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.
43
,
No
.
1
,
J
u
l
y
2
0
2
6
,
p
p
.
325
~
33
4
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
43
.i
1
.
pp
325
-
33
4
325
J
o
ur
na
l
ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Ana
ly
sis
of P
M
2
.
5
pollu
tant so
urce
s in Ja
ka
rta using
deep
lea
rning
mo
dels a
nd ba
ck
trajec
tory
appro
a
ch
H
endro
P
ra
t
a
m
a
Sa
ra
g
ih,
I
m
a
s
Su
k
a
esih
Sita
ng
g
a
ng
,
H
endra
Ra
hm
a
wa
n
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
S
c
h
o
o
l
o
f
D
a
t
a
S
c
i
e
n
c
e
,
M
a
t
h
e
m
a
t
i
c
s
a
n
d
I
n
f
o
r
ma
t
i
c
s,
I
P
B
U
n
i
v
e
r
si
t
y
,
B
o
g
o
r
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
2
3
,
2
0
2
5
R
ev
is
ed
J
u
n
1
6
,
2
0
2
6
Acc
ep
ted
J
u
n
2
7
,
2
0
2
6
P
M
2
.
5
c
o
n
c
e
n
trati
o
n
s
i
n
Ja
k
a
rta
fre
q
u
e
n
tl
y
e
x
c
e
e
d
Wo
rl
d
He
a
lt
h
Org
a
n
iza
ti
o
n
(W
HO
)
a
ir
q
u
a
li
t
y
g
u
i
d
e
li
n
e
s,
in
d
ica
ti
n
g
th
e
n
e
e
d
fo
r
a
n
in
teg
ra
ted
a
p
p
ro
a
c
h
fo
r
p
o
ll
u
ti
o
n
p
re
d
icti
o
n
a
n
d
s
o
u
rc
e
a
ss
e
ss
m
e
n
t.
T
h
is
stu
d
y
d
e
v
e
lo
p
s
a
sp
a
ti
o
tem
p
o
ra
l
p
re
d
ictio
n
fra
m
e
wo
rk
u
sin
g
a
lo
n
g
s
h
o
rt
-
term
m
e
m
o
ry
(LS
TM
)
m
o
d
e
l
i
n
teg
ra
ted
wit
h
t
h
e
h
y
b
ri
d
sin
g
l
e
p
a
rti
c
le
Lag
ra
n
g
ian
in
teg
ra
ted
t
ra
jec
to
ry
(HY
S
P
LIT
)
m
o
d
e
l
fo
r
b
a
c
k
wa
rd
traje
c
to
ry
a
n
a
ly
sis.
Da
il
y
P
M
2
.
5
d
a
ta
fro
m
fiv
e
m
o
n
it
o
rin
g
sta
ti
o
n
s
we
re
c
o
m
b
in
e
d
with
m
e
teo
r
o
lo
g
ica
l
v
a
riab
les
fr
o
m
ERA5
,
Visu
a
lcr
o
ss
in
g
,
a
n
d
th
e
g
lo
b
a
l
d
a
ta
a
ss
imilatio
n
sy
ste
m
,
wit
h
sp
a
ti
a
l
c
o
n
te
x
t
e
v
a
lu
a
te
d
u
si
n
g
S
e
n
ti
n
e
l
-
2
lan
d
c
o
v
e
r
m
a
p
s.
Afte
r
h
y
p
e
rp
a
ra
m
e
ter
tu
n
in
g
,
th
e
o
p
ti
m
ize
d
m
o
d
e
l
d
e
m
o
n
stra
ted
r
o
b
u
st
p
re
d
icti
v
e
c
a
p
a
b
il
it
ies
,
a
c
h
iev
i
n
g
a
p
e
a
k
c
o
e
f
ficie
n
t
o
f
d
e
term
in
a
ti
o
n
(
R
2
)
o
f
7
5
.
8
7
%
o
n
th
e
tes
t
d
a
ta.
Th
e
fra
m
e
wo
rk
e
x
h
ib
it
e
d
e
x
c
e
p
ti
o
n
a
l
re
lati
v
e
a
c
c
u
ra
c
y
,
p
a
rti
c
u
larly
a
t
t
h
e
Ja
g
a
k
a
rsa
a
n
d
Ke
b
u
n
Je
ru
k
sta
ti
o
n
s,
wh
ich
re
c
o
r
d
e
d
m
e
a
n
a
b
so
lu
te
p
e
rc
e
n
tag
e
e
rro
r
(M
APE
)
v
a
l
u
e
s
o
f
1
3
.
3
4
%
a
n
d
1
7
.
8
0
%
,
re
s
p
e
c
ti
v
e
ly
.
Ba
c
k
wa
rd
traje
c
to
r
y
a
n
a
l
y
sis
d
u
r
in
g
se
lec
ted
p
o
ll
u
t
io
n
e
p
iso
d
e
s
in
d
ica
tes
two
d
o
m
in
a
n
t
re
g
i
o
n
a
l
tran
sp
o
rt
p
a
th
wa
y
s
th
a
t
m
a
y
in
fl
u
e
n
c
e
P
M
2
.
5
lev
e
ls
in
Ja
k
a
rta.
Th
e
se
p
a
th
wa
y
s
a
re
a
ss
o
c
iate
d
with
a
ir
m
a
ss
tran
sp
o
rt
o
v
e
r
in
d
u
strial
a
n
d
b
u
il
t
-
u
p
a
re
a
s
in
e
a
ste
rn
a
n
d
n
o
rth
e
r
n
re
g
i
o
n
s
s
u
rr
o
u
n
d
i
n
g
Ja
k
a
rta.
Lan
d
c
o
v
e
r
a
n
a
ly
sis
sh
o
ws
li
m
it
e
d
v
e
g
e
tatio
n
a
lo
n
g
t
h
e
se
p
a
th
wa
y
s.
Ov
e
ra
ll
,
e
lev
a
ted
P
M
2
.
5
e
v
e
n
ts
a
re
a
ss
o
c
iate
d
with
c
o
m
b
in
e
d
l
o
c
a
l
e
m
issio
n
s,
re
g
i
o
n
a
l
tran
s
p
o
rt,
a
n
d
m
e
teo
ro
lo
g
ica
l
c
o
n
d
it
i
o
n
s t
h
a
t
li
m
it
p
o
l
lu
tan
t
d
is
p
e
rsio
n
n
e
a
r
t
h
e
su
rfa
c
e
.
K
ey
w
o
r
d
s
:
B
ac
k
war
d
tr
ajec
to
r
y
HYSPLI
T
L
STM
PM2
.
5
R
eg
io
n
al
tr
an
s
p
o
r
t
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
:
I
m
as Su
k
ae
s
ih
Sit
an
g
g
an
g
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
Sch
o
o
l
o
f
Data
Scien
ce
,
Ma
th
em
atics a
n
d
I
n
f
o
r
m
atics,
I
PB
Un
iv
er
s
ity
1
6
6
8
0
Dr
am
ag
a
,
B
o
g
o
r
,
I
n
d
o
n
esia
E
m
ail:
im
as.si
tan
g
g
an
g
@
ap
p
s
.
ip
b
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
J
a
k
a
r
t
a
f
a
c
e
s
a
s
e
r
i
o
u
s
c
h
a
ll
en
g
e
i
n
a
i
r
q
u
al
i
t
y
m
a
n
a
g
e
m
e
n
t
,
w
it
h
d
a
t
a
[
1
]
s
h
o
wi
n
g
t
h
a
t
t
h
e
a
n
n
u
a
l
a
v
e
r
a
g
e
P
M
2
.
5
c
o
n
c
e
n
t
r
at
i
o
n
r
e
a
c
h
e
s
1
0
8
.
6
μg/
m³
,
f
a
r
e
x
c
e
e
d
i
n
g
t
h
e
W
o
r
l
d
H
ea
l
t
h
Or
g
a
n
i
z
a
t
i
o
n
(
W
H
O
)
i
n
t
e
r
i
m
ta
r
g
e
t
o
f
3
5
μ
g
/
m
³
[
2
]
.
T
h
i
s
h
i
g
h
le
v
e
l
o
f
p
o
ll
u
t
i
o
n
is
tr
i
g
g
e
r
e
d
b
y
m
a
s
s
i
v
e
a
n
t
h
r
o
p
o
g
e
n
i
c
a
c
ti
v
i
t
ie
s
,
a
s
a
r
e
s
u
l
t
o
f
v
a
r
i
o
u
s
t
r
a
n
s
p
o
r
t
a
ti
o
n
a
c
t
i
v
i
t
i
es
,
b
o
t
h
d
o
m
e
s
t
i
c
a
n
d
in
d
u
s
t
r
i
a
l
,
a
s
we
l
l
a
s
c
o
n
s
t
r
u
c
t
io
n
a
c
t
i
v
i
t
i
es
a
i
m
e
d
a
t
i
m
p
r
o
v
i
n
g
t
h
e
ci
t
y
'
s
i
n
f
r
as
t
r
u
c
t
u
r
e
.
A
i
r
q
u
a
li
t
y
i
n
J
a
k
a
r
t
a
is
i
n
f
l
u
e
n
c
e
d
b
y
r
e
l
a
ti
v
e
l
y
s
t
a
g
n
a
n
t
m
e
t
e
o
r
o
l
o
g
i
c
al
c
o
n
d
i
t
i
o
n
s
,
w
it
h
a
v
e
r
a
g
e
s
u
r
f
ac
e
w
i
n
d
s
p
e
e
d
s
r
a
n
g
i
n
g
f
r
o
m
1
.
5
t
o
2
.
0
m
/
s
.
T
h
e
d
o
m
i
n
a
n
t
e
a
s
t
w
a
r
d
wi
n
d
p
a
t
t
e
r
n
c
a
r
r
i
e
s
a
c
c
u
m
u
la
t
e
d
p
o
l
l
u
t
a
n
ts
f
r
o
m
t
h
e
b
u
f
f
e
r
z
o
n
e
[
2
]
.
T
h
e
h
e
a
l
t
h
a
n
d
e
n
v
i
r
o
n
m
e
n
t
a
l
i
m
p
ac
t
s
o
f
t
h
i
s
s
i
t
u
at
i
o
n
a
r
e
s
i
g
n
i
f
i
c
a
n
t
.
A
s
t
u
d
y
b
y
Di
n
a
s
L
i
n
g
k
u
n
g
a
n
H
i
d
u
p
P
r
o
v
in
s
i
D
K
I
J
a
k
a
r
t
a
[
3
]
f
o
u
n
d
a
p
o
s
i
t
i
v
e
c
o
r
r
e
l
a
ti
o
n
b
e
t
w
e
e
n
a
n
i
n
c
r
e
as
e
i
n
P
M
2
.
5
a
n
d
a
1
2
%
s
u
r
g
e
i
n
c
as
e
s
o
f
a
cu
t
e
r
e
s
p
i
r
at
o
r
y
i
n
f
e
c
t
i
o
n
s
(
A
R
I
)
.
Desp
ite
its
h
ig
h
u
r
g
en
cy
,
t
h
e
cu
r
r
en
t
air
q
u
ality
m
an
a
g
em
en
t
s
y
s
tem
h
as
f
u
n
d
am
en
tal
l
im
itatio
n
s
.
T
h
e
r
esear
ch
h
ig
h
lig
h
ts
th
at
tr
ad
itio
n
al
em
is
s
io
n
s
o
u
r
ce
a
n
aly
s
is
b
ased
o
n
s
tatic
in
v
en
to
r
ies
f
ails
to
ac
co
u
n
t
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.
43
,
No
.
1
,
J
u
ly
20
26
:
325
-
33
4
326
f
o
r
r
ea
l
-
tim
e
atm
o
s
p
h
er
ic
d
y
n
am
ics.
Fu
r
th
e
r
m
o
r
e
,
co
n
v
en
tio
n
al
p
r
ed
ictio
n
m
eth
o
d
s
o
f
ten
n
e
g
lect
th
e
in
teg
r
atio
n
o
f
cr
u
cial
atm
o
s
p
h
er
ic
p
ar
am
eter
s
,
as
cr
iticiz
ed
[
4
]
.
W
h
ile
m
o
s
t
p
r
i
o
r
s
tu
d
ies
f
o
cu
s
o
n
air
q
u
ality
p
r
ed
ictio
n
o
r
s
o
u
r
ce
an
al
y
s
is
as
is
o
lated
task
s
,
th
is
s
tu
d
y
b
r
id
g
es
th
e
g
a
p
b
y
p
r
o
p
o
s
in
g
a
n
o
v
el,
in
teg
r
ated
s
y
s
tem
ar
ch
itectu
r
e.
