Co
m
pu
t
er
Science
a
nd
I
nfo
r
m
a
t
io
n T
ec
hn
o
lo
g
ies
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
,
p
p
.
3
9
4
~
4
0
3
I
SS
N:
2722
-
3
2
2
1
,
DOI
:
1
0
.
1
1
5
9
1
/csi
t
.
v7
i
3
.
p
3
9
4
-
4
0
3
394
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
p
r
ime.
co
m/in
d
ex
.
p
h
p
/csi
t
H
y
brid geo
sta
tis
ti
ca
l and ma
chine l
ea
rning
f
o
r go
ld g
ra
de
estima
tion
T
anyaradz
w
a
Mi
ri
a
m
M
t
et
w
a, M
onika
G
ond
o
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
m
a
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
S
c
h
o
o
l
o
f
I
n
f
o
r
ma
t
i
o
n
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
H
a
r
a
r
e
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
H
a
r
a
r
e
,
Zi
m
b
a
b
w
e
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
22
,
2
0
2
6
R
ev
is
ed
J
u
n
15
,
2
0
2
6
Acc
ep
ted
J
u
l
13
,
2
0
2
6
Th
e
e
v
a
lu
a
ti
o
n
o
f
o
re
g
ra
d
e
is
a
b
a
sic
p
a
rt
o
f
th
e
p
ro
c
e
ss
o
f
m
in
e
p
lan
n
in
g
,
p
ro
d
u
c
ti
o
n
sc
h
e
d
u
li
n
g
a
n
d
re
so
u
rc
e
e
v
a
lu
a
ti
o
n
.
Th
e
n
u
g
g
e
t
e
ffe
c
t
a
n
d
irreg
u
lar
m
i
n
e
ra
li
sa
ti
o
n
th
a
t
o
c
c
u
rs
in
so
m
e
g
re
e
n
st
o
n
e
b
e
lt
d
e
p
o
sits
o
n
t
h
e
Zi
m
b
a
b
we
a
n
Arc
h
e
a
n
c
a
u
se
s
p
ro
b
lem
s
in
e
stim
a
ti
n
g
a
c
c
u
ra
tely
.
Th
e
trad
it
io
n
a
l
g
e
o
sta
ti
stica
l
m
o
d
e
ls
li
k
e
Ord
i
n
a
ry
Krig
i
n
g
(OK
)
p
r
o
d
u
c
e
sm
o
o
th
e
d
e
stim
a
tes
wh
ich
h
a
v
e
sy
ste
m
a
ti
c
u
n
d
e
re
stim
a
ti
o
n
i
n
h
ig
h
-
g
ra
d
e
a
re
a
s
a
n
d
o
v
e
re
stim
a
ti
o
n
i
n
lo
w
-
g
ra
d
e
a
re
a
s,
th
u
s
a
ffe
c
ti
n
g
t
h
e
d
e
p
o
sit
se
lec
ti
v
it
y
.
In
a
d
d
it
i
o
n
,
m
a
c
h
in
e
lea
rn
in
g
(M
L)
tec
h
n
iq
u
e
s
c
a
n
c
a
p
tu
re
t
h
e
m
o
re
c
o
m
p
lex
n
o
n
li
n
e
a
r
g
ra
d
e
r
e
latio
n
sh
i
p
s,
b
u
t
t
h
e
y
a
re
u
n
a
b
le
to
m
o
d
e
l
sp
a
ti
a
l
c
o
n
ti
n
u
it
y
a
n
d
c
a
n
b
e
u
n
re
a
li
stic
in
p
re
d
icti
n
g
g
ra
d
e
s.
Th
e
h
y
b
rid
OK
-
G
r
a
d
ien
t
Bo
o
st
in
g
(G
B)
m
o
d
e
l
wa
s
d
e
sig
n
e
d
a
n
d
e
v
a
lu
a
ted
with
t
h
e
d
ril
l
-
h
o
le
d
a
ta
o
f
a
g
o
ld
m
i
n
e
in
Zi
m
b
a
b
we
.
Th
e
sp
a
ti
a
l
b
a
se
li
n
e
wa
s
p
ro
d
u
c
e
d
u
sin
g
OK
a
n
d
G
B
wa
s
train
e
d
t
o
c
o
rre
c
t
t
h
e
sy
ste
m
a
ti
c
re
sid
u
a
l
e
rro
rs.
