I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
22
,
No
.
1
,
A
p
r
il
2
0
2
1
,
p
p
.
5
8
0
~
589
I
SS
N:
2
5
02
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
2
2
.i
1
.
pp
580
-
5
8
9
580
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
A
surv
ey
on pre
di
cting o
il spills
by
study
ing
it
s ca
use
s usin
g
deep learning
tec
hniques
M
o
na
M
o
ha
m
ed
Na
s
r
1
,
F
a
hd
K
a
m
a
l K
a
m
el
2
,
Y
a
s
m
en
Sa
m
ha
n Abd El
W
a
ha
b
3
2,
3
In
f
o
rm
a
ti
o
n
S
y
ste
m
s De
p
a
rtme
n
t,
F
a
c
u
lt
y
o
f
C
o
m
p
u
ters
&
Artif
i
c
ial
In
telli
g
e
n
c
e
,
Be
n
i
-
S
u
e
f
Un
i
v
e
rsity
,
Be
n
i
-
S
u
e
f,
Eg
y
p
t
1
In
fo
rm
a
ti
o
n
S
y
ste
m
s De
p
a
rtme
n
t,
F
a
c
u
lt
y
o
f
Co
m
p
u
ters
&
&
Arti
ficia
l
In
telli
g
e
n
c
e
,
He
lwa
n
Un
i
v
e
rsity
,
Ca
ir
o
,
E
g
y
p
t
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
27
,
2
0
2
0
R
ev
is
ed
Ma
r
1
0
,
2
0
2
1
Acc
ep
ted
Mar
2
5
,
2
0
2
1
I
t
’
s
s
o
e
a
s
y
t
o
k
n
o
w
t
h
e
a
c
c
i
d
e
n
t
s
a
s
i
t
’
s
a
l
r
e
a
d
y
h
a
p
p
e
n
e
d
a
n
d
s
o
l
v
i
n
g
t
h
e
s
e
a
c
c
i
d
e
n
t
s
i
s
i
m
m
e
d
i
a
t
e
l
y
h
a
n
d
l
e
d
,
b
u
t
s
e
a
r
c
h
i
n
g
f
o
r
a
s
o
l
u
t
i
o
n
f
o
r
t
h
e
s
e
a
c
c
i
d
e
n
t
s
,
d
o
n
’
t
d
e
n
y
t
h
e
e
x
i
s
t
e
n
c
e
o
f
r
e
a
s
o
n
s
t
h
a
t
m
a
d
e
a
c
c
i
d
e
n
t
s
h
a
p
p
e
n
.
K
n
o
w
i
n
g
t
h
e
s
o
u
r
c
e
o
f
a
c
c
i
d
e
n
t
s
w
i
l
l
h
e
l
p
i
n
a
v
o
i
d
i
n
g
t
h
e
m
t
o
o
c
c
u
r
i
n
t
h
e
f
u
t
u
r
e
.
I
t
’
s
a
n
i
m
p
o
r
t
a
n
t
f
i
e
l
d
i
n
s
e
a
r
c
h
i
n
g
a
s
s
o
m
e
h
u
m
a
n
l
i
v
e
s
d
e
p
e
n
d
o
n
t
h
e
s
a
f
e
t
y
o
f
s
u
c
h
a
f
i
e
l
d
,
s
o
i
t
’
s
s
o
i
m
p
o
r
t
a
n
t
t
o
u
s
e
a
p
o
w
e
r
f
u
l
t
e
c
h
n
i
q
u
e
t
o
d
e
f
i
n
e
t
h
e
s
e
r
e
a
s
o
n
s
a
s
t
h
e
r
e
s
e
a
r
c
h
p
o
i
n
t
i
n
s
p
i
l
l
a
c
c
i
d
e
n
t
s
a
n
d
p
r
e
d
i
c
t
i
n
g
a
c
c
i
d
e
n
t
s
a
n
d
t
o
p
r
e
d
i
c
t
t
h
e
o
c
c
u
r
r
e
n
c
e
o
f
t
h
e
a
c
c
i
d
e
n
t
b
e
f
o
r
e
i
t
s
h
a
p
p
e
n
i
n
g
d
e
p
e
n
d
i
n
g
o
n
i
t
s
r
e
a
s
o
n
s
t
h
a
t
l
e
a
d
t
o
t
h
a
t
a
c
c
i
d
e
n
t
i
n
p
a
s
t
t
i
m
e
s
s
o
w
i
t
h
s
i
m
i
l
a
r
c
o
n
d
i
t
i
o
n
s
i
t
m
i
g
h
t
h
a
p
p
e
n
a
n
a
c
c
i
d
e
n
t
b
u
t
i
t
n
e
e
d
s
a
s
u
f
f
i
c
i
e
n
t
d
a
t
a
a
n
d
a
p
o
w
e
r
f
u
l
t
e
c
h
n
i
q
u
e
s
u
c
h
a
s
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
t
h
a
t
g
i
v
e
v
e
r
y
p
r
e
c
i
s
e
r
e
s
u
l
t
s
a
n
d
b
y
u
s
i
n
g
t
h
i
s
t
o
o
l
a
n
i
n
t
e
l
l
i
g
e
n
t
m
o
d
e
l
w
i
l
l
b
u
i
l
d
t
o
p
r
e
d
i
c
t
o
i
l
s
p
i
l
l
i
n
g
.
I
n
t
h
i
s
s
u
r
v
e
y
p
a
p
e
r
,
r
e
l
a
t
e
d
w
o
r
k
w
i
l
l
b
e
d
i
s
c
u
s
s
e
d
t
o
e
n
h
a
n
c
e
t
h
a
t
w
o
r
k
.
K
ey
w
o
r
d
s
:
Acc
id
en
ts
h
an
d
lin
g
Acc
id
en
ts
h
ap
p
en
Av
o
id
in
g
ac
ci
d
en
ts
Po
wer
f
u
l te
ch
n
iq
u
es
So
lu
tio
n
f
o
r
ac
cid
en
ts
Sp
ill ac
cid
en
ts
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Yasm
en
Sam
h
an
Ab
d
E
lW
ah
a
b
I
n
f
o
r
m
atio
n
Sy
s
tem
s
Dep
ar
tm
en
t
Facu
lty
o
f
C
o
m
p
u
ter
s
&
Ar
tifi
cial
I
n
t
ellig
en
ce
,
B
en
i
-
Su
ef
U
n
iv
er
s
ity
E
m
ail:
y
asm
en
_
s
am
h
an
@
y
ah
o
o
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Petr
o
l
is
s
o
im
p
o
r
tan
t
in
o
u
r
life
an
d
an
im
p
o
r
tan
t
is
s
u
e
to
s
p
ea
k
ab
o
u
t.
in
m
o
s
t
o
f
th
e
o
th
er
r
esear
ch
es
alo
t
o
f
m
o
n
ito
r
in
g
p
ip
lin
es
an
d
g
iv
e
wa
r
n
in
g
o
r
alar
m
as
m
en
tio
n
ed
in
[
1
]
t
h
at
th
er
'
s
a
leak
ag
e
in
s
o
m
e
p
ip
lin
es
t
h
at
ca
n
g
i
v
e
a
h
u
g
e
s
p
illi
n
g
th
at
lead
to
a
lo
t
o
f
lo
s
s
an
d
wastin
g
tim
e
o
r
a
n
ex
p
lo
r
atio
n
in
th
e
lo
ca
tio
n
th
at
lead
to
alo
t
o
f
l
o
s
in
g
in
h
u
m
a
n
life
an
d
m
o
n
ey
as
ex
p
lain
ed
in
[
2
,
3
]
.
An
o
th
er
r
esear
ch
es
th
at
s
tu
d
y
in
g
an
d
f
o
c
u
s
o
n
h
an
d
li
n
g
th
e
ac
cid
e
n
t
af
ter
its
o
cc
u
r
r
en
ce
.
I
n
o
u
r
r
esear
ch
will
s
tu
d
y
all
ca
u
s
es
th
at
ca
u
s
ed
th
at
ac
cid
en
t a
n
d
p
r
ev
e
n
t its
o
cc
u
r
r
en
ce
.
Pip
elin
es
ar
e
an
im
p
o
r
tan
t
is
u
u
e
in
th
is
f
ield
i
n
its
s
tr
u
ct
u
r
e
an
d
tr
a
n
s
p
o
r
tin
g
it
with
s
af
ety
way
s
in
[4
-
6
]
alo
t
o
f
m
eth
o
d
s
h
as
d
is
cu
s
s
ed
to
s
tr
u
ctu
r
e
th
e
p
ip
lin
es
with
p
er
f
ec
t
way
an
d
in
lim
ited
s
ize
s
with
ef
f
ec
ien
cy
wo
r
k
.
T
r
an
s
f
o
r
m
in
g
is
th
e
last
p
h
ase
af
ter
ex
tr
ac
t
io
n
o
il
to
m
ak
e
it
r
ea
d
y
f
o
r
u
s
e
an
d
it
d
ep
en
d
s
o
n
alo
t
o
f
f
ac
to
r
s
th
at
af
f
ec
t
o
n
it
s
u
ch
as
h
ig
h
tem
p
r
atu
r
e
t
h
at
o
il
p
r
o
p
e
r
ities
m
u
s
t
h
an
d
led
with
th
at
h
ig
h
tem
p
r
atu
r
e
an
d
alo
t
o
f
ch
allen
g
es
th
at
will
b
e
f
ac
ed
,
an
in
s
u
latin
g
o
il
is
u
s
ed
to
m
ak
e
th
e
t
r
an
s
f
o
r
m
er
s
o
co
l
d
to
o
p
er
ate
s
af
ely
an
d
u
s
in
g
a
s
p
ec
if
ic
m
ater
ials
with
ex
ac
t
t
em
p
r
atu
r
e
f
o
r
ea
ch
m
ater
ial
b
y
s
ec
u
r
e
tr
an
s
f
er
in
g
o
f
th
ese
m
ater
ials
an
d
e
n
er
g
i
es
[
7
,
8
]
.
I
n
[
9
,
1
0
]
tr
an
s
f
er
i
n
g
p
etr
o
l
p
r
o
ce
s
s
af
ter
ex
tr
ac
tio
n
p
r
o
ce
s
s
is
an
im
p
o
r
tan
t
p
h
ase
in
th
is
f
ield
as
it
d
ep
en
d
s
o
n
th
e
co
n
tain
e
r
o
f
th
e
m
ater
ial,
m
ater
ial
its
elf
,
clim
ate
o
f
th
e
ex
tr
ac
tio
n
lo
ca
tio
n
an
d
r
ec
eiv
ed
o
n
e,
p
ain
t
o
f
th
e
co
n
tain
er
,
an
d
th
e
tr
an
s
p
o
r
tatio
n
v
e
h
icle
th
at
lead
th
e
r
o
ad
.
T
r
an
s
p
o
r
tin
g
p
r
o
ce
s
s
also
af
f
e
cts
o
n
all
cr
ea
tu
r
es
s
u
ch
as
p
eo
p
le,
an
im
als,
an
d
p
lan
t'
s
life
as
d
is
cu
s
s
ed
in
[
1
0
]
in
Kab
u
l c
ity
an
d
th
e
b
ad
ef
f
e
ct
o
f
th
at
p
r
o
ce
s
s
o
n
all
th
ese
cr
ea
tu
r
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
s
u
r
ve
y
o
n
p
r
ed
ictin
g
o
il sp
ills
b
y
s
tu
d
yin
g
its
ca
u
s
e
s
u
s
in
g
d
ee
p
lea
r
n
in
g
…
(
Mo
n
a
Mo
h
a
med
N
a
s
r
)
581
T
h
is
r
ev
iewin
g
in
d
icate
to
u
s
h
o
w
th
at
f
iel
d
is
s
o
im
p
o
r
ta
n
t
an
d
wh
at
ar
e
r
is
k
s
an
d
b
e
n
ef
its
th
at
o
cc
u
r
wh
e
n
will
y
o
u
wo
r
k
in
t
h
at
f
ield
o
r
s
im
ilar
f
ield
s
s
u
ch
as
co
il,
m
etal,
an
d
all
m
in
in
g
m
ater
ials
th
at
g
iv
e
u
s
a
wea
lth
in
in
d
u
s
tr
y
a
n
d
a
m
ain
r
ea
s
o
n
f
o
r
n
atio
n
p
r
o
g
r
e
s
s
.
As
a
r
esu
lt
o
f
th
is
r
esear
ch
an
in
tellig
en
t
m
o
d
el
will
b
e
b
u
ilt
to
p
r
ed
ict
s
p
ill
ac
cid
en
t
b
y
s
tu
d
y
in
g
its
ca
u
s
es
u
s
in
g
d
ee
p
lear
n
in
g
tech
n
iq
u
e
s
to
m
ak
e
th
e
en
tire
wo
r
ld
s
af
e
an
d
clea
r
an
d
a
v
o
id
all
lo
s
s
es
in
m
o
n
ey
,
tim
e,
an
d
cr
ea
tu
r
e’
s
life
.
T
h
e
p
a
p
er
is
s
tr
u
ctu
r
ed
as
f
o
llo
ws:
Sectio
n
two
d
is
cu
s
s
e
s
in
cid
en
ts
in
v
o
l
v
in
g
o
il
s
p
ills
b
y
p
ar
titi
o
n
in
g
th
e
m
in
to
tw
o
ty
p
es
o
n
s
h
o
r
e
o
il
s
p
ills
an
d
o
f
f
s
h
o
r
e
o
il
s
p
ill
s
.
Sectio
n
s
th
r
ee
an
d
f
o
u
r
in
t
r
o
d
u
ce
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
with
Sam
p
les
o
f
co
m
b
in
atio
n
s
b
etwe
en
o
il sp
ills
th
at
tr
ea
ted
o
r
d
is
co
v
er
ed
b
y
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
f
iv
e
an
d
f
in
ally
s
ec
tio
n
f
iv
e
p
r
esen
ts
co
n
cl
u
s
io
n
o
f
th
e
s
u
r
v
ey
.
2.
O
I
L
SPI
L
L
ACCI
DE
N
T
S
Fro
m
[1
1
]
Oil
s
p
ill
ac
cid
en
ts
is
o
n
e
o
t
h
e
m
o
s
t
im
p
o
r
tan
t
p
r
o
b
le
m
s
we
n
ee
d
t
o
s
p
ea
k
ab
o
u
t
an
d
d
is
cu
s
s
it
’s
d
etails.
First,
we
a
r
e
g
o
in
g
to
k
n
o
w
a
lo
t o
f
is
s
u
e
s
s
u
ch
as 1
)
wh
at’
s
th
e
im
p
o
r
tan
ce
o
f
o
il u
s
ag
e
in
o
u
r
life
,
2
)
h
o
w
th
e
p
r
o
ce
s
s
o
f
ex
tr
ac
tio
n
an
d
tr
a
n
s
p
o
r
tatio
n
h
ap
p
en
e
d
,
3
)
h
o
w
p
r
o
b
lem
s
an
d
ac
cid
en
ts
af
f
ec
t
o
u
r
life
g
e
n
er
ally
a
n
d
ec
o
n
o
m
ic
s
p
ec
ially
,
4
)
h
o
w
to
f
ix
an
d
tr
ea
t
with
t
h
e
s
e
p
r
o
b
lem
s
,
a
n
d
5
)
k
n
o
win
g
s
o
m
e
o
f
th
e
ac
cid
e
n
ts
an
d
co
u
n
tr
ies
th
at
h
s
d
af
f
ec
t
ed
a
n
d
f
ac
e
a
lo
t
o
f
lo
s
es
b
ec
au
s
e
o
f
th
ese
p
r
o
b
lem
s
.
a)
W
h
at’
s
th
e
im
p
o
r
tan
ce
o
f
o
il
u
s
ag
e
in
o
u
r
life
:
we
ca
n
’t
d
en
y
th
at
o
il,
g
as,
n
atu
r
al
g
ases
,
an
d
all
o
f
s
u
c
h
m
ater
ials
ar
e
s
o
im
p
o
r
tan
t
in
th
e
life
as
all
o
f
th
e
tr
an
s
p
o
r
t
atio
n
p
r
o
ce
s
s
es
ca
n
’
t
h
ap
p
en
with
o
u
t
th
ese
m
ater
ials
.
Ma
ter
ial
s
u
ch
as
p
etr
o
l
co
n
tr
o
l
in
t
h
e
ec
o
n
o
m
y
o
f
th
e
co
u
n
tr
y
as
it
ca
n
m
ak
e
th
e
co
u
n
tr
y
t
h
at
ex
p
o
r
t o
il is
s
o
r
ich
an
d
h
as a
l
o
t o
f
wea
p
o
n
s
to
m
ak
e
it st
r
o
n
g
.
Few
co
u
n
tr
ies th
at
h
av
e
th
e
ad
v
an
tag
e
o
f
h
av
in
g
th
e
o
il
in
th
eir
la
n
d
s
a
s
th
ese
f
ew
co
u
n
tr
ies
s
av
e
th
e
ir
o
wn
u
s
ag
e
o
f
th
e
o
il
an
d
s
u
ch
m
ater
ials
,
also
will
h
ir
e
a
lo
t
o
f
m
an
a
g
e
r
s
,
en
g
i
n
ee
r
s
,
wo
r
k
er
s
,
a
n
d
d
r
iv
er
s
to
e
m
p
lo
y
ee
in
th
is
f
ield
f
r
o
m
d
ig
g
in
g
th
e
lo
ca
tio
n
o
f
t
h
e
p
etr
o
l
to
d
e
liv
er
in
g
th
e
u
s
ag
e
m
a
t
e
r
i
a
l
s
t
o
t
he
i
r
us
er
s.
R
eg
ar
d
less
m
a
n
y
p
e
o
p
le
a
n
d
th
eir
b
en
ef
it
f
r
o
m
wo
r
k
in
g
in
s
u
ch
a
f
ield
,
th
e
co
u
n
tr
y
will
b
en
ef
it
f
ir
s
t
f
r
o
m
th
e
p
etr
o
l
th
at
ex
tr
ac
te
d
f
r
o
m
th
e
lan
d
to
th
eir
o
wn
tr
a
n
s
p
o
r
tatio
n
s
also
d
o
n
’
t
f
o
r
g
et
all
o
f
th
e
m
ac
h
in
es
an
d
f
ac
to
r
ies
th
at
ca
n
’
t
wo
r
k
with
o
u
t
p
etr
o
l
o
r
lik
e
m
ater
ials
,
also
th
e
p
r
o
f
it
o
f
th
e
ex
p
o
r
ted
o
f
th
is
o
il
th
at
ca
n
b
e
a
m
an
y
p
r
o
f
it
an
d
a
f
r
ien
d
s
h
ip
b
et
wee
n
co
u
n
tr
ies
th
at
ex
ch
an
g
e
th
e
o
il.
B
en
ef
it
n
o
t
o
n
ly
f
o
r
t
h
e
co
u
n
tr
y
o
f
h
a
v
in
g
t
h
e
o
il
also
th
e
co
u
n
tr
ies
th
at
im
p
o
r
ted
th
ese
o
ils
ca
n
’
t
wo
r
k
with
o
u
t
th
is
o
il,
s
o
i
n
th
at
ca
s
e
c
o
o
p
er
atin
g
o
f
th
e
co
u
n
tr
ies
is
s
o
im
p
o
r
tan
t
to
h
i
g
h
life
co
n
tin
u
e
[
1
2
,
1
3
]
.