Sp
ec
if
ic
ally
,
th
is
is
th
e
f
ir
s
t
in
teg
r
at
ed
lo
n
g
s
h
o
r
t
-
te
r
m
m
em
o
r
y
(
L
STM
)
an
d
h
y
b
r
id
s
in
g
le
p
ar
ticle
L
ag
r
an
g
ian
i
n
teg
r
ated
tr
ajec
to
r
y
(
HYSPLI
T
)
f
r
am
ewo
r
k
ap
p
lied
to
J
ak
ar
ta
t
h
at
co
m
b
in
es
lo
ca
l
m
eteo
r
o
lo
g
ical
m
o
n
ito
r
in
g
wi
th
s
atellite
v
alid
atio
n
(
Sen
tin
el
-
2
)
f
o
r
p
r
ec
is
e
s
o
u
r
ce
attr
ib
u
tio
n
.
T
h
is
en
d
-
to
-
en
d
f
r
am
ewo
r
k
n
o
t
o
n
ly
f
o
r
ec
asts
tem
p
o
r
al
PM2
.
5
co
n
ce
n
tr
atio
n
s
b
u
t
also
d
y
n
am
ica
lly
tr
ig
g
er
s
s
p
at
ial
b
ac
k
war
d
tr
ajec
to
r
y
a
n
aly
s
is
to
h
ig
h
lig
h
t
tr
an
s
b
o
u
n
d
a
r
y
e
m
is
s
io
n
co
r
r
id
o
r
s
,
p
r
o
v
id
in
g
a
cr
u
cial,
ac
tio
n
a
b
le
to
o
l
f
o
r
r
eg
io
n
al
air
q
u
ality
p
o
licy
an
d
e
n
g
in
ee
r
i
n
g
ea
r
l
y
-
war
n
in
g
s
y
s
tem
s
.
T
h
e
r
esear
ch
[
5
]
h
as
d
em
o
n
s
tr
ated
th
at
th
e
L
STM
m
o
d
el
is
ca
p
a
b
le
o
f
p
r
ed
ictin
g
PM2
.
5
with
h
ig
h
ac
c
u
r
ac
y
(R
2
>
0
.
9
)
,
wh
ic
h
in
th
is
s
tu
d
y
will
b
e
co
m
b
in
ed
with
th
e
HYSPLI
T
m
o
d
el
f
o
r
cr
o
s
s
-
b
o
r
d
er
em
i
s
s
io
n
s
o
u
r
ce
tr
ac
k
in
g
,
v
alid
ated
f
o
r
ef
f
ec
tiv
e
n
ess
by
[
6
]
,
to
p
r
o
d
u
ce
an
ea
r
ly
wa
r
n
in
g
s
y
s
tem
an
d
m
itig
atio
n
th
at
is
m
o
r
e
p
r
ec
is
e.
2.
M
E
T
H
O
D
T
h
is
s
tu
d
y
co
m
p
r
is
es
s
ev
er
al
s
tag
es:
d
ata
p
r
ep
ar
atio
n
,
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
m
o
d
el
tr
ain
in
g
,
h
y
p
er
p
ar
am
eter
tu
n
in
g
,
m
o
d
e
l
test
in
g
,
HYSPLI
T
s
im
u
lat
i
o
n
,
an
d
PM2
.
5
s
o
u
r
ce
an
aly
s
is
.
Deta
il
s
o
f
th
e
r
esear
ch
s
tag
es a
r
e
p
r
esen
ted
i
n
Fig
u
r
e
1
.
Fig
u
r
e
1
.
R
esear
ch
s
tep
s
2
.
1
.
Da
t
a
c
o
llec
t
io
n
T
h
e
d
ataset
u
s
ed
v
ar
io
u
s
s
o
u
r
ce
s
[
7
]
r
elev
an
t
to
th
e
r
esea
r
ch
f
o
cu
s
,
n
am
ely
PM2
.
5
c
o
n
ce
n
tr
atio
n
p
r
ed
ictio
n
s
an
d
s
o
u
r
ce
tr
ac
k
in
g
,
co
v
er
i
n
g
th
e
p
e
r
io
d
f
r
o
m
J
a
n
u
ar
y
2
0
2
2
to
Dec
em
b
er
2
0
2
4
.
PM2
.
5
d
ata
wer
e
o
b
tain
ed
v
ia
web
s
cr
ap
in
g
(
w
ith
p
er
m
is
s
io
n
f
r
o
m
th
e
o
wn
e
r
,
J
ak
ar
ta
E
n
v
ir
o
n
m
en
tal
Ser
v
ice)
f
r
o
m
R
en
d
ah
E
m
is
i
J
ak
ar
ta
W
eb
.
T
h
e
d
ata
p
r
o
v
id
es
d
aily
air
q
u
ality
in
f
o
r
m
atio
n
f
r
o
m
s
ev
er
al
m
o
n
ito
r
in
g
s
tatio
n
s
.
Me
an
wh
ile,
m
eteo
r
o
lo
g
ical
d
ata
wer
e
o
b
tain
ed
f
r
o
m
two
s
o
u
r
ce
s
:
E
R
A5
C
o
p
e
r
n
icu
s
(
E
u
r
o
p
ea
n
C
en
tr
e
f
o
r
Me
d
iu
m
-
R
an
g
e
W
ea
th
er
Fo
r
ec
asts
:
E
C
MW
F)
[
8
]
,
[
9
]
an
d
Vis
u
al
cr
o
s
s
in
g
[
1
0
]
f
o
r
m
o
d
el
-
p
r
ed
ictio
n
in
p
u
t
f
ea
tu
r
es
[
1
1
]
,
[
1
2
]
,
a
n
d
g
lo
b
a
l
d
ata
ass
im
ilatio
n
s
y
s
tem
(
G
DAS
)
o
f
th
e
Natio
n
al
Oce
a
n
ic
an
d
Atm
o
s
p
h
er
ic
Ad
m
in
is
tr
atio
n
(
NOAA
)
as
in
p
u
t
f
o
r
HYS
PLI
T
s
im
u
latio
n
s
.
Data
co
llectio
n
was
ca
r
r
ied
o
u
t
b
y
in
teg
r
atin
g
d
atasets
f
r
o
m
v
ar
io
u
s
s
o
u
r
ce
s
to
s
u
p
p
o
r
t
co
m
p
r
e
h
en
s
iv
e
s
p
atio
tem
p
o
r
al
an
aly
s
is
,
in
clu
d
in
g
d
aily
PM2
.
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
n
a
lysi
s
o
f P
M2
.
5
p
o
llu
t
a
n
t s
o
u
r
ce
s
in
Ja
ka
r
ta
u
s
in
g
d
ee
p
l
ea
r
n
in
g
mo
d
els
… (
Hen
d
r
o
P
r
a
ta
ma
S
a
r
a
g
ih
)
327
co
n
ce
n
tr
atio
n
d
ata
o
b
tain
ed
t
h
r
o
u
g
h
web
s
cr
a
p
in
g
tech
n
iq
u
es
f
r
o
m
th
e
J
ak
ar
ta
R
en
d
ah
E
m
is
i
web
p
o
r
tal
at
f
iv
e
m
o
n
ito
r
in
g
s
tatio
n
s
(
J
an
2
0
2
2
–
Dec
2
0
2
4
)
,
g
lo
b
al
m
eteo
r
o
lo
g
ical
d
ata
(
tem
p
er
atu
r
e,
h
u
m
id
ity
,
win
d
,
r
ain
f
all,
an
d
d
ew
p
o
in
t
)
f
r
o
m
E
R
A5
C
o
p
er
n
icu
s
,
Vis
u
alcr
o
s
s
in
g
,
an
d
GDAS,
as
well
as
s
p
atial
lan
d
co
v
e
r
d
ata
an
d
ae
r
o
s
o
l
o
p
tical
d
ep
th
(A
OD)
ex
tr
ac
te
d
f
r
o
m
Sen
tin
el
-
2
an
d
MO
DI
S
s
atellite
im
ag
er
y
u
s
in
g
Go
o
g
le
E
ar
th
E
n
g
i
n
e
(
GE
E
)
[
1
3
]
.
2
.
2
.
Da
t
a
pre
pro
ce
s
s
ing
T
h
e
d
ata
p
r
ep
r
o
ce
s
s
in
g
s
tag
e
is
ap
p
lied
to
en
s
u
r
e
th
e
q
u
ality
o
f
m
o
d
el
in
p
u
t,
s
tar
t
in
g
with
th
e
h
an
d
lin
g
o
f
m
is
s
in
g
v
alu
es
u
s
in
g
lin
ea
r
in
ter
p
o
latio
n
t
o
m
ain
tain
th
e
co
n
tin
u
ity
o
f
th
e
tim
e
tr
en
d
,
f
o
llo
wed
b
y
th
e
n
o
r
m
aliza
tio
n
o
f
all
v
ar
ia
b
les
to
th
e
r
an
g
e
0
u
n
til
1
u
s
in
g
Min
-
Ma
x
Scaler
f
o
r
tr
ain
in
g
s
tab
ilit
y
,
an
d
en
d
in
g
with
ch
r
o
n
o
lo
g
ica
l
d
ata
s
p
litt
in
g
in
to
7
0
%
tr
ain
in
g
d
ata,
1
5
%
v
alid
atio
n
d
ata,
an
d
1
5
%
test
d
ata
[
1
4
]
to
ev
alu
ate
th
e
m
o
d
el'
s
g
en
er
a
lizatio
n
ab
ilit
y
o
n
f
u
tu
r
e
d
ata.
2
.
3
.
T
ra
ini
ng
t
he
L
ST
M
m
o
del f
o
r
P
M
2
.
5
predict
io
n
L
STM
m
o
d
el
tr
ain
in
g
was
c
o
n
d
u
cte
d
u
s
in
g
a
m
u
ltiv
ar
iate
tim
e
-
s
er
ies
d
ataset
[
1
5
]
th
a
t
h
ad
b
ee
n
n
o
r
m
alize
d
with
a
Min
-
Ma
x
Scaler
an
d
ar
r
an
g
ed
in
to
a
s
e
q
u
en
ce
o
f
3
0
tim
estep
s
to
p
r
ed
ict
d
aily
PM
2
.
5
co
n
ce
n
tr
atio
n
s
o
n
e
s
tep
ah
ea
d
.
T
h
e
m
o
d
el
ar
ch
itectu
r
e
co
n
s
is
ted
o
f
two
s
tack
ed
L
STM
la
y
er
s
f
o
llo
wed
b
y
a
d
en
s
e
f
u
lly
co
n
n
ec
te
d
lay
er
a
s
th
e
o
u
tp
u
t,
with
th
e
lear
n
in
g
p
r
o
ce
s
s
o
p
tim
ized
u
s
in
g
th
e
Ad
am
alg
o
r
ith
m
,
s
ig
m
o
id
,
an
d
r
m
s
p
r
o
p
[
1
6
]
,
a
n
d
an
ea
r
ly
s
to
p
p
in
g
m
ec
h
a
n
is
m
to
m
itig
ate
th
e
r
is
k
o
f
o
v
er
f
i
ttin
g
[
1
7
]
.
Fig
u
r
e
2
illu
s
tr
ates
th
e
ar
ch
i
tectu
r
e
o
f
th
e
d
ee
p
lear
n
in
g
m
o
d
el
e
m
p
lo
y
e
d
in
th
is
s
tu
d
y
,
wh
ic
h
p
r
o
ce
s
s
es
s
ix
m
eteo
r
o
l
o
g
ical
in
p
u
t
f
ea
t
u
r
es
v
ia
a
h
id
d
en
la
y
er
co
m
p
r
is
in
g
s
tack
ed
L
ST
M
u
n
its
with
b
atch
n
o
r
m
aliza
tio
n
an
d
d
r
o
p
o
u
t,
to
p
r
ed
ict
PM2
.
5
co
n
ce
n
tr
atio
n
.
T
h
e
n
etwo
r
k
ar
ch
it
ec
tu
r
e
u
til
izes
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
as
th
e
lo
s
s
f
u
n
ctio
n
,
wh
ich
is
h
ig
h
ly
s
u
itab
le
f
o
r
r
eg
r
ess
io
n
task
s
in
co
n
tin
u
o
u
s
p
o
llu
tan
t
co
n
ce
n
tr
atio
n
f
o
r
e
ca
s
tin
g
.
T
h
e
s
elec
ted
tem
p
o
r
al
win
d
o
w
o
f
3
0
tim
estep
s
was
ex
p
licitly
ch
o
s
en
as
it
o
p
tim
ally
ca
p
tu
r
es
th
e
m
o
n
th
l
y
cy
clica
l
p
atter
n
s
o
f
lo
ca
l
m
e
teo
r
o
lo
g
y
an
d
an
th
r
o
p
o
g
en
ic
e
m
is
s
io
n
s
in
J
ak
ar
ta
with
o
u
t in
tr
o
d
u
cin
g
e
x
ce
s
s
iv
e
h
is
to
r
ical
n
o
is
e.