Th
e
h
y
b
rid
m
o
d
e
l
wa
s
fo
u
n
d
to
h
a
v
e
t
h
e
m
a
x
imu
m
o
v
e
ra
ll
e
x
p
lan
a
to
r
y
p
o
we
r
(R²
=
0
.
8
7
9
5
),
c
o
m
p
e
ti
ti
v
e
p
re
d
ictio
n
a
c
c
u
ra
c
y
a
n
d
in
c
re
a
se
d
sp
a
ti
a
l
re
a
li
sm
.
A
sp
a
t
ial
p
re
d
ictio
n
m
a
p
a
n
d
e
x
trac
ti
o
n
p
rio
r
it
y
z
o
n
e
c
las
sifica
ti
o
n
wa
s c
re
a
ted
to
a
id
o
p
e
ra
ti
o
n
a
l
m
i
n
e
p
la
n
n
i
n
g
.
K
ey
w
o
r
d
s
:
Go
ld
m
in
in
g
Gr
ad
ien
t
B
o
o
s
tin
g
Hy
b
r
id
m
o
d
ellin
g
Or
d
in
ar
y
Kr
i
g
in
g
Or
e
g
r
ad
e
esti
m
atio
n
Sp
atial
p
r
ed
ictio
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
:
T
an
y
ar
ad
zwa
Mir
iam
Mte
twa
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
T
e
ch
n
o
lo
g
y
,
Sch
o
o
l o
f
I
n
f
o
r
m
ati
o
n
Scien
ce
an
d
T
ec
h
n
o
lo
g
y
Har
ar
e
I
n
s
titu
te
o
f
T
ec
h
n
o
l
o
g
y
Har
ar
e,
Z
im
b
ab
we
E
m
ail: m
tetwata
n
ia@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Go
ld
m
in
in
g
co
n
tin
u
es
to
p
lay
a
s
ig
n
if
ican
t
r
o
le
in
Z
im
b
a
b
we
’
s
ec
o
n
o
m
y
,
p
r
o
v
id
in
g
a
s
ig
n
if
ican
t
am
o
u
n
t
o
f
f
o
r
eig
n
cu
r
r
en
cy
a
n
d
jo
b
s
.
Min
in
g
is
also
a
p
r
i
o
r
ity
ec
o
n
o
m
ic
ac
tiv
ity
in
n
at
io
n
al
d
e
v
elo
p
m
e
n
t
p
lan
s
lik
e
Vis
io
n
2
0
3
0
an
d
Sm
ar
t
Z
im
b
ab
we
2
0
3
0
,
a
n
d
ac
cu
r
ate
esti
m
atio
n
o
f
th
e
m
in
er
al
r
eso
u
r
ce
s
is
im
p
o
r
tan
t
co
m
m
er
cially
an
d
s
tr
ateg
ically
[
1
]
,
[
2
]
.
E
s
tab
lis
h
in
g
o
r
e
g
r
ad
e
at
th
e
o
p
er
atio
n
a
l
lev
el
is
th
e
b
asis
f
o
r
f
ea
s
ib
ilit
y
s
tu
d
ies,
p
r
o
d
u
ct
io
n
tar
g
ets,
r
eser
v
e
d
ec
lar
atio
n
s
an
d
ex
tr
ac
tio
n
s
eq
u
en
ce
s
.
T
h
e
er
r
o
r
s
m
ad
e
at
th
is
p
o
in
t
ca
r
r
y
f
o
r
war
d
th
r
o
u
g
h
o
u
t
th
e
p
lan
n
i
n
g
p
r
o
ce
s
s
:
a
g
r
ad
e
o
v
er
esti
m
ate
will
o
v
er
esti
m
ate
r
ev
en
u
es
an
d
m
is
allo
ca
te
ca
p
ital,
a
n
d
a
g
r
ad
e
u
n
d
er
esti
m
ate
will
r
esu
lt
in
m
is
s
in
g
o
u
t
o
n
r
ec
o
v
er
y
o
p
p
o
r
tu
n
ities
an
d
u
n
d
er
p
r
o
d
u
ctio
n
[
3
]
.
E
s
tim
atin
g
g
o
ld
g
r
ad
es
in
Z
i
m
b
ab
wea
n
d
ep
o
s
its
r
em
ain
s
c
h
allen
g
in
g
.
