e
d
if
f
er
e
n
ce
o
f
th
e
y
ea
r
o
f
r
ef
er
en
ce
d
ata
th
at
i
s
P
ad
d
y
Fie
ld
Ma
p
f
r
o
m
t
h
e
Mo
A
(
2
0
1
2
)
an
d
i
m
a
g
e
o
f
MO
DI
S
-
T
er
r
a
class
i
f
ic
atio
n
(
2
0
1
6
)
is
also
in
f
lu
e
n
ci
n
g
th
e
r
es
u
lt
s
o
f
co
m
p
ar
ativ
e
an
al
y
s
i
s
T
ab
le
1
.
T
h
e
C
o
n
cu
r
r
en
ce
Ma
tr
ix
R
e
s
u
l
t
w
it
h
th
e
I
n
p
u
ts
o
f
t
h
e
R
ef
lecta
n
ce
I
m
a
g
es o
f
B
an
d
s
R
ed
,
NI
R
,
SW
I
R
-
1
(
%)
R
e
f
e
r
e
n
c
e
s
M
O
D
I
S
-
T
e
r
r
a
N
o
n
-
P
a
d
d
y
F
i
e
l
d
P
a
d
d
y
F
i
e
l
d
T
o
t
a
l
N
o
n
-
P
a
d
d
y
F
i
e
l
d
6
2
.
8
4
3
.
2
4
6
6
.
0
8
P
a
d
d
y
F
i
e
l
d
1
3
.
2
6
2
0
.
6
6
3
3
.
9
2
T
o
t
a
l
7
6
.
1
0
2
3
.
9
0
1
0
0
T
ab
le
2
.
T
h
e
C
o
n
cu
r
r
en
ce
Ma
tr
ix
R
e
s
u
l
t
w
it
h
th
e
I
n
p
u
t
o
f
th
e
I
n
d
e
x
I
m
a
g
es o
f
N
DVI
an
d
NO
A
I
(
%)
R
e
f
e
r
e
n
c
e
s
M
O
D
I
S
-
T
e
r
r
a
N
o
n
-
P
a
d
d
y
F
i
e
l
d
P
a
d
d
y
F
i
e
l
d
T
o
t
a
l
N
o
n
-
P
a
d
d
y
F
i
e
l
d
5
9
.
0
6
5
.
4
7
6
4
.
5
4
P
a
d
d
y
F
i
e
l
d
1
2
.
8
3
2
2
.
6
4
3
5
.
4
6
T
o
t
a
l
7
1
.
8
9
2
8
.
1
1
1
0
0
T
ab
le
3
.
T
h
e
C
o
n
cu
r
r
en
ce
Ma
tr
ix
R
e
s
u
l
t
w
it
h
th
e
I
n
p
u
t o
f
t
h
e
C
o
m
b
in
at
io
n
o
f
R
ef
lecta
n
ce
I
m
a
g
es
R
ed
,
NI
R
,
SW
I
R
-
1
(
%)
an
d
th
e
I
n
d
ex
I
m
a
g
es o
f
NDVI
an
d
NO
A
I
(
%)
R
e
f
e
r
e
n
c
e
s
M
O
D
I
S
-
T
e
r
r
a
N
o
n
-
P
a
d
d
y
F
i
e
l
d
P
a
d
d
y
F
i
e
l
d
T
o
t
a
l
N
o
n
-
P
a
d
d
y
F
i
e
l
d
6
5
.
5
1
1
.
4
1
6
6
.
9
2
P
a
d
d
y
F
i
e
l
d
1
3
.
1
6
1
9
.
9
2
3
3
.
0
8
T
o
t
a
l
7
8
.
6
7
2
1
.
3
3
1
0
0
T
ab
le
4
.
T
h
e
R
esu
lt
s
o
f
t
h
e
C
a
lcu
latio
n
o
f
M
L
C
o
f
T
h
r
ee
T
y
p
es o
f
C
las
s
if
icatio
n
I
n
p
u
ts
C
l
a
ssi
f
i
c
a
t
i
o
n
i
n
p
u
t
s
A
c
c
u
r
a
c
y
(
%)
U
se
r
P
r
o
d
u
c
e
r
O
v
e
r
a
l
l
R
e
f
l
e
c
t
a
n
c
e
6
0
.