Fig
u
r
e
2
.
Mu
ltiv
a
r
iate
L
STM
m
o
d
els ar
ch
itectu
r
e
2
.
4
.
H
y
perpa
ra
m
e
t
er
t
un
i
ng
o
n L
ST
M
m
o
de
ls
Hy
p
er
p
ar
a
m
eter
tu
n
i
n
g
is
p
e
r
f
o
r
m
e
d
to
o
p
tim
ize
th
e
L
S
T
M
ar
ch
itectu
r
e.
T
h
e
m
ain
p
ar
am
eter
s
ad
ju
s
ted
in
clu
d
e
th
e
n
u
m
b
e
r
o
f
h
id
d
e
n
lay
er
s
,
th
e
n
u
m
b
e
r
o
f
n
eu
r
o
n
s
p
er
la
y
er
,
th
e
d
r
o
p
o
u
t
r
ate,
th
e
ep
o
ch
s
ize,
an
d
th
e
ac
tiv
atio
n
f
u
n
ctio
n
[
1
8
]
.
I
n
a
d
d
itio
n
,
t
h
e
ea
r
ly
s
to
p
p
in
g
tech
n
i
q
u
e
is
u
s
ed
to
p
r
ev
en
t
o
v
er
f
itti
n
g
,
an
d
v
ar
io
u
s
lea
r
n
in
g
r
ate
v
alu
es
an
d
o
p
tim
izatio
n
alg
o
r
ith
m
s
ar
e
test
ed
.
T
h
ese
ad
j
u
s
tm
en
ts
ar
e
m
a
d
e
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.
43
,
No
.
1
,
J
u
ly
20
26
:
325
-
33
4
328
iter
ativ
ely
b
ased
o
n
v
alid
atio
n
ev
alu
atio
n
r
esu
lts
to
s
elec
t
th
e
m
o
d
el
co
n
f
i
g
u
r
atio
n
th
a
t
p
r
o
v
id
es
th
e
b
est
p
er
f
o
r
m
an
ce
.
T
h
e
h
y
p
e
r
p
ar
a
m
eter
tu
n
in
g
p
r
o
ce
s
s
u
s
es
a
g
r
id
s
ea
r
ch
[
1
9
]
,
[
2
0
]
to
test
v
ar
io
u
s
p
ar
am
ete
r
co
m
b
in
atio
n
s
.
T
h
e
g
r
i
d
p
ar
a
m
eter
s
u
s
ed
ar
e
s
h
o
wn
in
T
ab
le
1
.
Hy
p
er
p
ar
a
m
eter
tu
n
i
n
g
was
p
er
f
o
r
m
ed
to
f
in
d
th
e
o
p
tim
al
co
n
f
ig
u
r
atio
n
f
o
r
th
e
L
ST
M
m
o
d
el.
T
h
r
o
u
g
h
a
g
r
id
s
ea
r
ch
ap
p
r
o
ac
h
,
v
ar
io
u
s
co
m
b
i
n
atio
n
s
o
f
p
ar
am
eter
s
s
u
ch
as th
e
n
u
m
b
er
o
f
h
id
d
en
lay
er
s
an
d
n
eu
r
o
n
s
,
d
r
o
p
o
u
t
r
ate,
ep
o
ch
s
ize,
an
d
ac
tiv
atio
n
f
u
n
ctio
n
w
er
e
test
ed
iter
ativ
ely
.
T
ab
le
1
.
Gr
id
s
ea
r
ch
p
ar
a
m
eter
f
o
r
m
u
ltiv
ar
iate
L
STM
m
o
d
el
No
P
a
r
a
me
t
e
r
V
a
l
u
e
1
O
p
t
i
mi
z
e
r
a
d
a
m,
n
a
d
a
m,
r
ms
p
r
o
p
,
sg
d
2
Le
a
r
n
i
n
g
R
a
t
e
0.
0
0
0
1
,
0
.
0
0
1
,
0
.
0
1
,
0
.
1
3
LSTM
un
i
t
s
1
6
,
3
2
,
6
4
4
D
r
o
p
o
u
t
r
a
t
e
0
.
2
5
Ep
o
c
h
1
0
0
0
w
i
t
h
e
a
r
l
y
st
o
p
p
i
n
g
6
B
a
t
c
h
si
ze
32
2
.
5
.
L
ST
M
m
o
del f
o
r
P
M
2
.
5
predict
io
n
T
h
e
L
STM
m
o
d
el
was
test
ed
b
y
a
p
p
ly
in
g
th
e
tr
ain
e
d
m
o
d
el
to
a
test
s
et
co
m
p
r
is
in
g
s
ep
ar
ate
p
er
io
d
d
ata
th
at
th
e
m
o
d
el
h
a
d
n
ev
e
r
s
ee
n
b
ef
o
r
e
to
e
v
alu
ate
its
g
en
er
aliza
tio
n
ab
ilit
y
an
d
p
r
e
d
ictio
n
ac
cu
r
ac
y
i
n
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
.
M
o
d
el
p
er
f
o
r
m
an
ce
was
co
m
p
r
eh
en
s
iv
ely
v
alid
ate
d
b
y
co
m
p
a
r
in
g
th
e
p
r
ed
icted
d
aily
PM2
.
5
co
n
ce
n
t
r
atio
n
v
alu
es
with
ac
tu
al
o
b
s
er
v
atio
n
d
ata
u
s
in
g
ev
alu
atio
n
m
etr
ics,
n
am
e
ly
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
or
(
R
MSE
)
,
m
ea
n
ab
s
o
lu
t
e
er
r
o
r
(
MA
E
)
,
m
ea
n
a
b
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
(
MA
PE
)
,
an
d
co
ef
f
icien
t
o
f
d
eter
m
in
atio
n
(
R
2
)
,
to
ass
ess
t
h
e
ac
cu
r
ac
y
o
f
t
h
e
d
ata
d
is
tr
ib
u
tio
n
p
atter
n
.
1.
R
MSE
m
ea
s
u
r
es h
o
w
f
ar
th
e
p
r
ed
ictio
n
r
esu
lts
ar
e
f
r
o
m
th
e
a
ctu
al
v
alu
es
[
2
1
]
. T
h
e
R
MSE
f
o
r
m
u
la
is
:
R
M
SE
=
√
1
N
∑
(
yi
−
y
̂
i
)
2
N
i
=
1
(
1
)
2.
MA
E
to
m
ea
s
u
r
e
th
e
a
v
er
ag
e
ab
s
o
lu
te
er
r
o
r
[
2
1
]
.
T
he
f
o
llo
win
g
is
th
e
m
ath
em
atica
l
of
M
AE
f
o
r
m
u
la
:
MAE
=
1
N
∑
|
yi
−
y
̂
i
|
N
i
=
1
(
2
)
3.
R
²
Sco
r
e
as a
n
in
d
icato
r
o
f
g
o
o
d
n
ess
-
of
-
f
it
[
2
1
]
. T
h
e
m
ath
e
m
atica
l e
q
u
atio
n
f
o
r
th
e
R
²
f
o
r
m
u
la
is
:
R
2
=
1
−
∑
(
yi
−
y
̂
i
)
2
N
i
=
1
∑
(
yi
−
y
̅
i
)
2
N
i
=
1
(
3
)
4.
MA
PE
to
ca
lcu
late
th
e
a
b
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
[
2
2
]
.
T
h
e
f
o
llo
win
g
is
th
e
m
ath
em
atica
l
eq
u
a
tio
n
f
o
r
th
e
MA
PE
f
o
r
m
u
la
:
M
A
PE
=
∑
|
yi
−
y
̂
i
y
̂
i
|
N
i
=
1
(
4
)
wh
er
e:
yi
:
a
ctu
al
v
alu
e
i
y
̂
i
:
t
h
e
i
-
th
p
r
ed
icted
v
al
u
e
y
̅
i
:
t
h
e
av
er
ag
e
o
f
all
ac
tu
al
v
al
u
es (
yi
)
N
: t
o
tal
n
u
m
b
er
o
f
o
b
s
er
v
atio
n
s
T
h
is
v
er
if
icatio
n
s
tep
s
er
v
es
a
s
a
q
u
ality
g
ate
to
en
s
u
r
e
th
e
r
eliab
ilit
y
o
f
p
r
ed
ictio
n
s
b
ef
o
r
e
th
ey
ar
e
f
u
r
th
er
i
n
teg
r
ated
with
t
h
e
HYSPLI
T
tr
ajec
to
r
y
s
im
u
latio
n
.
2
.
6
.
H
YSPLI
T
s
im
ula
t
io
n
Fro
m
an
en
g
in
ee
r
in
g
s
y
s
tem
p
er
s
p
ec
tiv
e,
th
e
HYSPLI
T
b
ac
k
war
d
tr
ajec
to
r
y
s
er
v
es
as
a
d
y
n
am
icall
y
tr
ig
g
er
ed
atm
o
s
p
h
e
r
ic
v
e
r
if
ica
tio
n
m
o
d
u
le.
I
t
is
a
u
to
n
o
m
o
u
s
l
y
ac
tiv
ated
o
n
l
y
wh
e
n
th
e
L
S
T
M
p
r
e
d
icts
PM2
.
5
co
n
ce
n
tr
atio
n
s
ex
ce
e
d
in
g
7
5
µg
/m
³.
T
h
is
s
p
ec
if
ic
th
r
esh
o
ld
is
s
tr
o
n
g
ly
ju
s
tifie
d
as
it
alig
n
s
with
th
e
'
Un
h
ea
lth
y
'
ca
teg
o
r
y
u
n
d
e
r
I
n
d
o
n
esia'
s
Air
Po
llu
tio
n
St
an
d
ar
d
I
n
d
ex
(
I
SP
U)
,
en
s
u
r
in
g
th
at
th
e
h
ig
h
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
n
a
lysi
s
o
f P
M2
.
5
p
o
llu
t
a
n
t s
o
u
r
ce
s
in
Ja
ka
r
ta
u
s
in
g
d
ee
p
l
ea
r
n
in
g
mo
d
els
… (
Hen
d
r
o
P
r
a
ta
ma
S
a
r
a
g
ih
)
329
co
m
p
u
tatio
n
al
co
s
t
o
f
s
p
atial
tr
ajec
to
r
y
s
im
u
latio
n
s
is
ef
f
ici
en
tly
allo
ca
ted
o
n
ly
d
u
r
i
n
g
ex
tr
em
e,
h
ig
h
-
im
p
ac
t
p
o
llu
tio
n
e
p
is
o
d
es
[
2
3
]
.
I
n
th
i
s
s
ce
n
ar
io
,
th
e
HYSPLI
T
m
o
d
el
r
u
n
s
a
7
2
-
h
o
u
r
b
ac
k
war
d
tr
ajec
to
r
y
an
aly
s
is
at
an
altit
u
d
e
o
f
5
0
0
m
eter
s
ab
o
v
e
g
r
o
u
n
d
lev
el
u
s
in
g
win
d
d
ata
f
r
o
m
GDAS,
to
tr
ac
k
ai
r
m
ass
tr
ajec
to
r
ies
an
d
id
en
tify
th
e
g
e
o
g
r
ap
h
ical
o
r
i
g
in
s
o
f
r
eg
io
n
al
p
o
ten
tial
p
o
llu
tan
t
s
o
u
r
ce
s
[
2
4
]
co
n
tr
ib
u
tin
g
to
p
o
llu
tio
n
ep
is
o
d
es in
J
ak
ar
ta.
2
.
7
.
Ana
ly
s
is
o
f
P
M
2
.
5
s
o
u
rces
Valid
atio
n
with
s
atellite
d
ata,
s
u
ch
as
Sen
tin
el
-
2
,
p
lay
s
a
k
e
y
r
o
le
in
th
is
in
teg
r
atio
n
.
L
an
d
u
s
e
d
ata
f
r
o
m
Sen
tin
el
-
2
h
elp
s
class
if
y
p
o
ten
tial
p
o
llu
tan
t
s
o
u
r
ce
s
,
s
u
ch
as
d
is
tin
g
u
is
h
in
g
b
etw
ee
n
em
is
s
io
n
s
an
d
v
eg
etatio
n
[
2
5
]
.
Ad
d
itio
n
ally
,
s
atellite
AOD
d
ata
is
u
s
ed
to
co
r
r
ec
t
s
u
r
f
ac
e
p
o
llu
tan
t
c
o
n
ce
n
tr
atio
n
s
.