M
en
tio
n
in
g
th
at
b
ef
o
r
e
t
h
e
p
r
o
ce
s
s
o
f
ex
tr
ac
tio
n
o
il
th
e
wo
r
ld
was
d
ep
en
d
in
g
o
n
th
e
Pis
ce
s
o
il
th
a
t
ex
tr
ac
t
f
r
o
m
th
e
wh
ales
th
at
f
o
u
n
d
in
t
h
e
s
ea
th
at
n
ee
d
a
lo
t
o
f
wo
r
k
er
s
,
f
is
h
er
s
,
an
d
s
tr
o
n
g
wo
r
k
f
o
r
c
e
to
g
ettin
g
th
at
Pis
ce
s
o
il
f
r
o
m
d
an
g
er
o
u
s
wh
ales.
Fro
m
k
n
o
win
g
th
e
p
a
s
t
th
is
p
r
o
ce
s
s
o
f
ex
tr
ac
tin
g
o
i
l
is
s
o
m
o
r
e
s
av
e
t
h
at
wh
ales
a
n
d
c
o
v
er
a
lo
t
o
f
u
s
ag
e
o
f
co
u
n
tr
ies,
h
o
wev
e
r
th
er
e’
r
e
a
lo
t
o
f
p
r
o
b
lem
s
an
d
h
az
ar
d
s
th
at
f
ac
e
th
is
o
p
er
at
io
n
an
d
n
ee
d
to
a
lo
t o
f
w
o
r
k
er
s
,
tim
e,
an
d
b
u
d
g
et
t
o
tr
ea
t w
ith
an
y
p
r
o
b
l
em
o
f
o
il
p
r
o
b
lem
s
[
1
4
]
.
b)
Ho
w
th
e
p
r
o
ce
s
s
o
f
ex
tr
ac
tio
n
an
d
tr
an
s
p
o
r
tatio
n
h
ap
p
e
n
e
d
:
in
[
1
5
-
17]
o
il
ex
tr
ac
tio
n
is
n
o
t
an
ea
s
y
o
p
er
atio
n
f
o
r
all
an
d
n
o
t
ev
er
y
p
eo
p
le
ca
n
d
o
.
I
t
n
ee
d
s
a
l
o
t
o
f
p
eo
p
le
to
ex
ec
u
te
th
at
o
p
e
r
atio
n
an
d
n
o
t
o
n
ly
p
eo
p
le
ar
e
im
p
o
r
tan
t
in
th
at
o
p
er
atio
n
,
b
u
t
also
a
lo
t
a
n
d
b
ig
o
f
g
ian
t
eq
u
ip
m
en
t’
s
th
at
o
n
ly
s
o
m
e
co
m
p
an
ies
ca
n
i
n
tr
o
d
u
ce
it.
T
h
is
eq
u
ip
m
e
n
t
s
o
m
etim
es
it’s
n
o
t
f
o
r
s
ellin
g
,
b
u
t
o
th
e
r
c
o
m
p
an
ies
h
ir
e
th
i
s
eq
u
ip
m
en
t’
s
f
o
r
th
e
d
ig
g
in
g
a
n
d
ex
t
r
ac
tio
n
c
o
m
p
a
n
ies.
I
n
s
u
ch
f
ield
s
p
ec
if
ic
e
q
u
ip
m
e
n
t
t
h
at
u
s
ed
also
a
s
p
ec
if
ic
p
ain
ts
f
o
r
th
ese
eq
u
ip
m
en
t’
s
an
d
tr
an
s
p
o
r
tatio
n
p
r
o
ce
s
s
n
ee
d
to
ex
ec
u
te
th
ese
p
r
o
ce
s
s
es
s
af
ely
.
First
ch
o
o
s
in
g
th
e
p
e
r
f
ec
t
p
o
in
t
to
d
ig
i
n
it
th
at
will
b
e
th
e
s
o
u
r
ce
o
f
ex
tr
ac
tio
n
also
th
e
y
u
s
e
a
p
ac
if
i
c
ex
p
lo
s
io
n
a
n
d
h
az
ar
d
m
ater
ial
s
f
o
r
t
h
e
p
r
o
ce
s
s
o
f
d
ig
g
in
g
.
I
t
’
s
s
o
im
p
o
r
tan
t
to
b
e
ca
r
ef
u
l
i
n
th
e
lo
ca
tio
n
o
f
th
e
d
ig
g
in
g
p
o
i
n
t
also
th
er
e
’
r
e
a
lo
t
o
f
g
ia
n
t
eq
u
ip
m
en
t’
s
th
at
n
ee
d
a
h
u
g
e
s
p
ac
e
to
p
u
t
i
t
in
.
No
t
o
n
ly
eq
u
ip
m
en
t
th
at
im
p
o
r
tan
t
b
u
t
also
a
lo
t
o
f
wo
r
k
er
s
f
r
o
m
d
if
f
er
en
t
d
eg
r
ee
s
a
r
e
n
ee
d
ed
to
m
ak
e
w
o
r
k
co
n
tin
u
e.
Seco
n
d
ly
th
e
e
x
tr
a
ctio
n
af
ter
d
ig
g
in
g
n
ee
d
a
p
r
ec
is
e
wo
r
k
is
s
o
im
p
o
r
tan
t
i
n
th
at
s
tag
e
as
ex
p
lo
s
io
n
m
ay
h
ap
p
en
d
u
r
in
g
th
is
p
r
o
ce
s
s
.
A
lo
t
o
f
Pet
r
o
leu
m
cy
lin
d
e
r
s
ar
e
n
ee
d
e
d
to
s
to
r
e
th
e
ex
tr
ac
tio
n
o
il
s
af
ely
t
h
ese
Petr
o
leu
m
cy
lin
d
er
s
ar
e
d
esig
n
ed
in
a
h
ig
h
p
r
ec
is
way
to
b
e
s
a
v
e
f
o
r
s
to
r
in
g
s
u
c
h
as
k
in
d
o
f
m
ater
ials
th
at
th
ese
Petr
o
leu
m
cy
lin
d
er
s
m
a
d
e
with
it
also
th
e
ty
p
e
o
f
p
ain
tin
g
m
ater
ials
th
at
u
s
ed
i
n
th
is
Petr
o
le
u
m
cy
lin
d
er
s
also
t
h
ey
d
esig
n
ed
with
s
p
ec
if
ic
s
izes
to
b
e
f
i
t
f
o
r
s
to
r
in
g
,
tr
an
s
p
o
r
tin
g
a
n
d
m
o
r
e
s
af
ely
f
o
r
all
s
id
es.
T
h
ir
d
ly
t
h
e
tr
an
s
p
o
r
tatio
n
p
r
o
ce
s
s
es
n
ee
d
s
p
ec
if
ic
v
eh
icles
to
ca
r
r
y
all
o
f
th
ese
Petr
o
leu
m
cy
lin
d
er
s
o
r
Oil d
r
u
m
s
s
af
ely
to
th
e
p
ar
ticip
ato
r
s
o
f
th
e
p
etr
o
le
u
m
m
ater
ials
.
T
r
an
s
p
o
r
tatio
n
v
e
h
icles
ar
e
d
if
f
er
en
t
in
o
n
s
h
o
r
e
an
d
o
f
f
s
h
o
r
e
lo
ca
tio
n
s
.
Du
r
in
g
th
e
p
r
o
ce
s
s
o
f
tr
an
s
p
o
r
tatio
n
a
lo
t
o
f
p
r
o
b
le
m
s
th
at
ca
n
h
ap
p
en
b
etwe
en
th
e
lo
ca
tio
n
o
f
th
e
ex
tr
ac
tio
n
t
o
th
e
lo
ca
tio
n
o
f
s
ellin
g
it
f
o
r
o
r
d
in
a
r
y
p
eo
p
le.
Fin
ally
,
th
e
t
r
an
s
p
o
r
tatio
n
o
f
a
ll
wo
r
k
er
s
i
n
lo
ca
ti
o
n
s
with
all
d
eg
r
ee
s
th
a
t
r
etu
r
n
to
th
e
p
lace
th
ey
will
tr
an
s
m
it
to
if
it
at
t
h
e
wate
r
th
at
s
o
m
etim
es
n
ee
d
a
p
lan
e
o
r
b
o
ats
to
tr
an
s
f
er
th
em
to
th
e
lo
ca
tio
n
o
f
d
ig
g
in
g
,
ac
co
r
d
in
g
to
lo
ca
tio
n
s
o
n
la
n
d
s
it n
ee
d
a
d
if
f
er
e
n
t ty
p
e
o
f
ca
r
s
.
c)
Ho
w
p
r
o
b
lem
s
an
d
ac
cid
e
n
ts
af
f
ec
t
o
u
r
life
g
e
n
er
ally
an
d
ec
o
n
o
m
ic
s
p
ec
ially
:
As
m
en
ti
o
n
ed
b
ef
o
r
e
o
i
l
h
as
an
im
p
o
r
tan
t
r
o
le
T
h
e
r
e
n
aiss
an
ce
o
f
th
e
co
u
n
tr
y
o
r
T
h
e
f
all
o
f
th
e
co
u
n
tr
y
,
th
en
o
cc
u
r
r
in
g
an
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
1
,
Ap
r
il
2
0
2
1
:
5
8
0
-
5
8
9
582
p
r
o
b
lem
in
t
h
is
f
ield
will
ca
u
s
e
a
lo
t
o
f
lo
s
s
es
o
r
th
e
co
u
n
tr
y
th
at
f
ac
e
s
u
ch
a
p
r
o
b
lem
.
Sp
il
lin
g
ac
cid
en
ts
ca
n
h
ap
p
en
d
u
r
i
n
g
a
n
y
f
ac
e
o
f
t
h
e
o
il
ex
tr
ac
tio
n
an
d
tr
a
n
s
p
o
r
tatio
n
an
d
th
ese
p
r
o
b
le
m
s
will
af
f
ec
t
in
co
u
n
tr
y
g
en
er
ally
a
n
d
in
th
e
co
m
p
an
y
s
p
ec
if
ically
.
I
n
[
1
8
-
2
0
]
Acc
o
r
d
in
g
to
th
e
ef
f
ec
ts
o
n
co
u
n
tr
y
,
lo
s
in
g
a
m
ass
iv
e
am
o
u
n
t
o
f
o
il
will
lead
o
r
a
d
ef
icit
i
n
th
e
u
s
e
an
d
e
x
p
o
r
t,
wh
ic
h
lea
d
s
to
th
e
d
eter
io
r
atio
n
o
f
th
e
ec
o
n
o
m
y
,
wh
ich
in
tu
r
n
af
f
ec
ts
th
e
s
tat
e
an
d
welf
ar
e
o
f
t
h
e
co
u
n
tr
y
.
Acc
o
r
d
in
g
to
th
e
ef
f
ec
ts
o
n
c
o
m
p
an
y
a
lo
t
o
f
m
a
n
y
will
lo
s
e
b
ec
au
s
e
o
f
th
e
lo
s
in
g
am
o
u
n
t
f
ir
s
t
th
at
s
er
v
e
a
lo
t
o
f
m
an
y
also
s
p
illi
n
g
in
an
y
lo
ca
tio
n
ca
n
’
t
leav
e
it
an
d
g
o
th
er
e’
r
e
d
if
f
icu
lt
p
r
o
ce
d
u
r
es
to
h
a
n
d
le
it,
p
eo
p
l
e
o
f
th
e
cr
ash
ed
p
lace
will
g
iv
e
th
em
a
lo
t
o
f
m
o
n
ey
to
m
a
k
e
u
p
f
o
r
t
h
em
.
Sp
illi
n
g
also
will
n
ee
d
a
lo
t
o
f
wo
r
k
er
s
an
d
en
g
in
ee
r
s
to
h
an
d
le
th
is
p
r
o
b
lem
a
n
d
it’s
a
co
n
s
u
m
p
tio
n
o
f
co
m
p
an
y
r
eso
u
r
c
e
s
an
d
wastin
g
a
lo
t
o
f
tim
e
also
o
th
er
eq
u
ip
m
en
t
will
b
e
u
s
ed
to
tr
ea
t
th
at
p
r
o
b
lem
.
Af
ter
ac
cid
e
n
t
o
f
s
p
illi
n
g
n
o
t
o
n
ly
co
m
p
an
y
will
lo
s
e
th
eir
r
eso
u
r
ce
s
an
d
tim
e
b
u
t
also
an
o
t
h
er
p
r
o
b
lem
will
d
is
p
lay
s
u
ch
as
t
h
e
p
r
o
b
lem
o
f
T
h
e
b
ad
s
m
ell
o
f
p
etr
o
le
u
m
a
n
d
h
ar
d
b
r
ea
th
in
g
as
air
will
p
o
llu
te
an
d
af
f
ec
t
in
all
liv
es
ar
o
u
n
d
th
is
ar
ea
also
all
b
ir
d
s
will
b
e
af
f
ec
ted
an
d
a
lo
t
o
f
th
em
d
ie
f
r
o
m
th
i
s
ac
cid
en
t
an
d
in
o
f
f
s
h
o
r
e
lo
c
atio
n
s
n
o
t
o
n
ly
b
ir
d
s
o
r
h
u
m
a
n
will
af
f
ec
t,
b
u
t
also
th
e
Aq
u
atic
life
will
f
ac
e
a
b
ig
p
r
o
b
lem
as
all
f
is
h
es
an
d
o
th
e
r
Sea
cr
ea
tu
r
es
will
b
e
d
ea
d
in
th
e
s
am
e
m
o
m
en
t
o
f
d
r
in
k
o
r
s
m
ell
it.
I
n
ad
d
itio
n
to
all
o
f
th
ese
p
r
o
b
lem
s
th
er
e’
s
a
p
r
o
b
lem
o
f
clim
ate
c
h
an
g
e
.
d)
Ho
w
to
f
ix
an
d
tr
ea
t
with
th
is
p
r
o
b
lem
s
:
Fix
in
g
o
il
s
p
ill
ac
cid
en
ts
as
m
en
tio
n
ed
b
ef
o
r
e
will
tak
e
a
lo
t
o
f
tim
e,
wo
r
k
in
g
,
em
p
lo
y
m
e
n
ts
in
d
if
f
er
e
n
t
d
e
g
r
ee
s
,
an
d
a
l
o
t
o
f
m
o
n
ey
s
o
in
t
h
at
ca
s
e
f
i
x
in
g
a
g
o
o
d
s
o
lu
tio
n
af
ter
s
p
illi
n
g
b
u
t
t
h
er
e’
s
a
b
etter
s
o
lu
tio
n
f
o
r
th
at
s
u
ch
as
p
r
ev
e
n
tin
g
s
u
ch
a
p
r
o
b
lem
lik
e
th
at
an
d
th
at
wh
at
th
e
r
esear
c
h
a
b
o
u
t.
Fo
r
p
r
ev
en
tin
g
th
at
p
r
o
b
lem
f
r
o
m
h
ap
p
e
n
in
g
a
d
et
ailed
s
tu
d
y
o
f
r
ea
s
o
n
s
will
h
ap
p
e
n
an
d
a
lo
t
o
f
s
af
ety
m
ea
s
u
r
es
will
tak
e
i
n
all
lo
ca
tio
n
s
o
f
t
h
e
p
et
r
o
l
w
h
en
ev
er
in
th
e
lo
ca
tio
n
o
f
th
e
d
ig
g
in
g
o
r
d
u
r
i
n
g
th
e
tr
an
s
p
o
r
tatio
n
p
r
o
ce
s
s
an
d
a
lo
t o
f
in
s
t
r
u
ctio
n
s
will b
e
teac
h
es to
all
wo
r
k
f
o
r
ce
o
f
th
e
all
lo
ca
tio
n
.
A
p
o
wer
f
u
l
to
o
l
is
n
ec
ess
ar
y
f
o
r
th
is
s
tu
d
y
to
p
r
ev
en
t
th
e
p
r
o
b
lem
o
f
ac
cid
en
t
[
2
1
,
2
2
]
.
e)
Kn
o
win
g
s
o
m
e
o
f
th
e
ac
cid
e
n
ts
an
d
t
h
e
co
u
n
tr
ies
th
at
af
f
e
ct
an
d
f
ac
e
a
lo
t
o
f
l
o
s
in
g
b
e
ca
u
s
e
o
f
t
h
ese
p
r
o
b
lem
s
:
th
er
e’
r
e
a
lo
t
o
f
c
o
u
n
tr
ies
th
at
f
ac
e
a
lo
t
o
f
p
r
o
b
lem
s
b
ec
au
s
e
o
f
s
p
ill
ac
cid
en
t.
T
ab
le
1
an
d
2
d
is
p
lay
th
e
to
p
te
n
ac
cid
en
ts
i
n
b
o
th
U
n
ited
States
an
d
th
e
w
o
r
ld
.
T
ab
le
1
.
T
o
p
ten
o
il sp
ill ac
cid
en
ts
in
th
e
Un
ited
States
R
a
n
k
D
a
t
e
C
a
u
se
S
o
u
r
c
e
Lo
c
a
t
i
o
n
S
p
i
l
l
V
o
l
u
m
e
1)
2
0
A
p
r
i
l
2
0
1
0
O
u
t
b
r
e
a
k
D
e
e
p
w
a
t
e
r
H
o
r
i
z
o
n
D
r
i
l
l
i
n
g
G
u
l
f
o
f
M
e
x
i
c
o
,
5
0
mi
l
e
s
f
r
o
m
t
h
e
L
o
u
i
s
i
a
n
a
c
o
a
st
A
n
a
d
d
i
t
i
o
n
a
l
2
0
0
,
0
0
0
l
i
t
e
r
s
p
e
r
d
a
y
2)
2
4
M
a
r
c
h
1
9
8
9
C
o
l
l
i
si
o
n
w
i
t
h
c
o
r
a
l
Ex
x
o
n
V
a
l
d
e
z
p
e
t
r
o
l
t
a
n
k
e
r
S
o
u
n
d
f
r
o
m
P
r
i
n
c
e
W
i
l
l
i
a
m,
A
l
a
s
k
a
M
o
r
e
t
h
a
n
1
0
m
i
l
l
i
o
n
G
a
l
l
o
n
s
3)
1
5
D
e
c
1
9
7
6
r
a
n
a
g
r
o
u
n
d
t
a
n
k
e
r
A
r
g
o
M
e
r
c
h
a
n
t
N
a
n
t
u
c
k
e
t
I
sl
a
n
d
7
.
7
M
i
l
l
i
o
n
Lb
s
.
4)
A
u
g
–
S
e
p
t
.
2
0
0
5
-
2
0
0
5
H
u
r
r
i
c
a
n
e
K
a
t
r
i
n
a
v
a
r
i
o
u
s s
o
u
r
c
e
s
N
e
w
O
r
l
e
a
n
s,
La
.
7
m
i
l
l
i
o
n
L
b
s
5)
8
J
u
n
e
1
9
9
0
O
u
t
b
r
e
a
k
M
e
g
a
-
B
o
r
g
t
a
n
k
e
r
G
a
l
v
e
st
o
n
,
T
e
x
a
s
6
0
mi
l
e
s
5
.
