I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
rm
a
t
ics a
nd
Co
m
m
un
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
1
4
,
No
.
3
,
Dec
em
b
er
20
2
5
,
p
p
.
1
1
4
6
~
1
155
I
SS
N:
2252
-
8
7
7
6
,
DOI
:
1
0
.
1
1
5
9
1
/iji
ct
.
v
1
4
i
3
.
pp
1
1
4
6
-
1
155
1146
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ict.
ia
esco
r
e.
co
m
Na
v
ig
a
ting
predic
tive la
ndsca
pes o
f
clo
ud burs
t
pr
edi
ction
a
ppro
a
ches: insig
hts f
ro
m
co
mpa
ra
tive resea
rch
Anil H
ing
m
ire
1
,
Su
na
y
a
na
J
a
dh
a
v
2
,
M
eg
ha
T
riv
edi
1
,
K
a
ra
n Sa
nk
he
1
,
O
m
ka
r
K
ha
no
l
k
a
r
1
,
Yuk
t
a
P
a
t
il
1
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
V
i
d
y
a
v
a
r
d
h
i
n
i
’
s
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
y
o
f
M
u
m
b
a
i
,
V
a
sa
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
T
e
l
e
c
o
mm
u
n
i
c
a
t
i
o
n
E
n
g
i
n
e
e
r
i
n
g
,
V
i
d
y
a
v
a
r
d
h
i
n
i
’
s
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
y
o
f
M
u
m
b
a
i
,
V
a
sa
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
2
6
,
2
0
2
4
R
ev
is
ed
J
u
n
1
9
,
2
0
2
5
Acc
ep
ted
J
u
l 1
,
2
0
2
5
Clo
u
d
b
u
rst
fo
re
c
a
stin
g
re
m
a
in
s
a
n
e
v
o
lv
in
g
field
t
h
a
t
g
ra
p
p
les
with
th
e
c
o
m
p
lex
it
ies
o
f
a
tmo
s
p
h
e
ric
p
h
e
n
o
m
e
n
a
a
n
d
t
h
e
ir
imp
a
c
t
o
n
l
o
c
a
l
e
n
v
iro
n
m
e
n
ts.
Cl
o
u
d
b
u
rst
s i
n
h
il
l
y
re
g
i
o
n
s
d
e
m
a
n
d
ro
b
u
st
p
re
d
ict
i
v
e
m
o
d
e
ls
to
m
it
i
g
a
te
risk
s.
T
h
is
stu
d
y
a
d
d
re
ss
e
s
th
e
c
h
a
ll
e
n
g
e
o
f
imb
a
la
n
c
e
d
c
lo
u
d
b
u
rst
o
c
c
u
rre
n
c
e
s,
e
m
p
h
a
siz
in
g
th
e
n
e
e
d
fo
r
a
c
c
u
ra
te
p
re
d
i
c
ti
o
n
s
to
m
in
imiz
e
d
a
m
a
g
e
.
It
d
e
v
e
lo
p
s
a
n
d
e
v
a
lu
a
tes
a
m
a
c
h
in
e
lea
r
n
in
g
-
b
a
se
d
fo
re
c
a
stin
g
a
p
p
ro
a
c
h
th
a
t
in
c
l
u
d
e
s
se
v
e
ra
l
we
a
th
e
r
fa
c
to
rs
su
c
h
a
s
tem
p
e
ra
tu
re
,
h
u
m
id
it
y
,
wi
n
d
s
p
e
e
d
,
a
n
d
a
tmo
sp
h
e
ric
p
re
ss
u
re
.
Th
e
stu
d
y
a
lso
tac
k
les
th
e
imb
a
lan
c
e
in
c
lo
u
d
b
u
rst
d
a
ta.
A
d
u
a
l
-
a
x
is
c
h
a
rt
v
isu
a
ll
y
m
e
rg
e
s
c
lo
u
d
b
u
rst
o
c
c
u
rre
n
c
e
s
with
we
a
th
e
r
p
a
ra
m
e
ters
,
p
ro
v
id
i
n
g
i
n
sig
h
ts
in
to
th
e
ir
re
lati
o
n
s
h
ip
s
o
v
e
r
ti
m
e
.
Th
e
m
o
d
e
l
’
s
o
v
e
ra
ll
a
c
c
u
ra
c
y
is
0
.
6
8
,
wit
h
p
re
c
isio
n
a
n
d
re
c
a
ll
fo
r
c
l
o
u
d
b
u
r
st
e
v
e
n
ts
a
t
0
.
2
5
a
n
d
0
.
0
7
,
re
sp
e
c
ti
v
e
ly
,
a
n
d
a
n
F
1
-
sc
o
re
o
f
0
.
1
1
.
H
o
we
v
e
r,
w
h
e
n
i
t
c
o
m
e
s
t
o
f
o
re
c
a
stin
g
n
o
n
-
c
lo
u
d
b
u
rst
o
c
c
u
rre
n
c
e
s,
it
sh
o
ws
a
h
i
g
h
p
re
c
isio
n
o
f
0
.
7
2
.
Th
is
st
u
d
y
e
v
a
l
u
a
tes
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
ls
f
o
r
c
lo
u
d
b
u
rst
p
re
d
ictio
n
,
h
ig
h
li
g
h
ti
n
g
ra
n
d
o
m
fo
re
st
a
s
th
e
to
p
p
e
rfo
rm
e
r
wi
th
a
n
a
c
c
u
ra
c
y
o
f
8
5
.
4
3
%
,
e
ffe
c
ti
v
e
ly
b
a
lan
c
in
g
tru
e
p
o
siti
v
e
s
a
n
d
tru
e
n
e
g
a
ti
v
e
s
wh
il
e
m
in
imiz
in
g
m
isc
las
sifica
ti
o
n
s.
T
h
is
re
se
a
rc
h
c
o
n
tri
b
u
tes
to
c
l
o
u
d
b
u
r
st
p
re
d
icti
o
n
,
o
ff
e
ri
n
g
p
e
rfo
rm
a
n
c
e
in
sig
h
ts
a
n
d
su
g
g
e
sti
n
g
a
v
e
n
u
e
s f
o
r
fu
t
u
re
e
x
p
l
o
ra
ti
o
n
.
K
ey
w
o
r
d
s
:
C
lo
u
d
b
u
r
s
t
L
in
ea
r
r
eg
r
ess
io
n
Ma
ch
in
e
lear
n
in
g
R
an
d
o
m
f
o
r
est
Su
p
p
o
r
t
v
ec
to
r
r
e
g
r
ess
io
n
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
:
An
il Hin
g
m
ir
e
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
,
Vid
y
av
ar
d
h
in
i
’
s
C
o
lleg
e
o
f
E
n
g
in
ee
r
i
n
g
an
d
T
ec
h
n
o
lo
g
y
Un
iv
er
s
ity
o
f
Mu
m
b
ai
Vasai,
Ma
h
ar
ash
tr
a,
I
n
d
ia
E
m
ail: a
n
il.h
in
g
m
ir
e@
v
ce
t.e
d
u
.
in
1.
I
NT
RO
D
UCT
I
O
N
Un
ex
p
ec
ted
ca
tast
r
o
p
h
es
s
u
c
h
as
ea
r
t
h
q
u
a
k
es,
c
lo
u
d
b
u
r
s
t
s
,
lan
d
s
lid
es,
an
d
f
l
o
o
d
s
ar
e
u
n
f
o
r
eseen
ev
en
ts
th
at
in
f
lict
co
n
s
id
er
ab
l
e
am
o
u
n
t
o
f
d
estru
ctio
n
an
d
lo
s
s
o
f
life
,
co
s
tin
g
b
illi
o
n
s
o
f
d
o
llar
s
ea
ch
y
ea
r
.
C
h
an
g
in
g
wea
th
er
p
atter
n
s
m
ak
e
it
d
if
f
icu
lt
to
an
ticip
ate
m
eteo
r
o
lo
g
ical
p
h
en
o
m
e
n
a,
an
d
wo
r
ld
wid
e
s
tu
d
ies
s
h
o
w
th
at
g
lacie
r
s
ar
e
r
etr
ea
tin
g
at
an
av
e
r
ag
e
p
a
ce
o
f
1
0
-
1
5
m
eter
s
p
er
y
ea
r
as a
r
esu
lt o
f
c
lim
ate
ch
an
g
e
[
1
]
.
I
n
a
n
u
ts
h
ell,
T
iwar
i
an
d
Ve
r
m
a
[
2
]
,
o
u
tlin
e
h
o
w
it
b
eg
i
n
s
with
b
u
ild
in
g
a
s
tr
o
n
g
f
o
u
n
d
atio
n
b
y
m
eth
o
d
ically
g
ath
er
in
g
a
n
d
an
aly
zin
g
p
ast
wea
th
er
d
ata.
T
h
e
co
m
p
le
x
s
tu
d
y
is
c
o
n
d
u
cted
u
s
in
g
a
m
e
th
o
d
ical
ap
p
r
o
ac
h
in
ten
d
ed
to
f
u
lly
a
d
d
r
ess
th
e
is
s
u
es
r
aised
b
y
c
lo
u
d
b
u
r
s
t
ev
e
n
ts
.
T
h
is
en
tails
a
th
o
r
o
u
g
h
a
n
aly
s
is
o
f
s
ig
n
if
ican
t
f
ac
to
r
s
t
o
p
r
o
v
id
e
a
d
etailed
d
ataset
th
at
ca
p
t
u
r
es
th
e
v
ar
ied
an
d
d
y
n
am
ic
c
h
ar
ac
ter
o
f
wea
th
er
p
atter
n
s
in
th
e
ar
ea
in
q
u
e
s
tio
n
.
T
o
im
p
r
o
v
e
th
e
s
y
s
tem
’
s
f
o
r
ec
asti
n
g
s
k
ills
,
th
e
r
esear
c
h
attem
p
ts
to
u
s
e
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
N
a
vig
a
tin
g
p
r
ed
ictive
la
n
d
s
ca
p
es o
f c
lo
u
d
b
u
r
s
t p
r
ed
ictio
n
a
p
p
r
o
a
ch
es:
in
s
ig
h
ts
…
(
A
n
il Hin
g
mir
e
)
1147
v
ar
iety
o
f
c
h
ar
ac
ter
is
tics
,
s
u
ch
as
m
eteo
r
o
lo
g
ical
c
o
n
d
itio
n
s
,
g
eo
g
r
ap
h
ic
v
ar
iab
les,
an
d
c
lim
atic
p
atter
n
s
[
3
]
.
T
h
is
s
tag
e
is
ess
en
tial
to
m
atch
in
g
th
e
in
tr
icate
d
etails
o
f
t
h
e
u
n
iq
u
e
co
n
d
itio
n
s
th
at
d
ef
in
e
th
e
r
eg
io
n
with
th
e
p
r
ed
ictio
n
m
o
d
el.
Ad
d
itio
n
al
en
d
ea
v
o
r
s
co
m
p
r
is
e
cr
u
cial
s
tag
es
o
f
p
r
e
p
r
o
ce
s
s
in
g
d
ata
an
d
tr
ain
in
g
th
e
m
o
d
el,
wh
er
e
ex
ac
tin
g
m
eth
o
d
s
ar
e
em
p
lo
y
ed
to
g
u
ar
an
tee
th
e
ca
lib
r
e
a
n
d
d
e
p
en
d
a
b
ilit
y
o
f
th
e
d
ataset,
au
g
m
e
n
tin
g
th
e
r
esil
ien
ce
o
f
th
e
a
n
aly
s
is
th
at
f
o
llo
ws.
T
o
m
a
x
im
ize
f
o
r
ec
ast
ac
cu
r
ac
y
,
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
el
is
ca
r
ef
u
lly
tr
ain
e
d
u
s
in
g
cu
ttin
g
-
ed
g
e
tech
n
iq
u
es
[
4
]
.
Dim
r
i
et
a
l.
[
5
]
,
th
e
last
g
r
o
u
p
o
f
task
s
f
o
cu
s
es
o
n
co
m
p
ar
is
o
n
a
n
aly
s
es
an
d
ass
ess
m
e
n
t
m
ea
s
u
r
es.
R
o
b
u
s
t
ev
alu
atio
n
m
ea
s
u
r
es
ar
e
u
s
ed
t
o
th
o
r
o
u
g
h
ly
ass
ess
th
e
d
ev
elo
p
e
d
ef
f
ec
tiv
e
n
ess
o
f
s
y
s
tem
.
A
cr
u
cial
p
ar
t o
f
th
e
r
ese
ar
ch
is
co
m
p
ar
in
g
th
e
m
o
d
el
’
s
p
r
ed
ictio
n
s
to
p
ast
c
lo
u
d
b
u
r
s
t
ev
en
ts
th
r
o
u
g
h
a
c
o
m
p
ar
ativ
e
an
al
y
s
is
.
Ass
e
s
s
in
g
th
e
s
y
s
tem
s
ef
f
icac
y
in
p
r
ac
tical
s
ce
n
ar
io
s
an
d
im
p
r
o
v
in
g
its
p
r
ed
ictin
g
s
k
ills
n
ee
d
ca
r
ef
u
l c
o
n
s
id
er
atio
n
o
f
th
is
co
m
p
ar
is
o
n
elem
e
n
t.
I
n
d
ia
’
s
u
n
iq
u
e
to
p
o
g
r
ap
h
y
a
n
d
clim
ate
r
en
d
er
it
s
u
s
ce
p
tib
le
to
f
r
eq
u
e
n
t
c
lo
u
d
b
u
r
s
t
s
,
p
ar
t
icu
lar
ly
in
m
o
u
n
tain
o
u
s
ar
ea
s
.
N
o
tab
le
in
s
tan
ce
s
in
clu
d
e
th
e
Ma
y
2
6
,
2
0
1
7
,
c
lo
u
d
b
u
r
s
t
in
T
atalg
ao
n
an
d
B
ijra
n
i,
w
h
ich
d
em
o
lis
h
ed
a
h
o
m
e
an
d
k
illed
eig
h
t
d
o
m
esti
c
an
im
als,
an
d
t
h
e
Au
g
u
s
t
1
4
,
2
0
1
7
ev
e
n
t
in
Ma
n
g
ti
an
d
Ma
lp
a,
wh
ich
r
esu
lted
in
n
in
e
d
ea
th
s
,
1
8
m
is
s
in
g
p
e
o
p
le,
an
d
th
e
l
o
s
s
o
f
5
1
a
n
im
a
ls
.
T
h
e
f
o
llo
win
g
c
lo
u
d
b
u
r
s
t
on
J
u
ly
1
7
,
2
0
1
8
,
n
ea
r
Yam
n
o
tr
i
,
Uttar
k
ash
i,
s
wep
t
awa
y
a
f
o
o
tb
r
id
g
e
an
d
s
er
io
u
s
ly
d
estro
y
ed
th
e
Kali
Kam
li
Dh
ar
am
s
h
ala,
d
em
o
n
s
tr
atin
g
t
h
e
ter
r
ib
le
im
p
ac
t
o
f
n
atu
r
al
d
i
s
aster
s
an
d
th
e
cr
itical
n
ee
d
f
o
r
p
r
ep
a
r
ed
n
ess
an
d
m
itig
at
io
n
tech
n
iq
u
es in
s
u
s
ce
p
tib
le
p
lace
s
[
6
]
.