9
1
8
6
.
4
3
8
3
.
5
0
I
n
d
e
x
6
3
.
8
2
8
0
.
5
3
8
1
.
7
0
R
e
f
l
e
c
t
a
n
c
e
an
d
I
n
d
e
x
6
0
.
2
2
9
3
.
4
0
8
5
.
4
3
T
h
e
h
ig
h
er
th
e
s
lo
p
e
f
ac
to
r
th
e
lo
w
er
u
s
er
ac
cu
r
ac
y
,
as
s
h
o
w
n
in
Gr
ap
h
o
f
A
cc
u
r
ac
y
r
ela
tio
n
to
th
e
s
lo
p
e
in
F
ig
u
r
e
8
.
Fro
m
t
h
e
g
r
ap
h
,
it
ca
n
b
e
s
ee
n
th
a
t
th
e
h
ig
h
er
th
e
s
lo
p
e
th
e
lo
w
er
t
h
e
ac
cu
r
ac
y
,
t
h
e
u
s
er
ac
cu
r
ac
y
a
n
d
t
h
e
p
r
o
d
u
ce
r
ac
cu
r
ac
y
.
I
t
ca
n
al
s
o
b
e
s
ee
n
t
h
at
u
s
er
ac
c
u
r
ac
y
d
ec
r
ea
s
es
l
in
ea
r
l
y
,
at
s
lo
p
e
<1
7
%
u
s
er
ac
cu
r
ac
y
w
ill
b
e
>
8
0
%;
an
d
also
p
r
o
d
u
ce
r
ac
cu
r
ac
y
d
r
o
p
s
s
h
ar
p
l
y
b
et
w
ee
n
s
lo
p
e
1
%
to
s
l
o
p
e
2
%,
th
en
d
o
w
n
li
n
ea
r
l
y
.
T
h
i
s
i
n
d
icate
s
th
at
o
n
t
h
e
s
lo
p
e
o
f
0
-
2
%
p
ad
d
y
f
ield
s
ca
n
b
e
w
ell
id
e
n
ti
f
ie
d
b
y
MO
DI
S
-
T
er
r
a
d
ata,
w
h
er
ea
s
o
n
s
lo
p
e
>
2
% is
d
if
f
ic
u
lt to
id
en
t
if
y
.
T
y
p
es
o
f
p
ad
d
y
f
ield
w
i
ll
a
l
s
o
in
f
l
u
e
n
ce
t
h
e
r
es
u
lt
s
o
f
cl
ass
i
f
icatio
n
ac
c
u
r
ac
y
.
T
h
e
r
e
s
u
lt
o
f
t
h
e
ca
lcu
latio
n
o
f
th
e
i
n
f
l
u
en
ce
o
f
th
e
s
e
t
y
p
e
s
o
f
p
ad
d
y
f
ield
s
i
s
s
h
o
w
n
in
T
ab
le
5
.
Fro
m
th
e
t
ab
le,
it
is
k
n
o
w
n
th
at
t
h
e
v
ar
iatio
n
o
f
ac
cu
r
ac
y
d
if
f
er
en
ce
s
o
v
er
th
e
id
en
tifie
d
p
ad
d
y
f
ield
t
y
p
es
is
q
u
ite
l
ar
g
e,
r
an
g
i
n
g
f
r
o
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il 2
0
1
9
:
1
3
4
6
-
1358
1354
2
3
%
to
7
8
%.
An
d
a
r
a
in
-
f
ed
l
o
w
la
n
d
p
ad
d
y
is
t
h
e
m
o
s
t
d
i
f
f
icu
lt
t
y
p
e
o
f
p
ad
d
y
w
it
h
u
s
er
ac
cu
r
ac
y
o
f
2
2
.
9
2
%
id
en
ti
f
ied
b
y
t
h
i
s
ap
p
r
o
ac
h
.