1
m
i
l
l
i
o
n
L
b
s
6)
2
8
N
o
v
2
0
0
0
r
a
n
a
g
r
o
u
n
d
t
a
n
k
e
r
W
e
s
t
c
h
e
s
t
e
r
P
o
r
t
S
u
l
p
h
u
r
,
La
.
5
6
7
,
0
0
0
L
b
s
7)
2
3
Ja
n
2
0
1
0
C
o
l
l
a
p
s
e
O
t
o
m
e
E
a
g
l
e
Ta
n
k
e
r
H
a
r
b
o
r
A
r
t
h
u
r
,
Te
x
a
s
4
6
2
,
0
0
0
L
b
s
8)
2
5
Ju
l
y
2
0
0
8
C
o
l
l
a
p
s
e
u
n
n
a
me
d
b
a
r
g
e
N
e
w
O
r
l
e
a
n
s,
La
.
4
1
9
,
0
0
0
L
b
s
9)
7
D
e
c
2
0
0
4
W
a
s
r
u
n
n
i
n
g
a
g
r
o
u
n
d
M
/
V
A
y
u
S
e
l
e
n
d
a
n
g
.
I
l
e
s Ale
u
t
i
a
n
s,
A
l
a
s
k
a
3
3
7
,
0
0
0
L
b
s
10)
1
0
A
u
g
1
9
9
3
c
o
l
l
i
si
o
n
b
a
r
g
e
B
o
u
c
h
a
r
d
B
1
5
5
Ta
mp
a
B
a
y
,
F
l
a
.
3
3
6
,
0
0
0
L
b
s
T
ab
le
2
.
T
o
p
ten
o
il s
p
ill
ac
cid
en
ts
in
th
e
wo
r
ld
[
1
]
No
A
c
c
i
d
e
n
t
Y
e
a
r
D
a
y
a
n
d
M
o
n
t
h
S
h
i
p
/
I
n
c
i
d
e
n
t
A
c
c
i
d
e
n
t
C
o
u
n
t
r
y
A
c
c
i
d
e
n
t
L
o
c
a
t
i
o
n
To
n
s
(×
10
3
)
1)
1
9
9
1
2
6
/
1
Th
e
C
o
n
f
l
i
c
t
i
n
t
h
e
G
u
l
f
K
u
w
a
i
t
Th
e
i
s
l
a
n
d
o
f
t
h
e
s
e
a
8
0
0
2)
2
0
1
0
2
0
/
4
D
e
e
p
S
e
a
H
o
r
i
z
o
n
U
n
i
t
e
d
S
t
a
t
e
s
M
e
x
i
c
o
g
u
l
f
5
0
0
3)
1
9
7
9
5
/
6
B
l
o
w
O
u
t
I
X
TO
C
M
e
x
i
c
o
M
e
x
i
c
o
g
u
l
f
4
7
0
4)
1
9
7
9
1
9
/
7
A
t
l
a
n
t
i
c
I
mp
e
r
i
a
l
i
s
t
/
C
a
p
t
a
i
n
A
e
g
e
a
n
O
f
f
To
b
a
g
o
Th
e
C
a
r
i
b
b
e
a
n
2
8
7
5)
1
9
9
2
2
/
3
B
l
o
w
o
u
t
O
i
l
w
e
l
l
U
z
b
e
k
i
st
a
n
Th
e
V
a
l
l
e
y
o
f
F
e
r
g
a
n
a
2
8
5
6)
1
9
9
3
4
/
2
B
l
o
w
-
o
u
t
o
n
t
h
e
o
i
l
p
l
a
t
f
o
r
m
I
r
a
n
N
o
w
r
u
z
sec
t
o
r
2
7
0
7)
1
9
8
3
6
/
8
B
e
l
l
v
e
r
C
a
s
t
l
e
S
o
u
t
h
A
f
r
i
c
a
B
a
y
o
f
S
a
l
d
a
n
h
a
2
6
0
8)
1
9
9
1
2
8
/
5
A
B
T
S
u
mm
e
r
O
f
f
A
n
g
o
l
a
Th
e
A
t
l
a
n
t
i
c
2
6
0
9)
1
9
7
8
1
6
/
3
C
d
i
z
A
m
o
c
o
F
r
a
n
c
e
B
r
i
t
t
a
n
y
2
2
3
10)
1
9
9
1
1
1
/
4
A
v
e
n
u
e
I
TA
L
I
A
G
e
n
o
a
-
G
e
n
e
v
a
1
4
4
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
s
u
r
ve
y
o
n
p
r
ed
ictin
g
o
il sp
ills
b
y
s
tu
d
yin
g
its
ca
u
s
e
s
u
s
in
g
d
ee
p
lea
r
n
in
g
…
(
Mo
n
a
Mo
h
a
med
N
a
s
r
)
583
Af
etr
d
is
cu
s
s
in
g
all
b
e
n
ef
its
a
n
d
im
p
o
r
tan
ce
o
f
ex
is
r
ac
e
p
etr
o
l
in
o
u
r
life
a
n
d
k
n
o
wig
r
is
k
s
o
f
lo
s
in
g
th
at
wea
lth
,
it’s
s
o
im
p
o
r
tan
t
t
o
p
lan
f
o
r
s
ec
u
r
ity
o
f
t
h
at
f
iel
d
as
m
a
n
y
r
esear
ch
f
o
c
u
s
in
th
at
p
o
i
n
t
s
u
ch
as
i
n
[2
3
]
th
at
th
e
s
tr
aig
h
t
ex
is
tin
g
in
d
u
ctio
n
m
eth
o
d
was
d
is
co
v
e
r
ed
to
b
e
s
af
e
f
o
r
th
e
im
p
r
es
s
ed
cu
r
r
en
t
ca
th
o
d
ic
p
r
o
tectio
n
(
I
C
C
P
)
d
ev
ice
an
d
o
u
td
o
o
r
ar
ea
.
I
n
[2
4
]
th
e
ce
n
t
er
o
f
t
h
e
p
ip
e
n
ee
d
ca
n
b
e
ev
alu
ated
at
Al
-
Qu
d
s
p
etr
o
l
lo
ca
tio
n
in
B
ag
h
d
a
d
.
N
o
n
eth
eless
,
s
u
s
tain
in
g
th
is
is
a
lm
o
s
t
to
u
g
h
.
T
h
in
k
o
f
th
e
Al
-
Qu
d
s
p
etr
o
l
lo
ca
tio
n
an
aly
s
is
f
o
r
ex
am
p
le
,
th
e
len
g
th
o
f
th
e
p
ip
e
is
6
0
0
0
m
eter
s
s
o
,
if
th
e
o
u
tco
m
es
o
f
th
e
ANSYS
ar
e
ac
ce
p
ted
,
th
e
cr
itical
an
o
d
es a
r
e
t
o
b
e
in
h
u
m
ed
at
2
0
0
0
m
eter
s
f
r
o
m
th
e
p
ip
e.
Dr
illi
n
g
f
o
r
ex
tr
ac
tio
n
p
etr
o
l
is
an
im
o
r
tan
t
p
h
ase
o
f
th
a
t
f
ield
an
d
it’s
ess
esn
tial
to
m
ak
e
th
at
o
p
er
atio
n
s
af
e
an
d
o
r
g
an
ized
.
As
d
is
cu
s
s
ed
in
[
2
5
]
,
in
o
r
d
er
to
cr
ea
te
s
af
e
an
d
o
p
e
r
atio
n
al
d
ig
g
in
g
an
ad
d
itio
n
al
s
tar
ch
f
r
o
m
w
h
ea
t
f
lo
u
r
h
as
b
ee
n
r
em
o
v
ed
an
d
p
er
f
o
r
m
ed
as
a
liq
u
id
in
s
u
f
f
icien
cy
m
o
n
ito
r
in
g
o
p
er
ato
r
an
d
s
h
o
wed
th
at
th
e
ef
f
ec
tiv
en
ess
o
f
s
tar
ch
f
r
o
m
wh
ea
t
f
lo
u
r
is
in
cr
ea
s
in
g
in
r
h
eo
lo
g
ical
ch
ar
ac
ter
is
tics
as
co
n
tr
asted
to
s
tar
ch
m
o
s
tly
o
n
f
lea
m
ar
k
e
t
b
y
u
s
in
g
m
atch
in
g
a
n
d
d
if
f
e
r
en
t
am
o
u
n
ts
f
r
o
m
b
o
th
.
I
n
[
2
6
]
k
ee
p
in
g
o
u
r
h
o
u
s
eh
o
l
d
co
n
f
ir
m
ed
f
r
o
m
an
y
ty
p
e
o
f
th
r
ea
t,
a
r
ec
o
m
m
en
d
e
d
ef
f
o
r
t
is
u
s
ed
to
id
en
tify
g
as
s
p
ill
o
v
er
a
g
as
r
ad
ar
an
d
to
d
ete
r
m
in
e
th
e
wei
g
h
t
o
f
th
e
cy
lin
d
er
o
v
e
r
th
e
c
ap
ac
ity
o
f
th
e
ce
lls
.
T
h
e
ac
tu
al
p
er
io
d
in
f
o
r
m
atio
n
an
d
d
ata
will
b
e
k
ep
t
i
n
th
e
clo
u
d
f
o
r
m
o
r
e
u
s
e
in
th
e
co
m
in
g
ev
id
en
ce
.
I
t
is
also
n
ec
ess
ar
y
to
ac
k
n
o
wled
g
e
th
e
q
u
a
n
tity
o
f
g
as
o
b
tain
a
b
le
b
y
weig
h
t
o
f
th
e
cy
lin
d
er
an
d
d
u
e
to
tim
e
o
f
alter
atio
n
o
f
d
if
f
e
r
en
t
tu
b
e.
I
n
[
2
7
]
an
r
e
p
lace
m
en
t
m
eth
o
d
o
lo
g
y
h
as
ex
is
tin
g
to
ev
o
l
v
in
g
a
d
ev
ice
th
at
ca
n
au
to
m
atica
lly
d
is
co
v
er
an
d
tr
ac
k
in
g
g
as
s
p
ills
an
d
also
o
b
s
er
v
e
th
e
h
ea
t
a
n
d
e
v
id
en
ce
d
th
at
th
is
m
ac
h
in
e
m
ea
n
in
g
f
u
lly
r
is
in
g
o
f
th
e
p
o
s
s
ib
ilit
ies an
d
ef
f
ec
tiv
en
ess
o
f
r
ejec
tin
g
g
as sp
illi
n
g
.
I
n
[
2
8
]
a
n
o
th
er
ex
p
e
r
im
en
ts
to
d
is
co
v
er
g
as
s
p
illi
n
g
u
s
in
g
a
d
ev
ice
th
at
ca
n
u
s
e
Sen
s
o
r
Mq
-
2
to
s
p
ill
s
o
u
n
d
g
as
co
n
s
ter
n
ati
o
n
b
y
Mo
d
u
l I
SD
1
7
6
0
,
an
d
b
y
u
s
in
g
a
s
o
len
o
id
v
alv
e
to
p
r
ev
e
n
t
g
as f
r
o
m
m
o
v
i
n
g
f
r
o
m
th
e
p
ip
e
to
th
e
b
o
n
f
i
r
e.
T
h
e
r
e
is
also
th
e
h
ar
d
war
e
o
f
a
to
r
ch
r
ad
ar
t
o
d
is
co
v
e
r
a
co
m
b
u
s
tio
n
if
th
er
e
is
a
n
ew
s
p
ar
k
an
d
d
is
p
er
s
in
g
wate
r
in
to
th
e
m
ac
u
la
th
at
is
ex
p
ec
ted
to
s
p
a
r
k
f
ir
e
.
W
h
en
u
s
in
g
AT
Me
g
a
3
2
8
m
icr
o
co
n
tr
o
ller
.
O
b
s
er
v
in
g
ca
n
u
s
e
an
d
r
o
id
s
m
ar
tp
h
o
n
e
,
all
h
a
r
d
war
e
will
b
e
in
,
with
th
e
ap
p
licatio
n
th
at
ca
n
g
iv
e
th
e
m
o
b
ile
p
h
o
n
e
a
q
u
ick
an
d
d
ir
ec
t c
au
tio
n
.
2
.
1
.
O
ns
ho
re
o
il
s
pil
ls
(
la
n
d
s
pil
l
s
)
Sp
ills
in
lan
d
co
n
s
id
er
a
b
ig
d
is
aster
s
a
s
it
h
ar
m
s
th
e
g
r
o
u
n
d
f
ir
s
t
as
cities
an
d
to
wn
s
al
s
o
it
h
ar
m
s
th
e
ag
r
icu
ltu
r
e
th
e
n
it
h
ar
m
s
h
u
m
an
th
at
liv
e
in
to
th
ese
p
lac
es
o
r
n
ea
r
to
th
em
s
o
it’s
s
o
im
p
o
r
tan
t
to
r
ec
o
v
er
th
ese
s
p
ills
in
th
e
s
am
e
m
o
m
en
t
th
e
y
h
ap
p
e
n
ed
Sp
ill
r
esp
o
n
s
e
ap
p
r
o
ac
h
es,
f
o
r
ex
am
p
le
in
u
r
b
an
en
v
ir
o
n
m
en
ts
,
p
u
t
p
r
im
ar
y
im
p
o
r
tan
ce
o
n
p
r
o
tectin
g
h
u
m
an
h
ea
lth
an
d
r
esto
r
in
g
ac
ce
s
s
ib
i
lity
at
th
e
s
p
ill
s
ite
as
q
u
ick
ly
as
p
o
s
s
ib
le.
Sin
ce
th
e
"in
d
u
s
t
r
ial"
f
lag
m
ay
i
n
clu
d
e
ev
er
y
th
i
n
g
f
r
o
m
m
ar
k
ed
r
o
ad
s
to
ju
n
g
les
an
d
p
ar
k
s
,
th
e
ex
ac
t
r
esp
o
n
s
e
n
ee
d
s
to
b
e
d
etailed
to
th
e
af
f
ec
ted
en
v
ir
o
n
m
en
t.
Sin
ce
s
p
illed
o
il
o
n
lan
d
p
r
ev
e
n
ts
wate
r
f
r
o
m
b
ein
g
co
m
p
letely
f
illed
with
s
o
il
t
h
at
wo
u
ld
k
ill
an
y
life
i
n
th
e
w
ater
an
d
o
u
t
o
f
th
e
wate
r
,
s
p
ills
o
n
ag
r
icu
ltu
r
al
s
ites
o
r
g
r
ass
lan
d
s
h
av
e
th
e
ef
f
ec
t
o
f
ch
o
k
in
g
o
f
f
p
lan
t
life
.
I
f
a
s
p
ill
o
cc
u
r
s
in
th
ese
en
v
ir
o
n
m
en
ts
,
th
e
h
ig
h
est
p
r
i
m
ac
ies
o
f
t
h
e
r
ea
ctio
n
a
r
e
to
av
o
id
lea
k
ag
e
o
f
o
il
in
t
o
g
r
o
u
n
d
wate
r
o
r
t
o
en
te
r
wate
r
wa
y
s
as a
r
u
n
-
o
f
f
,
an
d
to
r
etu
r
n
t
h
e
s
o
il a
s
q
u
ick
ly
as p
o
s
s
ib
le
f
o
r
p
r
o
d
u
ctio
n
.
I
n
[
2
9
]
a
b
lu
r
r
ed
n
eu
r
al
n
etwo
r
k
m
o
d
el
b
ased
o
n
f
ailu
r
e
tr
ee
an
d
b
lu
r
r
ed
n
u
m
b
e
r
co
m
p
u
tin
g
h
as b
ee
n
d
ev
elo
p
e
d
to
p
r
e
d
ict
th
e
p
o
s
s
ib
ilit
y
o
f
f
ailu
r
e
o
f
o
il
/g
as
p
ip
elin
es
an
d
a
p
r
ed
ictio
n
m
o
d
el
b
ased
o
n
th
e
MA
T
L
AB
n
eu
r
al
n
etwo
r
k
to
o
lb
o
x
u
s
ed
to
m
ea
s
u
r
e
th
e
p
o
s
s
ib
ilit
y
o
f
f
ailu
r
e
o
f
th
e
f
ilter
ed
o
il
p
ip
elin
e
L
an
zh
o
u
-
C
h
en
g
d
u
-
C
h
o
n
g
q
in
g
.
I
t
ca
n
b
e
f
o
u
n
d
th
at
th
e
co
n
s
eq
u
en
ce
s
o
f
th
e
an
al
y
s
is
ar
e
f
o
u
n
d
to
b
e
m
o
s
tly
co
n
s
is
ten
t
with
th
e
co
n
s
eq
u
en
ce
s
th
at
wer
e
b
ased
o
n
p
r
ev
io
u
s
f
au
lt
d
ata;
th
er
ef
o
r
e
th
e
ac
c
u
r
ac
y
an
d
ac
cu
r
ac
y
o
f
th
e
FNN
m
o
d
el
ca
n
b
e
co
n
f
ir
m
ed
.
T
h
e
ac
cu
r
ac
y
o
f
th
e
FNN
is
r
elate
d
to
a
n
u
m
b
er
o
f
f
u
n
ctio
n
s
.
T
h
er
e
is
s
till
a
lo
t
o
f
co
m
in
g
r
esear
ch
wo
r
k
to
d
o
,
in
clu
d
in
g
m
o
d
el
s
ta
g
es,
T
h
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
,
th
e
s
elec
tio
n
o
f
tr
an
s
m
is
s
io
n
f
u
n
ctio
n
s
an
d
t
h
e
tr
ain
in
g
o
f
er
r
o
r
v
alu
e
a
n
d
p
r
i
ce
,
o
r
ev
e
n
th
e
s
elec
tio
n
o
f
p
r
ep
ar
atio
n
s
am
p
les,
will
h
a
v
e
a
m
ajo
r
im
p
ac
t
o
n
th
e
ac
cu
r
ac
y
o
f
p
r
ed
ictin
g
r
esu
lts
,
b
u
t
th
e
s
elec
t
io
n
o
f
ap
p
r
o
p
r
iate
m
o
d
el
p
ar
am
eter
s
s
h
o
u
ld
b
e
f
u
r
th
er
s
tu
d
ied
.
In
[
30
]
in
th
is
r
esear
ch
p
a
p
er
m
in
in
g
tech
n
iq
u
es
wer
e
u
s
ed
to
an
aly
s
is
th
e
to
p
r
e
aso
n
s
th
at
r
esp
o
n
s
ib
le
f
o
r
u
n
d
er
g
r
o
u
n
d
an
d
s
u
r
f
ac
e
ac
cid
en
ts
in
Sp
ai
n
u
s
in
g
s
o
f
twar
e
wek
a.
Data
f
r
o
m
th
e
Sp
a
n
is
h
Min
is
tr
y
o
f
J
o
b
s
an
d
So
cial
Secu
r
ity
was
u
s
ed
b
etwe
en
2
0
0
5
an
d
2
0
1
5
.