A
ca
s
e
s
tu
d
y
in
B
eijin
g
s
h
o
ws
t
h
at
i
n
teg
r
atio
n
o
f
Sen
tin
el
-
2
d
ata
with
HYSPLI
T
ca
n
r
ed
u
ce
u
n
ce
r
tain
ty
i
n
s
o
u
r
ce
id
en
tific
atio
n
[
2
6
]
.
So
m
e
f
r
a
m
ewo
r
k
s
[
2
7
]
,
[
2
8
]
p
r
o
v
id
e
alg
o
r
ith
m
s
f
o
r
tr
ajec
t
o
r
y
clu
s
ter
in
g
,
co
n
n
ec
tin
g
p
o
llu
tio
n
p
ea
k
s
t
o
d
o
m
in
an
t
s
o
u
r
ce
s
,
a
n
d
v
is
u
alizin
g
r
esu
lts
in
GI
S.
An
e
x
am
p
le
o
f
its
s
u
cc
ess
f
u
l
ap
p
licatio
n
is
th
e
Me
k
o
n
g
Delta,
wh
er
e
th
is
f
r
am
ewo
r
k
h
elp
ed
id
e
n
tify
PM2
.
5
s
o
u
r
ce
s
f
r
o
m
lan
d
f
i
r
es
[
6
]
.
T
h
is
ap
p
r
o
ac
h
no
t o
n
l
y
im
p
r
o
v
es a
n
aly
s
is
ac
cu
r
ac
y
b
u
t a
ls
o
f
ac
ilit
ates d
ata
v
is
u
aliza
tio
n
an
d
in
te
r
p
r
etatio
n
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3.
1
.
Da
t
a
prepr
o
ce
s
s
ing
T
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tag
e
is
a
cr
u
cial
p
h
ase
f
o
r
en
s
u
r
in
g
o
p
tim
al
d
ata
q
u
ality
an
d
s
tr
u
ctu
r
e
f
o
r
th
e
L
STM
ar
ch
itectu
r
e.
B
ef
o
r
e
d
a
ta
p
r
o
ce
s
s
in
g
,
it is
n
ec
ess
ar
y
t
o
an
aly
ze
th
e
m
is
s
in
g
v
alu
es f
r
o
m
ea
ch
s
tatio
n
,
as
s
h
o
wn
in
T
ab
le
2
.
T
h
en
,
c
o
m
p
ar
e
th
e
s
tatis
tical
s
u
m
m
ar
y
v
alu
es
f
r
o
m
ea
ch
s
tatio
n
f
o
r
t
h
e
PM2
.
5
v
ar
ia
b
le
b
ef
o
r
e
p
r
ep
r
o
ce
s
s
in
g
,
as
s
h
o
w
n
in
T
ab
le
3
,
an
d
th
e
s
tatis
tic
al
s
u
m
m
ar
y
v
alu
es
af
ter
p
r
ep
r
o
ce
s
s
in
g
,
as
s
h
o
wn
in
T
ab
le
4
.
T
ab
le
2
.
Nu
m
b
er
o
f
m
is
s
in
g
v
alu
e
in
PM2
.
5
Data
P
M
2
.
5
s
t
a
t
i
o
n
N
u
m
b
e
r
o
f
d
a
t
a
M
i
ss
i
n
g
va
l
u
e
s
D
K
I
1
B
u
n
d
a
r
a
n
H
I
8
9
5
2
0
1
D
K
I
2
K
e
l
a
p
a
G
a
d
i
n
g
9
9
4
1
0
2
D
K
I
3
J
a
g
a
k
a
r
s
a
8
9
5
2
0
1
D
K
I
4
Lu
b
a
n
g
B
u
a
y
a
8
9
5
2
0
1
D
K
I
5
K
e
b
u
n
J
e
r
u
k
8
9
5
2
0
1
T
ab
le
3
.
Su
m
m
a
r
y
o
f
PM2
.
5
d
ata
s
tatis
t
ics b
ef
o
r
e
d
ata
p
r
e
p
r
o
ce
s
s
in
g
P
M
2
.
5
s
t
a
t
i
o
n
N
u
mb
e
r
o
f
d
a
t
a
A
v
e
r
a
g
e
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
M
i
n
M
e
d
i
a
n
M
a
x
D
K
I
1
B
u
n
d
a
r
a
n
H
I
8
9
5
7
0
.
1
6
2
1
.
5
2
0
7
3
.
5
0
1
2
5
.
1
6
D
K
I
2
K
e
l
a
p
a
G
a
d
i
n
g
9
9
4
5
6
.
4
9
1
9
.
6
1
0
6
9
.
5
2
1
0
9
.
5
0
D
K
I
3
J
a
g
a
k
a
r
s
a
8
9
5
7
1
.
6
1
1
9
.
4
5
0
7
2
.
6
1
1
3
7
.
1
6
D
K
I
4
L
u
b
a
n
g
B
u
a
y
a
8
9
5
7
2
.
4
7
2
0
.
7
0
0
7
5
.
5
5
1
3
1
.
7
2
D
K
I
5
K
e
b
u
n
J
e
r
u
k
8
9
5
5
6
.
4
9
3
7
.
9
4
0
6
8
.
8
0
1
5
3
.
7
7
T
ab
le
4
.
Su
m
m
a
r
y
s
tatis
tics
o
f
PM2
.
5
d
ata
af
ter
d
ata
p
r
ep
r
o
c
ess
in
g
P
M
2
.
5
S
t
a
t
i
o
n
N
u
mb
e
r
o
f
d
a
t
a
A
v
e
r
a
g
e
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
M
i
n
M
e
d
i
a
n
M
a
x
D
K
I
1
B
u
n
d
a
r
a
n
H
I
1096
7
0
.
2
1
1
9
.
7
3
3
.
3
3
7
3
.
0
3
1
2
5
.
1
7
D
K
I
2
K
e
l
a
p
a
G
a
d
i
n
g
1096
6
6
.
4
0
2
0
.
2
3
0
.
7
2
6
8
.
1
3
1
0
9
.
5
5
D
K
I
3
J
a
g
a
k
a
r
s
a
1096
7
1
.
1
6
1
7
.
8
9
2
.
5
5
7
1
.
8
4
1
3
7
.
1
6
D
K
I
4
Lu
b
a
n
g
B
u
a
y
a
1096
7
1
.
4
7
2
0
.
3
9
7
.
3
9
7
5
.
0
8
1
3
1
.
7
2
D
K
I
5
K
e
b
u
n
J
e
r
u
k
1096
7
0
.
0
3
2
0
.
9
2
4
.
2
2
6
8
.
9
1
1
5
3
.
7
7
3
.
2
.
L
ST
M
mo
del
T
h
e
p
r
ed
ictio
n
m
o
d
el
was d
ev
elo
p
ed
u
s
in
g
a
m
u
ltiv
ar
iate
L
S
T
M
ar
ch
itectu
r
e
o
p
tim
ize
d
th
r
o
u
g
h
g
r
id
s
ea
r
ch
to
d
eter
m
in
e
th
e
b
est
h
y
p
er
p
ar
am
eter
s
(
n
u
m
b
e
r
o
f
n
eu
r
o
n
s
,
lear
n
in
g
r
ate,
o
p
tim
i
ze
r
)
at
ea
ch
s
tatio
n
.
T
ab
le
5
s
h
o
ws
th
e
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
r
el
iab
le
m
o
d
el,
as
in
d
icate
d
b
y
th
e
h
ig
h
est
R
2
v
alu
e
o
f
7
5
.
8
7
%
at
th
e
DKI
1
B
u
n
d
ar
a
n
HI
Statio
n
an
d
th
e
l
o
west
MA
PE
o
f
1
3
.
3
4
%
at
th
e
DKI
3
J
ag
ak
ar
s
a
Statio
n
,
d
em
o
n
s
tr
atin
g
t
h
e
m
o
d
el'
s
ef
f
ec
tiv
en
ess
in
ca
p
tu
r
in
g
d
aily
P
M2
.
5
f
lu
ctu
atio
n
p
atter
n
s
.
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.
43
,
No
.
1
,
J
u
ly
20
26
:
325
-
33
4
330
T
h
e
v
a
r
ian
ce
in
p
r
e
d
ictiv
e
p
er
f
o
r
m
an
ce
ac
r
o
s
s
s
tatio
n
s
h
ig
h
l
ig
h
ts
th
e
in
f
lu
en
ce
o
f
lo
ca
l
u
r
b
an
m
icr
o
-
en
v
ir
o
n
m
en
ts
.
T
h
e
lo
west
MA
PE
ac
h
iev
ed
at
J
ag
ak
ar
s
a
(
1
3
.
3
4
%)
ca
n
b
e
attr
ib
u
t
ed
to
its
s
u
b
u
r
b
an
to
p
o
g
r
a
p
h
y
an
d
d
e
n
s
er
v
eg
et
atio
n
co
v
e
r
,
wh
ic
h
b
u
f
f
er
s
s
u
d
d
en
e
m
is
s
io
n
s
p
ik
es
an
d
r
esu
lts
in
m
o
r
e
s
tab
le
m
eteo
r
o
lo
g
ical
p
atter
n
s
.
C
o
n
v
er
s
ely
,
B
u
n
d
ar
a
n
HI
ac
h
ie
v
ed
th
e
h
ig
h
est
(
7
5
.
8
7
%)
d
u
e
to
its
h
ig
h
ly
r
h
y
th
m
ic
an
d
p
r
ed
ictab
le
an
th
r
o
p
o
g
en
ic
em
is
s
io
n
s
,
p
r
im
ar
ily
d
r
iv
en
b
y
d
en
s
e,
d
aily
v
eh
i
cu
lar
tr
af
f
ic
in
th
e
ce
n
tr
al
b
u
s
in
ess
d
is
tr
ict.
Fu
r
th
er
m
o
r
e,
wh
ile
th
e
o
v
er
all
v
alu
es
(
6
5
.
5
5
%
-
7
5
.
8
7
%)
d
em
o
n
s
tr
ate
m
o
d
e
r
ate
to
h
ig
h
p
r
ed
ictiv
e
ca
p
ab
ilit
y
,
t
h
eir
lim
itatio
n
s
m
u
s
t b
e
ac
k
n
o
wled
g
ed
.
T
h
e
m
o
d
el
o
cc
asio
n
ally
u
n
d
er
esti
m
ates
s
u
d
d
en
,
an
o
m
alo
u
s
p
ea
k
ev
en
ts
.
T
h
is
lim
itatio
n
s
tem
s
f
r
o
m
u
n
p
r
e
d
ictab
le
lo
ca
l
em
is
s
io
n
s
o
u
r
ce
s
(
s
u
d
d
en
waste
b
u
r
n
in
g
o
r
ab
r
u
p
t
co
n
s
tr
u
ctio
n
ac
tiv
ities
)
th
at
ar
e
n
o
t
ca
p
tu
r
ed
b
y
s
tan
d
ar
d
m
eteo
r
o
lo
g
ical
o
r
AOD
in
p
u
t
f
ea
tu
r
es.
L
STM
s
ig
n
if
ican
tly
ex
ce
l
s
in
ca
p
tu
r
in
g
n
o
n
-
lin
ea
r
tem
p
o
r
al
d
ep
en
d
en
cies,
th
o
u
g
h
f
u
tu
r
e
iter
atio
n
s
co
u
l
d
b
en
e
f
it
f
r
o
m
i
n
teg
r
atin
g
r
ea
l
-
tim
e
tr
af
f
ic
d
en
s
ity
API
s
to
f
u
r
th
er
p
u
s
h
th
e
b
o
u
n
d
ar
y
.
T
ab
le
5
.
L
STM
m
o
d
elin
g
ac
c
u
r
ac
y
r
esu
lts
f
o
r
ea
ch
PM2
.
5
m
o
n
ito
r
in
g
s
tatio
n
P
M
2
.
5
S
t
a
t
i
o
n
R
2
R
M
S
E
M
A
E
M
A
P
E
D
K
I
1
B
u
n
d
a
r
a
n
H
I
7
5
.
8
7
%
1
1
.
4
6
7
1
8
.
5
0
4
6
2
9
.
9
2
%
D
K
I
2
K
e
l
a
p
a
G
a
d
i
n
g
7
0
.
2
8
%
1
1
.
4
9
6
7
8
.
6
2
6
7
4
7
.
3
8
%
D
K
I
3
Ja
g
a
k
a
r
sa
6
5
.
5
5
%
9
.
6
8
0
8
7
.
3
6
0
4
1
3
.
3
4
%
D
K
I
4
Lu
b
a
n
g
B
u
a
y
a
7
0
.
0
1
%
1
2
.
6
0
6
9
9
.
3
3
2
8
1
6
.
3
5
%
D
K
I
5
K
e
b
u
n
J
e
r
u
k
7
4
.
5
5
%
1
4
.
2
4
9
3
1
0
.
1
9
7
2
1
7
.
8
0
%
3
.