Ma
n
y
d
ep
o
s
its
o
c
cu
r
with
in
Ar
ch
ea
n
g
r
ee
n
s
to
n
e
b
elts
,
wh
er
e
m
in
er
aliza
tio
n
is
s
tr
u
ctu
r
ally
co
n
tr
o
lled
b
y
s
h
ea
r
zo
n
es,
f
au
lt
s
y
s
tem
s
,
an
d
h
y
d
r
o
th
er
m
al
alter
atio
n
,
r
esu
ltin
g
in
s
p
atially
h
eter
o
g
en
eo
u
s
an
d
d
is
co
n
tin
u
o
u
s
g
r
ad
e
d
is
tr
ib
u
tio
n
s
[
4
]
,
[
5
]
.
Stro
n
g
n
u
g
g
et
ef
f
ec
ts
(
ab
r
u
p
t
ch
an
g
es
in
g
r
ad
e
v
al
u
e
o
v
er
s
h
o
r
t
d
is
tan
ce
s
)
o
cc
u
r
r
eg
u
la
r
ly
an
d
ar
e
h
ar
d
to
d
ef
in
e
f
r
o
m
a
lim
ited
n
u
m
b
er
o
f
d
r
ill
-
h
o
le
s
.
T
h
e
m
o
s
t
c
o
m
m
o
n
ly
u
s
ed
g
e
o
s
tatis
tical
est
i
m
atio
n
tech
n
i
q
u
e
in
m
in
in
g
is
Or
d
in
ar
y
Kr
ig
in
g
(
OK)
wh
ich
f
o
r
m
ally
co
n
s
id
er
s
th
e
s
p
atial
au
to
co
r
r
elatio
n
s
tr
u
ctu
r
e
in
th
e
d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Hyb
r
id
g
eo
s
ta
tis
tica
l a
n
d
ma
c
h
in
e
lea
r
n
in
g
f
o
r
g
o
ld
g
r
a
d
e
e
s
tima
tio
n
(
Ta
n
ya
r
a
d
z
w
a
Mir
ia
m
Mtetw
a
)
395
b
y
u
s
in
g
th
e
v
ar
i
o
g
r
am
an
d
y
ield
s
m
i
n
im
u
m
-
v
ar
ian
ce
lin
ea
r
u
n
b
iased
esti
m
ates
[
6
]
,
[
7
]
.
Ho
wev
e
r
,
its
well
-
k
n
o
wn
s
m
o
o
th
in
g
p
r
o
p
er
ty
ca
u
s
es
a
co
m
p
r
ess
io
n
o
f
th
e
g
r
ad
e
d
is
tr
ib
u
tio
n
o
f
h
ig
h
ly
v
ar
ia
b
le
d
ep
o
s
i
ts
,
with
a
m
o
v
em
e
n
t
o
f
h
ig
h
-
g
r
a
d
e
s
am
p
les
to
war
d
th
e
m
ea
n
an
d
an
in
cr
ea
s
e
o
f
lo
w
-
g
r
ad
e
r
eg
io
n
s
.
T
h
is
lead
s
to
an
in
co
r
r
ec
t selec
tiv
ity
o
f
th
e
d
ep
o
s
it [
3
]
,
[
8
]
.
R
ec
en
tly
,
m
in
er
al
r
eso
u
r
ce
e
s
tim
atio
n
with
th
e
h
elp
o
f
m
ac
h
in
e
lear
n
in
g
(
ML
)
tech
n
iq
u
es
h
as
attr
ac
ted
a
g
r
ea
t
a
m
o
u
n
t
o
f
in
t
er
est
b
ec
au
s
e
th
ey
ca
n
m
ap
co
m
p
lex
,
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
with
o
u
t
r
e
q
u
ir
in
g
p
r
io
r
u
s
er
-
d
ef
in
e
d
p
a
r
am
etr
ic
ass
u
m
p
tio
n
s
[
9
]
,
[
1
0
]
.
A
n
u
m
b
er
o
f
tech
n
i
q
u
es
s
u
ch
as
r
a
n
d
o
m
f
o
r
est,
s
u
p
p
o
r
t
v
ec
to
r
r
eg
r
ess
io
n
,
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
,
XGBo
o
s
t,
an
d
Gr
ad
ien
t
B
o
o
s
tin
g
(
GB
)
h
av
e
b
ee
n
u
s
ed
to
ad
d
r
ess
o
r
e
g
r
ad
e
esti
m
atio
n
.