On
J
u
ly
1
9
,
2
0
1
8
,
Ma
lar
i
h
am
let
in
C
h
am
o
li
s
aw
a
d
ev
as
tatin
g
c
lo
u
d
b
u
r
s
t
th
at
k
illed
two
p
eo
p
le
an
d
d
a
m
ag
ed
th
e
J
o
s
h
im
ath
-
Ma
lar
i
r
o
ad
.
Pad
m
alla
-
Fald
iy
a
an
d
M
o
r
i
teh
s
ils
in
Uttar
k
a
s
h
i
s
aw
ev
en
m
o
r
e
d
ev
astatio
n
in
Au
g
u
s
t 2
0
1
9
,
w
ith
6
0
p
eo
p
le
k
illed
,
co
u
n
tles
s
an
im
als lo
s
t,
an
d
ex
ten
s
iv
e
p
r
o
p
er
ty
d
am
a
g
e.
B
y
Sep
tem
b
er
,
c
lo
u
d
b
u
r
s
t
s
in
Go
v
in
d
g
h
at
h
a
d
ca
u
s
ed
c
o
n
s
id
e
r
ab
le
r
o
a
d
d
am
a
g
e,
h
i
g
h
lig
h
ti
n
g
th
e
c
r
itical
n
ee
d
f
o
r
co
m
p
r
eh
e
n
s
iv
e
d
is
aster
p
lan
n
in
g
i
n
s
u
s
ce
p
tib
le
p
lace
s
[
7
]
.
T
h
e
r
esear
ch
o
n
“
C
lo
u
d
b
u
r
s
t
Pre
d
ictio
n
”
is
es
s
en
tially
m
u
lt
if
ac
eted
,
r
an
g
in
g
f
r
o
m
f
u
n
d
am
en
tal
d
ata
co
llectio
n
an
d
m
o
d
el
d
ev
el
o
p
m
en
t
to
r
i
g
o
r
o
u
s
tr
ain
in
g
an
d
ev
alu
atio
n
,
all
o
f
wh
ich
a
r
e
aim
ed
at
im
p
r
o
v
in
g
th
e
o
v
er
ar
ch
i
n
g
g
o
al
o
f
im
p
r
o
v
in
g
t
h
e
p
r
ec
is
i
o
n
a
n
d
r
elev
an
ce
o
f
c
l
o
u
d
b
u
r
s
t
p
r
e
d
ictio
n
s
with
in
t
h
e
d
esig
n
ated
g
eo
g
r
ap
h
ic
ar
ea
.
2.
RE
L
AT
E
D
WO
RK
T
h
e
o
v
er
v
iew
o
f
cu
r
r
en
t
s
tu
d
ies
o
n
c
lo
u
d
b
u
r
s
t
p
r
ed
ictio
n
s
y
s
tem
s
m
ay
b
e
f
o
u
n
d
in
th
e
liter
atu
r
e
r
ev
iew
th
at
f
o
llo
ws.
T
h
e
r
esear
ch
in
clu
d
ed
i
n
th
is
d
is
cu
s
s
io
n
co
n
ce
n
tr
ates
o
n
v
a
r
io
u
s
ap
p
r
o
ac
h
es
-
f
r
o
m
d
ee
p
lear
n
in
g
tech
n
iq
u
es
to
h
ar
d
war
e
-
b
ased
s
y
s
tem
s
-
th
at
aid
in
t
h
e
co
m
p
r
eh
en
s
io
n
an
d
f
o
r
ec
a
s
tin
g
o
f
c
lo
u
d
b
u
r
s
t
ev
en
ts
in
d
iv
er
s
e
g
e
o
g
r
a
p
h
ical
ar
ea
s
.
T
iwar
i
an
d
Ver
m
a
[
2
]
ex
p
l
o
r
e
d
th
e
d
etr
im
en
tal
im
p
ac
t
o
f
c
l
o
u
d
b
u
r
s
t
s
in
th
e
Him
alay
an
r
eg
io
n
s
an
d
u
n
d
er
s
co
r
e
th
e
in
ad
e
q
u
ac
ies
o
f
tr
a
d
itio
n
al
p
r
ed
ictio
n
m
et
h
o
d
s
.
T
h
e
a
u
th
o
r
s
p
r
o
p
o
s
e
a
n
o
v
el
c
lo
u
d
b
u
r
s
t
p
r
ed
eter
m
in
atio
n
s
y
s
tem
lev
er
ag
in
g
Ar
d
u
in
o
tech
n
o
l
o
g
y
,
in
co
r
p
o
r
atin
g
a
r
ain
g
a
u
g
e,
f
lo
at
s
witch
,
an
d
s
u
b
m
er
s
ib
le
p
u
m
p
f
o
r
r
ea
l
-
t
im
e
ca
lcu
latio
n
o
f
r
ai
n
f
all
i
n
ten
s
ity
.
T
h
is
co
s
t
-
ef
f
ec
tiv
e
s
o
lu
tio
n
aim
s
to
o
v
er
co
m
e
th
e
lim
itatio
n
s
o
f
c
o
n
v
en
tio
n
al
m
eth
o
d
s
,
p
r
o
v
id
in
g
a
p
r
ac
tical
an
d
ef
f
icien
t m
o
n
it
o
r
in
g
a
p
p
r
o
ac
h
.
Siv
ag
am
i
et
a
l.
[
3
]
d
e
v
elo
p
ed
a
c
lo
u
d
b
u
r
s
t
p
r
ed
ictio
n
m
o
d
e
l
u
s
in
g
d
ee
p
lear
n
in
g
,
s
p
ec
if
ic
ally
g
ated
r
ec
u
r
r
en
t
u
n
it
(
GR
U)
an
d
l
o
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
n
etwo
r
k
s
.
T
h
ey
ap
p
lied
p
r
e
d
ictiv
e
p
o
wer
s
co
r
e
(
PP
S)
to
id
en
tify
k
ey
f
ea
tu
r
es
f
o
r
th
ese
m
o
d
els.
T
h
e
d
ataset
ex
h
ib
ited
class
im
b
alan
ce
,
wi
th
1
6
o
f
2
0
ev
en
ts
b
ein
g
c
lo
u
d
b
u
r
s
t
s
,
a
ty
p
ical
ch
allen
g
e
in
e
x
tr
em
e
e
v
en
t
d
atasets
.
Su
n
il
et
a
l.
[
4
]
in
tr
o
d
u
ce
s
“
Pre
d
is
ter
,
”
d
esig
n
ed
f
o
r
clo
u
d
b
u
r
s
t
p
r
ed
ictio
n
in
h
illy
ar
ea
s
,
em
p
h
asizin
g
th
e
cr
itical
im
p
o
r
tan
ce
o
f
ea
r
ly
war
n
in
g
s
in
p
r
ev
en
tin
g
th
e
lo
s
s
o
f
life
a
n
d
p
r
o
p
e
r
ty
.
T
h
e
s
y
s
tem
in
te
g
r
ates
en
v
ir
o
n
m
en
tal
s
en
s
o
r
s
,
d
ata
s
cien
ce
,
a
n
d
ar
tific
ial
in
tellig
en
ce
to
m
o
n
ito
r
atm
o
s
p
h
er
ic
co
n
d
itio
n
s
.
T
im
ely
aler
ts
ar
e
i
s
s
u
ed
b
ased
o
n
ab
n
o
r
m
al
co
n
d
itio
n
s
,
s
h
o
wca
s
in
g
t
h
e
p
o
ten
tial to
s
av
e
liv
es a
n
d
p
r
o
p
er
ty
in
r
em
o
te
a
n
d
v
u
ln
er
a
b
le
ar
ea
s
.
Dim
r
i
et
a
l.
[
5
]
f
o
cu
s
o
n
c
lo
u
d
b
u
r
s
t
ev
en
ts
in
th
e
s
o
u
th
er
n
r
an
g
e
o
f
th
e
I
n
d
ian
Him
alay
as.
Utilizi
ng
d
iv
er
s
e
d
ata
s
o
u
r
ce
s
,
in
clu
d
in
g
NASA
’
s
ME
R
R
A
d
ataset
a
n
d
I
MD
’
s
R
ain
Gau
g
e
s
tatio
n
s
,
th
e
s
tu
d
y
ex
p
lo
r
es
ex
tr
em
e
p
r
ec
ip
itatio
n
p
atter
n
s
an
d
lar
g
e
-
s
ca
le
f
ac
to
r
s
co
n
tr
ib
u
tin
g
to
c
lo
u
d
b
u
r
s
t
s
.
T
h
e
p
ap
er
p
r
o
v
id
es
a
co
n
ce
p
tu
al
m
o
d
el
f
o
r
u
n
d
e
r
s
tan
d
in
g
t
h
ese
ev
e
n
ts
,
co
v
er
in
g
a
s
p
ec
ts
s
u
ch
as
p
r
ec
ip
itatio
n
p
atter
n
s
,
o
r
o
g
r
ap
h
ic
in
f
lu
en
ce
s
,
an
d
s
o
cieta
l
co
n
s
eq
u
en
ce
s
.
R
ed
d
y
et
a
l.
[
6
]
i
n
tr
o
d
u
ce
a
r
ai
n
f
all
p
r
ed
ictio
n
m
o
d
el
e
m
p
lo
y
i
n
g
m
u
ltip
le
lin
ea
r
r
eg
r
ess
io
n
(
M
L
R
)
f
o
r
I
n
d
ian
m
eteo
r
o
lo
g
ica
l
d
ata.
E
m
p
h
asizin
g
th
e
s
ig
n
i
f
ican
ce
o
f
ac
cu
r
ate
r
ain
f
all
p
r
ed
ictio
n
s
f
o
r
in
d
u
s
tr
ies,
p
ar
ticu
lar
ly
ag
r
ic
u
ltu
r
e,
t
h
e
r
esear
ch
s
h
o
wca
s
es
th
e
ef
f
icac
y
o
f
th
e
ML
R
-
b
ased
ap
p
r
o
a
ch
.
B
y
in
co
r
p
o
r
atin
g
m
u
ltip
le
m
eteo
r
o
lo
g
ic
al
p
ar
am
eter
s
,
th
e
s
tu
d
y
en
h
an
ce
s
p
r
ed
ictio
n
ac
cu
r
ac
y
,
o
f
f
er
in
g
p
o
ten
tial
b
en
ef
its
f
o
r
v
ar
i
o
u
s
in
d
u
s
tr
ies
r
elian
t
o
n
wea
th
er
f
o
r
ec
asti
n
g
.
T
h
e
in
teg
r
atio
n
o
f
ex
p
er
t sy
s
tem
s
ad
d
s
a
lay
er
o
f
s
o
p
h
is
ticatio
n
to
th
e
p
r
e
d
ictio
n
m
o
d
el,
c
o
n
tr
ib
u
tin
g
to
its
p
r
ac
tical
ap
p
licab
ilit
y
in
d
iv
er
s
e
s
ec
to
r
s
.
T
h
e
Natio
n
al
C
en
tr
e
f
o
r
Me
d
i
u
m
R
an
g
e
W
ea
th
er
Fo
r
ec
asti
n
g
u
s
ed
a
h
ig
h
-
r
eso
lu
tio
n
W
R
F
m
o
d
el
t
o
s
tu
d
y
th
e
2
0
1
0
L
eh
c
lo
u
d
b
u
r
s
t
,
wh
ich
ca
u
s
ed
o
v
er
2
0
0
d
ea
th
s
in
L
ad
ak
h
.
T
h
e
3
k
m
m
o
d
el
alig
n
ed
with
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
4
,
No
.
3
,
Dec
em
b
er
20
2
5
:
1
1
4
6
-
1
1
5
5
1148
T
R
MM
s
atell
ite
d
ata,
s
h
o
win
g
p
ea
k
r
ai
n
f
all
o
f
o
v
er
4
cm
i
n
th
r
ee
h
o
u
r
s
.
An
aly
s
is
r
ev
ea
l
ed
th
e
ev
en
t
r
esu
lted
f
r
o
m
a
h
u
m
id
n
o
r
th
west
f
lo
w
ca
p
p
e
d
b
y
co
o
ler
,
d
r
ier
air
,
with
in
s
tab
ilit
y
tr
ig
g
e
r
ed
b
y
a
clo
u
d
clu
s
ter
f
r
o
m
Nep
al
[
8
]
.
Pab
r
eja
an
d
Datta
[
9
]
d
e
m
o
n
s
tr
ated
th
e
u
s
e
o
f
k
-
m
ea
n
s
clu
s
ter
in
g
o
n
n
u
m
er
ica
l
wea
th
er
p
r
ed
ictio
n
d
ata
t
o
d
etec
t
c
lo
u
d
b
u
r
s
t
s
ig
n
als 3
-
4
d
ay
s
in
a
d
v
an
ce
,
u
s
in
g
a
ca
s
e
s
tu
d
y
o
f
a
c
l
o
u
d
b
u
r
s
t
i
n
Uttar
ak
h
an
d
.
Das
et
a
l.
[
1
0
]
a
n
aly
ze
d
th
e
Sh
illag
ar
h
c
lo
u
d
b
u
r
s
t
o
f
J
u
ly
1
6
,
2
0
0
3
,
wh
ich
last
ed
le
s
s
th
an
3
0
m
in
u
tes
an
d
ca
u
s
ed
s
ig
n
if
ican
t
d
am
ag
e.
Usi
n
g
th
e
MM
5
m
eso
s
ca
lm
o
d
el
with
n
ested
d
o
m
a
in
s
(
8
1
-
3
k
m
r
eso
lu
tio
n
)
,
th
e
s
tu
d
y
s
u
cc
ess
f
u
lly
p
r
e
d
icted
r
ain
f
all
2
4
h
o
u
r
s
in
ad
v
an
ce
b
u
t
ex
h
ib
ited
a
lo
ca
tio
n
er
r
o
r
o
f
s
ev
er
al
k
ilo
m
eter
s
.
L
ak
s
h
m
i
an
d
Kar
th
ik
e
y
an
[
1
1
]
s
tu
d
ied
K
-
m
ea
n
s
an
d
s
p
ec
tr
al
clu
s
ter
in
g
ap
p
r
o
ac
h
es
f
o
r
c
lo
u
d
b
u
r
s
t
p
r
ed
ictio
n
.
T
h
eir
ex
am
in
atio
n
o
f
s
p
ec
if
ic
h
u
m
id
ity
an
d
r
elativ
e
h
u
m
id
ity
at
v
ar
io
u
s
atm
o
s
p
h
er
ic
p
r
ess
u
r
e
lev
els
f
o
u
n
d
th
at
c
lo
u
d
b
u
r
s
t
s
ar
e
m
o
s
t
co
m
m
o
n
ar
o
u
n
d
9
2
5
h
Pa,
wh
er
ea
s
tem
p
er
atu
r
e
d
ata
s
u
g
g
ested
d
ev
elo
p
m
en
t a
t
4
0
0
h
Pa,
allo
win
g
f
o
r
ea
r
ly
id
en
tif
icatio
n
o
f
c
lo
u
d
b
u
r
s
t
ev
en
ts
.
W
an
g
et
a
l.