3
.
H
YSPLI
T
si
m
ula
t
io
n
T
h
e
H
Y
S
P
L
I
T
b
a
c
k
w
a
r
d
t
r
a
j
e
c
t
o
r
y
s
i
m
u
l
a
t
i
o
n
w
a
s
c
o
n
d
u
c
t
e
d
in
r
e
s
p
o
n
s
e
to
a
n
ex
tr
em
e
p
o
llu
tio
n
ep
is
o
d
e
(
>7
5
μ
g
/m
³
)
an
d
co
n
ce
n
tr
atio
n
s
th
at
e
x
ce
ed
ed
th
e
th
r
esh
o
ld
s
s
et
b
y
n
atio
n
al
r
eg
u
latio
n
s
.
B
ased
o
n
th
e
I
n
d
o
n
esian
G
o
v
er
n
m
en
t
R
eg
u
latio
n
No
.
22
of
2
0
2
1
,
wh
i
ch
s
ets
th
e
a
m
b
ien
t
air
q
u
ality
s
tan
d
ar
d
(
NAB)
a
t
55
μ
g
/m
3
p
er
d
a
y
.
I
n
ac
co
r
d
a
n
ce
with
DKI
J
ak
ar
ta
Go
v
er
n
o
r
R
e
g
u
l
a
t
i
o
n
Nu
m
b
er
7
7
o
f
2
0
2
0
o
n
air
p
o
llu
tio
n
co
n
tr
o
l,
th
is
ex
tr
em
e
th
r
esh
o
ld
ex
ce
ed
an
ce
tr
ig
g
er
ed
an
i
n
v
e
s
tig
atio
n
in
to
th
e
s
o
u
r
ce
o
f
p
o
t
en
tial
p
o
llu
tan
ts
to
tr
ac
k
th
e
o
r
i
g
in
o
f
t
h
e
air
m
ass
d
u
r
in
g
th
e
p
r
ev
i
o
u
s
2
4
-
7
2
h
o
u
r
s
,
w
h
ich
s
u
cc
ess
f
u
lly
r
ev
ea
led
two
m
ain
co
r
r
i
d
o
r
s
of
r
eg
io
n
al
p
o
llu
ta
n
t
tr
an
s
p
o
r
t
f
r
o
m
th
e
ea
s
t
-
s
o
u
th
ea
s
t
an
d
n
o
r
th
-
n
o
r
th
west,
an
d
id
en
tifie
d
th
e
m
eteo
r
o
lo
g
ical
p
h
e
n
o
m
e
n
o
n
o
f
s
u
b
s
id
en
c
e
(
t
h
e
d
escen
t
o
f
air
m
ass
es
f
r
o
m
a
n
altitu
d
e
o
f
>
1000
m
to
th
e
s
u
r
f
ac
e)
wh
ich
p
lay
s
a
cr
u
cial
r
o
le
in
tr
a
p
p
in
g
p
o
llu
tan
ts
in
th
e
h
u
m
an
r
esp
ir
ato
r
y
tr
ac
t.
T
ab
le
6
d
escr
ib
es
th
e
ex
tr
em
e
p
o
llu
tan
t
ep
is
o
d
es
th
at
o
cc
u
r
r
ed
d
u
r
in
g
th
e
p
er
io
d
f
r
o
m
J
an
u
ar
y
2
0
2
2
to
Dec
em
b
er
2
0
2
4
.
B
ased
o
n
th
e
d
ata
d
is
tr
ib
u
tio
n
in
Fig
u
r
e
3
,
b
ac
k
war
d
tr
ajec
to
r
ies
wer
e
g
en
er
ate
d
f
o
r
ea
ch
PM2
.
5
m
o
n
ito
r
in
g
s
tatio
n
d
u
r
in
g
p
o
l
lu
ta
n
t
ep
is
o
d
e
s
,
as
s
h
o
wn
in
T
a
b
le
6
.
Fig
u
r
e
3
(
a
)
p
r
esen
ts
th
e
HYSPLI
T
b
ac
k
war
d
tr
ajec
to
r
y
f
o
r
th
e
DKI
1
B
u
n
d
ar
an
HI
Statio
n
,
Fig
u
r
e
3
(
b
)
f
o
r
th
e
DKI
2
Kela
p
a
Gad
in
g
Statio
n
,
Fig
u
r
e
3
(
c)
f
o
r
th
e
DKI
3
J
ag
ak
ar
s
a
Statio
n
,
Fig
u
r
e
3
(
d
)
f
o
r
th
e
DKI
4
L
u
b
an
g
B
u
ay
a
Statio
n
,
an
d
Fi
g
u
r
e
3
(
e)
f
o
r
th
e
DKI
5
Keb
u
n
J
er
u
k
Statio
n
.
T
h
ese
tr
ajec
t
o
r
ies
r
ev
ea
l
d
if
f
er
e
n
t
r
eg
io
n
al
tr
an
s
p
o
r
t
p
ath
way
s
o
f
air
m
ass
es
th
at
m
ay
co
n
tr
ib
u
te
to
elev
ated
PM2
.
5
co
n
ce
n
tr
atio
n
s
at
ea
c
h
m
o
n
ito
r
in
g
s
tatio
n
.
T
a
b
l
e
6
.
P
o
l
l
u
t
a
n
t
e
p
i
s
o
d
es
w
i
th
t
h
e
h
i
g
h
e
s
t
PM
2
.
5
c
o
n
c
e
n
t
r
a
ti
o
n
s
P
M
2
.
5
st
a
t
i
o
n
Lo
n
g
i
t
u
d
e
La
t
i
t
u
d
e
Ep
i
s
o
d
e
p
o
l
l
u
t
a
n
t
P
M
2
.
5
co
n
c
e
n
t
r
a
t
i
o
n
AOD
D
K
I
1
B
u
n
d
a
r
a
n
H
I
1
0
6
.
8
2
3
5
0
-
6
.
1
9
4
6
6
2
O
c
t
2
0
2
3
1
2
5
.
20
1
.
25
D
K
I
2
K
e
l
a
p
a
G
a
d
i
n
g
1
0
6
.
9
1
0
8
8
-
6
.
1
5
3
5
7
1
7
N
o
v
2
0
2
4
1
1
2
.
80
1
.
36
D
K
I
3
Ja
g
a
k
a
r
sa
1
0
6
.
8
0
3
6
7
-
6
.
3
5
6
9
3
1
8
Ju
n
2
0
2
4
1
3
7
.
20
1
.
88
D
K
I
4
Lu
b
a
n
g
B
u
a
y
a
1
0
6
.
9
0
9
1
9
-
6
.
2
8
8
8
9
2
8
S
e
p
2
0
2
3
1
2
3
.
60
2
.
71
D
K
I
5
K
e
b
u
n
J
e
r
u
k
1
0
6
.
7
5
3
1
8
-
6
.
2
0
7
3
4
1
7
N
o
v
2
0
2
4
1
5
3
.
8
0
1
.
89
T
o
m
ap
th
e
o
r
ig
in
s
o
f
air
m
a
s
s
es
ca
r
r
y
in
g
p
o
llu
ta
n
ts
d
u
r
in
g
ex
tr
em
e
p
o
llu
tio
n
ep
is
o
d
es,
HYSPLI
T
b
ac
k
war
d
tr
ajec
to
r
y
s
im
u
latio
n
s
wer
e
r
u
n
at
f
iv
e
s
elec
t
ed
m
o
n
ito
r
i
n
g
s
tatio
n
s
in
J
ak
ar
ta
wh
en
PM2
.
5
co
n
ce
n
tr
atio
n
s
e
x
ce
ed
ed
7
5
μ
g
/m
³.
T
h
is
s
u
m
m
ar
y
o
f
t
h
e
s
im
u
latio
n
r
esu
lts
p
r
esen
ts
k
ey
p
ar
a
m
eter
s
,
in
clu
d
in
g
th
e
tim
in
g
o
f
o
cc
u
r
r
en
ce
,
th
e
d
o
m
in
a
n
t
d
ir
ec
tio
n
o
f
air
-
m
ass
tr
ajec
to
r
ies,
an
d
th
e
id
en
tifie
d
v
er
tical
atm
o
s
p
h
er
ic
d
y
n
am
ics.
3
.
4
.
Ana
ly
s
is
o
f
P
M
2
.
5
s
o
urce
s
Po
llu
tan
t
s
o
u
r
ce
an
aly
s
is
was
co
n
d
u
cte
d
th
r
o
u
g
h
s
p
atial
in
te
g
r
atio
n
(
o
v
er
lay
)
b
etwe
en
th
e
HYSPLI
T
tr
ajec
to
r
ies.
T
h
e
Sen
tin
el
-
2
la
n
d
co
v
e
r
m
ap
,
wh
ich
v
alid
ated
th
at
th
e
air
m
ass
ca
r
r
y
in
g
th
e
p
o
llu
tan
ts
was
co
n
s
is
ten
tly
cr
o
s
s
in
g
a
r
ea
s
w
ith
h
ig
h
em
is
s
io
n
d
en
s
ities
s
u
ch
as
th
e
m
an
u
f
ac
t
u
r
in
g
in
d
u
s
tr
ial
co
r
r
id
o
r
in
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
n
a
lysi
s
o
f P
M2
.
5
p
o
llu
t
a
n
t s
o
u
r
ce
s
in
Ja
ka
r
ta
u
s
in
g
d
ee
p
l
ea
r
n
in
g
mo
d
els
… (
Hen
d
r
o
P
r
a
ta
ma
S
a
r
a
g
ih
)
331
Kar
awa
n
g
-
B
ek
asi,
h
ea
v
y
in
d
u
s
tr
ial
ar
ea
s
in
B
an
ten
,
an
d
co
al
-
f
ir
ed
p
o
wer
p
lan
ts
o
n
th
e
n
o
r
th
co
ast,
co
n
f
ir
m
s
th
at
ex
tr
em
e
p
o
llu
tio
n
in
J
ak
a
r
ta
is
th
e
r
esu
lt
o
f
a
s
u
p
er
p
o
s
i
tio
n
o
f
lo
ca
l
u
r
b
an
em
is
s
io
n
s
a
n
d
tr
a
n
s
b
o
u
n
d
ar
y
p
o
llu
tio
n
.
L
an
d
co
v
er
an
aly
s
is
is
ex
p
lai
n
ed
in
T
a
b
le
7
an
d
illu
s
tr
ated
f
o
r
all
m
o
n
ito
r
in
g
s
tatio
n
s
in
Fig
u
r
e
4
.
T
h
e
o
v
er
lay
r
esu
lts
b
etwe
en
th
e
E
s
r
i
Sen
tin
el
-
2
lan
d
co
v
e
r
m
ap
an
d
th
e
HYSPLI
T
b
ac
k
war
d
tr
ajec
to
r
ies
ar
e
p
r
esen
ted
in
Fig
u
r
e
4
.
Fig
u
r
e
4
(
a)
illu
s
tr
ates
th
e
DKI
1
B
u
n
d
ar
an
HI
Statio
n
,
Fig
u
r
e
4
(
b
)
s
h
o
ws
th
e
DKI
2
Kela
p
a
Gad
in
g
Statio
n
,
Fig
u
r
e
4
(
c)
p
r
esen
ts
th
e
DKI
3
J
ag
ak
ar
s
a
Statio
n
,
Fig
u
r
e
4
(
d
)
d
ep
icts
th
e
DKI
4
L
u
b
an
g
B
u
ay
a
Statio
n
,
an
d
Fi
g
u
r
e
4
(
e)
illu
s
tr
ates
th
e
DKI
5
Keb
u
n
J
er
u
k
St
atio
n
.
T
h
e
o
v
er
lay
d
em
o
n
s
tr
ates
th
at
th
e
air
-
m
ass
p
ath
way
s
in
ter
s
ec
t
d
if
f
er
en
t
lan
d
-
co
v
e
r
ty
p
es,
in
clu
d
in
g
b
u
ilt
-
u
p
ar
ea
s
,
in
d
u
s
tr
ial
zo
n
es,
ag
r
icu
ltu
r
al
lan
d
,
an
d
co
astal
r
eg
io
n
s
,
p
r
o
v
i
d
in
g
s
p
atial
ev
id
en
ce
f
o
r
id
en
tify
i
n
g
p
o
ten
ti
al
PM2
.
5
em
is
s
io
n
s
o
u
r
ce
s
.
(
a)
(
b
)
(
c)
(
d
)
(
e)
Fig
u
r
e
3
.
HYSPLI
T
b
ac
k
wa
r
d
tr
aj
ec
to
r
y
f
o
r
ea
ch
PM2
.