Dee
p
lear
n
i
n
g
a
r
ch
itectu
r
es
an
d
f
e
d
er
ated
lea
r
n
in
g
tech
n
i
q
u
es
f
o
r
g
eo
s
cien
ce
ap
p
licatio
n
s
h
a
v
e
also
b
ee
n
in
v
esti
g
ated
r
ec
en
tly
[
1
1
]
.
GB
is
ch
o
s
en
h
er
e
b
ec
au
s
e
it
is
s
h
o
w
n
to
b
e
ef
f
ec
tiv
e
f
o
r
ta
b
u
lar
s
p
atial
r
eg
r
ess
io
n
in
ca
s
es
o
f
h
eter
o
g
en
eo
u
s
v
ar
i
an
ce
,
ca
n
b
e
in
ter
p
r
eted
u
s
in
g
th
e
im
p
o
r
tan
ce
o
f
f
ea
tu
r
es,
an
d
ca
n
b
e
im
p
lem
en
ted
in
s
tan
d
ar
d
m
in
e
in
f
o
r
m
ati
o
n
tech
n
o
lo
g
y
(
IT
)
en
v
ir
o
n
m
e
n
ts
[
1
0
]
,
[
1
2
]
.
ML
p
r
ed
ictio
n
s
o
f
ten
lack
s
p
atial
co
n
tin
u
ity
an
d
m
ay
n
o
t
f
u
lly
p
r
eser
v
e
g
e
o
lo
g
ical
r
ea
l
is
m
wh
en
m
ap
p
ed
.
T
o
ad
d
r
ess
th
ese
li
m
itatio
n
s
,
h
y
b
r
id
g
eo
s
tatis
tical
an
d
ML
a
p
p
r
o
ac
h
es
h
av
e
b
ee
n
d
ev
elo
p
e
d
b
y
co
m
b
in
in
g
th
e
s
tr
en
g
th
s
o
f
s
p
atial
in
ter
p
o
latio
n
an
d
ML
f
o
r
m
o
r
e
ac
c
u
r
ate
o
r
e
g
r
ad
e
est
im
atio
n
[
1
3
]
,
[
1
4
]
.
T
h
e
n
o
v
elty
o
f
th
is
s
tu
d
y
is
th
e
u
s
e
o
f
OK
an
d
GB
in
a
r
esi
d
u
al
-
lear
n
in
g
ap
p
r
o
ac
h
f
o
r
est
im
atin
g
g
o
l
d
g
r
ad
e
in
s
tr
u
ctu
r
ally
co
m
p
lex
g
r
e
e
n
s
to
n
e
b
elt
d
ep
o
s
its
in
Z
im
b
ab
we.
T
h
e
f
r
a
m
ewo
r
k
p
r
o
p
o
s
ed
in
th
is
p
ap
er
i
s
d
esig
n
ed
t
o
lev
e
r
ag
e
th
e
a
d
v
an
tag
es
o
f
g
e
o
s
tatis
tics
an
d
th
e
ML
ap
p
r
o
ac
h
in
a
way
t
h
at
tr
an
s
ce
n
d
s
th
e
s
m
o
o
th
in
g
ef
f
ec
t
o
f
th
e
g
e
o
s
tatis
tics
an
d
th
e
lack
o
f
s
p
atia
l
co
n
tin
u
ity
f
o
u
n
d
in
s
tan
d
-
al
o
n
e
ML
m
eth
o
d
s
,
wh
ils
t
m
ain
tain
in
g
g
eo
lo
g
ical
r
ea
lis
m
an
d
en
h
a
n
ci
n
g
p
r
e
d
ictiv
e
p
er
f
o
r
m
an
ce
.
T
h
e
d
ev
el
o
p
ed
h
y
b
r
id
m
o
d
el
is
u
s
ef
u
l f
o
r
m
in
e
p
la
n
n
in
g
an
d
r
eso
u
r
ce
ev
alu
atio
n
as a
d
ec
is
io
n
s
u
p
p
o
r
t to
o
l.
T
h
is
p
ap
er
f
o
llo
ws
s
u
ch
an
a
p
p
r
o
ac
h
with
OK
c
o
m
b
in
e
d
with
GB
an
d
co
m
p
ar
es
it
wit
h
th
e
s
tan
d
-
alo
n
e
ap
p
r
o
ac
h
es
th
at
ar
e
a
p
p
l
ied
u
s
in
g
t
h
e
d
r
ill
-
h
o
le
d
ata
o
f
a
g
o
ld
d
ep
o
s
it
f
r
o
m
Z
im
b
ab
w
e.