[
1
2
]
p
r
esen
ted
a
s
tu
d
y
o
n
th
e
Z
h
u
jiatan
g
L
a
n
d
s
lid
e
in
C
h
in
a
th
at
cr
ea
tes
a
f
r
am
ewo
r
k
f
o
r
a
n
ticip
atin
g
lan
d
s
lid
e
d
ef
o
r
m
atio
n
p
h
ases
u
tili
zin
g
m
u
lti
s
o
u
r
ce
d
ata
a
n
d
m
ac
h
in
e
lear
n
in
g
.
T
h
e
f
i
n
d
in
g
s
s
h
o
w
th
at
th
e
lan
d
s
lid
e
’
s
d
e
f
o
r
m
atio
n
,
wh
ich
is
m
o
s
t
s
tr
o
n
g
in
th
e
f
r
o
n
t
an
d
d
ec
r
ea
s
es
to
war
d
s
th
e
b
ac
k
,
is
clo
s
ely
r
elate
d
to
r
ain
f
all
p
a
tter
n
s
.
T
h
e
m
o
d
el
u
s
es
th
e
C
5
.
0
d
ec
is
io
n
tr
ee
to
ex
tr
ac
t
cr
iter
ia,
a
g
r
ap
h
co
n
v
o
l
u
tio
n
al
n
etwo
r
k
to
an
ti
cip
ate
s
tag
es,
an
d
th
e
Mo
r
g
e
n
s
ter
n
-
Pric
e
ap
p
r
o
ac
h
to
p
e
r
f
o
r
m
c
r
itical
s
lid
in
g
.
Ov
er
f
itti
n
g
c
o
n
ce
r
n
s
in
C
5
.
0
,
ch
allen
g
es
i
n
cr
u
cial
s
lid
in
g
p
r
ed
ictio
n
with
th
e
Mo
r
g
en
s
ter
n
-
Pric
e
a
p
p
r
o
ac
h
,
an
d
co
m
p
licated
k
n
o
wled
g
e
r
ep
r
esen
tatio
n
d
if
f
icu
lties
in
th
e
r
an
d
o
m
f
o
r
est
alg
o
r
it
h
m
ar
e
am
o
n
g
t
h
e
lim
itatio
n
s
.
T
h
e
s
tu
d
y
b
y
C
h
en
[
1
3
]
f
o
cu
s
es
o
n
im
p
r
o
v
em
e
n
ts
in
lan
d
s
li
d
e
p
r
e
d
ictio
n
,
s
p
ec
if
ically
u
s
in
g
cu
ttin
g
-
ed
g
e
m
o
d
elin
g
s
tr
ateg
ies
th
at
in
clu
d
e
k
n
o
wled
g
e
g
r
a
p
h
e
m
b
ed
d
in
g
.
I
t
d
is
cu
s
s
es
th
e
r
is
in
g
f
r
eq
u
en
cy
o
f
lan
d
s
lid
es,
wh
ich
is
m
ad
e
wo
r
s
e
b
y
clim
ate
ch
a
n
g
e,
an
d
cr
i
ti
cize
s
co
n
v
en
tio
n
al
f
o
r
ec
asti
n
g
tech
n
iq
u
es,
wh
ich
ar
e
f
r
eq
u
en
tly
e
x
p
en
s
iv
e
a
n
d
d
ep
en
d
e
n
t
o
n
s
p
ec
ialized
k
n
o
wled
g
e.
I
n
o
r
d
e
r
to
i
n
cr
ea
s
e
f
o
r
ec
ast
ac
cu
r
ac
y
a
n
d
m
ak
e
th
ese
m
eth
o
d
s
m
o
r
e
wid
ely
av
ailab
le,
p
a
r
ticu
lar
ly
f
o
r
r
em
o
te
s
en
s
in
g
ap
p
licatio
n
s
,
th
e
au
th
o
r
s
s
u
g
g
est
a
m
o
r
e
ef
f
ec
tiv
e
m
eth
o
d
f
o
r
a
s
s
es
s
in
g
p
o
s
s
ib
le
lan
d
s
lid
e
s
itu
atio
n
s
.
Data
-
d
r
i
v
en
m
o
d
els
h
av
e
is
s
u
es
in
clu
d
in
g
o
v
er
f
itti
n
g
,
h
ig
h
d
im
en
s
io
n
ali
ty
,
an
d
d
i
f
f
icu
lt
f
ea
tu
r
e
s
elec
tio
n
,
a
n
d
t
h
ey
r
u
n
th
e
d
an
g
er
o
f
o
v
er
s
im
p
lify
in
g
lan
d
s
lid
e
d
y
n
am
ics.
Sch
m
i
th
et
a
l
.
[
1
4
]
u
s
es
h
is
to
r
ical
d
aily
p
r
ec
ip
itatio
n
d
ata
(
1
9
1
4
-
2
0
1
0
)
an
d
r
ec
en
t
h
o
u
r
ly
r
ec
o
r
d
s
to
in
v
esti
g
ate
g
eo
g
r
a
p
h
ical
v
ar
ia
tio
n
s
in
c
lo
u
d
b
u
r
s
t
f
r
eq
u
e
n
cy
in
Den
m
ar
k
.
T
h
ey
d
ef
i
n
e
c
lo
u
d
b
u
r
s
t
d
ay
s
b
ased
o
n
h
o
u
r
ly
th
r
esh
o
ld
s
an
d
u
s
e
a
b
in
ar
y
r
eg
r
ess
io
n
m
o
d
el
to
p
r
ed
ict
c
lo
u
d
b
u
r
s
t
p
r
o
b
ab
ilit
y
f
r
o
m
d
aily
p
r
ec
ip
itatio
n
am
o
u
n
ts
,
in
d
icatin
g
g
r
ea
ter
f
r
e
q
u
en
c
y
in
wester
n
J
u
tlan
d
.
Mo
d
el
v
alid
atio
n
d
em
o
n
s
tr
ates
s
tr
o
n
g
p
r
ed
ictiv
e
ca
p
ab
ilit
y
,
a
n
d
th
e
d
ata
in
d
icate
s
th
at
r
eg
io
n
al
f
r
e
q
u
en
cy
v
ar
iatio
n
s
ar
e
d
u
e
t
o
s
p
ati
al
p
r
ec
ip
itatio
n
d
is
tr
ib
u
tio
n
r
ath
e
r
th
an
v
ar
ian
ce
s
in
th
e
m
o
d
el
’
s
p
r
ed
ictiv
e
c
o
n
n
ec
tio
n
.
Gar
g
et
a
l
.
[
1
5
]
ev
alu
ated
h
ig
h
-
r
eso
lu
tio
n
d
atasets
-
I
n
d
ian
Mo
n
s
o
o
n
Data
Ass
im
ilatio
n
a
n
d
An
aly
s
is
(
I
MD
AA)
an
d
I
ME
R
G
-
V0
6
B
-
f
o
r
id
en
tif
y
in
g
c
lo
u
d
b
u
r
s
t
o
cc
u
r
r
en
ce
s
in
th
e
No
r
th
west
Him
alay
as
(
NW
H)
.
I
MD
AA
s
u
cc
ess
f
u
lly
d
etec
ts
1
1
o
f
1
6
c
l
o
u
d
b
u
r
s
t
s
,
ex
ce
e
d
in
g
s
tan
d
ar
d
I
n
d
ia
Me
teo
r
o
lo
g
ical
Dep
ar
tm
en
t
(
I
MD
)
d
ata
in
a
r
ea
s
s
u
ch
as
J
am
m
u
a
n
d
Kash
m
ir
.
I
ME
R
G
-
V0
6
B
id
en
tifie
s
c
lo
u
d
b
u
r
s
t
s
with
a
m
o
d
est
p
r
o
b
a
b
ilit
y
(
3
3
.
3
3
%
-
6
3
.
3
9
%)
,
b
u
t
its
p
er
f
o
r
m
an
ce
in
cr
ea
s
es
with
tim
e
-
b
ased
m
o
d
if
ic
atio
n
s
to
4
1
.
2
4
%
-
6
8
.
2
5
%.
W
h
ile
b
o
t
h
d
atasets
co
u
ld
m
o
n
ito
r
s
ev
er
e
o
cc
u
r
r
en
c
es
in
NW
H,
th
eir
p
er
f
o
r
m
an
ce
in
d
if
f
icu
lt
ter
r
ain
r
em
ain
s
u
n
k
n
o
wn
,
u
n
d
er
s
co
r
i
n
g
th
e
n
ee
d
f
o
r
a
d
d
itio
n
al
v
a
lid
atio
n
o
f
c
l
o
u
d
b
u
r
s
t
d
etec
ti
o
n
in
m
o
u
n
tain
o
u
s
p
lace
s
.
Him
alay
an
s
tates
lik
e
Ut
tar
ak
h
an
d
,
Him
ac
h
al
Pra
d
esh
,
an
d
J
am
m
u
an
d
Kash
m
ir
ar
e
esp
ec
ially
v
u
ln
er
ab
le
t
o
c
lo
u
d
b
u
r
s
t
s
d
u
e
to
th
eir
r
u
g
g
ed
ter
r
ain
a
n
d
m
o
n
s
o
o
n
al
p
atter
n
s
,
lead
in
g
to
f
r
eq
u
en
t
lo
s
s
o
f
life
an
d
in
f
r
astru
ctu
r
e
d
a
m
ag
e.
Sati
[
1
6
]
ex
p
lo
r
es
th
e
im
p
ac
t
o
f
c
lo
u
d
b
u
r
s
t
-
ca
u
s
ed
h
az
ar
d
s
in
th
e
Uttar
ak
h
an
d
Him
alay
a,
in
clu
d
in
g
f
lash
f
l
o
o
d
s
an
d
lan
d
s
lid
es,
b
y
ex
a
m
in
in
g
p
r
o
ce
s
s
es,
im
p
ac
ts
,
an
d
m
itig
atio
n
o
p
tio
n
s
.
T
h
e
s
tu
d
y
u
s
es
f
ield
v
is
its
an
d
ca
s
e
s
tu
d
ies
to
illu
s
tr
ate
s
ev
er
e
h
u
m
a
n
an
d
p
r
o
p
e
r
ty
lo
s
s
es
f
r
o
m
o
cc
u
r
r
e
n
ce
s
s
u
ch
as
th
e
Au
g
u
s
t
2
0
1
7
c
lo
u
d
b
u
r
s
t
.
T
h
e
s
tu
d
y
u
n
d
er
lin
es
th
at,
wh
ile
n
atu
r
al
d
is
aste
r
s
ar
e
u
n
a
v
o
id
ab
le,
p
r
o
ac
tiv
e
ac
tio
n
s
,
s
u
ch
as
av
o
id
in
g
d
e
v
elo
p
m
e
n
t
n
ea
r
r
iv
e
r
s
an
d
s
tr
ea
m
s
an
d
p
r
o
m
o
tin
g
r
ef
o
r
estatio
n
,
ca
n
l
ess
en
ca
tast
r
o
p
h
e
s
ev
er
ity
.
Kar
u
n
an
id
y
et
a
l.
[
1
7
]
ad
d
r
ess
c
lo
u
d
b
u
r
s
t
p
r
e
d
ictio
n
in
I
n
d
ia
b
y
u
s
in
g
a
s
p
ec
if
ic
d
ataset
an
d
u
s
in
g
m
ac
h
in
e
lear
n
i
n
g
m
et
h
o
d
s
.
T
h
ey
co
n
s
id
er
tem
p
er
at
u
r
e,
wi
n
d
s
p
ee
d
,
h
u
m
i
d
ity
,
an
d
clo
u
d
d
en
s
ity
in
p
lace
s
p
r
o
n
e
t
o
c
lo
u
d
b
u
r
s
t
s
,
s
u
ch
as
th
e
Him
alay
as.
I
t
test
ed
m
u
ltip
le
m
o
d
els
an
d
d
is
co
v
e
r
ed
th
at
C
at
B
o
o
s
t
o
u
tp
er
f
o
r
m
ed
th
e
m
all
with
8
6
.
1
8
%
ac
cu
r
ac
y
,
p
r
o
v
in
g
m
ac
h
in
e
lear
n
in
g
’
s
ab
ilit
y
to
f
o
r
ec
ast
ex
tr
em
e
wea
th
er
o
cc
u
r
r
e
n
ce
s
ev
en
with
in
s
u
f
f
i
cien
t
h
is
to
r
ical
d
ata.
Sah
a
a
n
d
B
er
a
[
1
8
]
r
elate
s
r
ain
f
all
in
te
n
s
ity
-
d
u
r
atio
n
(
I
-
D)
th
r
esh
o
ld
s
to
lan
d
s
lid
e
o
cc
u
r
r
e
n
ce
s
in
th
e
Gar
h
wal
Him
alay
a
,
d
is
co
v
er
in
g
th
at
r
ain
f
all
in
te
n
s
ities
o
f
0
.
4
5
-
0
.
5
0
m
m
/h
o
u
r
o
v
er
4
8
h
o
u
r
s
m
i
g
h
t
ca
u
s
e
lan
d
s
lid
es,
p
ar
ticu
lar
l
y
wh
en
an
tece
d
en
t
r
ain
f
all
is
8
0
m
m
in
1
5
d
ay
s
.
T
h
e
s
tu
d
y
em
p
h
asizes th
e
s
ig
n
if
ican
ce
o
f
ea
r
ly
war
n
in
g
s
y
s
t
em
s
,
clim
ate
as
s
es
s
m
en
ts
,
an
d
lo
ca
l p
ar
ticip
atio
n
,
wh
ile
also
r
ec
o
m
m
en
d
in
g
f
u
tu
r
e
r
esear
ch
ar
ea
s
o
n
clim
ate
-
d
r
iv
en
th
r
esh
o
l
d
ch
an
g
es a
n
d
v
u
ln
er
ab
ilit
y
[
1
8
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
N
a
vig
a
tin
g
p
r
ed
ictive
la
n
d
s
ca
p
es o
f c
lo
u
d
b
u
r
s
t p
r
ed
ictio
n
a
p
p
r
o
a
ch
es:
in
s
ig
h
ts
…
(
A
n
il Hin
g
mir
e
)
1149
Hu
n
t
an
d
Dim
r
i
[
1
9
]
ex
p
lo
r
e
h
o
w
s
y
n
o
p
tic
-
s
ca
le
cir
c
u
latio
n
,
esp
ec
ially
ex
t
r
atr
o
p
ica
l
wester
n
d
is
tu
r
b
an
ce
s
(
W
Ds)
an
d
tr
o
p
ical
d
ep
r
ess
io
n
s
(
T
Ds),
af
f
ec
t
lan
d
s
lid
e
o
cc
u
r
r
en
ce
s
in
th
e
Up
p
er
I
n
d
u
s
B
asin
(
UI
B
)
o
f
th
e
wester
n
Him
ala
y
a
an
d
Kar
ak
o
r
am
.
T
h
eir
r
esear
ch
s
h
o
wed
s
ea
s
o
n
al
f
lu
ctu
atio
n
s
in
lan
d
s
lid
es,
with
a
r
ate
o
f
0
.
0
5
p
e
r
d
ay
i
n
win
ter
,
attr
ib
u
ted
m
o
s
tly
to
W
D
s
,
wh
ich
im
p
r
o
v
e
m
o
is
tu
r
e
m
o
v
em
en
t
an
d
p
r
ec
ip
itatio
n
.