R
esu
lts
s
h
o
wed
th
at
th
e
m
o
s
t
s
ig
n
if
ican
t
im
m
ed
iate
ca
u
s
e
is
p
h
y
s
ical
ex
er
tio
n
o
r
o
v
er
e
x
er
tio
n
o
f
b
o
d
y
m
o
v
em
en
t.
T
h
is
p
ap
er
u
s
ed
a
p
o
o
r
p
r
o
g
r
a
m
lik
e
wek
a
with
s
m
all
d
ata
as
we
k
a
is
u
n
ab
le
t
o
p
r
o
ce
s
s
lar
g
e
d
at
a
a
n
d
p
r
o
d
u
ce
m
em
o
r
y
m
ess
ag
es
in
lar
g
e
d
atab
ases
.
An
ev
o
lu
tio
n
o
f
f
ilm
s
b
y
g
as
s
tag
e
ep
itax
y
h
as
b
ee
n
in
v
esti
g
ated
in
[
31
]
.
E
s
tab
lis
h
ed
b
y
th
e
s
tu
d
y
,
th
ey
ex
p
r
ess
cir
cu
m
s
tan
ce
s
f
o
r
en
h
an
cin
g
th
e
s
im
ilar
ity
o
f
th
e
b
elo
n
g
in
g
s
o
f
t
h
e
f
ilm
s
g
ain
ed
.
Fo
r
s
tu
d
y
p
r
o
ce
d
u
r
es,
a
s
y
s
tem
atic
m
et
h
o
d
o
lo
g
y
o
f
f
er
ed
g
as
s
tag
e
ep
itax
y
s
tr
u
ctu
r
e
with
ex
p
ec
ted
ex
p
la
n
atio
n
o
f
co
n
v
ec
tio
n
,
an
d
th
e
lik
elih
o
o
d
o
f
v
ar
y
in
g
t
h
e
b
io
l
o
g
ical
co
m
m
u
n
icatio
n
r
atio
b
etwe
en
r
ea
g
en
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
1
,
Ap
r
il
2
0
2
1
:
5
8
0
-
5
8
9
584
2
.
2
.
O
f
f
s
ho
re
o
il
s
pil
ls
(
wa
t
er
s
pil
ls
)
T
h
e
s
p
r
ea
d
in
g
o
f
wate
r
is
u
s
u
ally
f
ix
ed
t
h
r
o
u
g
h
u
n
d
e
r
g
r
o
u
n
d
tu
b
es.
I
t
is
im
p
o
r
tan
t
t
o
o
b
s
er
v
e
th
e
u
n
d
er
g
r
o
u
n
d
wate
r
tu
b
es
th
an
to
o
b
s
er
v
e
th
e
o
p
e
n
s
p
o
t
wate
r
tu
b
es
lo
ca
ted
o
n
t
h
e
g
r
o
u
n
d
.
T
h
is
co
n
d
itio
n
ca
n
ca
u
s
e
co
n
tin
u
ed
h
a
r
m
if
a
p
r
o
b
lem
s
u
ch
as sp
illi
n
g
h
ap
p
en
s
in
th
e
t
u
b
e.
T
u
b
e
s
p
ills
ca
n
b
e
p
r
o
d
u
ce
d
f
o
r
m
an
y
r
ea
s
o
n
s
,
s
u
ch
as th
e
ag
e
o
f
th
e
tu
b
e,
th
e
i
n
co
r
r
ec
t stru
ct
u
r
e
a
n
d
th
e
n
atu
r
al
ca
tast
r
o
p
h
e
[
3
2
]
.
Sp
ills
th
at
h
ap
p
en
ed
in
th
e
wate
r
wh
eth
er
o
ce
an
s
o
r
o
n
th
e
s
ea
o
r
o
n
th
e
lak
es
ar
e
s
o
im
p
o
r
tan
t
to
d
is
cu
s
s
as
h
er
e
it
e
f
f
ec
ts
o
n
h
u
m
an
life
,
air
an
d
wea
th
er
in
n
ea
r
ly
p
lace
s
,
wate
r
,
a
n
d
cr
ea
t
u
r
es
in
t
h
e
s
ea
also
,
it
ef
f
ec
ts
o
n
th
e
b
ir
d
s
th
at
tr
y
to
d
r
in
k
o
r
to
u
ch
th
ese
s
p
ills
.
I
t
d
am
ag
es
th
e
f
is
h
in
g
wea
lth
an
d
it
will
af
f
ec
t
in
th
e
p
u
b
lic
ec
o
n
o
m
y
a
n
d
p
u
b
li
c
h
ea
lth
.
On
ce
o
il
is
leak
ed
i
n
to
th
e
o
ce
a
n
,
it
s
p
r
ea
d
s
m
o
s
tly
o
v
er
th
e
s
u
r
f
ac
e
i
n
th
e
wate
r
,
d
ep
en
d
in
g
o
n
its
r
elativ
e
d
en
s
ity
an
d
v
o
lu
m
e.
T
h
e
f
o
r
m
ed
o
il
s
lick
ca
n
p
er
s
is
t
o
r
in
ter
f
er
e
with
th
e
p
r
esen
ce
o
f
r
o
u
g
h
s
ea
s
.
W
av
es,
wate
r
cu
r
r
en
ts
an
d
win
d
ca
u
s
e
th
e
o
il
s
p
ill
t
o
f
lo
at
o
v
er
v
ast
ar
ea
s
,
af
f
ec
tin
g
th
e
o
p
en
o
ce
an
,
th
e
co
astal r
eg
io
n
s
,
an
d
m
a
r
in
e
an
d
ter
r
estria
l e
co
s
y
s
tem
s
alo
n
g
th
e
d
r
if
t c
o
u
r
s
e.
In
[3
3
]
a
p
r
ess
u
r
e
-
b
alan
ce
-
b
ased
ap
p
r
o
ac
h
was
p
r
o
p
o
s
ed
to
ca
p
tu
r
e
two
f
o
r
m
s
o
f
ac
tiv
e
cir
cle
p
r
ess
u
r
e
b
eh
av
io
r
s
in
a
g
as w
ell
with
s
u
s
tain
ed
ca
s
e
p
r
ess
u
r
e
(
SC
P
)
tr
ig
g
er
ed
b
y
th
e
p
i
p
es lea
k
ag
e
at
d
if
f
er
e
n
t
p
er
f
ec
t
d
ep
th
s
an
d
th
e
g
as
-
lift
f
au
ce
t
f
ailu
r
e
in
o
p
er
atio
n
T
h
i
s
m
eth
o
d
in
clu
d
es
m
o
d
els
r
ep
r
esen
tin
g
th
e
ef
f
ec
t
o
f
tu
b
in
g
a
n
d
an
n
u
lu
s
f
lu
id
te
m
p
er
atu
r
e
an
d
p
r
ess
u
r
e
s
p
r
ea
d
in
g
th
at
ar
e
u
s
ed
to
ass
ess
tu
b
in
g
s
p
ill
p
o
in
ts
an
d
to
test
th
e
av
er
ag
e
a
n
n
u
lu
s
p
r
ess
u
r
e
at
th
e
r
ig
u
n
d
er
d
if
f
er
e
n
t
cir
cu
m
s
tan
ce
s
.
Diag
n
o
s
is
o
f
o
f
f
s
h
o
r
e
g
as
leak
test
ed
in
th
is
r
esear
ch
.
I
n
[
3
4
]
New
m
eth
o
d
s
f
o
r
q
u
an
tif
y
i
n
g
g
eo
m
etr
ic
u
n
ce
r
tai
n
ty
wer
e
d
ev
elo
p
e
d
u
s
in
g
f
in
e
-
an
d
co
ar
s
e
-
g
r
id
m
o
d
els
i
n
th
e
lak
e'
s
m
o
u
th
alo
n
g
th
e
n
o
r
th
s
h
o
r
e
o
f
th
e
Gu
lf
o
f
M
ex
ico
.
W
e
p
r
o
p
o
s
ed
an
d
test
ed
a
n
ew
d
ata
-
d
r
iv
e
n
am
b
ig
u
ity
m
o
d
el
alo
n
g
s
id
e
a
m
u
ltip
le
m
o
d
els
in
teg
r
atio
n
a
p
p
r
o
ac
h
to
m
ea
s
u
r
e
th
is
am
b
ig
u
ity
in
a
w
o
r
k
in
g
s
en
s
e
b
y
u
s
in
g
g
e
o
m
etr
ic
u
n
c
er
tain
ty
p
r
o
ce
d
u
r
es.
T
h
e
d
ata
-
d
r
iv
en
u
n
ce
r
tain
t
y
m
o
d
el
is
d
ev
elo
p
ed
b
y
ap
p
l
y
in
g
an
alg
o
r
ith
m
f
o
r
m
ac
h
in
e
lear
n
in
g
th
at
p
r
o
v
id
es
a
p
r
io
r
i
v
alu
atio
n
o
f
th
e
ass
u
r
an
ce
p
o
i
n
t
o
f
th
e
f
o
r
ec
ast.
T
h
e
in
co
r
p
o
r
atio
n
o
f
m
u
ltip
le
m
o
d
els
g
en
er
ates
j
o
in
t
f
o
r
e
ca
s
ts
b
y
co
n
tr
asti
n
g
th
em
with
m
in
im
al
f
in
e
g
r
id
f
o
r
ec
asts
.
T
h
e
two
m
eth
o
d
o
lo
g
ies
p
r
o
v
id
e
o
b
v
io
u
s
in
f
o
r
m
atio
n
o
n
th
e
p
r
ed
ictab
le
s
ca
le
o
f
m
o
d
elin
g
er
r
o
r
s
m
ad
e
b
y
g
eo
m
etr
ic
co
n
f
u
s
io
n
in
an
ac
ce
p
tab
le
m
o
d
elin
g
p
r
o
ce
s
s
m
eth
o
d
.
I
n
[
3
5
]
a
m
u
lti
-
f
r
eq
u
e
n
cy
r
a
d
a
r
s
y
s
tem
was
u
s
ed
to
p
h
o
to
g
r
a
p
h
m
o
n
ito
r
ed
r
elea
s
es
o
f
h
az
a
r
d
o
u
s
an
d
n
o
x
io
u
s
s
u
b
s
tan
ce
(
HNS
)
ab
o
v
e
th
e
Me
d
iter
r
an
ea
n
Sea
in
Ma
y
2
0
1
5
.
T
h
e
m
ain
o
b
jectiv
e
o
f
th
is
r
esear
ch
wa
s
to
estab
lis
h
a
p
r
o
ce
d
u
r
e
f
o
r
c
o
llectin
g
ev
id
e
n
ce
o
f
illeg
al
o
ce
an
ic
co
n
tam
in
atio
n
b
y
to
x
ic
liq
u
id
m
ater
ials
u
s
in
g
air
b
o
r
n
e
r
ad
a
r
s
en
s
o
r
s
o
r
a
f
ly
in
g
r
ad
ar
s
en
s
o
r
with
an
o
th
er
m
ea
n
in
g
.
T
h
ey
v
alid
ate
r
ad
ar
im
ag
in
g
'
s
ab
ilit
y
to
d
is
co
v
er
,
d
escr
ib
e,
an
d
d
is
tin
g
u
is
h
ch
em
icals
th
at
h
av
e
b
ee
n
f
o
u
n
d
at
s
ea
.
T
h
ey
im
p
lem
en
ted
a
r
eg
u
lated
p
o
lar
izatio
n
v
ar
ian
ce
p
ar
am
eter
to
lis
t
b
o
th
th
e
ef
f
ec
ts
o
f
th
e
s
u
b
s
tan
ce
r
el
ea
s
ed
o
n
th
e
o
ce
an
s
u
r
f
ac
e
an
d
th
e
r
elativ
e
c
o
n
ce
n
tr
atio
n
o
f
th
e
m
ate
r
ial
in
th
e
s
p
ill,
wh
ich
d
em
o
n
s
tr
ates
th
at
r
ad
ar
im
a
g
in
g
m
ay
in
co
r
p
o
r
ate
k
n
o
wled
g
e
o
f
th
e
in
clu
d
ed
H
NS.
I
n
p
ar
ticu
lar
,
o
n
e
ca
n
d
is
tin
g
u
is
h
a
p
r
o
d
u
ct
t
h
at
m
ak
es
u
p
a
f
ilm
at
th
e
to
p
o
f
th
e
s
u
r
f
ac
e
o
f
th
e
s
ea
f
r
o
m
an
o
th
er
th
at
co
m
b
i
n
es
with
s
ea
wa
ter
,
in
f
o
r
m
atio
n
th
at
is
s
er
io
u
s
f
o
r
ef
f
ec
tiv
e
clea
n
u
p
p
r
o
ce
d
u
r
es.
I
n
[
3
5
]
t
h
e
n
o
r
m
alize
d
p
o
la
r
izatio
n
d
if
f
e
r
en
c
e
(
NPD
)
was
d
ev
elo
p
ed
as
a
m
etr
ic
to
d
if
f
e
r
en
tiate
p
o
llu
tan
ts
b
u
t it
is
n
o
t su
f
f
icien
t to
av
o
id
th
e
h
az
ar
d
s
o
f
th
ese
item
s
.
I
n
[
3
6
]
th
ey
f
o
u
n
d
th
e
h
y
b
r
id
-
p
o
lar
im
etr
ic
s
y
n
t
h
etic
ap
er
tu
r
e
r
ad
ar
(
SAR
)
d
ata
p
o
in
ts
o
f
o
il
o
n
th
e
s
u
r
f
ac
e
o
f
th
e
o
ce
an
an
d
b
elie
v
e
d
th
at
we
co
u
ld
d
esig
n
a
s
y
s
tem
ca
p
ab
le
o
f
d
is
tin
g
u
is
h
in
g
b
etwe
en
m
in
er
al
o
il,
p
lan
t
o
il,
an
d
clea
n
wate
r
.
Fo
r
SAR
im
ag
es
o
f
o
ce
an
s
u
r
f
ac
es,
d
ata
s
et
c
h
an
g
es
ar
e
u
s
u
ally
ca
u
s
ed
b
y
d
ev
iatin
g
win
d
r
ates
an
d
ac
ci
d
en
t
d
ir
ec
tio
n
s
th
at
d
ir
ec
tly
a
f
f
ec
t
th
e
b
ac
k
s
c
atter
s
tr
en
g
th
.
Sev
er
al
class
if
ier
s
,
d
o
m
ain
a
d
ap
tatio
n
p
lan
s
,
an
d
m
u
ltil
o
o
k
in
g
p
o
licies
ar
e
esti
m
ated
.
T
h
e
d
ata
o
f
t
h
e
h
y
b
r
id
-
p
o
lar
im
etr
ic
SAR
wer
e
f
alsi
f
ied
f
r
o
m
q
u
ad
-
p
o
l
im
ag
es
o
f
th
e
R
ad
ar
s
at
-
2
.
Her
e,
alth
o
u
g
h
th
ey
h
av
e
u
s
ed
th
e
co
m
p
ac
t
p
o
lar
im
etr
ic
C
L
-
m
o
d
e
d
ata
s
tr
u
ctu
r
e
to
ca
teg
o
r
ize
o
il
p
o
i
n
ts
o
n
th
e
s
u
r
f
ac
e
o
f
th
e
o
c
ea
n
.
Mo
s
t
s
ets
o
f
f
ea
tu
r
es,
class
if
ier
s
,
d
o
m
ain
ad
ap
tatio
n
s
tr
ateg
ies
wer
e
n
o
t
in
ter
ested
in
av
o
id
in
g
o
r
p
r
ev
en
tin
g
th
e
s
p
ill
o
f
th
ese
g
ass
es.
I
n
[
3
7
]
T
r
an
s
f
er
a
n
d
s
en
d
i
n
g
o
f
o
il
s
p
ill
r
e
s
o
u
r
ce
s
ad
d
r
ess
ed
an
d
d
em
o
n
s
tr
ated
th
a
t
th
e
s
p
ill
r
eso
u
r
ce
s
ar
e
an
ess
en
tial
p
ar
t
o
f
th
e
em
er
g
e
n
cy
r
esp
o
n
s
e
s
y
s
tem
f
o
r
m
ar
in
e
o
il
s
p
ills
.
B
alan
ce
d
ch
o
ice
o
f
lo
ca
tio
n
s
f
o
r
r
eso
u
r
ce
s
to
r
ag
e
an
d
tr
an
s
p
o
r
tatio
n
r
o
a
d
s
p
lay
s
a
v
ital
r
o
le
in
en
s
u
r
in
g
ti
m
ely
an
d
e
f
f
ec
tiv
e
r
esp
o
n
s
e
to
o
il
s
p
ill
ac
cid
en
t
.
I
n
th
is
p
ap
er
,
a
m
u
lti
-
o
b
je
ctiv
e
r
eso
u
r
ce
s
h
ip
p
in
g
m
o
d
el
th
at
r
ed
u
ce
s
th
e
n
u
m
b
er
o
f
s
to
r
ag
e
s
p
ac
es
th
at
ar
e
av
ailab
le
f
o
r
r
esp
o
n
s
e
as
well
as
th
e
m
ax
im
u
m
r
esp
o
n
s
e
tim
e
tak
in
g
in
to
ac
co
u
n
t
r
eso
u
r
ce
v
alu
e.
T
h
er
e
is
al
s
o
a
s
o
lu
tio
n
alg
o
r
ith
m
.
T
h
e
p
r
ac
ticality
an
d
u
s
ef
u
ln
e
s
s
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
is
p
r
o
v
en
b
y
a
s
tatis
t
ical
ex
p
er
im
en
t.
T
h
ey
d
ev
elo
p
th
e
d
u
al
o
b
jectiv
e
e
m
er
g
e
n
cy
s
ch
ed
u
lin
g
m
o
d
el
u
n
d
er
m
u
ltip
le
r
eso
u
r
ce
m
ix
with
th
e
tar
g
et
o
f
s
h
o
r
test
em
er
g
en
cy
d
is
p
atch
t
im
e
an
d
m
i
n
im
u
m
e
m
er
g
en
c
y
s
av
in
g
s
p
o
in
ts
.
Fin
ally
,
th
is
ar
ticle
p
r
o
v
id
es
ca
lc
u
latio
n
s
o
f
t
h
is
m
o
d
el
a
n
d
a
n
ex
a
m
p
le
to
v
alid
ate
th
e
m
o
d
el,
b
u
t
it
f
o
cu
s
es
s
o
lely
o
n
e
m
er
g
en
cy
s
er
v
ices
f
o
r
o
n
e
in
ci
d
en
t
p
o
in
t
n
o
t
m
u
lti
-
ac
cid
en
t
p
o
in
t
an
d
tr
an
s
p
o
r
tatio
n
o
f
th
es
e
r
eso
u
r
ce
s
to
m
u
lti
-
ac
c
id
en
t p
o
in
ts
as m
an
y
ac
cid
en
ts
o
cc
u
r
c
o
n
cu
r
r
en
tly
.