On
a
wid
er
I
C
T
co
n
tex
t,
th
is
f
r
am
ewo
r
k
alig
n
s
with
th
e
cu
r
r
en
t
tr
en
d
s
in
th
e
p
ar
ad
ig
m
s
o
f
cl
o
u
d
-
b
ased
g
eo
lo
g
ical
m
o
d
ellin
g
an
d
d
ig
ital
m
in
e
s
y
s
tem
s
.
T
h
e
r
est
o
f
th
e
p
ap
er
is
o
r
g
an
ized
as:
in
s
ec
tio
n
2
,
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
f
r
am
ewo
r
k
is
d
escr
ib
ed
,
in
s
ec
tio
n
3
th
e
m
eth
o
d
is
p
r
esen
ted
,
an
d
in
s
e
ctio
n
4
th
e
r
esu
lts
ar
e
r
ep
o
r
ted
an
d
d
is
cu
s
s
ed
,
an
d
in
s
ec
tio
n
5
th
e
p
ap
er
is
co
n
clu
d
ed
.
2.
T
H
E
P
RO
P
O
SE
D
H
YB
R
I
D
M
O
DE
L
L
I
NG
F
RAM
E
WO
RK
A
h
y
b
r
i
d
m
o
d
ellin
g
f
r
a
m
ewo
r
k
was
d
esig
n
ed
to
im
p
r
o
v
e
g
o
ld
o
r
e
g
r
a
d
e
esti
m
atio
n
in
a
s
t
r
u
ctu
r
ally
co
m
p
lex
g
o
ld
d
e
p
o
s
it
in
Z
i
m
b
ab
we
wh
er
e
t
h
er
e
is
a
h
ig
h
n
u
g
g
et
ef
f
ec
t
a
n
d
ir
r
eg
u
lar
m
in
er
aliza
tio
n
.
T
h
e
f
r
am
ewo
r
k
is
a
m
ix
tu
r
e
o
f
OK
a
n
d
GB
,
wh
er
e
g
eo
s
tatis
tical
s
p
atial
m
o
d
ellin
g
i
s
b
len
d
ed
with
ML
r
esid
u
al
co
r
r
ec
tio
n
.
T
h
e
f
ir
s
t
m
o
d
el
u
s
ed
was
v
ar
io
g
r
a
m
-
b
ased
in
ter
p
o
latio
n
wh
ich
p
r
o
d
u
ce
d
s
p
atial
co
n
tin
u
ity
o
f
g
o
ld
g
r
ad
e
d
is
tr
ib
u
tio
n
.
T
h
e
b
aselin
e
s
p
atial
p
r
ed
ictio
n
s
u
r
f
ac
e
was
th
en
g
en
er
ated
u
s
in
g
OK
.
Un
iv
er
s
al
Kr
ig
in
g
is
r
ec
o
m
m
en
d
e
d
o
v
er
OK
wh
e
n
th
er
e
i
s
n
o
ad
eq
u
ate
s
tatio
n
ar
y
m
e
an
ass
u
m
p
tio
n
f
o
r
d
ep
o
s
its
,
b
ec
au
s
e
it
tr
ies
to
f
it
th
e
d
r
if
t
c
o
m
p
o
n
en
t
to
f
ew
d
ata
p
o
in
ts
,
wh
ich
is
a
r
is
k
o
f
o
v
er
-
f
itti
n
g
th
e
d
ata
[
1
5
]
.
T
h
e
d
if
f
er
en
ce
b
etwe
en
th
e
Kr
ig
in
g
-
p
r
ed
icted
g
o
ld
g
r
ad
e
an
d
th
e
r
ea
l
g
o
ld
g
r
ad
e
(
r
esid
u
als)
wer
e
ca
lcu
lated
,
s
p
atial
co
o
r
d
in
ates
n
o
r
m
alize
d
an
d
th
e
n
o
r
m
aliz
ed
s
p
atial
co
o
r
d
in
ates
an
d
th
e
Kr
ig
in
g
r
esid
u
als
wer
e
u
s
ed
as
p
r
ed
icto
r
an
d
t
ar
g
et
v
alu
es,
r
esp
ec
tiv
ely
,
f
o
r
tr
ain
in
g
th
e
GB
.