5
s
tatio
n
i
n
J
ak
ar
ta
:
(
a
)
DKI
1
B
u
n
d
ar
an
HI
Statio
n
,
(
b
)
DKI
2
Kela
p
a
Gad
in
g
Stati
o
n
,
(
c)
DKI
3
J
ag
ak
a
r
s
a
Statio
n
,
(
d
)
DKI
4
L
u
b
an
g
B
u
ay
a
Statio
n
,
(
e)
DKI
5
Keb
u
n
J
er
u
k
Statio
n
T
ab
le
7
.
R
esu
lt o
f
o
v
er
lay
lan
d
co
v
er
E
SR
I
Sen
tin
el2
an
d
H
YSPLI
T
tr
ajec
to
r
y
f
o
r
ea
ch
s
t
atio
n
PM2
.
5
M
o
n
i
t
o
r
i
n
g
st
a
t
i
o
n
D
o
mi
n
a
n
t
l
a
n
d
c
o
v
e
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
S
p
e
c
i
f
i
c
a
r
e
a
s
p
a
ss
e
d
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
p
o
t
e
n
t
i
a
l
e
mi
ss
i
o
n
s
o
u
r
c
e
s
D
K
I
1
B
u
n
d
a
r
a
n
H
I
B
u
i
l
t
-
u
p
a
r
e
a
s
& c
r
o
p
s
K
a
r
a
w
a
n
g
-
B
e
k
a
si
I
n
d
u
s
t
r
y
M
a
n
u
f
a
c
t
u
r
i
n
g
i
n
d
u
st
r
y
&
l
a
n
d
b
u
r
n
i
n
g
i
n
P
a
n
t
u
r
a
.
D
K
I
2
K
e
l
a
p
a
G
a
d
i
n
g
B
u
i
l
t
-
u
p
a
r
e
a
& w
a
t
e
r
P
r
i
o
k
&
M
a
r
u
n
d
a
P
o
r
t
s
Emi
ssi
o
n
s fr
o
m s
h
i
p
s,
p
o
r
t
s,
a
n
d
c
o
a
s
t
a
l
i
n
d
u
st
r
i
e
s.
D
K
I
3
Ja
g
a
k
a
r
sa
B
u
i
l
t
-
u
p
a
r
e
a
C
i
k
a
r
a
n
g
-
C
i
b
i
n
o
n
g
I
n
d
u
st
r
y
A
c
c
u
m
u
l
a
t
i
o
n
o
f
e
a
s
t
e
r
n
a
n
d
l
o
c
a
l
d
o
mest
i
c
i
n
d
u
st
r
i
a
l
e
m
i
ssi
o
n
s
.
D
K
I
4
Lu
b
a
n
g
B
u
a
y
a
B
u
i
l
t
-
u
p
a
r
e
a
(
d
e
n
se)
Jab
a
b
e
k
a
&
M
M
2
1
0
0
D
i
r
e
c
t
a
d
v
e
c
t
i
o
n
o
f
f
a
c
t
o
r
y
e
mi
ss
i
o
n
s
& h
e
a
v
y
l
o
g
i
s
t
i
c
s.
D
K
I
5
K
e
b
u
n
J
e
r
u
k
B
u
i
l
t
-
u
p
a
r
e
a
& c
r
o
p
s
C
i
l
e
g
o
n
&
S
e
r
a
n
g
I
n
d
u
st
r
i
e
s
C
r
o
ss
-
b
o
r
d
e
r
t
r
a
n
sp
o
r
t
a
t
i
o
n
f
o
r
B
a
n
t
e
n
p
o
w
e
r
p
l
a
n
t
s &
st
e
e
l
i
n
d
u
s
t
r
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.
43
,
No
.
1
,
J
u
ly
20
26
:
325
-
33
4
332
(
a)
(
b
)
(
c)
(
d
)
(
e)
F
i
g
u
r
e
4
.
O
v
e
r
l
a
y
l
a
n
d
c
o
v
e
r
E
s
r
i
Se
n
t
i
n
e
l
-
2
P
w
it
h
H
YS
P
L
I
T
b
a
c
k
w
a
r
d
t
r
a
j
e
ct
o
r
y
:
(
a
)
D
K
I
1
B
u
n
d
a
r
a
n
H
I
S
t
a
ti
o
n
(
b
)
D
K
I
2
K
e
l
a
p
a
G
a
d
i
n
g
S
t
a
t
i
o
n
(
c
)
DK
I
3
J
a
g
a
k
a
r
s
a
St
a
t
i
o
n
,
(
d
)
D
K
I
4
L
u
b
a
n
g
B
u
a
y
a
S
t
a
ti
o
n
,
a
n
d
(
e
)
D
K
I
5
K
e
b
u
n
J
e
r
u
k
St
a
t
i
o
n
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
s
u
cc
ess
f
u
lly
d
ev
el
o
p
ed
a
h
y
b
r
i
d
f
r
am
ewo
r
k
th
at
in
teg
r
ates
d
ee
p
lea
r
n
in
g
p
r
ed
i
ctio
n
s
an
d
s
p
atial
s
o
u
r
ce
an
al
y
s
is
to
m
o
d
el
PM2
.
5
p
o
llu
tio
n
in
J
ak
ar
ta.
T
h
e
m
u
ltiv
ar
iate
L
STM
m
o
d
el
b
u
ilt
s
h
o
we
d
th
e
b
est
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
a
t
th
e
DKI
1
B
u
n
d
ar
an
HI
Stati
o
n
(
R
2
v
alu
e
o
f
7
5
.
8
7
%)
an
d
th
e
h
ig
h
est
r
elativ
e
ac
cu
r
ac
y
at
th
e
DKI
3
J
ag
ak
ar
s
a
Statio
n
(
MA
PE
v
alu
e
o
f
1
3
.
3
4
%).
So
u
r
ce
a
n
aly
s
is
u
s
in
g
HYSPLI
T
b
ac
k
war
d
tr
ajec
to
r
ies
tr
ig
g
er
ed
wh
en
P
M2
.
5
co
n
ce
n
tr
atio
n
s
ex
ce
ed
e
d
th
e
th
r
esh
o
ld
7
5
μ
g
⁄m
3
r
e
v
ea
l
ed
s
p
ec
if
ic
p
o
llu
tan
t
tr
an
s
p
o
r
t p
att
er
n
s
d
u
r
in
g
ex
tr
e
m
e
p
o
llu
tio
n
ep
is
o
d
es f
r
o
m
J
an
u
ar
y
2
0
2
2
to
Dec
em
b
er
2
0
2
4
.
Sp
ec
if
ically
,
tr
ajec
to
r
y
an
aly
s
is
id
en
tifie
d
two
m
ain
co
r
r
id
o
r
s
f
o
r
r
e
g
io
n
al
p
o
llu
tan
t
tr
an
s
p
o
r
t.
Du
r
in
g
p
o
llu
tio
n
ep
is
o
d
es
at
J
ag
ak
ar
s
a
Statio
n
(
J
u
n
e
1
8
,
2
0
2
4
)
an
d
L
u
b
an
g
B
u
ay
a
Sta
tio
n
(
Sep
tem
b
er
2
8
,
2
0
2
3
)
.
Sp
atial
v
alid
atio
n
u
s
in
g
E
s
r
i
Sen
tin
el
-
2
lan
d
co
v
er
m
ap
s
c
o
n
f
ir
m
s
th
ese
f
i
n
d
in
g
s
with
s
u
r
f
ac
e
ev
id
en
ce
.
Fo
r
th
e
L
u
b
an
g
B
u
ay
a
Statio
n
,
th
e
air
-
m
ass
tr
an
s
p
o
r
t
p
ath
way
in
ter
s
ec
ts
lar
g
e
b
u
ilt
-
u
p
r
eg
i
o
n
s
o
f
th
e
C
ik
ar
an
g
–
B
ek
asi
in
d
u
s
tr
ial
co
r
r
id
o
r
,
wh
ich
m
ay
r
e
p
r
ese
n
t
a
p
o
ten
tial
r
eg
io
n
al
em
is
s
io
n
in
f
lu
en
ce
d
u
r
in
g
th
e
an
aly
ze
d
ep
is
o
d
e.
Me
a
n
wh
ile,
f
o
r
th
e
Keb
u
n
J
er
u
k
Statio
n
,
th
e
tr
ajec
to
r
y
c
r
o
s
s
es
a
m
o
s
aic
o
f
B
u
ilt
Ar
ea
in
C
ileg
o
n
-
Ser
an
g
an
d
cr
o
p
s
(
ag
r
icu
ltu
r
al
la
n
d
)
o
n
th
e
N
o
r
t
h
C
o
ast
o
f
B
an
ten
.
T
h
e
lack
o
f
v
e
g
etatio
n
c
o
v
er
an
d
tr
ee
s
alo
n
g
th
e
ad
v
ec
tio
n
p
ath
an
d
in
th
e
J
ak
ar
ta
r
ec
ep
t
o
r
ar
ea
in
d
icate
s
lo
w
n
atu
r
al
ab
s
o
r
p
tio
n
ca
p
ac
ity
(
s
in
k
s
)
,
a
c
o
n
d
itio
n
th
at
is
f
u
r
th
er
i
n
f
lu
en
ce
d
b
y
s
u
b
s
id
en
ce
-
r
elate
d
m
eteo
r
o
lo
g
ical
p
r
o
ce
s
s
es
(
air
m
ass
d
escen
t)
f
r
o
m
altitu
d
es
ex
ce
e
d
in
g
1
0
0
0
m
eter
s
,
wh
ich
p
r
o
m
o
te
th
e
ac
c
u
m
u
latio
n
o
f
b
o
t
h
r
eg
io
n
al
an
d
lo
ca
l
p
o
llu
tan
ts
with
in
th
e
s
u
r
f
ac
e
lay
er
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
th
an
k
t
h
e
J
ak
ar
ta
E
n
v
ir
o
n
m
en
tal
Ser
v
ice
f
o
r
p
r
o
v
id
in
g
p
o
llu
tan
t d
ata.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
th
an
k
th
e
Sch
o
o
l
o
f
Data
Scien
ce
,
Ma
th
em
atic
s
,
an
d
I
n
f
o
r
m
atics
at
I
PB
Un
i
v
er
s
ity
f
o
r
p
ar
tially
s
u
p
p
o
r
tin
g
th
e
p
u
b
lic
atio
n
co
s
ts
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
(
a)
DKI
1
B
u
n
d
ar
an
HI
Statio
n
(
b
)
DKI
2
Kela
p
a
Gad
in
g
Stati
o
n
(
c)
DKI
3
J
ag
ak
a
r
s
a
Statio
n
(
d
)
D
K
I
4
Lu
b
a
n
g
B
u
a
y
a
S
t
a
t
i
o
n
(
e
)
D
K
I
5
K
e
b
u
n
J
e
r
u
k
S
t
a
t
i
o
n
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
n
a
lysi
s
o
f P
M2
.
5
p
o
llu
t
a
n
t s
o
u
r
ce
s
in
Ja
ka
r
ta
u
s
in
g
d
ee
p
l
ea
r
n
in
g
mo
d
els
… (
Hen
d
r
o
P
r
a
ta
ma
S
a
r
a
g
ih
)
333
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Hen
d
r
o
Pra
tam
a
Sar
ag
ih
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
I
m
as Su
k
ae
s
ih
Sit
an
g
g
an
g
✓
✓
✓
✓
✓
✓
✓
✓
Hen
d
r
a
R
ah
m
awa
n
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
a
u
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
DATA
AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
atasets
,
p
r
e
-
p
r
o
ce
s
s
in
g
s
cr
ip
ts
,
an
d
L
STM
co
n
f
ig
u
r
atio
n
f
iles
g
en
er
ated
an
d
an
aly
ze
d
d
u
r
in
g
th
e
cu
r
r
e
n
t
s
tu
d
y
ar
e
av
ailab
le
in
th
e
p
u
b
lic
r
ep
o
s
ito
r
y
to
e
n
s
u
r
e
f
u
ll
r
ep
r
o
d
u
cib
ilit
y
:
h
ttp
s
://g
ith
u
b
.
co
m
/h
e
n
d
r
o
s
ar
ag
ih
/I
PB
U_
PM2
5
_
An
aly
s
is
So
u
r
ce
Po
llu
tio
n
_
J
ak
ar
ta
.
R
E
FE
R
E
N
C
E
S
[
1
]
B
a
d
a
n
P
u
sa
t
S
t
a
t
i
st
i
k
,
“
S
t
a
t
i
s
t
i
k
l
i
n
g
k
u
n
g
a
n
h
i
d
u
p
I
n
d
o
n
e
si
a
2
0
2
4
(
E
n
v
i
r
o
n
men
t
s
t
a
t
i
st
i
c
s
o
f
I
n
d
o
n
e
s
i
a
2
0
2
4
)
,
”
J
a
k
a
r
t
a
,
2
0
2
4
.