In
[
3
8
]
th
e
y
p
r
esen
t
th
e
d
ev
el
o
p
m
en
t
o
f
co
n
tr
o
l
-
law
p
at
h
way
p
lan
n
i
n
g
m
eth
o
d
s
f
o
r
an
a
u
to
n
o
m
o
u
s
s
u
r
f
ac
e
v
e
h
icle
(
ASV)
ca
p
a
b
l
e
o
f
d
elin
ea
tin
g
th
e
o
il
s
p
ill
wh
ile
d
ep
lo
y
i
n
g
b
ac
ter
ia
a
n
d
n
u
tr
ien
ts
ca
p
a
b
le
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
s
u
r
ve
y
o
n
p
r
ed
ictin
g
o
il sp
ills
b
y
s
tu
d
yin
g
its
ca
u
s
e
s
u
s
in
g
d
ee
p
lea
r
n
in
g
…
(
Mo
n
a
Mo
h
a
med
N
a
s
r
)
585
co
n
tr
o
llin
g
a
n
d
s
u
s
tain
in
g
th
e
s
p
r
ea
d
o
f
o
il
s
p
ill
in
co
o
p
er
a
tio
n
with
an
au
to
m
o
tiv
e
u
n
m
an
n
ed
er
ial
v
eh
icle
(
UAV
)
.
I
n
Gaz
eb
o
,
an
o
il
s
p
ill
s
im
u
latio
n
s
ce
n
ar
io
wa
s
d
ev
elo
p
ed
to
h
elp
th
e
esti
m
ate
o
f
th
e
s
u
p
p
o
r
tin
g
ac
tiv
ities
b
etwe
en
t
h
e
ASV
an
d
UAV,
an
d
to
d
ed
u
ce
t
h
e
p
la
n
n
in
g
o
f
th
e
ASV
r
o
u
te
f
o
r
ea
ch
o
f
th
e
s
u
g
g
ested
co
n
tr
o
l
law
m
eth
o
d
s
Fro
m
th
e
m
eth
o
d
o
lo
g
ies
ex
am
in
e
d
,
it
b
ec
am
e
ap
p
ar
en
t
th
at
t
h
e
o
n
e
th
at
p
r
o
v
id
ed
th
e
b
est
way
to
m
itig
ate
o
il
s
p
ill
s
was
th
e
m
eth
o
d
o
l
o
g
y
t
h
at
u
s
es
o
r
d
in
ar
y
tr
ajec
to
r
ies
to
m
ea
s
u
r
e
a
n
ew
a
n
d
d
is
ten
d
ed
co
n
t
o
u
r
,
a
n
d
th
e
n
th
e
p
o
in
ts
f
r
o
m
t
h
at
co
n
to
u
r
ar
e
tr
an
s
f
er
r
ed
o
v
er
a
p
r
o
b
ab
le
f
i
eld
s
alg
o
r
ith
m
th
at
u
s
es th
em
as su
cc
ess
iv
e
tar
g
ets.
In
[
3
9
]
T
h
e
y
ty
p
ically
u
s
ed
s
ix
ty
p
es
o
f
s
ea
s
p
ec
tr
a
,
i.e
.
T
h
e
u
n
if
o
r
m
r
a
d
a
r
cr
o
s
s
s
eg
m
en
ts
ar
e
m
ea
s
u
r
ed
b
y
s
m
all
p
e
r
tu
r
b
ati
o
n
m
eth
o
d
(
SP
M)
,
two
s
ca
le
m
o
d
el
(
T
SM)
an
d
s
m
all
s
lo
p
e
ap
p
r
o
x
im
atio
n
(
SS
A
-
1
)
,
elf
o
u
h
aily
,
h
wan
g
,
r
o
m
eiser
,
ap
el,
f
u
n
g
an
d
p
ier
s
o
n
s
p
e
ctr
a
.
At
th
e
s
am
e
tim
e,
to
m
ea
s
u
r
e
b
etter
th
e
p
r
ec
is
io
n
o
f
u
n
alik
e
s
ea
s
p
ec
tr
a
an
d
to
p
r
ep
ar
e
an
ev
alu
atio
n
b
etwe
en
m
at
h
em
atica
l
ca
lcu
l
atio
n
s
an
d
r
ea
lis
tic
C
MO
D5
f
o
r
v
ar
io
u
s
in
cid
en
t a
n
g
les,
w
in
d
s
p
ee
d
s
an
d
win
d
d
ir
ec
tio
n
s
.
T
h
e
r
esu
lts
s
h
o
w
th
at
in
s
o
m
e
s
p
ec
if
ic
ca
s
es
th
e
NR
C
S,
m
ea
s
u
r
ed
u
s
in
g
th
e
R
o
m
eiser
r
a
n
g
e,
is
in
s
tr
o
n
g
er
ag
r
ee
m
e
n
t
with
C
MO
D5
.
In
[
4
0
]
a
n
o
v
el
lo
ca
tio
n
alg
o
r
ith
m
is
s
u
g
g
ested
b
ased
o
n
th
e
atten
u
atio
n
o
f
t
h
e
n
eg
ativ
e
p
r
ess
u
r
e
wa
v
e
(
A
NPW
)
to
ac
cu
r
ately
id
en
tify
wh
e
r
e
a
s
p
ill
ac
cid
e
n
t
o
cc
u
r
r
e
d
with
in
it.
T
h
e
ANPW
tech
n
iq
u
e
d
o
d
g
es
th
e
p
o
s
s
ib
le
d
if
f
icu
lties
o
f
th
e
co
n
v
en
tio
n
al
NPW
tech
n
iq
u
e
s
u
ch
as
s
p
ec
if
ically
d
et
er
m
in
in
g
th
e
tim
e
v
ar
ian
ce
a
n
d
NPW
'
s
v
elo
city
an
x
iety
b
y
th
e
t
u
b
e'
s
f
lu
id
m
o
tio
n
r
ate.
W
ith
th
e
lar
g
est
lo
ca
tio
n
er
r
o
r
o
f
1
.
1
6
1
p
e
r
ce
n
t
a
n
d
th
e
s
m
allest
er
r
o
r
o
f
0
.
3
5
5
p
e
r
ce
n
t
in
th
e
r
ea
l
wate
r
p
ip
elin
e,
th
e
ANPW
te
ch
n
iq
u
e
ca
n
s
u
cc
ess
f
u
lly
d
is
co
v
er
an
d
lo
ca
te
th
e
p
ip
e
o
u
tf
lo
w.
T
h
ey
u
s
ed
two
s
en
s
o
r
s
;
a
wav
elet
tr
an
s
f
o
r
m
s
y
s
tem
u
s
ed
to
r
ed
u
ce
th
e
n
o
is
e
ef
f
ec
t
th
at
h
ap
p
en
s
wh
en
th
e
p
i
p
e
b
eg
i
n
s
s
p
illi
n
g
an
d
im
p
r
o
v
e
th
e
p
r
ec
is
io
n
o
f
t
h
e
m
ea
s
u
r
em
en
t.
I
n
[
41
]
a
teth
er
ed
u
n
d
er
wate
r
r
o
b
o
t
(
T
UR
)
is
o
f
f
er
ed
f
o
r
u
n
d
er
wate
r
co
n
tain
er
a
n
ch
o
r
ex
t
r
ac
tio
n
.
I
n
th
e
s
ea
o
il
a
n
d
p
etr
o
l
en
v
ir
e
o
n
m
en
t,
t
h
is
h
as
p
r
o
d
u
ce
d
ac
tu
al
th
o
u
g
h
tf
u
l
h
o
r
r
o
r
f
o
r
co
n
tain
er
p
r
o
p
r
ieto
r
s
an
d
th
u
s
th
e
g
o
al
o
f
t
h
is
s
tu
d
y
t
o
i
m
p
r
o
v
e
T
UR
th
at
c
o
u
ld
b
e
u
s
ed
b
y
co
n
tain
er
ag
en
ts
in
s
tead
o
f
d
iv
er
s
t
o
e
x
tr
ac
t
th
e
attac
h
ed
an
ch
o
r
d
e
p
r
iv
ed
o
f
an
y
lo
s
s
.
T
h
e
ap
p
licatio
n
was
ex
ec
u
ted
an
d
th
e
s
am
p
le
s
y
s
tem
v
er
if
ied
f
o
r
test
in
g
in
th
e
6
m
eter
d
is
ta
n
ce
s
wim
m
in
g
-
b
ath
at
th
e
Un
iv
er
s
ity
o
f
Po
r
t
Har
co
u
r
t.
I
n
s
wim
m
in
g
a
nd
ex
tr
ac
tin
g
b
u
ilt an
ch
o
r
u
n
d
er
wate
r
th
e
r
o
b
o
t a
ch
iev
e
d
v
er
y
p
er
f
ec
t r
esu
lts
.
3.
DE
E
P
L
E
A
RNING
A
L
G
O
R
I
T
H
M
S
Dee
p
l
ea
r
n
in
g
i
s
a
n
ew
f
ield
o
f
m
ac
h
in
e
lear
n
in
g
r
esear
ch
th
at
was
in
tr
o
d
u
ce
d
with
t
h
e
aim
o
f
m
o
v
in
g
m
ac
h
in
e
lear
n
in
g
clo
s
er
to
o
n
e
o
f
its
o
r
ig
in
al
an
d
p
r
elim
in
ar
y
g
o
als,
s
u
ch
as
a
r
tific
ial
in
tellig
en
ce
.
I
t
is
ab
o
u
t
m
u
lti
-
s
tag
e
ed
u
ca
ti
o
n
o
f
r
ep
r
esen
tatio
n
an
d
a
b
s
tr
ac
tio
n
th
at
h
elp
s
to
u
n
d
er
s
tan
d
d
ata
s
u
ch
as
s
o
u
n
d
,
s
u
ch
as
im
ag
es
an
d
tex
t
as
id
en
tifie
d
in
[
42
]
.
Dee
p
lear
n
i
n
g
h
elp
s
u
s
to
teac
h
m
ac
h
in
es
h
o
w
to
co
m
p
lete
an
d
ac
h
iev
e
ch
alle
n
g
in
g
task
s
wi
th
o
u
t
p
r
o
g
r
am
m
in
g
th
e
m
.
W
e'
r
e
en
ter
in
g
t
h
e
a
g
e
o
f
m
ac
h
in
e
lear
n
in
g
an
d
ar
tific
ial
in
tellig
en
ce
.
Dee
p
le
ar
n
in
g
m
et
h
o
d
s
ar
e
t
h
o
s
e
th
at
ca
n
o
v
er
c
o
m
e
a
v
ar
iety
o
f
p
r
o
b
lem
s
th
r
o
u
g
h
d
ee
p
lear
n
in
g
.
3
.
1
.
Ar
t
if
icia
l
neura
l net
wo
rk
s
(
ANN)
I
n
[
43
]
(
ANN)
is
a
n
o
n
-
p
ar
am
etr
ic,
ex
p
er
im
en
tal
th
r
ea
t m
in
i
m
izatio
n
b
ased
m
o
d
elin
g
tech
n
iq
u
e
with
th
e
ab
ilit
y
to
ap
p
r
o
x
im
ate
an
y
n
o
n
-
lin
ea
r
f
u
n
ctio
n
to
a
r
b
it
r
ar
y
an
d
ty
r
an
n
ical
p
r
ec
is
io
n
,
d
ep
en
d
i
n
g
o
n
th
e
tr
ain
in
g
o
f
th
e
n
etwo
r
k
n
eu
r
o
n
s
to
ad
ju
s
t
th
e
weig
h
ts
co
n
n
ec
tin
g
th
ese
n
eu
r
o
n
s
,
an
d
i
s
ty
p
ically
u
s
ed
f
o
r
d
ev
ice
s
ec
u
r
ity
an
d
p
r
o
tectio
n
esti
m
atio
n
.
ANN
h
as
b
ee
n
s
u
cc
ess
f
u
lly
ap
p
lied
to
d
ef
ic
ien
cy
esti
m
atio
n
in
m
an
y
f
ield
s
b
u
t
th
er
e
ar
e
m
a
n
y
d
r
awb
ac
k
s
,
s
u
ch
as
n
o
n
-
c
o
n
v
ex
o
b
jectiv
e
f
u
n
ctio
n
,
d
if
f
icu
lty
in
m
ea
s
u
r
in
g
th
e
am
o
u
n
t
o
f
h
id
d
en
lay
e
r
s
a
s
well
as
o
v
er
f
itti
n
g
,
wh
ich
a
r
is
e
d
u
e
to
t
h
e
h
u
g
e
n
u
m
b
e
r
o
f
p
ar
am
eter
s
in
th
e
m
o
d
el
an
d
is
a
m
ajo
r
a
n
d
s
ig
n
i
f
ican
t w
ea
k
n
ess
o
f
th
e
t
h
eo
r
y
o
f
ex
p
e
r
im
en
tal
h
az
a
r
d
m
in
im
is
atio
n
.
3
.
2
.
Co
nv
o
lutio
na
l
neura
l net
wo
rk
(
CNN)
I
n
all
th
ese
r
esear
ch
es
[
44
-
46
]
(
C
NN)
is
a
d
ee
p
lear
n
in
g
te
ch
n
iq
u
e
s
p
ec
if
ically
d
esig
n
ed
to
id
en
tify
an
d
r
ec
o
g
n
ize
p
ictu
r
es.
I
t
is
b
u
ilt
with
th
e
p
r
esen
ce
o
f
m
u
ltil
ay
er
n
eu
r
al
n
etwo
r
k
s
.
C
NN
is
id
ea
l
f
o
r
id
en
tify
in
g
two
-
d
im
en
s
io
n
al
f
ig
u
r
es
an
d
s
tu
d
y
in
g
o
r
g
a
n
izatio
n
al
s
tr
u
ctu
r
es,
an
d
o
f
f
er
s
a
m
ea
n
s
o
f
au
to
m
atica
lly
s
ep
ar
atin
g
f
ea
t
u
r
es
f
r
o
m
p
ix
els.
T
h
e
litt
le
t
r
ain
in
g
tim
e
m
ak
es
t
h
e
u
s
e
o
f
m
u
ltil
ay
er
n
e
u
r
al
n
etwo
r
k
s
s
im
p
le
a
n
d
r
etr
iev
es
th
e
p
r
ec
is
io
n
o
f
r
ec
o
g
n
itio
n
.
T
h
e
ex
te
n
s
iv
e
u
s
e
in
th
e
s
o
r
ti
n
g
a
n
d
r
ec
o
g
n
itio
n
o
f
p
h
o
to
g
r
ap
h
s
h
as
s
h
o
wn
th
at
C
NN
p
r
o
v
id
es
ac
ce
p
ta
b
le
r
esu
lts
in
h
an
d
wr
itten
i
d
en
tific
atio
n
.
C
NN
is
also
u
s
ed
f
o
r
s
ep
a
r
atin
g
im
ag
es.
Fas
ter
R
-
C
NN
h
as
a
d
is
tr
ict
ap
p
licatio
n
n
etwo
r
k
th
at
p
r
o
v
i
d
es
th
e
p
o
s
itio
n
s
in
t
h
e
p
h
o
to
th
at
h
a
v
e
ad
v
an
ce
d
p
o
s
s
ib
ilit
ies
o
f
h
av
in
g
an
o
b
ject,
an
d
a
class
if
ier
th
at
m
ak
es
all
o
f
th
o
s
e
o
b
ject
iv
e
ap
p
licatio
n
s
as
o
n
e
o
f
th
e
class
es in
th
e
lear
n
i
n
g
d
ataset
[
47
].
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
1
,
Ap
r
il
2
0
2
1
:
5
8
0
-
5
8
9
586
4.
AP
P
L
I
E
D
DE
E
P
L
E
ARN
I
N
G
AL
G
O
RIT
H
M
S O
N
O
I
L
SPIL
L
I
N
CID
E
NT
S
As
m
en
tio
n
ed
b
e
f
o
r
e
o
il
s
p
ill
is
an
im
p
o
r
tan
t
is
s
u
e
to
s
p
ea
k
ab
o
u
t
as
it
in
clu
d
e
h
u
m
an
life
h
ea
lth
,
clim
ate
ch
an
g
in
g
,
wate
r
a
n
d
a
ir
p
o
llu
tio
n
,
an
d
f
is
h
in
g
life
in
th
e
s
ea
o
r
i
n
an
y
s
o
u
r
ce
o
f
w
ater
th
at
in
clu
d
e
o
il
o
p
er
atio
n
s
.
Fo
r
p
r
o
tectin
g
th
e
s
e
im
p
o
r
tan
t
liv
es
a
p
o
wer
f
u
l
tech
n
iq
u
es
ar
e
n
ee
d
ed
to
p
r
e
v
en
t
lik
e
ac
cid
en
ts
,
s
o
d
ee
p
lear
n
i
n
g
is
th
e
p
o
wer
f
u
l te
ch
n
iq
u
e
f
o
r
s
o
lv
in
g
th
ese
p
r
o
b
lem
s
n
o
wad
ay
s
.
An
eq
u
iv
alen
t
s
tr
u
ctu
r
e
f
o
r
th
e
n
o
v
el
ap
p
licatio
n
o
f
s
u
p
p
o
r
tin
g
v
ec
to
r
m
ac
h
in
e
(
SVM
)
an
d
ANN
tech
n
iq
u
es
was
s
u
g
g
ested
f
o
r
th
e
v
u
ln
er
ab
ilit
y
v
al
u
atio
n
o
f
th
e
u
r
b
a
n
b
u
r
ie
d
g
as
p
ip
eli
n
e
n
etwo
r
k
,
a
n
d
an
ev
alu
atio
n
was
m
ad
e
o
n
d
if
f
er
en
t
p
h
ases
b
etwe
en
th
ese
t
wo
tech
n
iq
u
es.
Sam
p
le
d
ata
n
ee
d
ed
f
o
r
m
o
d
el
d
ev
elo
p
m
e
n
t
wer
e
s
im
u
lated
an
d
d
is
tr
ib
u
ted
in
to
two
s
ets
o
f
d
ata
f
o
r
m
o
d
el
tr
ain
in
g
an
d
co
n
f
ir
m
atio
n
.
As
an
o
u
tco
m
e,
ANN
is
m
o
r
e
c
o
m
p
licated
th
an
th
at
f
o
r
SVM
a
n
d
th
is
m
a
k
es
ANN
clea
r
ly
o
v
er
-
f
itti
n
g
,
SVM'
s
tr
ain
in
g
r
esu
lts
ar
e
well
m
atch
ed
with
th
e
d
esire
d
o
u
tp
u
ts
th
an
ANN,
an
d
wh
en
ap
p
lied
to
u
n
id
en
tifie
d
ca
s
es,
th
e
SVM
m
o
d
el
ca
n
p
r
o
d
s
atis
f
ac
to
r
y
p
r
o
d
u
ctio
n
v
alu
es
a
n
d
is
m
o
r
e
ac
cu
r
ate
th
a
n
th
e
A
NN
m
o
d
el
as
s
h
o
wn
in
[
4
3
].
I
n
[
48
]
a
p
o
p
u
lar
m
eth
o
d
o
l
o
g
y
s
u
ch
as
C
NN
h
as
also
u
s
ed
a
b
asic
d
is
cr
im
in
atio
n
a
n
aly
s
is
to
d
escr
ib
e
th
e
s
elec
ted
f
ea
tu
r
es
s
u
b
g
r
o
u
p
to
ca
teg
o
r
ize
u
n
s
tr
u
ctu
r
ed
d
ata.