No
tab
ly
,
W
D
in
ten
s
ity
d
id
n
o
t
lin
k
with
la
n
d
s
lid
e
lik
elih
o
o
d
,
i
n
d
icatin
g
th
at
s
m
aller
-
s
ca
le
o
r
o
g
r
a
p
h
ic
p
r
ec
ip
itatio
n
m
ay
also
b
e
in
v
o
lv
ed
.
I
n
th
e
s
u
m
m
er
,
lan
d
s
lid
es
in
cr
ea
s
e
t
o
0
.
1
1
p
e
r
d
a
y
,
with
T
D
s
fr
o
m
ce
n
tr
al
I
n
d
ia
ac
co
u
n
tin
g
f
o
r
6
0
%,
illu
s
tr
atin
g
th
e
im
p
o
r
tan
ce
o
f
m
o
n
s
o
o
n
al
f
l
o
ws.
T
h
is
s
tu
d
y
ad
v
an
ce
s
o
u
r
u
n
d
er
s
tan
d
in
g
o
f
m
eteo
r
o
lo
g
ical
in
ter
ac
tio
n
s
an
d
lan
d
s
lid
e
h
az
ar
d
s
,
ass
is
t
in
g
in
th
e
d
ev
elo
p
m
en
t
o
f
ef
f
ec
tiv
e
m
itig
atio
n
tech
n
iq
u
e
s
.
Sin
g
h
an
d
Pan
d
ey
[
2
0
]
s
tu
d
y
f
lash
f
lo
o
d
r
is
k
in
Uttar
ak
h
an
d
’
s
Up
p
er
Gan
g
a
B
asin
,
a
r
eg
io
n
p
r
o
n
e
to
s
ev
er
e
f
lo
o
d
s
.
T
h
e
y
u
s
e
GI
S
to
an
aly
ze
m
o
r
p
h
o
m
et
r
ic
ch
a
r
ac
ter
is
tics
f
r
o
m
SR
T
M
DE
M
d
ata
an
d
u
s
e
th
e
weig
h
ted
s
u
m
ap
p
r
o
ac
h
(
W
SA)
,
p
r
in
cip
al
c
o
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
,
an
d
an
in
teg
r
ated
ap
p
r
o
ac
h
(
I
A)
to
2
9
s
u
b
-
wate
r
s
h
ed
s
.
T
h
eir
f
in
d
in
g
s
d
em
o
n
s
tr
ate
t
h
at
PC
A
an
d
I
A
g
en
er
ate
eq
u
i
v
alen
t
v
u
ln
er
ab
ilit
y
ass
ess
m
en
ts
wh
en
ev
alu
ated
a
g
ain
s
t
h
is
to
r
ical
f
lo
o
d
o
cc
u
r
r
e
n
ce
s
f
r
o
m
2
0
1
8
a
n
d
2
0
1
9
.
T
h
e
s
tu
d
y
r
e
v
ea
ls
f
iv
e
d
en
s
ely
in
h
ab
ited
s
u
b
-
wat
er
s
h
ed
s
at
h
ig
h
r
is
k
,
co
n
f
ir
m
in
g
th
e
I
A
m
eth
o
d
’
s
d
ep
en
d
ab
ilit
y
f
o
r
f
las
h
f
lo
o
d
ass
ess
m
en
t
an
d
th
e
ef
f
icac
y
o
f
GI
S a
n
d
r
e
m
o
te
s
en
s
in
g
in
h
illy
a
r
ea
s
.
Mo
b
in
i
et
a
l.
[
2
1
]
u
s
es
g
eo
g
r
ap
h
ically
p
r
ec
is
e
p
r
o
p
er
t
y
-
le
v
el
d
ata
to
in
v
esti
g
ate
th
e
c
o
s
ts
o
f
an
in
ten
s
e
r
ain
ev
en
t
th
at
o
cc
u
r
r
e
d
o
n
Au
g
u
s
t
3
1
,
2
0
1
4
,
in
Ma
lm
ö
,
Swed
en
,
with
an
em
p
h
asi
s
o
n
th
e
in
ter
ac
tio
n
b
etwe
en
p
lu
v
ial
f
lo
o
d
d
am
a
g
e
an
d
th
e
b
u
ilt
en
v
ir
o
n
m
en
t.
T
h
e
f
in
d
in
g
s
s
h
o
w
th
at
h
o
m
es
co
n
n
ec
ted
to
co
m
b
in
ed
s
ewa
g
e
s
y
s
tem
s
h
a
v
e
m
u
ch
h
ig
h
e
r
f
lo
o
d
d
a
m
ag
e
claim
s
th
an
th
o
s
e
with
s
ep
ar
ate
s
y
s
tem
s
,
d
esp
ite
eq
u
al
to
tal
co
s
ts
,
em
p
h
asizin
g
th
e
n
ec
ess
ity
f
o
r
d
ir
ec
t a
c
ce
s
s
to
in
s
u
r
an
ce
d
ata
to
im
p
r
o
v
e
f
u
tu
r
e
s
tu
d
y
.
T
h
e
“
C
lo
u
d
b
u
r
s
t
Pre
d
ictio
n
”
r
esear
ch
p
r
o
ject
em
p
lo
y
s
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
t
ec
h
n
iq
u
es,
f
o
cu
s
in
g
o
n
t
h
e
an
aly
s
is
o
f
h
is
to
r
ical
m
eteo
r
o
lo
g
ical
d
at
a,
in
clu
d
in
g
p
r
ec
ip
itatio
n
p
at
ter
n
s
,
tem
p
er
atu
r
e
v
ar
iatio
n
s
,
h
u
m
id
ity
,
an
d
air
p
r
ess
u
r
e
ch
an
g
es.
Vijay
k
u
m
ar
et
a
l.
[
2
2
]
e
x
am
in
e
th
e
d
ev
astatin
g
f
lo
o
d
s
in
Ker
ala
d
u
r
in
g
th
e
2
0
1
8
an
d
2
0
1
9
m
o
n
s
o
o
n
s
,
id
en
tif
y
in
g
a
n
o
m
a
lo
u
s
ly
war
m
s
ea
tem
p
er
atu
r
es
an
d
u
n
s
tab
le
atm
o
s
p
h
er
ic
co
n
d
itio
n
s
as
k
ey
f
ac
t
o
r
s
in
t
h
e
u
n
p
r
ec
ed
en
ted
m
eso
s
ca
le
c
lo
u
d
b
u
r
s
t
ev
en
t
o
f
2
0
1
9
.
C
h
au
h
an
et
a
l.
[
2
3
]
ap
p
l
y
ex
t
r
em
e
v
alu
e
d
is
tr
ib
u
tio
n
a
n
d
th
e
m
ar
k
o
v
ch
ain
ap
p
r
o
ac
h
to
f
o
r
ec
ast
p
r
ec
ip
itatio
n
p
atter
n
s
in
t
h
eir
s
tu
d
y
o
f
h
y
d
r
o
m
eteo
r
o
lo
g
ical
d
ata
f
r
o
m
th
e
Yam
u
n
a
R
iv
er
B
asin
.
W
h
ile
ar
tific
ial
in
tellig
en
ce
ap
p
r
o
ac
h
es
h
av
e
lim
its
,
th
e
m
ar
k
o
v
ch
ain
m
o
d
el
p
r
ed
icts
r
ain
f
all
with
a
7
9
.
1
7
%
ac
cu
r
ac
y
,
em
p
h
asizin
g
th
e
n
ee
d
o
f
u
n
d
er
s
tan
d
in
g
r
etu
r
n
tim
es f
o
r
d
r
o
u
g
h
t a
n
d
f
lo
o
d
th
r
ea
ts
.
Kn
ö
s
et
a
l.
[
2
4
]
e
x
p
lo
r
es
t
h
e
d
ev
elo
p
m
en
t
o
f
a
c
lo
u
d
b
u
r
s
t
c
atastro
p
h
e
m
o
d
el
in
J
ö
n
k
ö
p
in
g
,
Swed
en
,
u
s
in
g
r
ain
f
all
in
te
n
s
ity
as
a
d
ir
ec
t
h
az
ar
d
m
ea
s
u
r
e
to
ass
ess
u
r
b
an
v
u
ln
e
r
ab
ilit
y
an
d
estab
lis
h
a
tim
e
-
s
en
s
itiv
e
v
u
ln
er
ab
ilit
y
cu
r
v
e,
s
u
g
g
esti
n
g
p
o
te
n
tial
ap
p
licab
ilit
y
in
v
a
r
io
u
s
g
eo
g
r
ap
h
ical
co
n
tex
ts
d
esp
ite
u
n
ce
r
tain
ties
d
u
e
to
lim
ited
lo
s
s
d
ata.
Fro
m
2
0
0
1
to
2
0
1
8
,
m
o
r
e
th
an
5
,
0
0
0
wate
r
-
r
elate
d
d
is
aster
s
(
W
R
D
s
)
,
in
clu
d
in
g
f
lo
o
d
s
an
d
d
r
o
u
g
h
ts
,
ac
co
u
n
t
ed
f
o
r
7
3
.
9
%
o
f
all
n
atu
r
al
d
i
s
aster
s
,
k
illi
n
g
o
v
er
3
0
0
,
0
0
0
p
eo
p
le
a
n
d
ca
u
s
in
g
$
1
.
7
tr
illi
o
n
i
n
ec
o
n
o
m
ic
d
am
ag
e
wo
r
ld
wid
e.
T
h
e
f
r
eq
u
en
cy
an
d
in
ten
s
ity
o
f
t
h
ese
d
is
aster
s
h
av
e
in
cr
ea
s
ed
in
th
e
twen
ty
-
f
ir
s
t
ce
n
tu
r
y
,
with
ap
p
r
o
x
im
ately
$
6
0
0
b
illi
o
n
lo
s
t
o
win
g
to
o
v
er
2
,
9
0
0
f
l
o
o
d
s
an
d
2
9
0
d
r
o
u
g
h
ts
,
wh
ich
h
av
e
h
ad
a
s
ev
er
e
im
p
ac
t
o
n
th
e
h
ea
lth
o
f
2
.
8
b
illi
o
n
p
eo
p
le,
in
clu
d
in
g
n
e
ar
ly
3
0
0
,
0
0
0
f
lo
o
d
in
j
u
r
ies
[
2
5
]
.
C
lo
u
d
b
u
r
s
t
s
,
wh
ich
f
ea
tu
r
e
q
u
ick
an
d
s
tr
o
n
g
r
ain
f
all,
ca
n
ca
u
s
e
f
lash
f
lo
o
d
s
in
m
etr
o
p
o
litan
ar
ea
s
d
u
e
to
in
s
u
f
f
icien
t
d
r
ain
ag
e
ca
p
a
c
ity
.
T
o
s
o
lv
e
th
is
,
Hin
g
m
ir
e
an
d
B
h
alad
h
ar
e
[
2
6
]
cr
ea
ted
an
I
o
T
-
b
ased
u
r
b
an
f
lo
o
d
m
an
ag
e
m
en
t
s
y
s
tem
wit
h
f
u
zz
y
l
o
g
ic
th
at
ad
ap
ts
i
n
r
e
al
tim
e
to
r
ain
f
all
i
n
ten
s
ity
,
w
ater
lev
el,
a
n
d
f
lo
w
r
ate.
T
h
eir
m
eth
o
d
r
ed
u
ce
d
wate
r
lev
els
b
y
u
p
to
7
3
.
9
%
d
u
r
in
g
e
x
tr
em
e
co
n
d
itio
n
s
,
in
d
icatin
g
th
at
it
is
a
p
o
ten
tial te
ch
n
iq
u
e
f
o
r
m
itig
at
in
g
c
lo
u
d
b
u
r
s
t
-
r
elate
d
f
lo
o
d
in
g
in
s
m
ar
t c
ities
.
3.
M
O
T
I
VAT
I
O
NS A
N
D
P
RO
B
L
E
M
ST
A
T
E
M
E
N
T
Desp
ite
th
e
g
r
o
win
g
f
r
eq
u
e
n
c
y
o
f
clo
u
d
b
u
r
s
ts
d
u
e
to
clim
ate
ch
an
g
e,
th
er
e
is
a
lack
o
f
ef
f
ec
tiv
e
f
o
r
ec
asti
n
g
a
n
d
m
o
n
ito
r
i
n
g
s
y
s
tem
s
th
at
ca
n
p
r
e
d
ict
th
ese
e
v
en
ts
an
d
m
itig
ate
th
eir
im
p
a
cts.
T
h
is
s
tu
d
y
aim
s
to
r
eso
lv
e
th
is
g
ap
b
y
d
ev
elo
p
in
g
a
p
r
ed
ictiv
e
m
o
d
el
th
at
u
tili
ze
s
m
eteo
r
o
lo
g
ical
d
ata
an
d
ad
v
an
ce
d
an
aly
tics
to
f
o
r
ec
ast clo
u
d
b
u
r
s
ts
m
o
r
e
ac
cu
r
ately
.
B
y
f
o
cu
s
in
g
o
n
u
n
d
e
r
s
tan
d
in
g
th
e
u
n
d
er
l
y
in
g
ca
u
s
es
an
d
p
at
ter
n
s
o
f
clo
u
d
b
u
r
s
ts
,
th
is
s
tu
d
y
aim
s
to
cr
ea
te
a
f
r
am
e
wo
r
k
th
at
en
h
an
ce
s
ea
r
ly
war
n
in
g
s
y
s
tem
s
an
d
in
f
o
r
m
s
d
is
aster
p
r
ep
ar
ed
n
ess
in
itiativ
es.
Ultim
ately
,
th
e
g
o
al
is
to
im
p
r
o
v
e
co
m
m
u
n
ity
r
esil
ien
ce
to
ex
tr
em
e
wea
th
er
e
v
en
ts
,
en
s
u
r
in
g
th
at
v
u
l
n
er
ab
le
p
o
p
u
latio
n
s
ar
e
b
etter
eq
u
ip
p
e
d
to
r
esp
o
n
d
to
t
h
e
ch
allen
g
es
p
o
s
ed
b
y
clo
u
d
b
u
r
s
ts
.
4.
I
M
P
L
E
M
E
NT
A
T
I
O
N
M
E
T
H
O
DO
L
O
G
Y
T
h
is
s
tu
d
y
in
v
esti
g
ates
th
e
p
r
ed
ictiv
e
ac
cu
r
ac
y
o
f
f
o
u
r
m
ac
h
in
e
lear
n
in
g
alg
o
r
it
h
m
s
-
lin
ea
r
r
eg
r
ess
io
n
,
s
u
p
p
o
r
t
v
ec
to
r
m
a
ch
in
e
(
SVM)
,
r
an
d
o
m
f
o
r
est
a
n
d
d
ec
is
io
n
tr
ee
-
i
n
p
r
ed
ictin
g
clo
u
d
b
u
r
s
t
e
v
en
ts
.
A
co
m
p
r
eh
en
s
iv
e
s
tu
d
y
in
wh
ich
m
eteo
r
o
lo
g
ical
d
ata
was
s
y
s
tem
atica
lly
co
llected
f
r
o
m
a
cu
r
ate
d
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
4
,
No
.
3
,
Dec
em
b
er
20
2
5
:
1
1
4
6
-
1
1
5
5
1150
au
th
o
r
itativ
e
f
r
o
m
Kag
g
le.