[
2
]
W
o
r
l
d
H
e
a
l
t
h
O
r
g
a
n
i
z
a
t
i
o
n
,
“
W
H
O
g
l
o
b
a
l
a
i
r
q
u
a
l
i
t
y
g
u
i
d
e
l
i
n
e
s,”
2
0
2
1
.
[
3
]
D
i
n
a
s
L
i
n
g
k
u
n
g
a
n
H
i
d
u
p
P
r
o
v
i
n
s
i
D
K
I
Jak
a
r
t
a
,
“
La
p
o
r
a
n
p
e
m
a
n
t
a
u
a
n
k
u
a
l
i
t
a
s
u
d
a
r
a
2
0
2
3
(
A
i
r
q
u
a
l
i
t
y
mo
n
i
t
o
r
i
n
g
r
e
p
o
r
t
2
0
2
3
)
,
”
2
0
2
3
.
[
4
]
T.
I
st
i
a
n
a
e
t
a
l
.
,
“
C
a
u
s
a
l
i
t
y
a
n
a
l
y
si
s
o
f
a
i
r
q
u
a
l
i
t
y
a
n
d
me
t
e
o
r
o
l
o
g
i
c
a
l
p
a
r
a
met
e
r
s
f
o
r
P
M
2
.
5
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
d
e
t
e
r
mi
n
a
t
i
o
n
:
e
v
i
d
e
n
c
e
f
r
o
m J
a
k
a
r
t
a
,
”
Ae
r
o
s
o
l
a
n
d
Ai
r Q
u
a
l
i
t
y
Re
s
e
a
r
c
h
,
v
o
l
.
2
3
,
n
o
.
9
,
p
.
2
3
0
0
1
4
,
2
0
2
3
,
d
o
i
:
1
0
.
4
2
0
9
/
a
a
q
r
.
2
3
0
0
1
4
.
[
5
]
Z.
Z
h
a
n
g
,
S
.
Zh
a
n
g
,
C
.
C
h
e
n
,
a
n
d
J.
Y
u
a
n
,
“
A
sy
s
t
e
m
a
t
i
c
s
u
r
v
e
y
o
f
a
i
r
q
u
a
l
i
t
y
p
r
e
d
i
c
t
i
o
n
b
a
s
e
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Al
e
x
a
n
d
r
i
a
En
g
i
n
e
e
ri
n
g
J
o
u
rn
a
l
,
v
o
l
.
9
3
,
p
p
.
1
2
8
–
1
4
1
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
4
.
0
3
.
0
3
1
.
[
6
]
Y
.
K
i
m,
S
.
-
B
.
P
a
r
k
,
S
.
Le
e
,
a
n
d
Y
.
-
K
.
P
a
r
k
,
“
C
o
m
p
a
r
i
so
n
o
f
P
M
2
.
5
p
r
e
d
i
c
t
i
o
n
p
e
r
f
o
r
ma
n
c
e
o
f
t
h
e
t
h
r
e
e
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
:
A
c
a
se
st
u
d
y
o
f
S
e
o
u
l
,
D
a
e
j
e
o
n
,
a
n
d
B
u
sa
n
,
”
J
o
u
rn
a
l
o
f
I
n
d
u
s
t
ri
a
l
a
n
d
E
n
g
i
n
e
e
ri
n
g
C
h
e
m
i
s
t
ry
,
v
o
l
.
1
2
0
,
p
p
.
1
5
9
–
1
6
9
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
i
e
c
.
2
0
2
2
.
1
2
.
0
2
2
.
[
7
]
S
.
P
o
n
g
p
i
a
c
h
a
n
e
t
a
l
.
,
“
C
o
m
b
i
n
e
d
u
se
o
f
p
r
i
n
c
i
p
a
l
c
o
mp
o
n
e
n
t
a
n
a
l
y
s
i
s/
mu
l
t
i
p
l
e
l
i
n
e
a
r
r
e
g
r
e
ss
i
o
n
a
n
a
l
y
s
i
s
a
n
d
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
t
o
a
ss
e
ss
t
h
e
i
m
p
a
c
t
o
f
met
e
o
r
o
l
o
g
i
c
a
l
p
a
r
a
m
e
t
e
r
s
o
n
f
l
u
c
t
u
a
t
i
o
n
o
f
sel
e
c
t
e
d
P
M
2
.
5
-
b
o
u
n
d
e
l
e
me
n
t
s
,
”
PLO
S
O
N
E
,
v
o
l
.
1
9
,
n
o
.
3
,
p
.
e
0
2
8
7
1
8
7
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
8
7
1
8
7
.
[
8
]
B
.
L
i
u
e
t
a
l
.
,
“
Ev
a
l
u
a
t
i
n
g
u
r
b
a
n
a
n
d
n
o
n
u
r
b
a
n
P
M
2
.
5
v
a
r
i
a
b
i
l
i
t
y
u
n
d
e
r
c
l
e
a
n
a
i
r
a
c
t
i
o
n
s
i
n
C
h
i
n
a
d
u
r
i
n
g
2
0
1
0
–
2
0
2
2
b
a
s
e
d
o
n
a
n
e
w
h
i
g
h
-
q
u
a
l
i
t
y
d
a
t
a
set
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
D
i
g
i
t
a
l
E
a
rt
h
,
v
o
l
.
1
7
,
n
o
.
1
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
0
/
1
7
5
3
8
9
4
7
.
2
0
2
4
.
2
3
1
0
7
3
4
.
[
9
]
Y
.
Y
a
n
g
e
t
a
l
.
,
“
Es
t
i
m
a
t
i
o
n
o
f
P
M
2
.
5
c
o
n
c
e
n
t
r
a
t
i
o
n
a
c
r
o
ss
C
h
i
n
a
B
a
se
d
o
n
mu
l
t
i
-
so
u
r
c
e
r
e
mo
t
e
se
n
si
n
g
d
a
t
a
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s,
”
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
6
,
n
o
.
3
,
p
.
4
6
7
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
6
0
3
0
4
6
7
.
[
1
0
]
S
.
G
ü
n
d
o
ğ
d
u
a
n
d
T.
El
b
i
r
,
“
A
d
a
t
a
-
d
r
i
v
e
n
a
p
p
r
o
a
c
h
f
o
r
P
M
2
.
5
e
st
i
ma
t
i
o
n
i
n
a
m
e
t
r
o
p
o
l
i
s:
r
a
n
d
o
m
f
o
r
e
st
m
o
d
e
l
i
n
g
b
a
s
e
d
o
n
ER
A
5
r
e
a
n
a
l
y
si
s
d
a
t
a
,
”
E
n
v
i
r
o
n
m
e
n
t
a
l
R
e
se
a
rc
h
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
6
,
n
o
.
3
,
p
.
0
3
5
0
2
9
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
8
/
2
5
1
5
-
7
6
2
0
/
a
d
3
5
2
d
.
[
1
1
]
G
.
C
i
c
a
n
,
A
.
-
N
.
B
u
t
u
r
a
c
h
e
,
a
n
d
R
.
M
i
r
e
a
,
“
A
p
p
l
y
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
i
n
a
i
r
q
u
a
l
i
t
y
p
r
e
d
i
c
t
i
o
n
—
A
B
u
c
h
a
r
e
s
t
c
i
t
y
c
a
se
st
u
d
y
,
”
S
u
st
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
5
,
n
o
.
1
1
,
p
.
8
4
4
5
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
5
1
1
8
4
4
5
.
[
1
2
]
A
.
A
y
u
O
k
t
a
v
i
a
n
a
,
A
.
F
a
d
l
i
A
ss
o
mad
i
,
a
n
d
J.
H
e
r
ma
n
a
,
“
A
n
a
l
y
s
i
s
c
o
r
r
e
l
a
t
i
o
n
o
f
met
e
o
r
o
l
o
g
i
c
a
l
f
a
c
t
o
r
s
w
i
t
h
P
M
2
.
5
c
o
n
c
e
n
t
r
a
t
i
o
n
s
i
n
f
o
r
e
c
a
st
i
n
g
a
i
r
q
u
a
l
i
t
y
o
f
t
h
e
c
i
t
y
o
f
J
a
k
a
r
t
a
,
”
I
O
P
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s:
E
a
r
t
h
a
n
d
E
n
v
i
r
o
n
m
e
n
t
a
l
S
c
i
e
n
c
e
,
v
o
l
.
1
4
4
8
,
n
o
.
1
,
p
.
0
1
2
0
0
6
,
F
e
b
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
5
-
1
3
1
5
/
1
4
4
8
/
1
/
0
1
2
0
0
6
.
[
1
3
]
J.
H
a
n
d
s
c
h
u
h
,
T
.
Er
b
e
r
t
s
e
d
e
r
,
a
n
d
F
.
B
a
i
e
r
,
“
S
y
s
t
e
m
a
t
i
c
e
v
a
l
u
a
t
i
o
n
o
f
f
o
u
r
sat
e
l
l
i
t
e
A
O
D
d
a
t
a
set
s
f
o
r
e
s
t
i
m
a
t
i
n
g
P
M
2
.
5
u
si
n
g
a
r
a
n
d
o
m
f
o
r
e
s
t
a
p
p
r
o
a
c
h
,
”
R
e
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
5
,
n
o
.
8
,
p
.
2
0
6
4
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
5
0
8
2
0
6
4
.
[
1
4
]
B
.
M
i
t
r
a
e
t
a
l
.
,
“
E
x
p
l
o
r
i
n
g
s
p
a
t
i
a
l
a
n
d
t
e
mp
o
r
a
l
d
y
n
a
m
i
c
s
o
f
r
e
d
se
a
a
i
r
q
u
a
l
i
t
y
t
h
r
o
u
g
h
m
u
l
t
i
v
a
r
i
a
t
e
a
n
a
l
y
s
i
s,
t
r
a
j
e
c
t
o
r
i
e
s,
a
n
d
sat
e
l
l
i
t
e
o
b
s
e
r
v
a
t
i
o
n
s,
”
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
6
,
n
o
.
2
,
p
.
3
8
1
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
6
0
2
0
3
8
1
.
[
1
5
]
M
.
I
.
S
h
i
d
d
i
q
,
I
.
S
.
S
i
t
a
n
g
g
a
n
g
,
a
n
d
M
.
A
.
A
g
ma
l
a
r
o
,
“
T
e
mp
o
r
a
l
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
f
o
r
C
O
a
n
d
C
O
₂
p
o
l
l
u
t
a
n
t
s
u
s
i
n
g
l
o
n
g
sh
o
r
t
-
t
e
r
m
m
e
m
o
r
y
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
2
0
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
I
t
s
A
p
p
l
i
c
a
t
i
o
n
i
n
A
g
ri
c
u
l
t
u
re
(
I
C
O
S
I
C
A)
,
2
0
2
0
.
[
1
6
]
I
.
J.
Ju
n
i
o
r
,
J.
B
.
T
u
k
a
y
,
A
.
O
k
r
a
h
,
G
.
M
a
g
a
r
a
,
a
n
d
D
.
J.
M
a
su
n
g
a
,
“
P
r
e
c
i
p
i
t
a
t
i
o
n
n
o
w
c
a
st
i
n
g
i
n
D
a
r
e
s
S
a
l
a
a
m:
C
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
LSTM
a
n
d
b
i
d
i
r
e
c
t
i
o
n
a
l
LST
M
f
o
r
e
n
h
a
n
c
i
n
g
e
a
r
l
y
w
a
r
n
i
n
g
sy
s
t
e
ms
,
”
J
o
u
rn
a
l
o
f
G
e
o
sc
i
e
n
c
e
a
n
d
E
n
v
i
ro
n
m
e
n
t
Pro
t
e
c
t
i
o
n
,
v
o
l
.
1
3
,
n
o
.
0
4
,
p
p
.
3
2
7
–
3
4
2
,
2
0
2
5
,
d
o
i
:
1
0
.
4
2
3
6
/
g
e
p
.
2
0
2
5
.
1
3
4
0
1
8
.
[
1
7
]
D
.
L
o
p
e
z
-
B
e
t
a
n
c
u
r
e
t
a
l
.
,
“
E
v
a
l
u
a
t
i
o
n
o
f
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
ms
f
o
r
m
e
a
s
u
r
e
men
t
o
f
s
u
sp
e
n
d
e
d
s
o
l
i
d
s
,
”
W
a
t
e
r
,
v
o
l
.
1
6
,
n
o
.
1
3
,
p
.
1
7
6
1
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
w
1
6
1
3
1
7
6
1
.
[
1
8
]
H
.
A
.
D
.
N
g
u
y
e
n
e
t
a
l
.