F
r
o
m
th
e
r
es
u
lt
o
f
co
m
p
ar
ati
v
e
an
al
y
s
i
s
b
et
w
ee
n
t
h
e
r
es
u
lt
s
o
f
ar
ea
ca
lc
u
latio
n
b
ased
o
n
th
e
d
is
tr
ict
b
o
u
n
d
ar
y
o
f
th
r
ee
i
n
p
u
t
s
o
f
cla
s
s
i
f
icat
i
o
n
o
f
p
ad
d
y
f
ield
a
n
d
th
e
P
ad
d
y
Field
Ma
p
f
r
o
m
th
e
Mo
A
s
h
o
w
ed
th
a
t
all
o
f
th
e
clas
s
i
f
icatio
n
r
esu
lts
p
er
f
o
r
m
ed
ac
c
u
r
ac
y
m
o
r
e
th
a
n
0
.
8
5
.
T
h
o
s
e
ar
e
th
e
co
r
r
elatio
n
(
r
2
)
o
f
t
h
e
r
e
f
lecta
n
ce
in
p
u
t i
s
0
.
8
7
,
th
e
in
d
e
x
i
n
p
u
t i
s
0
.
8
9
,
an
d
t
h
e
co
m
b
in
a
tio
n
o
f
r
ef
l
ec
tan
ce
an
d
in
d
ex
i
n
p
u
t
is
0
.
8
5
.
T
h
e
co
r
r
elatio
n
a
m
o
n
g
th
o
s
e
ap
p
r
o
ac
h
es
is
s
h
o
w
n
i
n
Fi
g
u
r
e
9
.
T
h
e
r
es
u
lt
o
f
co
m
p
ar
ativ
e
an
al
y
s
is
b
et
w
ee
n
t
h
e
r
esu
l
ts
o
f
ar
ea
ca
lcu
latio
n
b
ased
o
n
th
e
p
r
o
v
in
ce
b
o
u
n
d
ar
y
o
f
th
r
ee
in
p
u
ts
o
f
class
i
f
icatio
n
o
f
p
ad
d
y
f
ield
a
n
d
t
h
e
P
ad
d
y
F
ield
Ma
p
f
r
o
m
th
e
Mo
A
,
s
h
o
w
ed
th
at
al
l
o
f
th
e
cla
s
s
i
f
icatio
n
r
esu
lt
s
p
er
f
o
r
m
ed
co
r
r
elatio
n
(
r
2
)
m
o
r
e
th
a
n
0
.
9
9
.
T
h
o
s
e
ar
e
th
e
co
r
r
elatio
n
(
r
2
)
o
f
th
e
r
ef
lecta
n
ce
i
n
p
u
t
is
0
.
9
9
8
,
th
e
in
d
ex
in
p
u
t
i
s
0
.
9
9
1
,
an
d
th
e
co
m
b
i
n
atio
n
o
f
r
e
f
l
ec
tan
ce
a
n
d
in
d
ex
in
p
u
t
i
s
0
.
9
9
8
.
T
h
e
co
r
r
elatio
n
a
m
o
n
g
t
h
o
s
e
ap
p
r
o
ac
h
es
is
s
h
o
w
n
i
n
F
ig
u
r
e
1
0
.
T
h
e
r
esu
l
ts
o
f
ca
lc
u
latio
n
p
er
p
r
o
v
in
ce
o
f
th
ese
p
h
e
n
o
lo
g
ical
m
o
d
el
s
ar
e
s
h
o
w
n
i
n
T
ab
le
6
.
T
h
e
r
esu
lt
o
f
th
is
s
t
u
d
y
p
r
o
v
id
es
a
h
ig
h
er
class
i
f
icatio
n
r
esu
l
t
th
an
t
h
e
p
r
ev
io
u
s
s
tu
d
y
co
n
d
u
cted
b
y
Xiao
et
al.
w
it
h
a
co
r
r
elatio
n
(
r
2
)
r
ea
ch
ed
0
.
4
9
-
0
.
6
5
(
h
ill
y
-
f
la
t
ar
ea
o
f
co
u
n
t
y
-
le
v
el)
an
d
0
.
8
0
-
0
.
8
8
(
h
ill
y
-
f
la
t a
r
ea
o
f
p
r
o
v
in
cial
le
v
el)
f
o
r
C
h
i
n
a,
an
d
r
ea
ch
ed
0
.
4
4
f
o
r
I
n
d
o
n
esia
[
2
8
]
.
Fig
u
r
e
7
.