T
h
e
r
esear
ch
f
o
cu
s
es
o
n
t
h
e
r
i
g
o
r
o
u
s
ac
q
u
is
itio
n
an
d
an
aly
s
is
o
f
th
is
d
ataset,
ex
p
lo
r
in
g
its
p
o
ten
tial
a
p
p
lica
tio
n
s
in
d
iv
er
s
e
d
o
m
ain
s
.
B
y
l
ev
er
ag
in
g
th
e
wea
lth
o
f
in
f
o
r
m
atio
n
a
v
ailab
le
o
n
th
is
m
eteo
r
o
lo
g
ical
p
latf
o
r
m
,
we
aim
to
co
n
tr
ib
u
te
v
al
u
ab
le
in
s
ig
h
ts
to
th
e
s
cien
tific
co
m
m
u
n
ity
an
d
a
d
v
an
ce
th
e
u
n
d
er
s
tan
d
in
g
o
f
clim
atic
p
atter
n
s
,
u
ltima
tely
f
o
s
ter
in
g
in
n
o
v
atio
n
s
in
wea
t
h
er
-
r
elate
d
ap
p
licatio
n
s
a
n
d
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
es.
S
u
d
d
en
atm
o
s
p
h
er
ic
c
h
an
g
es
p
o
s
e
ch
allen
g
es,
an
d
th
e
s
p
atial
-
tem
p
o
r
al
r
eso
l
u
tio
n
o
f
th
e
m
o
d
el
r
eq
u
ir
es
r
e
g
io
n
-
s
p
ec
if
ic
ad
ap
tatio
n
s
f
o
r
o
p
tim
al
p
er
f
o
r
m
an
ce
.
T
h
e
f
ea
tu
r
es
s
elec
ted
to
tr
ain
th
e
m
o
d
el
ar
e
m
in
im
u
m
tem
p
er
a
tu
r
e,
r
ai
n
f
all,
win
d
-
g
u
s
t
s
p
ee
d
,
h
u
m
id
ity
9
am
,
h
u
m
i
d
ity
3
p
m
,
p
r
ess
u
r
e
9
am
,
p
r
ess
u
r
e
3
p
m
,
clo
u
d
9
am
,
clo
u
d
3
p
m
.
T
h
e
d
ataset
was
s
p
lit
i
n
to
tr
ai
n
in
g
(
8
0
%)
an
d
test
in
g
(
2
0
%
)
s
ets
to
e
v
alu
ate
g
en
er
aliza
b
i
lity
.
E
ac
h
m
o
d
el
was
im
p
lem
en
ted
u
s
in
g
Py
th
o
n
’
s
s
cik
it
-
lear
n
lib
r
ar
y
,
an
d
h
y
p
er
p
ar
am
eter
s
wer
e
o
p
tim
ized
th
r
o
u
g
h
g
r
id
s
ea
r
ch
with
f
iv
e
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
o
n
th
e
tr
ai
n
in
g
d
ata
to
en
s
u
r
e
ea
ch
a
lg
o
r
ith
m
’
s
o
p
tim
al
p
er
f
o
r
m
an
ce
.
a
)
M
o
del
s
elec
t
io
n a
nd
ex
perim
ent
a
l set
up
Alg
o
r
ith
m
s
:
−
L
o
g
is
tic
r
eg
r
ess
io
n
was
s
elec
ted
as
a
b
aselin
e
li
n
ea
r
m
o
d
el
to
u
n
d
er
s
tan
d
its
p
r
e
d
ictiv
e
p
e
r
f
o
r
m
a
n
ce
with
a
p
r
o
b
a
b
ilis
tic
ap
p
r
o
ac
h
to
cla
s
s
if
icatio
n
.
I
n
th
e
r
ea
lm
o
f
clo
u
d
b
u
r
s
t
p
r
ed
ictio
n
,
th
is
m
eth
o
d
ass
u
m
es
th
at
th
er
e
is
a
d
ir
ec
t
an
d
p
r
o
p
o
r
tio
n
al
r
elatio
n
s
h
ip
b
etwe
en
d
if
f
e
r
en
t
wea
th
er
v
ar
iab
les
(
s
u
c
h
as
tem
p
er
atu
r
e,
h
u
m
id
ity
,
an
d
win
d
s
p
ee
d
)
an
d
th
e
lik
elih
o
o
d
o
f
clo
u
d
b
u
r
s
t
ev
en
ts
o
cc
u
r
r
in
g
.
W
h
en
s
u
ch
a
lin
ea
r
r
elatio
n
s
h
ip
d
o
es
ex
is
t
,
lin
ea
r
r
eg
r
ess
io
n
ca
n
p
r
o
v
i
d
e
r
ea
s
o
n
ab
ly
ac
cu
r
ate
p
r
ed
ictio
n
s
,
with
an
ac
h
iev
ab
le
ac
cu
r
a
cy
r
a
n
g
e
ty
p
ically
f
allin
g
b
etwe
en
5
0
% to
6
0
%.
−
R
an
d
o
m
f
o
r
est
was
u
s
ed
f
o
r
it
s
en
s
em
b
le
-
b
ased
ar
ch
itectu
r
e,
wh
ich
en
h
an
ce
s
p
r
e
d
ictio
n
ac
cu
r
ac
y
th
r
o
u
g
h
m
u
ltip
le
d
ec
is
io
n
tr
ee
s
an
d
m
i
tig
ates o
v
er
f
itti
n
g
.
−
SVM
was
im
p
lem
en
ted
f
o
r
its
m
ar
g
in
m
ax
im
izatio
n
,
o
f
f
er
i
n
g
an
o
p
tim
al
h
y
p
er
p
lan
e
f
o
r
b
in
a
r
y
class
if
icatio
n
o
f
clo
u
d
b
u
r
s
t
an
d
n
o
n
-
clo
u
d
b
u
r
s
t
ev
en
ts
.
−
Dec
is
io
n
tr
ee
p
r
o
v
id
es
an
in
ter
p
r
etab
le
m
o
d
el
to
ass
ess
th
e
im
p
ac
t
o
f
in
d
iv
id
u
al
f
ea
tu
r
e
s
o
n
clo
u
d
b
u
r
s
t
p
r
ed
ictio
n
.
I
m
p
lem
en
tatio
n
:
−
T
h
e
d
ataset
was sp
lit in
to
tr
ain
in
g
(
8
0
%)
an
d
test
in
g
(
2
0
%)
s
ets to
ev
alu
ate
g
en
er
aliza
b
ilit
y
.
−
E
ac
h
m
o
d
el
was
im
p
lem
en
te
d
u
s
in
g
Py
th
o
n
’
s
s
cik
it
-
lear
n
lib
r
ar
y
,
a
n
d
h
y
p
er
p
ar
am
eter
s
wer
e
o
p
tim
ized
th
r
o
u
g
h
g
r
id
s
ea
r
c
h
with
f
iv
e
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
o
n
th
e
tr
ain
in
g
d
ata
to
en
s
u
r
e
ea
ch
alg
o
r
ith
m
’
s
o
p
tim
al
p
er
f
o
r
m
an
ce
.
b)
M
o
del t
ra
ini
ng
a
nd
hy
pe
rpa
ra
m
et
er
t
un
ing
E
ac
h
alg
o
r
ith
m
was
tr
ain
ed
o
n
th
e
tr
ain
in
g
s
et,
with
th
e
f
o
llo
win
g
h
y
p
er
p
ar
a
m
eter
s
f
i
n
e
-
tu
n
ed
f
o
r
o
p
tim
al
ac
cu
r
ac
y
:
−
L
o
g
is
tic
r
eg
r
ess
io
n
:
r
e
g
u
lar
iz
atio
n
s
tr
en
g
th
was
v
ar
ie
d
to
f
in
d
an
o
p
tim
al
b
alan
ce
b
etwe
en
u
n
d
er
f
itti
n
g
an
d
o
v
er
f
itti
n
g
.
−
R
an
d
o
m
f
o
r
est:
n
u
m
b
er
o
f
tr
e
es
an
d
m
ax
im
u
m
d
ep
t
h
wer
e
t
u
n
ed
to
e
n
s
u
r
e
r
o
b
u
s
t
f
ea
tu
r
e
s
elec
tio
n
wh
ile
av
o
id
in
g
ex
ce
s
s
iv
e
co
m
p
u
tatio
n
al
co
s
t.
−
SVM:
th
e
k
er
n
el
f
u
n
ctio
n
a
n
d
r
eg
u
la
r
izatio
n
p
ar
am
eter
C
wer
e
o
p
tim
ized
to
f
in
d
th
e
b
est
h
y
p
er
p
lan
e
f
o
r
class
if
icatio
n
.
−
Dec
is
io
n
tr
ee
:
m
ax
im
u
m
d
e
p
th
an
d
m
in
im
u
m
s
am
p
les
p
er
s
p
lit
wer
e
ad
ju
s
ted
to
co
n
tr
o
l
m
o
d
el
co
m
p
lex
ity
a
n
d
en
h
an
ce
g
en
er
aliza
b
ilit
y
.
T
h
e
r
esu
lts
o
f
ea
ch
m
o
d
el,
in
clu
d
in
g
m
et
r
ic
s
co
r
es
an
d
cla
s
s
if
icatio
n
ac
cu
r
ac
y
,
wer
e
c
o
m
p
ar
ed
t
o
id
en
tify
th
e
m
o
s
t
ef
f
ec
tiv
e
m
a
ch
in
e
lear
n
in
g
ap
p
r
o
ac
h
f
o
r
cl
o
u
d
b
u
r
s
t
p
r
ed
ictio
n
.
Ad
d
itio
n
ally
,
ea
ch
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
was
an
aly
ze
d
in
ter
m
s
o
f
co
m
p
u
tatio
n
al
ef
f
ici
en
cy
an
d
in
te
r
p
r
etab
ilit
y
,
p
r
o
v
id
in
g
in
s
ig
h
ts
in
to
th
e
p
r
ac
tical
f
ea
s
ib
ilit
y
o
f
ea
c
h
ap
p
r
o
ac
h
in
r
ea
l
-
tim
e
p
r
ed
ic
tio
n
s
y
s
tem
s
.
5.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
W
e
o
b
tain
ed
th
e
co
n
f
u
s
io
n
m
atr
ix
o
f
tr
ain
ed
m
o
d
el,
as
d
e
p
icted
in
Fig
u
r
e
1
,
s
er
v
es
as
a
c
r
u
cial
to
o
l
f
o
r
ev
alu
atin
g
th
e
p
er
f
o
r
m
an
c
e
o
f
a
clo
u
d
b
u
r
s
t
p
r
e
d
icti
o
n
m
o
d
el.
B
ased
o
n
th
e
F
ig
u
r
e
1
(
a)
co
n
f
u
s
io
n
m
atr
ic
o
f
r
a
n
d
o
m
f
o
r
est
m
o
d
el,
th
e
m
o
d
el
ac
h
iev
es
a
h
ig
h
T
r
u
e
Po
s
itiv
e
r
ate
an
d
r
elativ
ely
lo
w
f
alse
p
o
s
itiv
e
an
d
f
alse
n
eg
ativ
e
r
ates.
I
t
h
as
a
g
o
o
d
b
alan
ce
o
f
co
r
r
ec
t
p
r
e
d
ictio
n
s
in
b
o
th
p
o
s
itiv
e
an
d
n
eg
ativ
e
class
es,
in
d
icatin
g
it
p
er
f
o
r
m
s
well
o
n
b
o
th
.
Fig
u
r
e
1
(
b
)
s
h
o
ws
th
at
th
e
SVM
h
as
th
e
h
ig
h
est
tr
u
e
p
o
s
itiv
e
r
ate,
wh
ich
s
u
g
g
ests
it
ex
ce
ls
a
t
id
en
tify
in
g
p
o
s
itiv
e
ca
s
es.
Ho
wev
er
,
it
h
as
a
r
elativ
ely
h
ig
h
f
alse
n
eg
ativ
e
r
ate,
wh
ich
m
ig
h
t
in
d
icate
it
o
cc
asio
n
ally
f
ails
to
id
e
n
tify
ac
t
u
al
p
o
s
itiv
es
co
r
r
ec
tly
.
I
t
h
as
th
e
lo
west
f
alse
p
o
s
itiv
e
(
FP
)
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
N
a
vig
a
tin
g
p
r
ed
ictive
la
n
d
s
ca
p
es o
f c
lo
u
d
b
u
r
s
t p
r
ed
ictio
n
a
p
p
r
o
a
ch
es:
in
s
ig
h
ts
…
(
A
n
il Hin
g
mir
e
)
1151
wh
ich
s
u
g
g
ests
m
in
im
al
o
v
er
-
p
r
ed
ictio
n
.
Fig
u
r
e
1
(
c)
s
h
o
ws
th
at
th
e
lo
g
is
tic
r
eg
r
ess
io
n
h
as
s
ig
n
if
ican
tly
lo
wer
T
P
an
d
T
N
v
alu
es,
lik
ely
in
d
icatin
g
it
s
tr
u
g
g
les
with
o
v
er
all
p
r
ed
ictio
n
ac
cu
r
ac
y
in
th
is
d
ataset.
T
h
e
lo
w
tr
u
e
p
o
s
itiv
e
(
T
P)
s
u
g
g
ests
it
f
ails
to
d
etec
t
p
o
s
itiv
es
ef
f
ec
tiv
ely
,
an
d
a
lo
w
tr
u
e
n
eg
ativ
e
(
T
N)
in
d
icate
s
s
im
ilar
is
s
u
es
with
n
eg
ativ
es.
Fig
u
r
e
1
(
d
)
s
h
o
ws
th
at
th
e
d
ec
is
io
n
t
r
ee
h
as
a
h
ig
h
T
P,
b
u
t
th
e
h
ig
h
est
FP
am
o
n
g
th
e
m
o
d
els.
T
h
is
s
u
g
g
ests
th
at
w
h
ile
it
ca
p
tu
r
es
p
o
s
itiv
e
ca
s
es
r
ea
s
o
n
ab
ly
well,
it
also
m
is
class
if
ies
n
eg
ativ
es
as
p
o
s
itiv
es m
o
r
e
f
r
e
q
u
en
tly
t
h
an
o
th
er
s
.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
1
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
m
o
d
els;
(
a)
r
a
n
d
o
m
f
o
r
est m
o
d
el,
(
b
)
s
u
p
p
o
r
t v
ec
to
r
m
ac
h
in
e
m
o
d
el,
(
c)
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el,
an
d
(
d
)
d
ec
is
io
n
tr
ee
m
o
d
el
Fig
u
r
e
2
s
h
o
ws
a
W
in
r
o
s
e
c
h
ar
t
o
f
win
d
s
p
ee
d
illu
s
tr
ates
th
e
in
cr
ea
s
in
g
m
ag
n
itu
d
e
o
f
th
e
win
d
s
p
ee
d
.
T
h
e
W
i
n
r
o
s
e
c
h
ar
t p
r
o
v
id
es
a
c
o
m
p
r
e
h
en
s
iv
e
a
n
d
v
is
u
ally
in
tu
itiv
e
o
v
e
r
v
iew
o
f
th
e
p
r
e
v
ailin
g
wea
th
e
r
co
n
d
itio
n
s
,
en
a
b
lin
g
u
s
er
s
to
q
u
ick
ly
g
r
asp
th
e
o
v
er
all
wea
th
er
p
atter
n
.