,
“
L
o
n
g
sh
o
r
t
-
t
e
r
m
me
mo
r
y
B
a
y
e
s
i
a
n
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
a
i
r
p
o
l
l
u
t
i
o
n
f
o
r
e
c
a
st
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
3
5
7
1
0
–
3
5
7
2
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
6
5
7
2
5
.
[
1
9
]
O
.
K
a
y
a
a
n
d
M
.
U
t
k
u
K
a
l
a
y
,
“
S
p
a
t
i
o
-
t
e
m
p
o
r
a
l
f
o
r
e
c
a
s
t
i
n
g
o
f
b
u
s a
r
r
i
v
a
l
t
i
mes
u
si
n
g
c
o
n
t
e
x
t
-
a
w
a
r
e
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s i
n
u
r
b
a
n
t
r
a
n
s
i
t
sy
s
t
e
m
s,”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
3
,
p
p
.
1
6
1
4
2
3
–
1
6
1
4
3
5
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
5
.
3
6
0
9
5
3
0
.
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.
43
,
No
.
1
,
J
u
ly
20
26
:
325
-
33
4
334
[
2
0
]
X
.
Li
u
,
“
En
h
a
n
c
e
d
p
r
e
d
i
c
t
i
o
n
o
f
k
a
r
st
sp
r
i
n
g
d
i
sc
h
a
r
g
e
u
si
n
g
a
h
y
b
r
i
d
LSTM
-
X
G
B
o
o
st
m
o
d
e
l
o
p
t
i
mi
z
e
d
w
i
t
h
g
r
i
d
s
e
a
r
c
h
,
”
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
2
,
p
.
1
0
0
7
4
0
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
l
w
a
.
2
0
2
5
.
1
0
0
7
4
0
.
[
2
1
]
L.
Li
u
,
J.
L
i
a
n
g
,
L.
M
a
,
H
.
Z
h
a
n
g
,
Z
.
L
i
,
a
n
d
S
.
Li
a
n
g
,
“
G
a
s
p
i
p
e
l
i
n
e
f
l
o
w
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
b
a
s
e
d
o
n
LST
M
w
i
t
h
g
r
i
d
se
a
r
c
h
p
a
r
a
m
e
t
e
r
o
p
t
i
m
i
z
a
t
i
o
n
,
”
Pr
o
c
e
sses
,
v
o
l
.
1
1
,
n
o
.
1
,
p
.
6
3
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
p
r
1
1
0
1
0
0
6
3
.
[
2
2
]
S
.
Tı
r
ı
n
k
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
f
o
r
e
c
a
st
i
n
g
o
f
a
i
r
q
u
a
l
i
t
y
i
n
d
e
x
u
n
d
e
r
l
o
n
g
-
t
e
r
m
e
n
v
i
r
o
n
m
e
n
t
a
l
p
a
t
t
e
r
n
s
:
A
c
o
mp
a
r
a
t
i
v
e
a
p
p
r
o
a
c
h
w
i
t
h
X
G
B
o
o
s
t
,
Li
g
h
t
G
B
M
,
a
n
d
S
V
M
,
”
PLO
S
O
n
e
,
v
o
l
.
2
0
,
n
o
.
1
0
,
p
.
e
0
3
3
4
2
5
2
,
O
c
t
.
2
0
2
5
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
3
3
4
2
5
2
.
[
2
3
]
X
.
B
a
i
,
N
.
Z
h
a
n
g
,
X
.
C
a
o
,
a
n
d
W
.
C
h
e
n
,
“
P
r
e
d
i
c
t
i
o
n
o
f
P
M
2
.
5
c
o
n
c
e
n
t
r
a
t
i
o
n
b
a
se
d
o
n
a
C
N
N
-
LSTM
n
e
u
r
a
l
n
e
t
w
o
r
k
a
l
g
o
r
i
t
h
m,
”
Pe
e
r
J
,
v
o
l
.
1
2
,
p
.
e
1
7
8
1
1
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
7
7
1
7
/
p
e
e
r
j
.
1
7
8
1
1
.
[
2
4
]
L.
Li
e
t
a
l
.
,
“
E
n
sem
b
l
e
-
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
e
st
i
ma
t
i
n
g
P
M
2
.
5
o
v
e
r
C
a
l
i
f
o
r
n
i
a
w
i
t
h
m
u
l
t
i
s
o
u
r
c
e
b
i
g
d
a
t
a
i
n
c
l
u
d
i
n
g
w
i
l
d
f
i
r
e
smo
k
e
,
”
E
n
v
i
r
o
n
m
e
n
t
I
n
t
e
r
n
a
t
i
o
n
a
l
,
v
o
l
.
1
4
5
,
p
.
1
0
6
1
4
3
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
v
i
n
t
.
2
0
2
0
.
1
0
6
1
4
3
.
[
2
5
]
M
.
C
i
e
p
i
e
l
a
,
W
.
S
o
b
c
z
y
k
,
a
n
d
E
.
J
.
S
o
b
c
z
y
k
,
“
M
o
d
e
l
l
i
n
g
b
a
c
k
w
a
r
d
t
r
a
j
e
c
t
o
r
i
e
s
o
f
a
i
r
mass
e
s
f
o
r
i
d
e
n
t
i
f
y
i
n
g
so
u
r
c
e
s o
f
p
a
r
t
i
c
u
l
a
t
e
mat
t
e
r
o
r
i
g
i
n
a
t
i
n
g
f
r
o
m
c
o
a
l
c
o
m
b
u
st
i
o
n
i
n
a
c
o
m
b
i
n
e
d
h
e
a
t
a
n
d
p
o
w
e
r
p
l
a
n
t
,
”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
8
,
n
o
.
3
,
p
.
4
9
3
,
Ja
n
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
8
0
3
0
4
9
3
.
[
2
6
]
N
.
Za
i
n
i
,
L.
W
.
Ea
n
,
A
.
N
.
A
h
me
d
,
M
.
A
b
d
u
l
M
a
l
e
k
,
a
n
d
M
.
F
.
C
h
o
w
,
“
P
M
2
.
5
f
o
r
e
c
a
s
t
i
n
g
f
o
r
a
n
u
r
b
a
n
a
r
e
a
b
a
s
e
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
d
e
c
o
m
p
o
si
t
i
o
n
me
t
h
o
d
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
2
,
n
o
.
1
,
p
.
1
7
5
6
5
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
0
2
2
-
2
1
7
6
9
-
1.
[
2
7
]
G
.
P
.
A
p
a
n
g
u
e
t
a
l
.
,
“
S
e
n
t
i
n
e
l
-
2
sa
t
e
l
l
i
t
e
a
n
d
H
Y
S
P
LI
T
mo
d
e
l
s
u
g
g
e
s
t
t
h
a
t
l
o
c
a
l
c
e
r
e
a
l
h
a
r
v
e
st
i
n
g
s
u
b
s
t
a
n
t
i
a
l
l
y
c
o
n
t
r
i
b
u
t
e
t
o
p
e
a
k
A
l
t
e
r
n
a
r
i
a
s
p
o
r
e
c
o
n
c
e
n
t
r
a
t
i
o
n
s,
”
Ag
r
i
c
u
l
t
u
r
a
l
a
n
d
F
o
res
t
M
e
t
e
o
ro
l
o
g
y
,
v
o
l
.
3
2
6
,
p
.
1
0
9
1
5
6
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
g
r
f
o
r
me
t
.
2
0
2
2
.
1
0
9
1
5
6
.
[
2
8
]
C
.
S
a
r
a
v
i
a
a
n
d
K
.
Tr
a
c
h
t
e
,
“
S
p
a
t
i
o
t
e
mp
o
r
a
l
a
n
a
l
y
si
s
o
f
N
H
3
e
m
i
ssi
o
n
s
o
u
r
c
e
s
a
n
d
t
h
e
i
r
r
e
l
a
t
i
o
n
t
o
l
a
n
d
u
se
t
y
p
e
s
i
n
t
h
e
Ea
s
t
e
r
n
G
e
r
man
L
o
w
l
a
n
d
s,”
At
m
o
s
p
h
e
re
,
v
o
l
.
1
6
,
n
o
.
3
,
p
.
3
4
6
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
a
t
m
o
s
1
6
0
3
0
3
4
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
H
e
n
d
r
o
Pra
ta
m
a
S
a
r
a
g
i
h
re
c
e
iv
e
d
a
B.
S
c
.
d
e
g
re
e
in
In
fo
rm
a
t
ics
fro
m
Telk
o
m
Un
iv
e
rsity
,
I
n
d
o
n
e
sia
,
in
2
0
2
0
a
n
d
is
c
u
rre
n
tl
y
p
u
rsu
i
n
g
a
n
M
.
S
c
.
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
t
IP
B
Un
iv
e
rsit
y
.
He
sp
e
c
ialize
s
in
th
e
fiel
d
s
o
f
c
o
m
p
u
tati
o
n
a
l
i
n
t
e
ll
ig
e
n
c
e
,
o
p
ti
m
iza
t
io
n
,
a
n
d
d
e
e
p
lea
rn
in
g
,
wit
h
a
p
a
rti
c
u
lar
fo
c
u
s
o
n
a
ir
q
u
a
li
ty
f
o
re
c
a
stin
g
u
sin
g
L
S
TM
m
o
d
e
ls.
He
h
a
s
a
n
e
x
ten
si
v
e
p
ro
fe
ss
io
n
a
l
b
a
c
k
g
r
o
u
n
d
a
s
a
d
a
ta
e
n
g
i
n
e
e
r
a
t
Ba
n
k
M
a
n
d
iri
,
wh
e
re
h
e
d
e
v
e
lo
p
s
g
e
n
e
r
a
ti
v
e
AI
a
n
d
d
a
ta,
re
g
u
lat
o
ry
a
n
d
c
o
m
p
li
a
n
c
e
sy
ste
m
s.
His
r
e
se
a
r
c
h
in
tere
sts
in
c
lu
d
e
n
u
m
e
rica
l
m
o
d
e
li
n
g
,
h
a
v
i
n
g
p
r
e
v
io
u
sl
y
d
e
v
e
lo
p
e
d
th
e
M
o
S
V
1
D
a
p
p
l
ica
ti
o
n
f
o
r
wa
v
e
sim
u
latio
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
e
n
d
r
o
sa
ra
g
ih
@a
p
p
s.i
p
b
.
a
c
.
id
.
Im
a
s
S
u
k
a
e
sih
S
ita
n
g
g
a
n
g
re
c
e
iv
e
d
a
P
h
D
in
Co
m
p
u
ter
S
c
ien
c
e
fro
m
t
h
e
F
a
c
u
lt
y
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
In
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
,
Un
i
v
e
rsiti
P
u
tra M
a
lay
sia
,
i
n
2
0
1
3
.
S
h
e
is
a
lec
tu
re
r
i
n
t
h
e
S
c
h
o
o
l
o
f
Da
ta
S
c
ien
c
e
,
M
a
th
e
m
a
ti
c
s,
a
n
d
In
f
o
rm
a
ti
c
s
a
t
IP
B
Un
iv
e
rsity
,
In
d
o
n
e
sia
.
He
r
m
a
in
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
s
p
a
ti
a
l
d
a
ta
m
in
in
g
a
n
d
sm
a
rt
a
g
ricu
lt
u
re
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ima
s.sitan
g
g
a
n
g
@a
p
p
s.i
p
b
.
a
c
.
i
d
.
H
e
n
d
r
a
Ra
h
m
a
w
a
n
is
a
fa
c
u
lt
y
m
e
m
b
e
r
in
th
e
Co
m
p
u
ter
S
c
ien
c
e
S
t
u
d
y
P
ro
g
ra
m
,
S
c
h
o
o
l
o
f
Da
ta
S
c
ien
c
e
,
M
a
th
e
m
a
ti
c
s,
a
n
d
In
fo
rm
a
ti
c
s,
IP
B
Un
iv
e
rsity
(I
n
stit
u
t
P
e
rtan
ian
Bo
g
o
r).
He
re
c
e
iv
e
d
h
is
b
a
c
h
e
lo
r’s
d
e
g
re
e
fro
m
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
IP
B
Un
iv
e
rsity
,
a
n
d
h
is
m
a
ste
r’s
a
n
d
d
o
c
t
o
ra
l
d
e
g
re
e
s
fro
m
th
e
S
c
h
o
o
l
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
a
n
d
I
n
fo
rm
a
ti
c
s,
In
st
it
u
t
Tek
n
o
lo
g
i
Ba
n
d
u
n
g
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
h
i
g
h
-
p
e
rfo
rm
a
n
c
e
c
o
m
p
u
t
in
g
,
i
n
tern
e
t
o
f
t
h
in
g
s
(I
o
T),
a
n
d
c
o
m
p
u
ter
n
e
t
wo
rk
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
r
a
h
m
a
wa
n
@a
p
p
s.ip
b
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.