C
o
m
b
in
at
io
n
o
f
R
G
B
o
f
v
ar
io
u
s
p
ad
d
y
f
ield
s
o
f
cl
ass
i
f
icatio
n
r
esu
l
ts
,
No
te:
R
ed
is
class
if
ica
tio
n
u
s
i
n
g
r
ef
lecta
n
ce
R
ed
,
NI
R
,
S
W
I
R
-
1
(
to
tal
ar
ea
=7
6
.
1
0
%);
g
r
ee
n
is
clas
s
i
f
icatio
n
u
s
i
n
g
b
o
th
co
m
b
in
a
tio
n
s
o
f
r
ef
lecta
n
ce
a
n
d
in
d
e
x
(
to
tal
ar
ea
=7
1
.
8
9
%);
b
lu
e
is
class
if
ica
tio
n
u
s
in
g
i
n
d
ex
NDVI
a
n
d
NO
A
I
(
to
tal
ar
ea
=7
8
.
6
7
%)
Fig
u
r
e
8
.
A
g
r
ap
h
o
f
th
e
r
elati
o
n
o
f
ac
cu
r
ac
y
o
f
r
esu
lt o
f
cla
s
s
i
f
icatio
n
w
it
h
th
e
i
n
p
u
t
co
m
b
in
atio
n
o
f
r
ef
lecta
n
ce
a
n
d
in
d
e
x
i
m
a
g
es t
o
s
lo
p
e
T
ab
le
5
.
T
h
e
A
cc
u
r
ac
y
o
f
Fo
u
r
T
y
p
es P
ad
d
y
Field
Ma
n
a
g
e
m
en
t o
f
t
h
e
C
la
s
s
i
f
icatio
n
w
it
h
th
e
I
n
p
u
t o
f
th
e
C
o
m
b
in
at
io
n
o
f
R
ef
lec
tan
ce
a
n
d
I
n
d
ex
(
%)
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
p
a
d
d
y
f
i
e
l
d
b
a
se
d
o
n
t
h
e
M
o
A
d
a
t
a
T
h
e
r
e
su
l
t
o
f
p
a
d
d
y
f
i
e
l
d
i
d
e
n
t
i
f
i
c
a
t
i
o
n
b
y
M
O
D
I
S
(
%)
U
se
r
a
c
c
u
r
a
c
y
o
f
p
a
d
d
y
f
i
e
l
d
N
o
n
-
p
a
d
d
y
f
i
e
l
d
P
a
d
d
y
f
i
e
l
d
T
o
t
a
l
T
e
c
h
n
i
c
a
l
l
y
I
r
r
i
g
a
t
e
d
3
.
2
8
1
1
.
6
3
1
4
.
9
1
7
8
.
0
0
T
e
c
h
n
i
c
a
l
l
y
S
e
mi
I
r
r
i
g
a
t
e
d
4
.
0
9
6
.
1
1
1
0
.
2
0
5
9
.
9
2
S
i
mp
l
e
I
r
r
i
g
a
t
e
d
0
.
9
1
0
.
7
3
1
.
6
4
4
4
.
5
6
R
a
i
n
-
f
e
d
4
.
8
9
1
.
4
5
6
.
3
4
2
2
.
9
2
N
o
n
-
P
a
d
d
y
F
i
e
l
d
6
5
.
5
1
1
.
4
1
6
6
.
9
2
-
T
o
t
a
l
7
8
.
6
7
2
1
.
3
3
1
0
0
.
0
0
-
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
P
a
d
d
y
field
cla
s
s
ifica
tio
n
w
ith
MODI
S
-
Ter
r
a
m
u
lti
-
temp
o
r
a
l
ima
g
e
tr
a
n
s
fo
r
ma
tio
n
…
(
Mu
h
a
mma
d
Dimya
ti
)
1355
Fig
u
r
e
9
.
C
o
r
r
elatio
n
b
et
w
ee
n
th
e
ca
lcu
latio
n
o
f
M
ODI
S
-
T
er
r
a
i
m
ag
e
cla
s
s
i
f
icatio
n
r
esu
lts
w
it
h
t
h
e
s
tat
is
tical
d
ata
o
f
P
ad
d
y
Field
s
f
r
o
m
th
e
Mo
A
b
ase
i
n
d
is
tr
ict
r
eg
io
n
Fig
u
r
e
1
0
.