I
n
th
e
C
-
b
an
d
p
o
l
ar
im
etr
ic
m
o
d
e,
th
e
f
ea
tu
r
es
s
tu
d
ied
in
clu
d
e
e
n
tr
o
p
y
,
alp
h
a
,
an
d
s
in
g
le
-
b
o
u
n
ce
eig
en
v
alu
e
r
elativ
e
d
if
f
er
en
c
e
(
SERD).
W
e
al
s
o
s
u
g
g
est
a
n
o
v
el
tech
n
iq
u
e
f
o
r
SAR
im
ag
e
d
is
cr
im
in
atio
n
o
n
o
il
s
p
ills
an
d
lo
o
k
alik
es.
T
h
e
class
if
icatio
n
ac
cu
r
ac
y
ac
h
ie
v
ed
th
r
o
u
g
h
th
e
u
s
e
o
f
9
0
0
test
d
ata
s
am
p
les
is
9
1
.
3
3
%.
I
t
is
h
e
r
e
as
a
r
es
u
lt
d
etec
ted
th
at
n
o
t
o
n
ly
ca
n
th
e
s
u
g
g
ested
tech
n
i
q
u
e
ac
cu
r
ately
r
ec
o
g
n
ize
th
e
b
lack
s
p
o
ts
o
n
SAR
im
ag
es,
b
u
t
also
co
n
f
ir
m
th
e
s
u
g
g
ested
alg
o
r
ith
m
'
s
ab
ilit
y
t
o
ca
teg
o
r
ize
u
n
s
tr
u
ctu
r
ed
f
ea
t
u
r
es.
T
h
e
r
esu
lt
also
s
h
o
ws
if
th
e
ch
an
g
e
in
s
ea
cir
cu
m
s
tan
ce
s
(
s
u
ch
as
clim
at
ic,
g
eo
g
r
ap
h
ical,
s
ea
tem
p
er
at
u
r
e,
an
d
en
v
ir
o
n
m
en
tal
co
n
d
it
io
n
s
)
b
etwe
en
test
an
d
tr
ain
in
g
d
ata
is
to
o
en
o
r
m
o
u
s
,
class
if
icatio
n
ac
cu
r
ac
y
w
o
u
ld
b
e
a
h
u
g
e
f
all.
T
o
r
e
d
u
ce
th
e
ef
f
ec
ts
o
f
th
o
s
e
in
f
lu
en
ce
s
o
n
f
u
tu
r
e
e
x
p
er
im
e
n
ts
,
f
o
r
th
e
co
n
s
tr
u
ctio
n
o
f
th
e
C
NN
m
o
d
el,
m
o
r
e
o
il
s
p
ill
d
ata
f
r
o
m
d
is
s
im
ilar
m
ar
in
e
r
e
g
io
n
s
will
b
e
u
s
ed
an
d
th
e
s
tr
en
g
th
o
f
th
e
tr
ain
i
n
g
s
tr
u
ctu
r
e
o
f
t
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
will
b
e
in
cr
ea
s
ed
.
I
f
f
o
r
th
e
class
if
icatio
n
r
esu
lt
th
e
p
r
ev
io
u
s
p
o
s
s
ib
ilit
ies
o
f
o
il
s
p
il
ls
an
d
lo
o
k
alik
es
ar
e
tak
en
in
to
ac
co
u
n
t,
th
e
class
if
icatio
n
p
r
e
cisi
o
n
wo
u
ld
d
ef
i
n
itely
b
e
im
p
r
o
v
ed
.
In
[
49
]
Usi
n
g
th
e
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
,
th
ey
d
is
co
v
er
ed
o
il
s
p
ill
r
eg
io
n
s
f
r
o
m
h
ig
h
-
r
eso
lu
tio
n
o
p
tical
im
ag
es
b
y
o
p
er
atio
n
al
co
n
q
u
est
o
f
au
s
ter
e
s
u
n
s
h
in
e
r
esu
lts
.
A
d
ir
ec
t
io
n
al
m
ed
ian
f
ilter
(
DM
F)
h
as
b
ee
n
d
ev
elo
p
e
d
to
allo
w
th
is
,
a
n
d
its
u
s
e
h
as
b
e
en
co
m
p
ar
ed
to
th
at
o
f
a
co
n
v
en
tio
n
al
l
o
w
-
p
ass
f
ilter
.
A
p
r
esen
tatio
n
test
was
s
h
o
wn
u
s
in
g
a
KOM
PS
AT
‐
2
im
ag
e
d
e
v
elo
p
ed
as
a
r
esu
lt
o
f
o
il
s
p
ill
ac
cid
en
ts
wh
ich
o
cc
u
r
r
ed
in
th
e
2
0
1
0
Gu
lf
o
f
Me
x
ico
.
T
h
e
s
u
g
g
ested
tech
n
iq
u
e
i
n
v
o
lv
e
d
two
m
ain
p
h
ases
:
(
1
)
u
s
in
g
th
e
DM
F,
th
e
s
u
n
s
h
in
e
ef
f
ec
ts
ca
u
s
ed
b
y
th
e
o
ce
an
wav
es
wer
e
ch
an
g
ed
a
n
d
(
2
)
th
e
AN
N
m
eth
o
d
was
u
s
ed
to
d
is
co
v
er
th
e
ar
ea
o
f
o
il
s
p
i
ll.
T
h
e
o
u
tc
o
m
es
d
is
p
lay
th
e
n
ex
t:
(
a)
T
h
e
co
n
s
tr
u
cted
DM
F,
wh
ich
tak
es
in
to
ac
co
u
n
t
t
h
e
s
ize
an
d
an
g
le
o
f
o
ce
an
wav
es,
h
as
b
ee
n
g
r
ea
t
an
d
clev
er
in
m
an
ip
u
latin
g
th
e
ef
f
ec
t
o
f
s
u
n
s
h
in
e
in
a
h
ig
h
-
r
eso
lu
tio
n
o
p
tical
im
ag
e;
an
d
(
b
)
o
il
s
p
ill
r
eg
io
n
s
h
av
e
b
ee
n
ef
f
ec
tiv
ely
d
is
co
v
er
ed
u
s
in
g
th
e
s
u
g
g
ested
tech
n
iq
u
e
o
f
th
e
ANN
m
eth
o
d
.
T
h
e
o
il
s
p
il
l
ar
ea
was
class
if
ied
s
ep
ar
atel
y
u
s
in
g
th
e
r
ec
ei
v
er
o
p
er
atin
g
ch
ar
ac
ter
is
tic
(
R
OC
)
cu
r
v
e
a
n
d
d
etec
tio
n
p
r
o
b
ab
ilit
y
(
POD)
m
ea
s
u
r
em
e
n
ts
,
with
p
r
ec
is
io
n
s
o
f
ab
o
u
t
9
8
.
1
2
p
er
ce
n
t
an
d
8
9
.
5
6
p
er
ce
n
t.
T
h
is
r
esu
lts
s
h
o
w
th
at,
co
m
p
ar
ed
with
th
e
s
tan
d
ar
d
d
etec
tio
n
al
g
o
r
ith
m
,
th
e
p
r
ec
is
io
n
o
f
th
e
s
u
g
g
ested
tech
n
iq
u
e
is
im
p
r
o
v
ed
b
y
ab
o
u
t 9
p
er
ce
n
t.
In
[5
0
]
I
n
SAR
im
ag
es
f
o
cu
s
e
d
o
n
co
n
v
o
l
u
tio
n
ar
y
n
eu
r
al
n
e
two
r
k
(
C
NN)
,
t
h
ey
p
r
o
p
o
s
ed
an
o
ce
a
n
ic
p
h
en
o
m
en
o
n
ex
p
l
o
r
atio
n
tec
h
n
iq
u
e.
Nex
t,
R
esNet
-
5
0
is
u
s
ed
b
y
t
h
e
tech
n
i
q
u
e
to
r
em
o
v
e
m
u
ltil
ev
el
f
u
n
ctio
n
ality
.
Seco
n
d
ly
,
to
e
x
tr
ac
t
m
u
ltis
ca
le
f
u
n
ctio
n
alit
y
,
it
u
s
es
th
e
atr
o
cio
u
s
s
p
atial
p
y
r
am
id
p
o
o
lin
g
(
ASPP
)
m
o
d
u
le.
Fin
ally
,
to
e
x
p
lo
r
e
o
ce
an
ic
p
h
en
o
m
en
a
it
in
co
r
p
o
r
ates
m
u
ltil
ev
el
f
ea
tu
r
es
an
d
m
u
ltis
ca
le
f
ea
tu
r
es.
T
h
e
SAR
im
ag
es
c
o
llected
f
r
o
m
th
e
s
atellite
Sen
tin
el
-
1
ar
e
u
s
ed
to
e
s
tab
lis
h
an
o
ce
an
ic
p
h
en
o
m
en
o
n
s
tu
d
y
d
ataset.
T
h
e
s
u
g
g
ested
m
eth
o
d
o
l
o
g
y
c
an
b
e
ef
f
ec
tiv
e
o
n
th
e
d
ataset
with
9
1
p
e
r
ce
n
t
p
r
ec
is
io
n
.
I
n
[
51
]
th
e
an
aly
s
is
m
atch
es
p
r
ev
io
u
s
ly
o
b
s
er
v
e
d
r
esp
o
n
s
es
to
ir
r
eg
u
lar
s
o
u
n
d
ev
en
t
d
etec
t
io
n
(
SED)
o
n
th
e
s
tr
u
ctu
r
e
o
f
th
e
ch
ar
a
cter
is
tic
SED
p
ip
elin
e
in
g
r
ed
ien
ts
.
T
h
e
s
y
s
tem
’
s
p
er
f
o
r
m
a
n
ce
o
n
a
lo
n
e
a
n
d
m
u
lti
-
class
b
ase
was
esti
m
at
ed
.
I
t
tu
r
n
ed
o
u
t
th
e
p
er
f
o
r
m
o
n
lo
n
e
class
is
lik
ely
n
o
t
t
o
b
e
th
e
s
am
e
an
d
d
if
f
er
en
tiate
b
etwe
en
m
eth
o
d
o
lo
g
ies.
Per
f
o
r
m
in
g
th
e
s
m
all
ab
er
r
atio
n
in
lo
n
e
class
wo
u
l
d
d
esig
n
ate
a
m
u
lti
-
p
u
r
p
o
s
e
tech
n
iq
u
e
th
at
is
n
o
t
p
r
ed
is
p
o
s
ed
t
o
a
ce
r
tain
k
i
n
d
o
f
o
u
tco
m
e.
T
h
e
m
eth
o
d
o
lo
g
y
is
th
er
ef
o
r
e
c
o
n
s
id
er
ed
to
b
e
im
p
r
o
v
ed
f
o
r
a
g
r
ea
ter
r
an
g
e
o
f
SED
co
m
p
licatio
n
s
.
T
h
e
g
r
ea
test
p
r
ac
tical
m
eth
o
d
o
l
o
g
y
is
th
e
m
ix
tu
r
e
o
f
m
ak
i
n
g
ch
a
r
a
cter
is
tics
u
s
ed
as
lo
g
-
m
el
en
er
g
ies
in
co
n
v
o
lu
tio
n
al
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
(
C
R
NN)
wi
th
lo
n
g
s
h
o
r
t
ter
m
m
em
o
r
y
(
L
STM
)
with
a
co
n
f
ir
m
atio
n
p
h
ase
o
f
th
r
esh
o
ld
in
g
h
as
f
o
u
n
d
9
3
.
1
%
F1
s
co
r
e
an
d
0
.
1
3
0
7
E
R
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
s
u
r
ve
y
o
n
p
r
ed
ictin
g
o
il sp
ills
b
y
s
tu
d
yin
g
its
ca
u
s
e
s
u
s
in
g
d
ee
p
lea
r
n
in
g
…
(
Mo
n
a
Mo
h
a
med
N
a
s
r
)
587
5.
CO
NCLU
SI
O
N
Hu
m
an
life
is
th
e
m
o
s
t
i
m
p
o
r
tan
t
th
in
g
to
p
r
o
tect
it,
as
th
e
im
p
o
r
tan
ce
o
f
h
u
m
an
life
a
ls
o
liv
in
g
cr
ea
tu
r
es
as
B
ir
d
s
o
r
Fis
h
o
r
a
n
y
cr
ea
tu
r
e
th
at
liv
e
u
n
d
er
th
e
wa
ter
o
r
f
ly
in
th
e
s
k
y
ar
e
s
o
im
p
o
r
tan
t
to
m
ak
e
life
b
e
c
o
n
tin
u
e
.
Oil
s
p
ills
ca
u
s
e
a
lo
t
o
f
h
ar
m
s
an
d
d
is
aster
s
f
o
r
th
ese
liv
es,
s
o
it’s
s
o
im
p
o
r
tan
t
to
in
ter
esti
n
g
in
th
is
p
r
o
b
lem
.
A
lo
t
o
f
r
esear
ch
es
s
p
ea
k
a
b
o
u
t
h
an
d
lin
g
t
h
at
af
ter
th
e
o
cc
u
r
r
en
ce
o
f
th
e
a
cc
id
en
t
b
u
t
it’s
s
o
s
en
s
itiv
e
to
av
o
id
s
u
ch
a
p
r
o
b
lem
s
.
Dete
ctin
g
r
ea
s
o
n
s
o
f
t
h
ese
in
cid
en
ts
an
d
av
o
i
d
in
g
i
t
co
n
s
id
er
th
e
m
o
s
t
im
p
o
r
tan
t
is
s
u
e
n
o
wad
ay
s
.
B
y
u
s
in
g
a
p
o
wer
f
u
l
tech
n
i
q
u
e
s
u
ch
as
d
ee
p
lear
n
in
g
tech
n
iq
u
es,
p
r
ed
ictin
g
th
ese
p
r
o
b
lem
s
an
d
av
o
id
it
ca
n
o
cc
u
r
r
ed
.
I
n
th
e
en
d
o
f
t
h
at
r
esear
ch
will
im
p
r
o
v
e
th
e
p
er
f
o
r
m
an
ce
o
f
f
o
r
ec
asti
n
g
s
p
ill
in
cid
en
ts
to
lead
h
u
m
a
n
i
ty
to
a
s
af
e
wo
r
ld
th
an
b
ef
o
r
e
an
d
to
let
p
eo
p
le
w
o
r
k
in
s
u
ch
a
f
ield
o
r
liv
in
g
n
ea
r
d
ig
g
i
n
g
lo
ca
tio
n
s
to
b
e
m
o
r
e
s
af
e
an
d
d
is
ap
p
ea
r
in
g
o
f
a
cc
id
en
ts
o
r
r
ed
u
cin
g
it
will
m
ak
e
th
em
R
ea
s
s
u
r
ed
.
As
a
f
u
tu
r
e
wo
r
k
af
ter
p
r
ed
ictin
g
th
e
ac
cid
en
t
a
s
im
ilar
ity
alg
o
r
ith
m
s
o
r
s
im
ilar
ad
v
an
ce
tech
n
iq
u
es c
an
g
iv
e
th
e
b
est s
o
lu
tio
n
f
o
r
d
ea
lin
g
with
th
at
a
cc
id
en
t a
cc
o
r
d
i
n
g
to
its
ty
p
e
.
RE
F
E
R
E
NC
E
S
[1
]
Ch
.
M
a
n
i
K
u
m
a
r,
Dr
P
.
S
u
m
it
h
a
b
h
a
sh
i
n
i,
P
.
S
u
m
a
n
y
a
,
B.
S
ra
v
a
n
t
h
i,
G
.
S
u
sm
it
h
a
,
"
Ad
v
a
n
c
e
d
IO
T
Ba
se
d
LP
G
Lea
k
a
g
e
S
e
n
sin
g
a
n
d
Al
e
rti
n
g
S
y
st
e
m
o
v
e
r
G
S
M
a
n
d
WI
F
I,
"
J
o
u
r
n
a
l
o
f
E
n
g
in
e
e
rin
g
S
c
ien
c
e
s
,
v
o
l
1
1
,
n
o
.
2
,
2
0
2
0
.
[2
]
Dr.
Um
u
n
n
a
k
we
Jo
h
n
b
o
sc
o
,
Dr.
Ah
a
ra
n
wa
Bib
ian
a
Ch
ime
z
ie,
S
u
r
v
.
Njo
k
u
Rich
a
r
d
.
E,
“
Im
p
a
c
t
Of
Us
e
d
M
o
to
r
Oil
On
Th
e
S
o
i
l
Qu
a
li
t
ies
Of
Orj
i
M
e
c
h
a
n
ic
Vil
lag
e
Ow
e
rri,
N
ig
e
ria
,
”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
E
n
g
i
n
e
e
rin
g
T
e
c
h
n
o
l
o
g
ies
a
n
d
M
a
n
a
g
e
me
n
t
R
e
se
a
rc
h
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
1
-
2
,
2
0
2
0
,
d
o
i
:
1
0
.
2
9
1
2
1
/i
jetm
r.
v
7
.
i
2
.
2
0
2
0
.
5
2
4
.
[3
]
P
ietro
P
.
F
a
lci
g
li
a
,
L
u
c
ia
Lu
m
ia,
M
a
ria
G
a
b
riella
G
iu
stra
,
Eri
c
a
Ga
g
li
a
n
o
,
P
a
o
l
o
Ro
c
c
a
ro
,
F
e
d
e
rico
G
.
A.
Va
g
li
a
sin
d
i,
G
a
e
tan
o
Di
Be
ll
a
,
"
Re
m
e
d
iatio
n
o
f
p
e
tr
o
l
h
y
d
r
o
c
a
rb
o
n
-
c
o
n
tam
in
a
ted
m
a
rin
e
s
e
d
ime
n
ts
b
y
th
e
rm
a
l
d
e
so
rp
ti
o
n
,
"
C
h
e
mo
sp
h
e
re
2
6
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/j
.
c
h
e
m
o
sp
h
e
re
.
2
0
2
0
.
1
2
7
5
7
6
.
[4
]
Ha
o
F
u
,
L
u
Ya
n
g
,
Hu
ir
o
n
g
Li
a
n
g
,
S
a
i
Wan
g
,
Ke
g
a
n
g
Li
n
g
,
"
Dia
g
n
o
sis
o
f
t
h
e
sin
g
le
lea
k
a
g
e
in
t
h
e
flu
i
d
p
ip
e
li
n
e
th
ro
u
g
h
e
x
p
e
rime
n
tal
stu
d
y
a
n
d
CF
D
sim
u
latio
n
,
"
J
o
u
r
n
a
l
o
f
Petro
leu
m
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j.
p
e
tr
o
l.
2
0
2
0
.
1
0
7
4
3
7
.
[5
]
Ha
rsh
P
a
tel•
Dh
iren
k
u
m
a
r
P
ra
jap
a
ti
•
Dh
a
r
a
m
ra
jsin
h
M
a
h
id
a
•
M
a
n
a
n
S
h
a
h
,
"
Tran
sf
o
rm
in
g
p
e
tro
leu
m
d
o
w
n
stre
a
m
se
c
to
r
th
ro
u
g
h
b
ig
d
a
ta:
a
h
o
li
stic
re
v
iew
,
"
J
o
u
rn
a
l
o
f
Petro
leu
m
E
x
p
lo
ra
ti
o
n
a
n
d
Pro
d
u
c
ti
o
n
T
e
c
h
n
o
lo
g
y
,
v
o
l.