Fig
u
r
e
2
.
W
in
r
o
s
e
c
h
a
r
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
4
,
No
.
3
,
Dec
em
b
er
20
2
5
:
1
1
4
6
-
1
1
5
5
1152
Fig
u
r
e
3
s
h
o
ws
a
h
ea
t
m
ap
t
h
at
p
r
o
v
i
d
es
a
v
is
u
al
s
n
ap
s
h
o
t
o
f
th
e
co
r
r
elatio
n
s
am
o
n
g
k
ey
wea
th
er
p
ar
am
eter
s
,
s
h
ed
d
in
g
lig
h
t
o
n
th
eir
in
ter
co
n
n
ec
ted
n
ess
an
d
p
o
ten
tial
im
p
licatio
n
s
f
o
r
clo
u
d
b
u
r
s
t
o
cc
u
r
r
en
ce
s
.
T
em
p
er
atu
r
e
’
s
in
f
lu
e
n
ce
is
d
is
ce
r
n
ed
th
r
o
u
g
h
its
c
o
r
r
ela
tio
n
s
with
o
th
e
r
f
ac
t
o
r
s
,
in
d
icatin
g
th
at
h
ig
h
er
tem
p
er
atu
r
es
m
a
y
c
o
n
tr
ib
u
te
to
clo
u
d
b
u
r
s
t
ev
e
n
ts
.
C
r
u
cia
l
to
clo
u
d
b
u
r
s
t
li
k
elih
o
o
d
,
h
u
m
id
ity
lev
els
a
r
e
s
h
o
wca
s
ed
in
th
e
h
ea
tm
a
p
,
h
ig
h
lig
h
tin
g
th
eir
in
ter
p
lay
with
v
ar
io
u
s
p
ar
am
eter
s
.
Fig
u
r
e
4
s
h
o
ws
a
d
u
al
-
a
x
is
ch
ar
t
th
at
m
e
r
g
es
clo
u
d
b
u
r
s
t
o
c
cu
r
r
en
ce
s
with
k
ey
wea
th
er
p
ar
am
eter
s
,
o
f
f
er
in
g
a
co
m
p
r
eh
e
n
s
iv
e
v
ie
w
o
f
th
eir
in
ter
r
elatio
n
s
h
ip
s
o
v
er
tim
e.
T
e
m
p
er
atu
r
e
tr
en
d
s
,
h
u
m
id
ity
lev
els,
win
d
s
p
ee
d
p
atter
n
s
,
clo
u
d
co
v
er
v
a
r
iatio
n
s
,
atm
o
s
p
h
er
ic
p
r
ess
u
r
e,
an
d
p
r
ec
ip
itatio
n
in
ten
s
ity
ar
e
all
v
is
u
ally
r
ep
r
esen
ted
.
Fig
u
r
e
3
.
H
ea
t m
a
p
f
o
r
co
r
r
elatio
n
s
am
o
n
g
k
ey
wea
th
e
r
p
ar
a
m
eter
s
Fig
u
r
e
4
.
C
lo
u
d
b
u
r
s
t
o
cc
u
r
r
e
n
ce
s
o
f
r
an
d
o
m
f
o
r
est
T
ab
le
1
s
h
o
ws
a
co
m
p
ar
is
o
n
o
f
m
o
d
els
b
ased
o
n
ac
c
u
r
ac
y
,
r
ec
all,
an
d
F1
-
s
co
r
e.
T
h
e
r
an
d
o
m
f
o
r
est
m
o
d
el
p
er
f
o
r
m
s
b
est,
with
h
ig
h
ac
cu
r
ac
y
(
0
.
9
5
1
0
)
an
d
r
ec
all
(
0
.
8
7
3
4
)
f
o
r
th
e
p
o
s
itiv
e
c
lass
,
r
esu
ltin
g
in
an
F1
-
s
co
r
e
o
f
0
.
9
1
0
6
.
W
h
ile
th
e
SVM
h
as
th
e
b
est
p
o
s
itiv
e
class
ac
cu
r
ac
y
(
0
.
9
7
6
6
)
,
its
lo
wer
r
ec
all
(
0
.
8
4
4
0
)
s
u
g
g
ests
o
cc
asio
n
al
m
is
s
es.
L
o
g
is
tic
r
eg
r
ess
io
n
s
co
r
es
p
o
o
r
ly
ac
r
o
s
s
all
cr
iter
ia,
wh
er
ea
s
d
ec
is
io
n
tr
ee
ac
h
iev
es
r
ea
s
o
n
ab
le
b
ala
n
ce
b
u
t
f
alls
s
h
o
r
t
o
f
r
an
d
o
m
f
o
r
est
an
d
SVM.
T
h
u
s
,
r
an
d
o
m
f
o
r
est
p
r
o
d
u
ce
s
th
e
m
o
s
t c
o
n
s
is
ten
t r
esu
lts
f
o
r
th
is
d
ataset.
T
ab
le
1
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
o
f
im
p
lem
e
n
ted
m
o
d
els
M
o
d
e
l
s
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
v
a
l
u
e
s
c
l
a
ss
P
o
si
t
i
v
e
N
e
g
a
t
i
v
e
P
o
si
t
i
v
e
N
e
g
a
t
i
v
e
P
o
si
t
i
v
e
N
e
g
a
t
i
v
e
R
a
n
d
o
m
f
o
r
e
st
0
.
9
5
1
0
0
.
5
1
1
9
0
.
8
7
3
4
0
.
7
4
6
9
0
.
9
1
0
6
0
.
6
0
7
4
S
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
0
.
9
7
6
6
0
.
3
6
1
0
0
.
8
4
4
0
0
.
8
1
3
2
0
.
1
5
6
0
0
.
9
0
5
5
Lo
g
i
s
t
i
c
r
e
g
r
e
ss
i
o
n
0
.
8
5
3
0
0
.
1
4
8
8
0
.
6
9
7
9
0
.
3
0
5
1
0
.
7
6
7
7
0
.
2
0
0
0
D
e
c
i
s
i
o
n
t
r
e
e
0
.
8
6
0
6
0
.
5
3
6
8
0
.
8
6
8
0
0
.
5
2
0
9
0
.
8
6
4
3
0
.
5
2
8
7
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
N
a
vig
a
tin
g
p
r
ed
ictive
la
n
d
s
ca
p
es o
f c
lo
u
d
b
u
r
s
t p
r
ed
ictio
n
a
p
p
r
o
a
ch
es:
in
s
ig
h
ts
…
(
A
n
il Hin
g
mir
e
)
1153
T
ab
le
2
s
h
o
ws
th
e
co
m
p
ar
is
o
n
o
f
th
e
ac
cu
r
ac
y
f
o
r
ea
ch
p
r
e
d
ictio
n
m
o
d
el.
T
h
e
r
an
d
o
m
f
o
r
est
m
o
d
el
ac
h
iev
es
th
e
h
ig
h
est
ac
cu
r
ac
y
at
8
5
.
4
3
%,
clo
s
ely
f
o
llo
w
ed
b
y
th
e
SVM
at
8
4
.
1
0
%.
T
h
e
d
ec
is
io
n
tr
ee
p
er
f
o
r
m
s
m
o
d
e
r
ately
well
wit
h
an
ac
c
u
r
ac
y
o
f
7
8
.
9
3
%,
w
h
ile
th
e
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el
h
as
th
e
l
o
west
ac
cu
r
ac
y
at
6
4
.
0
0
%.
T
ab
le
2
.
Per
f
o
r
m
an
ce
an
aly
s
is
o
f
m
o
d
els
M
o
d
e
l
n
a
m
e
A
c
c
u
r
a
c
y
R
a
n
d
o
m
f
o
r
e
s
t
8
5
.
4
3
%
S
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
8
4
.
1
0
%
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
6
4
.
0
0
%
D
e
c
i
s
i
o
n
t
r
e
e
7
8
.
9
3
%
6.
CO
NCLU
SI
O
N
T
h
e
s
tu
d
y
d
e
m
o
n
s
tr
ates
th
at
t
h
e
r
a
n
d
o
m
f
o
r
est
m
o
d
el,
wit
h
an
ac
cu
r
ac
y
o
f
8
5
.
4
3
%,
o
u
t
p
er
f
o
r
m
s
o
th
er
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
(
SVM
,
d
ec
is
io
n
tr
ee
,
an
d
lo
g
is
tic
r
eg
r
ess
io
n
)
in
p
r
e
d
ictin
g
c
lo
u
d
b
u
r
s
t
ev
en
ts
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
an
aly
s
is
h
ig
h
lig
h
ts
r
an
d
o
m
f
o
r
est
’
s
ef
f
ec
tiv
e
b
alan
ce
o
f
tr
u
e
p
o
s
itiv
es
an
d
tr
u
e
n
eg
ativ
es,
m
in
im
izin
g
b
o
t
h
f
a
ls
e
p
o
s
itiv
es
an
d
f
alse
n
eg
ati
v
es
.
I
ts
s
tr
o
n
g
p
r
ec
is
io
n
a
n
d
r
ec
all
v
alu
es
in
th
e
p
o
s
itiv
e
class
r
ein
f
o
r
ce
its
ab
ilit
y
to
ac
cu
r
ately
d
etec
t
p
o
te
n
tial
c
lo
u
d
b
u
r
s
t
s
wh
ile
m
ain
t
ain
in
g
a
m
o
d
er
ate
er
r
o
r
r
ate
f
o
r
n
eg
ativ
e
ca
s
es.
SVM
,
with
a
s
im
ilar
h
ig
h
ac
cu
r
ac
y
(
8
4
.
1
0
%),
s
h
o
ws
e
x
ce
llen
t
tr
u
e
p
o
s
itiv
e
r
ates
an
d
lo
w
f
alse
p
o
s
itiv
es
,
th
o
u
g
h
it
h
as
a
s
l
ig
h
tly
h
ig
h
er
f
alse
n
eg
ativ
e
r
ate,
s
u
g
g
esti
n
g
s
o
m
e
m
is
s
ed
p
o
s
itiv
es
.
C
o
n
v
er
s
ely
,
lo
g
is
tic
r
eg
r
ess
io
n
s
tr
u
g
g
les
s
ig
n
if
ican
tly
with
an
ac
cu
r
ac
y
o
f
6
4
.
0
0
%,
m
ak
i
n
g
it
u
n
s
u
itab
le
f
o
r
th
is
ap
p
licatio
n
.
T
h
e
d
ec
is
io
n
tr
ee
ac
h
iev
es m
o
d
er
ate
ac
cu
r
a
cy
(
7
8
.
9
3
%)
b
u
t su
f
f
er
s
f
r
o
m
h
ig
h
f
alse p
o
s
itiv
es,
wh
ich
c
an
im
p
ac
t
r
eliab
ilit
y
.
Ov
er
all
,
r
an
d
o
m
f
o
r
es
t
em
e
r
g
es
as
th
e
m
o
s
t
b
ala
n
ce
d
a
n
d
r
eliab
le
m
o
d
el
f
o
r
c
lo
u
d
b
u
r
s
t
p
r
e
d
ictio
n
in
th
is
s
tu
d
y
,
p
r
o
v
i
d
in
g
a
r
o
b
u
s
t
to
o
l
f
o
r
en
h
a
n
cin
g
ea
r
ly
war
n
i
n
g
s
y
s
tem
s
.
Fu
tu
r
e
r
esear
ch
co
u
ld
e
n
h
an
ce
p
r
e
d
ictio
n
ac
cu
r
ac
y
b
y
e
x
p
lo
r
in
g
ad
d
itio
n
al
en
s
em
b
le
m
eth
o
d
s
,
h
y
p
er
p
ar
am
e
ter
tu
n
in
g
,
a
n
d
u
s
in
g
lar
g
er
,
d
iv
er
s
e
d
atasets
with
r
ea
l
-
tim
e
wea
th
er
d
ata
f
o
r
im
p
r
o
v
e
d
m
o
d
el
g
en
e
r
aliza
tio
n
.
I
n
co
r
p
o
r
atin
g
d
ee
p
lear
n
in
g
te
ch
n
iq
u
es
an
d
d
e
p
lo
y
in
g
m
o
d
e
ls
with
in
r
ea
l
-
tim
e
s
y
s
tem
s
in
co
llab
o
r
atio
n
with
m
eteo
r
o
lo
g
ical
a
g
en
cies c
o
u
ld
s
tr
en
g
th
e
n
c
lo
u
d
b
u
r
s
t
p
r
e
d
ictio
n
s
tr
ateg
ies an
d
p
u
b
lic
s
af
ety
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
s
ac
k
n
o
wled
g
e
th
e
in
s
titu
tio
n
al
s
u
p
p
o
r
t
a
n
d
r
eso
u
r
ce
s
th
at
f
ac
ilit
ated
th
e
s
u
cc
ess
f
u
l
co
m
p
letio
n
o
f
th
is
r
esear
ch
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
n
o
f
u
n
d
in
g
o
r
f
in
an
cial
s
u
p
p
o
r
t
was
r
ec
eiv
ed
f
r
o
m
an
y
ex
te
r
n
al
f
u
n
d
in
g
ag
en
cy
f
o
r
th
e
r
esear
ch
r
e
p
o
r
t
ed
in
th
is
ar
ticle
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
An
il Hin
g
m
ir
e
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Su
n
ay
an
a
J
ad
h
a
v
✓
✓
✓
✓
✓
✓
Me
g
h
a
T
r
iv
e
d
i
✓
✓
✓
✓
✓
✓
✓
Kar
an
San
k
h
e
✓
✓
✓
✓
✓
Om
k
ar
Kh
an
o
lk
ar
✓
✓
✓
✓
✓
Yu
k
ta
Patil
✓
✓
✓
✓
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
au
th
o
r
s
d
ec
lar
e
th
at
th
e
r
e
is
n
o
co
n
f
lict o
f
in
ter
est r
eg
ar
d
in
g
th
e
p
u
b
licatio
n
o
f
th
is
p
a
p
er
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
4
,
No
.
3
,
Dec
em
b
er
20
2
5
:
1
1
4
6
-
1
1
5
5
1154
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
m
eteo
r
o
lo
g
ical
d
ata
u
s
ed
in
th
is
s
tu
d
y
was
s
o
u
r
ce
d
f
r
o
m
Kag
g
le,
a
p
u
b
lic
d
ata
p
latf
o
r
m
.
T
h
e
d
ataset
was
s
elec
ted
f
r
o
m
a
cu
r
ated
an
d
a
u
th
o
r
itativ
e
co
llectio
n
r
elev
an
t
to
th
e
s
tu
d
y
o
b
jectiv
es.
All
d
ata
u
s
ed
i
s
av
ailab
le
in
th
e
p
u
b
lic
d
o
m
ain
a
n
d
ca
n
b
e
ac
ce
s
s
ed
f
r
ee
ly
f
o
r
r
esear
ch
an
d
ed
u
ca
tio
n
al
p
u
r
p
o
s
es
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
M
.
H
i
n
g
mi
r
e
a
n
d
P
.
R
.