C
o
r
r
elatio
n
b
et
w
ee
n
th
e
ca
lc
u
latio
n
o
f
MO
DI
S
-
T
er
r
a
im
a
g
e
clas
s
i
f
icatio
n
r
es
u
lt
s
w
ith
t
h
e
s
tatis
t
ical
d
ata
o
f
P
ad
d
y
Field
s
f
r
o
m
th
e
Mo
A
b
ase
i
n
p
r
o
v
in
ce
r
eg
io
n
.
B
y
u
s
in
g
t
h
e
co
m
b
in
a
tio
n
o
f
r
ef
lecta
n
ce
an
d
i
n
d
ex
m
e
t
r
ic
in
p
u
t,
th
e
r
e
s
u
lt
o
f
an
al
y
s
i
s
u
s
i
n
g
s
tatis
t
ical
d
ata
o
f
2
0
1
6
o
n
l
y
p
er
f
o
r
m
ed
6
4
.
1
%
o
f
t
h
e
id
e
n
ti
f
ied
p
ad
d
y
f
ield
ar
ea
.
Ho
w
e
v
er
,
b
y
a
n
al
y
s
is
,
w
h
ic
h
,
co
n
s
id
er
in
g
s
p
atial
d
i
s
tr
ib
u
tio
n
d
ata
as
s
h
o
w
n
i
n
T
ab
le
5
(
%
a
r
ea
o
f
p
ad
d
y
f
ield
=2
1
.
3
3
%)
an
d
T
ab
le
3
(
%
ar
ea
o
f
p
ad
d
y
f
iel
d
=3
3
.
0
8
%),
th
e
r
esu
l
t
o
f
ac
cu
r
ac
y
b
ase
o
n
s
tat
is
tical
d
ata
is
2
1
.
3
3
/3
3
.
0
8
o
r
6
4
.
4
%.
T
ab
le
6
.
C
o
m
p
ar
is
o
n
o
f
P
ad
d
y
Field
A
r
ea
o
f
C
las
s
i
f
icatio
n
R
esu
lt
a
n
d
R
e
f
er
en
ce
Data
b
y
P
r
o
v
in
ce
No
P
r
o
v
i
n
c
e
T
h
e
r
e
su
l
t
o
f
c
l
a
ssi
f
i
c
a
t
i
o
n
w
i
t
h
p
h
e
n
o
l
o
g
i
c
a
l
mo
d
e
l
(
h
a
)
P
a
d
d
y
f
i
e
l
d
d
a
t
a
f
r
o
m t
h
e
M
o
A
o
f
2
0
1
6
(
h
a
)
R
e
f
l
e
c
t
a
n
c
e
I
n
d
e
x
C
o
mb
i
n
a
t
i
o
n
o
f
r
e
f
l
e
c
t
a
n
c
e
a
n
d
I
n
d
e
x
1
Ea
st
Jav
a
7
7
9
,
3
9
4
9
7
7
,
6
7
7
7
2
1
,
9
6
7
1
,
0
8
7
,
0
1
8
2
C
e
n
t
r
a
l
J
a
v
a
6
7
4
,
7
2
4
7
5
5
,
8
9
0
6
1
0
,
6
9
6
9
6
3
,
6
6
5
3
W
e
st
Jav
a
6
8
0
,
3
0
3
8
1
1
,
8
2
7
5
9
0
,
9
1
2
9
1
3
,
9
7
6
4
Jo
g
j
a
k
a
r
t
a
5
1
,
3
97
3
7
,
6
7
6
3
5
,
4
3
2
5
3
,
9
8
5
5
B
a
n
t
e
n
1
2
5
,
4
4
3
1
4
8
,
8
6
3
1
0
5
,
7
4
2
2
0
3
,
1
2
3
6
Jak
a
r
t
a
1
,
3
9
0
1
3
4
8
8
8
5
8
1
T
o
t
a
l
2
,
3
1
2
,
6
5
2
2
,
7
3
2
,
0
6
8
2
,
0
6
5
,
6
3
6
3
,
2
2
2
,
3
4
7
Evaluation Warning : The document was created with Spire.PDF for Python.