1
0
,
n
o
.
6
,
p
p
.
2
6
0
1
-
2
6
1
1
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
0
7
/s1
3
2
0
2
-
0
2
0
-
0
0
8
8
9
-
2.
[6
]
Jia
n
c
h
u
n
G
u
o
,
Zh
u
a
n
g
Li
u
,
Bo
G
o
u
,
M
in
g
y
o
n
g
Zen
g
,
"
S
tu
d
y
o
f
w
e
ll
b
o
re
h
e
a
t
tran
sfe
r
c
o
n
sid
e
ri
n
g
f
lu
id
r
h
e
o
l
o
g
ica
l
e
ffe
c
ts
in
d
e
e
p
we
ll
a
c
id
izin
g
,
"
J
o
u
rn
a
l
o
f
Petro
leu
m
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
v
o
l.
1
9
1
,
p
.
1
0
7
1
7
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j.
p
e
tr
o
l.
2
0
2
0
.
1
0
7
1
7
1
.
[7
]
Ch
e
n
Ni,
Yu
a
n
Y
u
a
n
Wan
g
,
Qin
g
fe
n
g
Ho
u
,
Xia
o
x
u
a
n
Li
,
Yin
g
Z
h
a
n
g
,
Ya
n
Wan
g
,
Ya
n
Xu
a
,
Yu
ju
n
Z
h
a
o
,
"
P
h
a
se
tran
sfo
rm
a
ti
o
n
o
f
th
e
rm
o
re
sp
o
n
siv
e
su
rfa
c
tan
t
tri
g
g
e
re
d
b
y
it
s
c
o
n
c
e
n
tratio
n
a
n
d
tem
p
e
ra
tu
re
,
"
J
o
u
rn
a
l
o
f
Petro
leu
m S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
v
o
l.
1
9
3
,
p
.
1
0
7
4
1
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/j
.
p
e
tro
l
.
2
0
2
0
.
1
0
7
4
1
0
.
[8
]
M
.
K.
Ism
a
y
il
o
v
a
,
"
In
f
lu
e
n
c
e
o
f
e
n
e
rg
y
tran
sfe
r
in
th
e
a
d
so
r
b
e
d
st
a
te
o
f
th
e
c
lay
a
t
th
e
p
e
tro
le
u
m
ra
d
io
l
y
sis
u
n
d
e
r
g
a
m
m
a
ra
d
iatio
n
a
t
ro
o
m
tem
p
e
ra
tu
re
,
"
R
a
d
i
a
ti
o
n
Ef
fec
ts
a
n
d
De
fec
ts
in
S
o
li
d
s
,
v
o
l
.
1
7
5
,
n
o
.
5
-
6
,
p
p
.
4
7
2
-
4
8
1
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
8
0
/
1
0
4
2
0
1
5
0
.
2
0
1
9
.
1
6
7
8
6
2
2
.
[9
]
Ka
tarz
y
n
a
S
to
lec
k
a
,
P
o
lan
d
,
"
H
a
z
a
rd
s
Of
Th
e
Ro
a
d
Tran
s
p
o
rta
ti
o
n
Of
Ha
z
a
rd
o
u
s
M
a
teria
l
s,"
S
y
ste
m
S
a
fety
:
Hu
ma
n
-
T
e
c
h
n
ica
l
F
a
c
il
it
y
–
En
v
iro
n
me
n
t,
Czo
t
o
,
v
o
l
.
2
,
n
o
.
1
,
2
0
2
0
,
d
o
i:
1
0
.
2
4
7
8
/cz
o
to
-
2
0
2
0
-
0
0
2
9
.
[1
0
]
S
h
u
k
ria
F
a
izi,
Na
ji
b
Ra
h
m
a
n
S
a
b
o
ry
,
a
n
d
Ab
d
u
l
Ha
m
id
Lay
a
n
,
"
I
m
p
a
c
t
o
f
F
u
e
l
c
o
n
su
m
p
ti
o
n
in
th
e
tran
sp
o
rtati
o
n
se
c
to
r
o
n
p
e
o
p
le,
a
n
ima
ls,
a
n
d
p
lan
t
li
fe
in
Ka
b
u
l
c
it
y
,
"
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
u
st
a
i
n
a
b
il
it
y
Ou
tre
a
c
h
i
n
De
v
e
lo
p
in
g
Co
u
n
tries
(S
OD
C
2
0
1
9
)
v
o
l
1
,
n
o
.
1
,
2
0
2
0
,
p
p
.
8
9
-
9
5
,
d
o
i:
1
0
.
3
7
3
5
7
/
1
0
6
8
/S
OD
C2
0
1
9
.
1
.
1
.
1
1
.
[1
1
]
M
e
rv
F
i
n
g
a
s,
“
T
h
e
b
a
sic
s o
f
o
il
s
p
il
l
c
lea
n
u
p
,”
t
h
ir
d
e
d
it
i
o
n
,
©
2
0
1
3
b
y
T
a
y
lo
r &
Fr
a
n
c
is Gro
u
p
,
L
L
C
.
[1
2
]
M
a
rc
e
l,
Va
lerie
.
"
Oil
Ti
tan
s:
Na
ti
o
n
a
l
Oi
l
Co
m
p
a
n
ies
in
t
h
e
M
i
d
d
le
Eas
t,
"
ro
y
a
l
i
n
stit
u
te o
f
n
a
ti
o
n
a
l
a
ff
a
irs
,
(2
0
0
6
).
[1
3
]
Wen
a
r,
Leif,
"
Blo
o
d
o
i
l:
T
y
ra
n
t
s,
v
i
o
len
c
e
,
a
n
d
t
h
e
ru
les
t
h
a
t
r
u
n
th
e
wo
r
ld
.
Ox
f
o
rd
U
n
iv
e
rsit
y
P
re
ss
,
"
Ox
fo
rd
Un
ive
rs
it
y
Pre
ss
2
0
1
5
.
[1
4
]
Rig
n
e
y
,
M
a
tt
.
“
In
P
u
rsu
it
o
f
G
ia
n
ts:
On
e
M
a
n
'
s
G
lo
b
a
l
S
e
a
rc
h
fo
r
th
e
Las
t
o
f
th
e
G
re
a
t
F
ish
,
”
Un
ive
rs
it
y
Pre
ss
o
f
Ne
w
En
g
l
a
n
d
,
2
0
1
7
.
[1
5
]
M
u
rtad
a
M
o
h
a
m
m
e
d
Ab
d
u
l
re
d
h
a
,
S
it
i
As
li
n
a
,
Hu
ss
a
in
,
L
u
q
m
a
n
,
Ch
u
a
h
A
b
d
u
ll
a
h
,
"
O
v
e
rv
iew
o
n
p
e
tro
leu
m
e
m
u
lsio
n
s,
fo
rm
a
ti
o
n
,
i
n
flu
e
n
c
e
a
n
d
d
e
m
u
ls
ifi
c
a
ti
o
n
trea
tme
n
t
tec
h
n
iq
u
e
s,"
Ara
b
ia
n
J
o
u
r
n
a
l
o
f
Ch
e
mistry
,
v
o
l.
1
3
,
n
o
.
1
,
p
p
.
3
4
0
3
-
3
4
2
8
,
d
o
i:
1
0
.
1
0
1
6
/j
.
a
ra
b
jc.
2
0
1
8
.
1
1
.
0
1
4
.
[1
6
]
Wan
li
Ka
n
g
,
e
t
a
l.
,
"
De
m
u
lsifi
c
a
t
io
n
p
e
rfo
rm
a
n
c
e
,
b
e
h
a
v
io
r
a
n
d
m
e
c
h
a
n
ism
o
f
d
iffere
n
t
d
e
m
u
lsif
iers
o
n
th
e
l
ig
h
t
c
ru
d
e
o
il
e
m
u
lsio
n
s,"
Co
l
lo
i
d
s
a
n
d
S
u
rf
a
c
e
s
A:
Ph
y
sic
o
c
h
e
mic
a
l
a
n
d
En
g
i
n
e
e
rin
g
Asp
e
c
ts
,
v
o
l.
5
4
5
,
2
0
1
8
,
p
p
.
1
9
7
-
2
0
4
,
d
o
i:
1
0
.
1
0
1
6
/j
.
c
o
lsu
rfa
.
2
0
1
8
.
0
2
.
0
5
5
.
[1
7
]
An
n
M
u
g
g
e
ri
d
g
e
,
An
d
re
w
Co
c
k
in
,
Ke
v
in
Web
b
,
Ha
rr
y
F
ra
m
p
t
o
n
,
Ia
n
C
o
ll
i
n
s,
T
im
M
o
u
l
d
s
a
n
d
P
e
ter
S
a
li
n
o
,
"
Re
c
o
v
e
ry
ra
tes
,
e
n
h
a
n
c
e
d
o
il
re
c
o
v
e
ry
a
n
d
tec
h
n
o
l
o
g
ica
l
li
m
it
s,"
p
h
i
lo
so
p
h
ica
l
tr
a
n
sa
c
t
io
n
s
o
f
th
e
ro
y
a
l
so
c
iety
,
v
o
l.
3
7
2
,
2
0
0
6
,
p
.
2
0
1
2
0
3
2
0
,
d
o
i:
1
0
.
1
0
9
8
/rsta.
2
0
1
2
.
0
3
2
0
.
[1
8
]
Ire
n
a
B.
Iv
sh
i
n
a
,
e
t
a
l.
,
"
Oil
s
p
il
l
p
r
o
b
lem
s
a
n
d
su
sta
in
a
b
le
r
e
sp
o
n
se
stra
teg
ies
th
ro
u
g
h
n
e
w
tec
h
n
o
l
o
g
ies
,
”
En
v
iro
n
me
n
ta
l
S
c
ien
c
e
Pro
c
e
ss
e
s &
Imp
a
c
ts
,
v
o
l
.
1
7
,
n
o
.
7
,
p
p
.
1
2
0
1
-
1
2
1
9
,
d
o
i
:
1
0
.
1
0
3
9
/c
5
e
m
0
0
0
7
0
j
.
[1
9
]
J.
Ro
c
h
e
tt
e
,
"
To
wa
r
d
s
a
n
i
n
tern
a
ti
o
n
a
l
re
g
u
lati
o
n
o
f
o
ffsh
o
re
o
il
e
x
p
lo
i
tatio
n
,”
P
a
ris
Oc
e
a
n
o
g
ra
p
h
ic
In
sti
tu
te
on
,
n
o
.
1
5
.
2
0
1
2
.
[2
0
]
B.
Ha
c
k
e
tt
,
E.
Co
m
e
rm
a
,
P
.
Da
n
iel
a
n
d
H.
Ic
h
ik
a
wa
,
“
M
a
rin
e
o
il
p
o
l
lu
ti
o
n
p
re
d
icti
o
n
,
”
Oc
e
a
n
o
g
ra
p
h
y
,
v
o
l.
2
2
,
2
0
0
9
,
p
p
.
1
6
8
-
1
7
5
,
d
o
i:
1
0
.
5
6
7
0
/
o
c
e
a
n
o
g
.
2
0
0
9
.
7
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
1
,
Ap
r
il
2
0
2
1
:
5
8
0
-
5
8
9
588
[2
1
]
Na
talia
S
c
h
e
v
e
rín
,
An
a
F
o
ss
a
ti
,
F
e
rn
a
n
d
a
Ho
rst,
Ve
ró
n
ica
Las
sa
ll
e
,
S
il
v
ia
Ja
c
o
b
o
,
"
M
a
g
n
e
ti
c
h
y
b
rid
g
e
ls
fo
r
e
m
u
lsifi
e
d
o
il
a
d
so
r
p
ti
o
n
:
a
n
o
v
e
rv
iew
o
f
th
e
ir
p
o
ten
ti
a
l
t
o
so
lv
e
e
n
v
iro
n
m
e
n
tal
p
r
o
b
lem
s
a
ss
o
c
iate
d
to
p
e
tro
le
u
m
sp
il
ls
,”
En
v
iro
n
me
n
ta
l
S
c
ien
c
e
a
n
d
Po
ll
u
ti
o
n
Res
e
a
rc
h
,
vol
.
2
7
,
p
p
.
8
6
1
-
8
7
2
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
0
7
/s1
1
3
5
6
-
0
1
9
-
0
6
7
5
2
-
0.
[
2
2
]
M
a
r
í
a
P
í
a
A
r
e
a
l
,
e
t
a
l
.
,
"
W
a
te
r
R
e
m
e
d
i
a
t
i
o
n
:
P
V
A
-
Ba
s
e
d
M
a
g
n
e
t
i
c
G
e
ls
a
s
E
f
f
i
c
ie
n
t
D
e
v
ic
e
s
t
o
H
e
a
v
y
M
e
t
a
l
R
e
m
o
v
a
l
,
"
J
o
u
r
n
a
l
o
f
P
o
l
y
m
e
r
s
a
n
d
t
h
e
E
n
v
i
r
o
n
m
e
n
t
,
v
o
l
.
2
6
,
p
p
.
3
1
2
9
-
3
1
3
8
,
2
0
1
8
,
doi
:
1
0
.
1
0
0
7
/
s
1
0
9
2
4
-
01
8
-
1
1
9
7
-
4
.
[2
3
]
Ro
h
a
n
a
Ism
a
il
,
Ar
n
a
wa
n
Ha
sib
u
a
n
,
M
u
z
a
m
ir
Isa
,
F
a
iza
r
Ab
d
u
rra
h
m
a
n
,
Nu
r
u
l
Isla
m
i,
“
M
it
ig
a
ti
o
n
o
f
h
ig
h
v
o
lt
a
g
e
in
d
u
c
ti
o
n
e
ffe
c
t
o
n
ICCP
sy
ste
m
o
f
g
a
s
p
ip
e
li
n
e
s:
a
fiel
d
c
a
se
stu
d
y
,”
T
E
L
KOM
NIKA
(
T
e
lec
o
mm
u
n
ica
t
io
n
Co
mp
u
t
in
g
El
e
c
tro
n
ics
a
n
d
C
o
n
tr
o
l)
,
v
o
l
.
1
7
,
n
o
.
6
,
p
p
.
3
2
2
6
~
3
2
3
1
6
,
2
0
1
9
,
d
o
i
:
1
0
.
1
2
9
2
8
/.
v
1
7
i6
.
1
2
4
9
3
.
[2
4
]
S
a
if
Ald
e
e
n
H.
M
o
h
a
m
m
e
d
,
Isa
m
M
.
A
b
d
u
lb
a
q
i,
“
De
sig
n
a
n
d
i
m
p
lem
e
n
tatio
n
o
f
a
n
im
p
re
ss
e
d
c
u
rre
n
t
c
a
th
o
d
ic
p
ro
tec
ti
o
n
s
y
ste
m
fo
r
b
u
ried
m
e
talli
c
p
ip
e
s
(
p
a
rt
II)
(c
o
n
si
d
e
rin
g
Al
-
Qu
d
s
g
a
s
sta
ti
o
n
in
Ba
g
h
d
a
d
)
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Po
we
r
El
e
c
tro
n
ics
a
n
d
Dr
ive
S
y
ste
m
(IJ
PE
DS
)
,
v
o
l.
1
1
,
n
o
.
1
,
p
p
.
2
7
5
-
2
8
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
j
p
e
d
s.v
1
1
.
i1
.
p
p
2
7
5
-
2
8
3
.
[2
5
]
Ra
h
e
e
l
Iq
b
a
l,
F
a
wa
d
P
i
rz
a
d
a
,
M
u
h
a
m
m
a
d
Zu
b
a
ir
,
Am
e
e
r
M
e
h
m
o
o
d
,
“
An
e
x
p
e
rime
n
tal
stu
d
y
o
n
p
e
rfo
rm
a
c
e
o
f
sta
rc
h
e
x
trac
ted
fro
m
wh
e
a
t
flo
u
r
a
s
fil
tratio
n
c
o
n
tro
l
a
g
e
n
t
in
d
ril
l
in
g
fl
u
id
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
s
in
Ap
p
li
e
d
S
c
ie
n
c
e
s (IJAAS
)
,
v
o
l
.
9
,
n
o
.
4
,
p
p
.
2
5
5
-
2
6
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
jaa
s.v
9
.
i4
.
p
p
2
5
5
-
2
6
0
.
[2
6
]
C.
R.
Ba
lam
u
ru
g
a
n
,
P
.
Vijay
a
k
u
m
a
r,
“
Clo
u
d
c
o
n
n
e
c
ted
sm
a
rt
h
o
m
e
g
a
s
c
y
li
n
d
e
r
p
latf
o
rm
b
a
se
d
wifi
c
o
n
tro
l
,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
I
n
fo
rm
a
ti
c
s
a
n
d
Co
mm
u
n
ica
t
io
n
T
e
c
h
n
o
l
o
g
y
(IJ
-
ICT
)
,
v
o
l.
8
,
n
o.
3
,
p
p
.
1
1
7
-
1
2
1
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
5
9
1
/
ij
ict.
v
8
i
3
.
[2
7
]
Ab
u
b
a
k
a
r
Ya
k
u
b
Na
sir,
U.
I.
Ba
t
u
re
,
N.
M
.
Ta
h
ir,
A.
Y.
Ba
b
a
wu
r
o
,
Ad
o
y
i
Bo
n
ifac
e
A.
M
.
Ha
ss
a
n
,
“
Ard
u
i
n
o
b
a
se
d
g
a
s
lea
k
a
g
e
c
o
n
tro
l
a
n
d
tem
p
e
ra
t
u
re
m
o
n
it
o
ri
n
g
sy
ste
m
,”
I
n
ter
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
In
f
o
rm
a
ti
c
s
a
n
d
Co
mm
u
n
ica
ti
o
n
T
e
c
h
n
o
l
o
g
y
(IJ
-
ICT
)
, v
o
l.
9
,
n
o.
3
,
p
p
.
1
7
1
-
1
7
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
ji
c
t.
v
9
i
3
.
p
p
1
7
1
-
1
7
8
.
[2
8
]
Ha
ry
a
G
u
sd
e
v
i,
Ad
e
S
e
ty
a
P
a
n
d
P
u
ji
Ha
n
d
in
i
Z
u
lae
h
a
,
“
P
ro
t
o
ty
p
e
o
f
LP
G
g
a
s
lea
k
a
g
e
d
e
tec
to
r
u
sin
g
flam
e
se
n
so
r
a
n
d
,
M
Q
-
2
se
n
s
o
r
,”
Co
mp
u
ter
S
c
ien
c
e
a
n
d
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
ies
,
v
o
l.
1
,
n
o
.
1
,
2
0
2
0
,
p
p
.
3
2
-
3
8
,
d
o
i
:
1
0
.
1
1
5
9
1
/cs
it
.
v
1
i
1
.
p
3
2
-
3
8
.