T
h
e
f
in
al
h
y
b
r
id
p
r
ed
ictio
n
in
teg
r
ates
OK
p
r
ed
ictio
n
s
with
th
e
GB
r
esid
u
al
co
r
r
ec
tio
n
s
to
p
r
o
v
id
e
s
p
atial
co
n
tin
u
ity
,
a
b
etter
r
ep
r
esen
tatio
n
o
f
lo
ca
l
g
r
a
d
e
v
ar
iatio
n
,
an
d
r
e
d
u
ce
b
ias
in
th
e
h
ig
h
-
g
r
ad
e
zo
n
es.
T
h
e
w
o
r
k
f
lo
w
o
f
th
e
GB
r
esid
u
al
lear
n
in
g
p
r
o
c
ess
is
p
r
esen
ted
in
Fig
u
r
e
1
,
a
n
d
th
e
o
v
er
all
h
y
b
r
i
d
m
o
d
ellin
g
p
r
o
ce
s
s
is
p
r
esen
ted
in
Fig
u
r
e
2
.
Fig
u
r
e
1
.
W
o
r
k
f
lo
w
o
f
GB
r
esid
u
al
lear
n
in
g
p
r
o
ce
s
s
Fig
u
r
e
2
.
C
o
m
p
lete
h
y
b
r
id
m
o
d
ellin
g
f
r
am
ew
o
r
k
I
np
ut
D
a
ta
C
o
o
r
d
i
n
a
t
e
s
a
n
d
AU
D
a
ta
Pr
e
p
r
o
c
e
s
s
i
n
g
C
l
e
a
ni
ng
& S
c
a
l
i
ng
T
r
a
i
n
-
T
e
st
S
pl
i
t
T
r
a
i
ni
ng
& T
e
st
i
ng
Gr
a
di
e
nt
B
o
o
s
t
i
n
g
M
o
de
l
T
r
a
i
ni
ng
Pr
e
di
c
ti
o
n
Gol
d
Gr
a
de
R
e
si
du
a
l
s
M
o
de
l
E
v
a
l
ua
ti
o
n
R
M
S
E
,
R
²
O
ut
pu
t
H
y
b
r
i
d
Mo
d
e
l
R
e
su
l
ts
G
E
O
L
O
G
I
C
A
L
D
A
T
A
D
A
T
A
P
R
E
P
R
O
C
E
S
S
I
NG
O
R
D
I
NA
R
Y
K
R
I
G
I
NG
R
E
S
I
D
U
A
L
C
A
L
C
U
L
A
T
I
O
N
G
R
A
D
I
E
NT
BO
O
S
T
I
NG
H
YBR
I
D
I
NT
E
G
R
A
T
I
O
N
G
R
A
D
E
P
R
E
D
I
C
T
I
O
N
M
A
P
S
E
X
T
R
A
C
T
I
O
N
P
R
I
O
R
I
T
Y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
:
3
9
4
-
403
396
3.
M
E
T
H
O
D
3
.
1
.
Study
a
re
a
Geo
lo
g
ical
in
f
o
r
m
atio
n
f
r
o
m
a
g
o
ld
m
in
e
in
th
e
Ar
ch
ea
n
g
r
ee
n
s
to
n
e
b
elt
o
f
Z
im
b
ab
we
was
u
s
ed
.
Go
ld
m
in
e
r
aliza
tio
n
in
th
e
Ar
ch
ea
n
g
r
ee
n
s
to
n
e
b
elts
is
s
tr
u
ctu
r
ally
co
n
tr
o
lled
b
y
s
h
ea
r
zo
n
es
an
d
f
a
u
lt
s
y
s
tem
s
th
at
ac
ted
as
p
ath
w
ay
s
f
o
r
h
y
d
r
o
th
er
m
al
f
lu
id
s
d
u
r
in
g
o
r
o
g
en
ic
ev
en
ts
[
4
]
,
[
5
]
.