B
h
a
l
a
d
h
a
r
e
,
“
A
r
e
v
i
e
w
o
n
u
r
b
a
n
f
l
o
o
d
ma
n
a
g
e
men
t
t
e
c
h
n
i
q
u
e
s
f
o
r
t
h
e
sm
a
r
t
c
i
t
y
a
n
d
f
u
t
u
r
e
r
e
sea
r
c
h
,
”
i
n
I
n
t
e
l
l
i
g
e
n
t
C
y
b
e
r
Ph
y
si
c
a
l
S
y
s
t
e
m
s
a
n
d
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
En
g
i
n
e
e
ri
n
g
C
y
b
e
r
-
P
h
y
si
c
a
l
S
y
s
t
e
m
s
a
n
d
C
r
i
t
i
c
a
l
I
n
f
ra
st
r
u
c
t
u
r
e
s
,
2
0
2
3
,
p
p
.
3
0
3
–
3
1
7
.
[
2
]
A
.
Ti
w
a
r
i
a
n
d
S
.
K
.
V
e
r
ma,
“
C
l
o
u
d
b
u
r
st
p
r
e
d
e
t
e
r
m
i
n
a
t
i
o
n
s
y
st
e
m,
”
2
0
1
5
.
[
3
]
M
.
S
i
v
a
g
a
mi
,
P
.
R
a
d
h
a
,
a
n
d
A
.
B
a
l
a
s
u
n
d
a
r
a
m,
“
S
e
q
u
e
n
c
e
mo
d
e
l
b
a
s
e
d
c
l
o
u
d
b
u
r
st
p
r
e
d
i
c
t
i
o
n
f
o
r
t
h
e
I
n
d
i
a
n
s
t
a
t
e
o
f
U
t
t
a
r
a
k
h
a
n
d
,
”
D
i
sa
s
t
e
r
Ad
v
a
n
c
e
s
,
v
o
l
.
1
4
,
n
o
.
7
,
p
p
.
1
–
9
,
Ju
n
.
2
0
2
1
,
d
o
i
:
1
0
.
2
5
3
0
3
/
f
2
5
1
2
1
0
5
.
[
4
]
A
.
S
u
n
i
l
,
B
.
A
.
B
i
n
n
y
,
J
.
B
e
n
n
y
,
R
.
R
a
j
e
e
v
,
a
n
d
M
.
A
.
M
a
n
u
e
l
,
“
P
r
e
d
i
st
e
r
(
‘
A
n
I
n
t
e
l
l
i
g
e
n
t
D
e
v
i
c
e
T
o
P
r
e
d
i
c
t
C
l
o
u
d
B
u
r
st
’
)
,
”
Pre
d
i
st
e
r:
A
n
I
n
t
e
l
l
i
g
e
n
t
D
e
v
i
c
e
t
o
Pr
e
d
i
c
t
C
l
o
u
d
B
u
rs
t
,
v
o
l
.
7
,
n
o
.
6
,
p
.
2
0
2
0
,
2
0
2
2
,
d
o
i
:
1
0
.
6
0
8
4
/
m
9
.
d
o
i
o
n
e
.
I
JR
T
I
2
2
0
6
3
0
3
.
[
5
]
A
.
P
.
D
i
mr
i
e
t
a
l
.
,
“
C
l
o
u
d
b
u
r
s
t
s
i
n
I
n
d
i
a
n
H
i
ma
l
a
y
a
s
:
A
R
e
v
i
e
w
,
”
E
a
rt
h
-
S
c
i
e
n
c
e
Re
v
i
e
w
s
,
2
0
1
6
.
[
6
]
G
.
B
.
R
e
d
d
y
,
J
.
C
h
e
t
h
a
n
,
a
n
d
M
.
S
a
r
a
v
a
n
a
m
u
t
h
u
,
“
C
l
o
u
d
b
u
r
s
t
f
o
r
e
c
a
st
u
s
i
n
g
e
x
p
e
r
t
s
y
s
t
e
ms
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
Re
s
e
a
r
c
h
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
2
0
2
2
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
w
w
w
.
i
r
j
e
t
.
n
e
t
.
[
7
]
S
.
K
h
a
n
d
u
r
i
,
“
C
l
o
u
d
b
u
r
st
s
o
v
e
r
I
n
d
i
a
n
S
u
b
-
c
o
n
t
i
n
e
n
t
o
f
U
t
t
a
r
a
k
h
a
n
d
H
i
m
a
l
a
y
a
:
a
t
r
a
d
i
t
i
o
n
a
l
h
a
b
i
t
a
t
i
o
n
i
n
p
u
t
f
r
o
m
B
a
n
so
l
i
,
D
i
s
t
r
i
c
t
-
C
h
a
mo
l
i
,
I
n
d
i
a
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
a
rt
h
S
c
i
e
n
c
e
s
K
n
o
w
l
e
d
g
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
4
8
–
6
3
,
2
0
2
0
.
[
8
]
R
.
A
sh
r
i
t
,
“
I
n
v
e
s
t
i
g
a
t
i
n
g
t
h
e
Le
h
‘
C
l
o
u
d
b
u
r
s
t
,
”
N
a
t
i
o
n
a
l
C
e
n
t
r
e
Fo
r
Me
d
i
u
m
R
a
n
g
e
We
a
t
h
e
r
Fo
r
e
c
a
st
i
n
g
M
i
n
i
st
r
y
O
f
E
a
rt
h
S
c
i
e
n
c
e
s
G
o
v
e
r
n
m
e
n
t
O
f
I
n
d
i
a
,
2
0
1
0
.
[
9
]
K
.
P
a
b
r
e
j
a
a
n
d
R
.
K
.
D
a
t
t
a
,
“
C
l
u
s
t
e
r
i
n
g
t
e
c
h
n
i
q
u
e
f
o
r
i
n
t
e
r
p
r
e
t
a
t
i
o
n
o
f
c
l
o
u
d
b
u
r
s
t
o
v
e
r
U
t
t
a
r
a
k
h
a
n
d
,
”
M
a
u
s
a
m
,
v
o
l
.
6
7
,
n
o
.
3
,
p
p
.
6
6
9
–
6
7
6
,
J
u
l
.
2
0
1
6
,
d
o
i
:
1
0
.
5
4
3
0
2
/
ma
u
sam
.
v
6
7
i
3
.
1
3
8
6
.
[
1
0
]
S
.
D
a
s,
R
.
A
s
h
r
i
t
,
a
n
d
M
.
W
.
M
o
n
c
r
i
e
f
f
,
“
S
i
m
u
l
a
t
i
o
n
o
f
a
H
i
m
a
l
a
y
a
n
c
l
o
u
d
b
u
r
s
t
e
v
e
n
t
,
”
J
o
u
rn
a
l
o
f
E
a
rt
h
S
y
s
t
e
m
S
c
i
e
n
c
e
,
v
o
l
.
1
1
5
,
n
o
.
3
,
p
p
.
2
9
9
–
3
1
3
,
Ju
n
.
2
0
0
6
,
d
o
i
:
1
0
.
1
0
0
7
/
B
F
0
2
7
0
2
0
4
4
.
[
1
1
]
D
.
l
a
k
sh
mi
a
n
d
J.
K
a
r
t
h
i
k
e
y
a
n
,
“
W
e
a
t
h
e
r
i
m
p
a
c
t
o
v
e
r
U
t
t
a
r
a
k
h
a
n
d
u
s
i
n
g
k
-
mea
n
s
c
l
u
s
t
e
r
i
n
g
t
e
c
h
n
i
q
u
e
f
o
r
c
l
o
u
d
b
u
r
s
t
p
r
e
d
i
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
D
a
t
a
Mi
n
i
n
g
T
e
c
h
n
i
q
u
e
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
5
,
n
o
.
2
,
p
p
.
1
4
8
–
1
4
9
,
D
e
c
.
2
0
1
6
,
d
o
i
:
1
0
.
2
0
8
9
4
/
I
JD
M
TA
.
1
0
2
.
0
0
5
.
0
0
2
.
0
1
0
.
[
1
2
]
X
.
W
a
n
g
,
M
.
D
i
a
o
,
H
.
G
u
o
,
L
.
W
a
n
g
,
H
.
G
u
o
,
a
n
d
D
.
Li
,
“
La
n
d
sl
i
d
e
d
e
f
o
r
ma
t
i
o
n
p
r
e
d
i
c
t
i
o
n
a
n
d
a
u
t
o
ma
t
i
c
w
a
r
n
i
n
g
b
y
c
o
u
p
l
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
p
h
y
si
c
a
l
m
o
d
e
l
s,”
E
a
r
t
h
a
n
d
S
p
a
c
e
S
c
i
e
n
c
e
,
v
o
l
.
1
1
,
n
o
.
6
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
2
9
/
2
0
2
3
EA
0
0
3
2
3
8
.
[
1
3
]
L.
C
h
e
n
,
L.
P
e
n
g
,
a
n
d
L.
Y
a
n
g
,
“
I
mp
r
o
v
i
n
g
l
a
n
d
sl
i
d
e
p
r
e
d
i
c
t
i
o
n
:
i
n
n
o
v
a
t
i
v
e
m
o
d
e
l
i
n
g
a
n
d
e
v
a
l
u
a
t
i
o
n
o
f
l
a
n
d
sl
i
d
e
sc
e
n
a
r
i
o
w
i
t
h
k
n
o
w
l
e
d
g
e
g
r
a
p
h
e
m
b
e
d
d
i
n
g
,
”
R
e
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
6
,
n
o
.
1
,
p
.
1
4
5
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
6
0
1
0
1
4
5
.
[
1
4
]
T.
S
c
h
m
i
t
h
,
P
.
Th
e
j
l
l
,
F
.
V
e
j
e
n
,
a
n
d
B
.
C
h
r
i
st
i
a
n
se
n
,
“
R
e
g
i
o
n
a
l
v
a
r
i
a
t
i
o
n
o
f
c
l
i
m
a
t
o
l
o
g
i
c
a
l
c
l
o
u
d
b
u
r
s
t
f
r
e
q
u
e
n
c
y
e
st
i
ma
t
e
d
f
r
o
m
h
i
s
t
o
r
i
c
a
l
o
b
ser
v
a
t
i
o
n
s
o
f
d
a
i
l
y
p
r
e
c
i
p
i
t
a
t
i
o
n
s
u
ms,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
l
i
m
a
t
o
l
o
g
y
,
v
o
l
.
4
3
,
n
o
.
1
6
,
p
p
.
7
7
6
1
–
7
7
7
4
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
2
/
j
o
c
.
8
2
9
1
.
[
1
5
]
S
.
G
a
r
g
,
P
.
Je
n
a
,
U
.
D
e
v
i
,
a
n
d
S
.
A
z
a
d
,
“
P
e
r
f
o
r
ma
n
c
e
e
v
a
l
u
a
t
i
o
n
o
f
h
i
g
h
-
r
e
so
l
u
t
i
o
n
I
M
D
A
A
a
n
d
I
M
E
R
G
f
o
r
d
e
t
e
c
t
i
n
g
c
l
o
u
d
b
u
r
s
t
e
v
e
n
t
s
o
v
e
r
t
h
e
N
o
r
t
h
w
e
st
H
i
ma
l
a
y
a
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
l
i
m
a
t
o
l
o
g
y
,
v
o
l
.
4
3
,
n
o
.
8
,
p
p
.
3
7
3
0
–
3
7
4
8
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
2
/
j
o
c
.
8
0
5
5
.
[
1
6
]
V
.
P
.
S
a
t
i
,
“
C
l
o
u
d
b
u
r
s
t
-
t
r
i
g
g
e
r
e
d
n
a
t
u
r
a
l
h
a
z
a
r
d
s
i
n
U
t
t
a
r
a
k
h
a
n
d
H
i
ma
l
a
y
a
:
mec
h
a
n
i
sm
,
p
r
e
v
e
n
t
i
o
n
,
a
n
d
m
i
t
i
g
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
G
e
o
l
o
g
i
c
a
l
a
n
d
E
n
v
i
ro
n
m
e
n
t
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
2
,
n
o
.
1
,
p
p
.
4
5
–
4
8
,
2
0
1
8
.
[
1
7
]
D
.
K
a
r
u
n
a
n
i
d
y
,
P
.
S
.
R
a
k
s
h
i
t
h
,
G
.
S
i
r
e
e
sh
a
,
M
.
N
a
n
d
h
i
n
i
,
N
.
M
a
g
e
s
h
K
u
mar,
a
n
d
M
.
S
r
e
e
d
e
v
i
,
“
C
l
o
u
d
b
u
r
st
p
r
e
d
i
c
t
i
o
n
i
n
I
n
d
i
a
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
2
3
6
t
h
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
Re
c
e
n
t
T
r
e
n
d
s
i
n
A
d
v
a
n
c
e
C
o
m
p
u
t
i
n
g
,
I
C
RTAC
2
0
2
3
,
D
e
c
.
2
0
2
3
,
p
p
.
6
4
5
–
6
5
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
R
TA
C
5
9
2
7
7
.
2
0
2
3
.
1
0
4
8
0
7
5
4
.
[
1
8
]
S
.
S
a
h
a
a
n
d
B
.
B
e
r
a
,
“
R
a
i
n
f
a
l
l
t
h
r
e
s
h
o
l
d
f
o
r
p
r
e
d
i
c
t
i
o
n
o
f
sh
a
l
l
o
w
l
a
n
d
sl
i
d
e
s
i
n
t
h
e
G
a
r
h
w
a
l
H
i
m
a
l
a
y
a
,
I
n
d
i
a
,
”
G
e
o
sys
t
e
m
s
a
n
d
G
e
o
e
n
v
i
r
o
n
m
e
n
t
,
v
o
l
.
3
,
n
o
.
3
,
p
.
1
0
0
2
8
5
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
e
o
g
e
o
.
2
0
2
4
.
1
0
0
2
8
5
.
[
1
9
]
K
.
M
.
R
.
H
u
n
t
a
n
d
A
.
P
.
D
i
mr
i
,
“
S
y
n
o
p
t
i
c
-
sca
l
e
p
r
e
c
u
r
s
o
r
s
o
f
l
a
n
d
sl
i
d
e
s
i
n
t
h
e
w
e
s
t
e
r
n
H
i
ma
l
a
y
a
a
n
d
K
a
r
a
k
o
r
a
m,”
S
c
i
e
n
c
e
o
f
t
h
e
T
o
t
a
l
En
v
i
r
o
n
m
e
n
t
,
v
o
l
.
7
7
6
,
p
.
1
4
5
8
9
5
,
J
u
l
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
sc
i
t
o
t
e
n
v
.
2
0
2
1
.
1
4
5
8
9
5
.
[
2
0
]
G
.
S
i
n
g
h
a
n
d
A
.
P
a
n
d
e
y
,
“
F
l
a
sh
f
l
o
o
d
v
u
l
n
e
r
a
b
i
l
i
t
y
a
ssessm
e
n
t
a
n
d
z
o
n
a
t
i
o
n
t
h
r
o
u
g
h
a
n
i
n
t
e
g
r
a
t
e
d
a
p
p
r
o
a
c
h
i
n
t
h
e
U
p
p
e
r
G
a
n
g
a
B
a
si
n
o
f
t
h
e
N
o
r
t
h
w
e
st
H
i
ma
l
a
y
a
n
r
e
g
i
o
n
i
n
U
t
t
a
r
a
k
h
a
n
d
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
D
i
s
a
st
e
r
R
i
sk
Re
d
u
c
t
i
o
n
,
v
o
l
.
6
6
,
p
.