[2
9
]
Xin
g
-
y
u
P
e
n
g
,
P
e
n
g
h
a
n
g
,
Li
-
q
i
o
n
g
C
h
e
n
,
“
Lo
n
g
-
Dista
n
c
e
Oi
l/
G
a
s
P
ip
e
li
n
e
F
a
il
u
re
Ra
te
P
re
d
i
c
ti
o
n
Ba
se
d
On
F
u
z
z
y
Ne
u
ra
l
Ne
two
rk
M
o
d
e
l
,”
©
2
0
0
8
IEE
E
,
I
n
2
0
0
9
W
RI
W
o
rld
Co
n
g
re
ss
o
n
Co
mp
u
ter
S
c
ien
c
e
a
n
d
I
n
fo
rm
a
ti
o
n
En
g
i
n
e
e
rin
g
,
v
o
l.
5
,
p
p
.
6
5
1
-
6
5
5
,
d
o
i:
1
0
.
1
1
0
9
/CS
IE
.
2
0
0
9
.
7
3
8
.
[3
0
]
Ll
u
ís
S
a
n
m
iq
u
e
l
,
M
a
rc
Ba
sc
o
m
p
ta,
Jo
se
p
M
.
R
o
ss
e
ll
,
He
rn
á
n
F
ra
n
c
isc
o
An
ti
c
o
i
a
n
d
Ed
u
a
rd
G
u
a
sh
,
“
An
a
l
y
sis
o
f
Oc
c
u
p
a
ti
o
n
a
l
Ac
c
id
e
n
ts
in
U
n
d
e
rg
ro
u
n
d
a
n
d
S
u
rfa
c
e
M
in
in
g
in
S
p
a
in
Us
in
g
Da
ta
-
M
in
i
n
g
Tec
h
n
iq
u
e
s
,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
Of
En
v
iro
n
me
n
t
a
l
Res
e
a
rc
h
An
d
Pu
b
li
c
He
a
lt
h
,
v
o
l.
1
5
,
n
o
.
3
,
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
ij
e
rp
h
1
5
0
3
0
4
6
2
.
[3
1
]
E.
L.
P
a
n
k
ra
t
o
v
,
“
On
a
p
p
r
o
a
c
h
f
o
r
h
o
m
o
g
e
n
e
it
y
in
c
re
a
sin
g
o
f
f
il
m
s
g
ro
wn
fro
m
t
h
e
g
a
s
p
h
a
se
with
a
c
c
o
u
n
t
n
a
t
u
ra
l
c
o
n
v
e
c
ti
o
n
a
n
d
c
h
a
n
g
e
s
in
t
h
e
ra
te
o
f
c
h
e
m
ica
l
in
tera
c
ti
o
n
b
e
twe
e
n
m
a
teria
ls
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
s
in
A
p
p
li
e
d
S
c
ien
c
e
s (IJAA
S
),
v
o
l.
8
,
n
o
.
3
,
p
p
.
1
9
5
-
2
0
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
ij
a
a
s.v
8
.
i3
.
p
p
1
9
5
-
2
0
3
.
[3
2
]
R
F
Ra
h
m
a
t,
I
S
S
a
tri
a
,
B
S
ire
g
a
r,
R
Bu
d
iarto
,
“
Wate
r
P
ip
e
li
n
e
M
o
n
it
o
rin
g
a
n
d
Lea
k
De
tec
ti
o
n
u
si
n
g
F
lo
w
Li
q
u
i
d
M
e
ter
S
e
n
so
r
,”
Pro
c
e
e
d
in
g
o
f
t
h
e
El
e
c
trica
l
En
g
i
n
e
e
rin
g
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
I
n
fo
rm
a
ti
c
s,
IOP
Co
n
fer
e
n
c
e
S
e
rie
s: M
a
t
e
ria
ls
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
X/
1
9
0
/1
/
0
1
2
0
3
6
.
[3
3
]
S
h
e
n
g
n
a
n
Wu
a
,
Lai
b
in
Zh
a
n
g
a
,
Jia
n
c
h
u
n
F
a
n
a
,
Xim
in
g
Z
h
a
n
g
b
,
Di
Li
u
a
,
De
g
u
o
Wa
n
g
a
,
”
A
lea
k
a
g
e
d
iag
n
o
si
s
tes
ti
n
g
m
o
d
e
l
fo
r
g
a
s
we
ll
s
with
s
u
sta
in
e
d
c
a
sin
g
p
re
ss
u
re
fro
m
o
ff
sh
o
re
p
latf
o
rm
,”
J
o
u
rn
a
l
o
f
N
a
tu
r
a
l
Ga
s
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
v
o
l.
5
5
,
p
p
.
2
7
6
-
2
8
7
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
1
6
/
j.
j
n
g
se
.
2
0
1
8
.
0
5
.
0
0
6
.
[3
4
]
Do
n
g
y
u
F
e
n
g
,
P
a
o
la
P
a
ss
a
lac
q
u
a
a
n
d
Be
n
R.
Ho
d
g
e
s,
”
In
n
o
v
a
ti
v
e
Ap
p
ro
a
c
h
e
s
fo
r
G
e
o
m
e
t
ric
Un
c
e
rtain
t
y
Qu
a
n
ti
fi
c
a
ti
o
n
in
a
n
O
p
e
ra
ti
o
n
a
l
Oil
S
p
il
l
M
o
d
e
li
n
g
S
y
ste
m
,”
J
o
u
rn
a
l
Of
M
a
rin
e
S
c
ien
c
e
A
n
d
E
n
g
i
n
e
e
rin
g
,
v
o
l.
7
,
n
o
.
8
,
p
.
2
5
9
,
2
0
1
9
,
d
o
i:
1
0
.
3
3
9
0
/j
m
se
7
0
8
0
2
5
9
.
[3
5
]
S
é
b
a
stien
An
g
e
ll
iau
m
e
,
Bre
n
t
M
in
c
h
e
w,
S
o
p
h
ie
Ch
a
tain
g
,
P
h
il
ip
p
e
M
a
rti
n
e
a
u
,
a
n
d
Vé
ro
n
i
q
u
e
M
ieg
e
b
ielle
,
”
M
u
lt
ifreq
u
e
n
c
y
Ra
d
a
r
Im
a
g
e
r
y
a
n
d
C
h
a
ra
c
teriz
a
ti
o
n
o
f
Ha
z
a
rd
o
u
s
a
n
d
N
o
x
i
o
u
s
S
u
b
sta
n
c
e
s
a
t
S
e
a
,”
IE
EE
T
ra
n
sa
c
ti
o
n
s O
n
Ge
o
sc
ien
c
e
An
d
Rem
o
te S
e
n
si
n
g
,
v
o
l.
5
5
,
n
o
.
5
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
0
2
/9
7
8
1
1
1
9
8
0
1
8
4
9
.
c
h
2
.
[3
6
]
Arn
t
-
Bø
rre
S
a
lb
e
r
g
,
M
e
m
b
e
r,
I
E
EE
,
a
n
d
S
iri
Ø
y
e
n
Lars
e
n
,
“
Clas
sifi
c
a
ti
o
n
o
f
Oc
e
a
n
S
u
rfa
c
e
S
li
c
k
s
in
S
imu
late
d
Hy
b
ri
d
-
P
o
larim
e
tri
c
S
AR
Da
ta
,”
IEE
E
T
ra
n
sa
c
t
i
o
n
s
On
Ge
o
sc
ien
c
e
An
d
Rem
o
te
S
e
n
sin
g
,
v
o
l.
5
6
,
n
o
.
1
2
,
2
0
1
8
,
d
o
i:
1
0
.
1
1
0
9
/T
G
RS
.
2
0
1
8
.
2
8
4
7
7
2
4
.
[3
7
]
S
h
e
n
g
Xu
,
Zh
o
u
h
u
a
X
u
,
Yi
L
iu
,
“
Op
ti
m
a
l
Disp
a
tc
h
o
f
Oil
S
p
il
l
Re
so
u
rc
e
s
Co
n
si
d
e
rin
g
Re
so
u
rc
e
P
ri
o
rit
y
,”
2
0
1
6
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
telli
g
e
n
t
T
r
a
n
sp
o
rt
a
ti
o
n
E
n
g
in
e
e
rin
g
,
2
0
1
6
,
p
p
.
7
6
-
7
9
,
d
o
i
:
1
0
.
1
2
8
7
/m
n
sc
.
3
1
.
1
2
.
1
4
7
5
.
[3
8
]
D.
P
e
d
r
o
sa
,
A.
Dia
s,
A.
M
a
rti
n
s,
J.
Alm
e
id
a
1
a
n
d
E.
S
i
lv
a
,
“
Co
n
tro
l
-
law
fo
r
Oil
S
p
il
l
M
it
i
g
a
ti
o
n
wit
h
a
n
Au
to
n
o
m
o
u
s S
u
r
fa
c
e
Ve
h
icle
,”
©2
0
1
8
IE
EE
,
p
p
.
1
-
6
,
2
0
1
8
,
d
o
i:
1
0
.
1
1
0
9
/OCEANSKOBE.
2
0
1
8
.
8
5
5
9
3
9
7
.
[3
9
]
Ho
n
g
lei
Z
h
e
n
g
,
Ali
Kh
e
n
c
h
a
f,
He
lmi
G
h
a
n
m
i,
Yu
n
h
u
a
Wan
g
,
Ch
a
o
fa
n
g
Z
h
a
o
,
“
No
rm
a
li
z
e
d
Ra
d
a
r
Cro
ss
S
e
c
ti
o
n
s
Of
S
e
a
S
u
r
fa
c
e
Esti
m
a
ted
Us
in
g
As
y
m
p
to
ti
c
An
d
S
e
m
i
-
Emp
iri
c
a
l
M
e
th
o
d
s
I
n
C
Ba
n
d
,”
©2
0
1
8
I
EE
E
,
9
7
8
-
1
-
5
3
8
6
-
7
1
5
0
-
4
,
2
0
1
8
,
p
p
.
5
3
-
5
6
,
d
o
i:
1
0
.
1
1
0
9
/I
G
ARSS
.
2
0
1
8
.
8
5
1
8
0
2
9
.
[4
0
]
Ju
a
n
Li
,
Qia
n
g
Z
h
e
n
g
,
Z
h
ih
o
n
g
Qia
n
,
Xia
o
p
i
n
g
Ya
n
g
,
“
A
n
o
v
e
l
lo
c
a
ti
o
n
a
lg
o
r
it
h
m
f
o
r
p
i
p
e
li
n
e
le
a
k
a
g
e
b
a
se
d
o
n
th
e
a
tt
e
n
u
a
ti
o
n
o
f
n
e
g
a
ti
v
e
p
re
ss
u
re
wa
v
e
,”
Pro
c
e
ss
S
a
fety
a
n
d
E
n
v
iro
n
me
n
t
a
l
Pr
o
tec
ti
o
n
,
v
o
l
.
1
2
3
,
p
p
.
3
0
9
-
3
1
6
,
2
0
1
9
,
d
o
i:
10.
1
0
1
6
/
j.
p
se
p
.
2
0
1
9
.
0
1
.
0
1
0
.
[4
1
]
Eze
o
fo
r
Ch
u
k
w
u
n
a
z
o
J
o
se
p
h
,
G
e
o
rg
e
will
O
y
e
n
g
i
y
e
M
o
se
s,
“
P
ro
t
o
ty
p
e
d
e
v
e
l
o
p
m
e
n
t
o
f
tet
h
e
re
d
u
n
d
e
rwa
ter
ro
b
o
t
fo
r
u
n
d
e
rwa
ter
v
e
ss
e
l
a
n
c
h
o
r
re
le
a
se
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ro
b
o
ti
c
s
a
n
d
Au
t
o
ma
t
io
n
(IJ
RA
)
,
v
o
l.
9
,
n
o.
3
,
p
p
.
196
-
2
1
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
ij
ra
.
v
9
i
3
.
p
p
1
9
6
-
2
1
0
.
[4
2
]
Th
e
a
n
o
De
v
e
l
o
p
m
e
n
t
Tea
m
,
“
De
e
p
Lea
rn
in
g
T
u
to
r
ial
,”
Re
lea
se
0
.
1
,
L
I
S
A
l
a
b
,
Un
ive
rs
it
y
o
f
M
o
n
tre
a
l
,
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
s
u
r
ve
y
o
n
p
r
ed
ictin
g
o
il sp
ills
b
y
s
tu
d
yin
g
its
ca
u
s
e
s
u
s
in
g
d
ee
p
lea
r
n
in
g
…
(
Mo
n
a
Mo
h
a
med
N
a
s
r
)
589
[4
3
]
F
e
n
g
Li
a
,
We
n
h
e
Wan
g
b
,
c
,
Jia
n
g
Xu
a
,
Ju
n
Yia
,
Qin
g
sh
e
n
g
Wan
g
c
,
”
Co
m
p
a
ra
ti
v
e
st
u
d
y
o
n
v
u
l
n
e
ra
b
il
it
y
a
ss
e
ss
m
e
n
t
fo
r
u
rb
a
n
b
u
ried
g
a
sp
ip
e
li
n
e
n
e
two
r
k
b
a
se
d
o
n
S
VM
a
n
d
AN
N
m
e
th
o
d
s
,”
Pr
o
c
e
ss
S
a
fety
a
n
d
En
v
iro
n
me
n
ta
l
Pro
tec
ti
o
n
,
v
o
l
.
1
2
2
,
p
p
.
2
3
-
3
2
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
1
6
/j
.
p
se
p
.
2
0
1
8
.
1
1
.
0
1
4
.
[4
4
]
Ch
e
n
,
B.
,
P
o
latk
a
n
,
G
.
,
S
a
p
iro
,
G
,
“
De
e
p
lea
rn
in
g
with
h
iera
rc
h
ica
l
c
o
n
v
o
l
u
ti
o
n
a
l
fa
c
to
r
a
n
a
l
y
sis
,”
IEE
E
T
ra
n
s.
Pa
tt
e
rn
A
n
a
l.
M
a
c
h
.
In
tell,
v
o
l.
3
5
,
p
p
.
1
8
8
7
-
1
9
0
1
,
2
0
1
3
,
d
o
i:
1
0
.
1
1
0
9
/T
P
AMI
.
2
0
1
3
.
1
9
.
[4
5
]
Zh
a
n
g
,
X.Y.,
Zo
u
,
J.H.,
He
,
K.
M
.
,
S
u
n
,
J,
“
Ac
c
e
lera
ti
n
g
v
e
ry
d
e
e
p
c
o
n
v
o
lu
ti
o
n
a
l
n
e
two
rk
s
fo
r
c
las
sifica
ti
o
n
a
n
d
d
e
tec
ti
o
n
,”
IE
EE
T
ra
n
s.
P
a
tt
e
rn
An
a
l.
M
a
c
h
.
In
tell
,
v
o
l.
3
8
,
p
p
.
1
9
4
3
-
1
9
5
5
,
2
0
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
TP
AMI.
2
0
1
5
.
2
5
0
2
5
7
9
.
[4
6
]
Lo
n
g
,
J,
S
h
e
l
h
a
m
e
r,
E,
Da
rre
ll
,
T,
“
F
u
ll
y
c
o
n
v
o
lu
ti
o
n
a
l
n
e
two
r
k
s fo
r
se
m
a
n
ti
c
se
g
m
e
n
tatio
n
,”
In
Pro
c
e
e
d
in
g
s o
f
t
h
e
IEE
E
Co
n
fer
e
n
c
e
o
n
Co
mp
u
ter
V
isio
n
a
n
d
P
a
tt
e
rn
Rec
o
g
n
it
io
n
,
B
o
sto
n
,
M
A,
USA,
7
-
1
2
Ju
n
e
2
0
1
5
.
[4
7
]
Im
a
n
e
Ha
c
h
c
h
a
n
e
,
Ab
d
e
lma
ji
d
Ba
d
ri,
A
c
h
a
S
a
h
e
l,
Ya
ss
in
e
Ru
i
c
h
e
k
,
“
Larg
e
-
sc
a
le
ima
g
e
-
to
-
v
id
e
o
fa
c
e
re
tri
e
v
a
l
with
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
fe
a
tu
re
s
,”
I
AE
S
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Arti
fi
c
i
a
l
I
n
telli
g
e
n
c
e
(IJ
-
AI)
,
v
o
l.
9
,
n
o
.
1
,
p
p
.
4
0
-
4
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
jai.
v
9
.
i
1
.
p
p
4
0
-
45.
[4
8
]
Ha
o
G
u
o
,
Da
n
n
i
W
u
a
n
d
Ju
b
a
i
An
,
“
Disc
rimin
a
ti
o
n
o
f
Oil
S
li
c
k
s
a
n
d
Lo
o
k
a
li
k
e
s
in
P
o
larim
e
tr
ic
S
AR
Im
a
g
e
s
Us
in
g
CNN
,”
S
e
n
so
rs
,
v
o
l.
1
7
,
2
0
1
6
,
p
.
1
8
3
7
,
d
o
i:
1
0
.
3
3
9
0
/s1
7
0
8
1
8
3
7
.
[4
9
]
S
u
n
g
‐Hw
a
n
P
a
rk
1
,
Hy
u
n
g
‐S
u
p
Ju
n
g
1
,
a
n
d
M
o
u
n
g
‐Ji
n
Lee
,
“
Oil
S
p
il
l
M
a
p
p
i
n
g
fro
m
Ko
m
p
sa
t‐2
Hig
h
‐Re
so
l
u
ti
o
n
Im
a
g
e
Us
in
g
Dire
c
ti
o
n
a
l
M
e
d
ian
F
il
terin
g
a
n
d
Arti
ficia
l
Ne
u
ra
l
Ne
two
rk
,”
Rem
o
te
S
e
n
s
.
v
o
l
.
1
2
,
n
o
.
2
,
p
.
2
5
3
,
2
0
2
0
,
d
o
i:
1
0
.
3
3
9
0
/rs
1
2
0
2
0
2
5
3
.
[5
0
]
Zh
u
o
fa
n
Ya
n
,
Ji
n
so
n
g
Ch
o
n
g
,
Ya
we
i
Zh
a
o
,
Ka
i
S
u
n
,
Y
u
h
a
n
g
W
a
n
g
,
a
n
d
Ya
n
Li
,
“
M
u
l
ti
fe
a
tu
re
F
u
sio
n
Ne
u
ra
l
Ne
two
rk
f
o
r
Oc
e
a
n
ic
P
h
e
n
o
m
e
n
a
De
tec
ti
o
n
in
S
AR
Im
a
g
e
s
,”
S
e
n
so
rs
,
v
o
l.
2
0
,
n
o
.
1
,
p
.
2
1
0
,
d
o
i:
1
0
.
3
3
9
0
/s
2
0
0
1
0
2
1
0
.
[5
1
]
Am
iru
l
S
a
d
i
k
in
M
d
Afe
n
d
i,
M
a
rin
a
Yu
so
ff
,
“
Re
v
iew
o
f
a
n
o
m
a
lo
u
s
s
o
u
n
d
e
v
e
n
t
d
e
tec
ti
o
n
a
p
p
r
o
a
c
h
e
s
,
”
IAE
S
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Art
if
icia
l
In
telli
g
e
n
c
e
(IJ
-
AI),
v
o
l.
8
,
n
o
.
3
,
p
p
.
2
6
4
-
2
6
9
,
2
0
1
9
,
doi
:
1
0
.
1
1
5
9
1
/i
jai.
v
8
.
i3
.
p
p
2
6
4
-
2
6
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.