1
0
2
5
7
3
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
d
r
r
.
2
0
2
1
.
1
0
2
5
7
3
.
[
2
1
]
S
.
M
o
b
i
n
i
,
E.
N
i
l
ss
o
n
,
A
.
P
e
r
sso
n
,
P
.
B
e
c
k
e
r
,
a
n
d
R
.
La
r
ss
o
n
,
“
A
n
a
l
y
si
s
o
f
p
l
u
v
i
a
l
f
l
o
o
d
d
a
ma
g
e
c
o
s
t
s i
n
r
e
si
d
e
n
t
i
a
l
b
u
i
l
d
i
n
g
s
–
A
c
a
se
st
u
d
y
i
n
M
a
l
mö
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
D
i
sa
s
t
e
r
Ri
s
k
Re
d
u
c
t
i
o
n
,
v
o
l
.
6
2
,
p
.
1
0
2
4
0
7
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
d
r
r
.
2
0
2
1
.
1
0
2
4
0
7
.
[
2
2
]
P
.
V
i
j
a
y
k
u
mar
e
t
a
l
.
,
“
K
e
r
a
l
a
f
l
o
o
d
s
i
n
c
o
n
s
e
c
u
t
i
v
e
y
e
a
r
s
-
I
t
s
a
sso
c
i
a
t
i
o
n
w
i
t
h
m
e
s
o
sca
l
e
c
l
o
u
d
b
u
r
st
a
n
d
s
t
r
u
c
t
u
r
a
l
c
h
a
n
g
e
s
i
n
mo
n
so
o
n
c
l
o
u
d
s
o
v
e
r
t
h
e
w
e
s
t
c
o
a
s
t
o
f
I
n
d
i
a
,
”
We
a
t
h
e
r
a
n
d
C
l
i
m
a
t
e
Ex
t
remes
,
v
o
l
.
3
3
,
p
.
1
0
0
3
3
9
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
w
a
c
e
.
2
0
2
1
.
1
0
0
3
3
9
.
[
2
3
]
P
.
C
h
a
u
h
a
n
,
M
.
E.
A
k
i
n
e
r
,
R
.
S
h
a
w
,
a
n
d
K
.
S
a
i
n
,
“
F
o
r
e
c
a
st
f
u
t
u
r
e
d
i
sas
t
e
r
s
u
s
i
n
g
h
y
d
r
o
-
m
e
t
e
o
r
o
l
o
g
i
c
a
l
d
a
t
a
s
e
t
s
i
n
t
h
e
Y
a
m
u
n
a
r
i
v
e
r
b
a
s
i
n
,
W
e
s
t
e
r
n
H
i
m
a
l
a
y
a
:
u
si
n
g
mar
k
o
v
c
h
a
i
n
a
n
d
LST
M
a
p
p
r
o
a
c
h
e
s,”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
G
e
o
sci
e
n
c
e
s
,
v
o
l
.
5
,
p
.
1
0
0
0
6
9
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
i
i
g
.
2
0
2
4
.
1
0
0
0
6
9
.
[
2
4
]
D
.
K
n
ö
s
,
K
.
K
a
r
a
g
i
o
r
g
o
s,
J.
H
a
a
s,
B
.
B
l
u
me
n
t
h
a
l
,
L.
N
y
b
e
r
g
,
a
n
d
S
.
H
a
l
l
d
i
n
,
“
C
l
o
u
d
b
u
r
st
-
d
i
s
a
st
e
r
m
o
d
e
l
l
i
n
g
.
A
n
e
w
o
p
e
n
-
s
o
u
r
c
e
c
a
t
a
st
r
o
p
h
e
m
o
d
e
l
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
D
i
s
a
s
t
e
r
Ri
s
k
R
e
d
u
c
t
i
o
n
,
v
o
l
.
6
7
,
p
.
1
0
2
6
7
9
,
J
a
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
d
r
r
.
2
0
2
1
.
1
0
2
6
7
9
.
[
2
5
]
J.
L
e
e
,
D
.
P
e
r
e
r
a
,
T
.
G
l
i
c
k
m
a
n
,
a
n
d
L.
Ta
i
n
g
,
“
W
a
t
e
r
-
r
e
l
a
t
e
d
d
i
sas
t
e
r
s
a
n
d
t
h
e
i
r
h
e
a
l
t
h
i
m
p
a
c
t
s
:
a
g
l
o
b
a
l
r
e
v
i
e
w
,
”
Pro
g
res
s
i
n
D
i
sa
s
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
8
,
p
.
1
0
0
1
2
3
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
d
i
sas
.
2
0
2
0
.
1
0
0
1
2
3
.
[
2
6
]
A
.
M
.
H
i
n
g
mi
r
e
a
n
d
P
.
R
.
B
h
a
l
a
d
h
a
r
e
,
“
A
d
v
a
n
c
e
u
r
b
a
n
f
l
o
o
d
c
o
n
t
r
o
l
sy
s
t
e
m
u
s
i
n
g
f
u
z
z
y
l
o
g
i
c
a
n
d
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
(
I
o
T)
f
o
r
smar
t
c
i
t
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
n
Re
c
e
n
t
a
n
d
I
n
n
o
v
a
t
i
o
n
T
r
e
n
d
s
i
n
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
,
v
o
l
.
1
1
,
n
o
.
6
S
,
p
p
.
4
4
7
–
4
5
6
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
7
7
6
2
/
i
j
r
i
t
c
c
.
v
1
1
i
6
s
.
6
9
5
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
N
a
vig
a
tin
g
p
r
ed
ictive
la
n
d
s
ca
p
es o
f c
lo
u
d
b
u
r
s
t p
r
ed
ictio
n
a
p
p
r
o
a
ch
es:
in
s
ig
h
ts
…
(
A
n
il Hin
g
mir
e
)
1155
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Dr
.
Ani
l
M.
H
in
g
m
ire
is
c
u
rre
n
tl
y
wo
r
k
i
n
g
a
s,
As
sista
n
t
P
ro
fe
ss
o
r
in
th
e
Co
m
p
u
ter
En
g
in
e
e
rin
g
De
p
a
rt
m
e
n
t
a
t
Vid
y
a
v
a
rd
h
in
i
’
s
Co
l
l
e
g
e
o
f
E
n
g
in
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
,
a
ffil
iate
d
wit
h
M
u
m
b
a
i
Un
i
v
e
rsity
,
In
d
ia.
He
h
o
l
d
s
a
P
h
.
D.
in
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
fr
o
m
S
a
n
d
i
p
Un
iv
e
rs
it
y
,
Na
sh
i
k
,
a
n
d
h
a
s
2
3
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
His
re
se
a
rc
h
fo
c
u
se
s
o
n
a
rti
fici
a
l
in
telli
g
e
n
c
e
,
c
o
m
p
u
ter
se
c
u
rit
y
,
c
r
y
p
t
o
g
ra
p
h
y
,
a
n
d
th
e
in
tern
e
t
o
f
th
i
n
g
s
.
He
h
a
s
o
v
e
r
2
6
re
se
a
rc
h
p
a
p
e
rs
p
u
b
li
c
a
ti
o
n
s
in
n
a
ti
o
n
a
l,
in
ter
n
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
re
p
u
ted
jo
u
rn
a
ls.
He
a
lso
h
a
s
3
p
u
b
li
sh
e
d
I
n
d
ian
p
a
ten
t
a
n
d
1
c
o
p
y
r
ig
h
t
t
o
h
is
c
re
d
it
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
il
.
h
in
g
m
ire@v
c
e
t.
e
d
u
.
in
.
Dr
.
S
u
n
a
y
a
n
a
J
a
d
h
a
v
is
c
u
rre
n
tl
y
wo
r
k
i
n
g
a
s,
As
so
c
i
a
te
P
ro
fe
ss
o
r,
in
De
p
t.
o
f
EXTC
a
t
VCE
T,
M
u
m
b
a
i,
In
d
ia.
S
h
e
h
a
s
c
o
m
p
lete
d
h
e
r
Do
c
t
o
ra
l
d
e
g
re
e
in
El
e
c
tro
n
ics
E
n
g
g
.
fr
o
m
M
u
m
b
a
i,
In
d
ia.
S
h
e
h
a
s
o
v
e
r
2
2
y
e
a
rs
o
f
tea
c
h
i
n
g
a
n
d
re
se
a
rc
h
e
x
p
e
rien
c
e
.
S
h
e
is
a
C
h
a
irp
e
rso
n
a
n
d
M
e
m
b
e
r
o
f
s
y
ll
a
b
u
s
se
tt
i
n
g
c
o
m
m
it
tee
fo
r
v
a
ri
o
u
s
su
b
jec
ts
in
M
u
m
b
a
i
Un
i
v
e
rsity
fo
r
El
e
c
tro
n
ics
a
n
d
Tele
c
o
m
m
.
En
g
g
.
a
n
d
El
e
c
tro
n
ics
a
n
d
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
.
He
r
a
re
a
o
f
re
se
a
rc
h
in
c
lu
d
e
s
d
ig
it
a
l
c
o
m
m
u
n
ica
ti
o
n
,
Io
T,
VLS
I
a
n
d
wire
les
s
se
n
so
r
n
e
two
rk
.
S
h
e
h
a
s
o
v
e
r
2
0
p
u
b
li
c
a
ti
o
n
s
i
n
in
ter
n
a
ti
o
n
a
l,
n
a
ti
o
n
a
l
jo
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
S
h
e
a
lso
h
a
s
2
In
d
i
a
n
p
a
ten
ts
p
u
b
li
sh
e
d
to
h
e
r
c
re
d
i
t.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
su
n
a
y
a
n
a
.
jad
h
a
v
@v
c
e
t.
e
d
u
.
in
.
Dr
.
Meg
h
a
Tr
iv
e
d
i
is
wo
rk
in
g
a
s
a
n
As
so
c
iate
P
ro
fe
ss
o
r,
in
D
e
p
t.
o
f
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
a
t
VCET,
M
u
m
b
a
i,
I
n
d
ia.
S
h
e
h
a
s
c
o
m
p
lete
d
h
e
r
Do
c
t
o
ra
l
d
e
g
re
e
i
n
S
y
ste
m
s
a
n
d
Co
n
tr
o
l
En
g
in
e
e
ri
n
g
fro
m
IIT
B
o
m
b
a
y
,
In
d
ia.
S
h
e
h
a
s
o
v
e
r
2
2
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
He
r
a
re
a
o
f
re
se
a
r
c
h
in
c
lu
d
e
s
c
o
n
tro
l
sy
ste
m
s,
o
p
ti
m
iza
ti
o
n
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
h
a
s
o
v
e
r
1
5
p
u
b
li
c
a
ti
o
n
s
i
n
n
a
ti
o
n
a
l,
in
ter
n
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
jo
u
r
n
a
ls.
S
h
e
a
lso
h
a
s
1
p
u
b
li
sh
e
d
I
n
d
ia
n
p
a
ten
t
a
n
d
7
c
o
p
y
rig
h
ts
to
h
e
r
c
re
d
it
.
S
h
e
is
a
lso
a
m
e
m
b
e
r
o
f
IEE
E
a
n
d
IS
TE
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
e
g
h
a
.
tri
v
e
d
i@v
c
e
t.
e
d
u
.
i
n
.
K
a
r
a
n
S
a
n
k
h
e
is
c
u
rre
n
tl
y
p
u
rsu
in
g
th
e
Ba
c
h
e
l
o
r
o
f
C
o
m
p
u
ter
E
n
g
i
n
e
e
rin
g
d
e
g
re
e
a
t
Vi
d
y
a
v
a
rd
h
i
n
i
’
s
Co
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
,
Va
sa
i,
In
d
ia.
He
h
a
s
p
a
rti
c
ip
a
ted
in
a
n
d
w
o
n
v
a
ri
o
u
s
Ha
c
k
th
o
n
so
f
twa
re
d
e
v
e
lo
p
m
e
n
t
c
o
m
p
e
ti
ti
o
n
s.
He
is
Tec
h
En
th
u
sia
st,
a
n
d
h
is
a
re
a
o
f
in
tere
st
is
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
g
e
n
e
ra
ti
v
e
AI.
He
is
a
n
e
x
p
e
rti
se
in
b
u
i
ld
i
n
g
d
y
n
a
m
ic,
u
se
r
-
c
e
n
tri
c
a
p
p
li
c
a
ti
o
n
s
u
sin
g
m
o
d
e
rn
fra
m
e
wo
rk
s
a
n
d
tec
h
n
o
l
o
g
ies
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
a
ra
n
.
2
1
1
5
3
3
1
0
8
@v
c
e
t.
e
d
u
.
i
n
.
O
m
k
a
r
K
h
a
n
o
lk
a
r
is
c
u
rre
n
tl
y
p
u
rs
u
in
g
th
e
Ba
c
h
e
lo
r
o
f
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
d
e
g
re
e
a
t
Vi
d
y
a
v
a
rd
h
i
n
i
’
s
Co
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
,
Va
sa
i,
In
d
ia.
He
h
a
s
p
a
rti
c
ip
a
ted
in
a
n
d
wo
n
v
a
rio
u
s
Ha
c
k
th
o
n
so
ftwa
re
d
e
v
e
lo
p
m
e
n
t
c
o
m
p
e
ti
ti
o
n
s.
His
a
re
a
o
f
in
tere
st
is
c
y
b
e
r
se
c
u
r
i
ty
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
we
b
d
e
v
e
lo
p
m
e
n
t.
He
is
a
fo
u
n
d
e
r
m
e
m
b
e
r
o
f
WE
BX.VCET
c
lu
b
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
o
m
k
a
r.
2
1
1
3
1
3
1
0
5
@v
c
e
t.
e
d
u
.
i
n
.
Yuk
ta
P
a
til
is
c
u
rre
n
tl
y
p
u
rsu
in
g
t
h
e
Ba
c
h
e
lo
r
o
f
Co
m
p
u
ter
E
n
g
in
e
e
rin
g
d
e
g
re
e
a
t
Vid
y
a
v
a
rd
h
in
i
’
s
Co
ll
e
g
e
o
f
E
n
g
in
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
,
Va
sa
i,
In
d
ia.
He
r
a
re
a
o
f
in
tere
st
is
e
n
terp
rise
we
b
a
p
p
li
c
a
ti
o
n
d
e
v
e
l
o
p
m
e
n
t,
AI
-
p
o
we
re
d
so
lu
ti
o
n
s,
a
n
d
m
o
b
il
e
a
p
p
d
e
v
e
lo
p
m
e
n
t,
with
a
k
n
a
c
k
fo
r
d
e
li
v
e
ri
n
g
u
se
r
-
c
e
n
tri
c
a
n
d
e
fficie
n
t
so
lu
ti
o
n
s.
S
h
e
c
o
n
tri
b
u
tes
t
o
d
y
n
a
m
ic
p
ro
jec
t
s
li
k
e
re
a
l
-
ti
m
e
sto
c
k
p
re
d
ictio
n
c
h
a
tb
o
ts,
c
ro
ss
-
p
latf
o
rm
m
o
b
il
e
a
p
p
s,
a
n
d
AIML
-
b
a
se
d
p
re
d
icti
v
e
sy
ste
m
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
y
u
k
y
a
.
2
1
1
4
6
3
2
0
5
@
v
c
e
t.
e
d
u
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.