Or
e
s
h
o
o
ts
ar
e
s
tr
u
ctu
r
ally
co
n
tr
o
lled
;
g
r
ad
e
d
is
tr
ib
u
tio
n
s
with
in
th
e
m
in
er
alize
d
en
v
elo
p
e
ar
e
ir
r
e
g
u
lar
;
as
well
a
s
th
er
e
i
s
a
s
ig
n
if
ican
t
n
u
g
g
et
e
f
f
ec
t
in
th
e
v
ar
io
g
r
am
,
wh
ich
is
a
s
h
o
r
t
-
r
an
g
e
g
r
ad
e
v
ar
ia
b
ilit
y
less
th
an
th
e
d
r
ill
-
h
o
le
s
p
ac
in
g
.
3
.
2
.
Da
t
a
s
et
des
cr
ipti
on
T
h
e
m
o
d
ellin
g
d
ataset
co
m
p
r
is
es
th
r
ee
d
ata
co
m
p
o
n
en
ts
r
elatin
g
to
d
r
ill
-
h
o
le;
co
llar
,
a
s
s
ay
,
an
d
s
u
r
v
ey
d
ata.
T
h
e
co
llar
d
ataset
co
n
tain
ed
th
r
ee
-
d
im
e
n
s
io
n
al
co
o
r
d
in
ates
f
o
r
th
e
en
tr
y
p
o
in
t
(
XC
OL
L
AR
,
YC
OL
L
A
R
,
an
d
Z
C
OL
L
AR
)
.
T
h
e
ass
ay
r
esu
lts
in
clu
d
ed
g
o
ld
g
r
ad
e
v
alu
es
(
AU
g
/t)
f
r
o
m
co
r
e
s
am
p
les
with
r
eg
u
lar
in
ter
v
als.
B
ea
r
in
g
an
d
d
ip
d
ata
f
r
o
m
th
e
s
u
r
v
ey
y
ield
ed
3
D
tr
ac
es
o
f
ea
ch
o
f
th
e
d
r
ill
-
h
o
les.
A
u
n
iq
u
e
d
r
ill
-
h
o
le
id
e
n
tifie
r
(
B
HI
D)
was
u
s
ed
to
tie
all
th
e
d
atasets
to
g
eth
er
.
T
h
e
d
ataset
co
m
p
r
is
es
o
f
th
e
f
o
llo
win
g
co
m
p
o
n
en
ts
,
as su
m
m
ar
ized
in
T
a
b
le
1
.
T
ab
le
1
.
Su
m
m
a
r
y
o
f
th
e
c
o
m
p
o
n
en
ts
o
f
th
e
g
e
o
lo
g
ical
d
ata
s
et
D
a
t
a
s
e
t
D
e
scri
p
t
i
o
n
C
o
l
l
a
r
D
r
i
l
l
-
h
o
l
e
e
n
t
r
y
p
o
i
n
t
c
o
o
r
d
i
n
a
t
e
s (X
C
O
LLA
R
,
Y
C
O
L
LA
R
,
a
n
d
Z
C
O
LL
A
R
)
o
f
t
h
e
c
o
l
l
a
r
.
A
ssay
A
t
r
e
g
u
l
a
r
i
n
t
e
r
v
a
l
s,
a
ssa
y
g
o
l
d
g
r
a
d
e
v
a
l
u
e
s (A
U
,
g
/
t
)
o
f
c
o
r
e
s
a
m
p
l
e
s.
S
u
r
v
e
y
D
r
i
l
l
-
h
o
l
e
b
e
a
r
i
n
g
a
n
d
d
i
p
t
o
p
r
o
v
i
d
e
3
D
t
r
a
j
e
c
t
o
r
y
r
e
c
o
n
st
r
u
c
t
i
o
n
3
.
3
.
Da
t
a
pre
-
pro
ce
s
s
ing
T
h
e
m
is
s
in
g
v
alu
es,
c
o
o
r
d
in
at
e
in
co
n
s
is
ten
cies,
an
d
e
x
tr
em
e
o
u
tlier
g
r
ad
e
v
alu
es
wer
e
d
e
alt
with
in
p
r
e
-
p
r
o
ce
s
s
in
g
.
T
h
e
d
is
tr
ib
u
tio
n
s
o
f
g
o
ld
g
r
a
d
e
ar
e
u
s
u
ally
s
k
ewe
d
to
war
d
th
e
h
ig
h
en
d
an
d
th
e
h
ig
h
es
t
v
alu
es
ar
e
g
eo
lo
g
ically
r
ea
l
b
u
t
s
m
all
an
d
s
o
o
u
tly
in
g
f
r
o
m
a
s
tatis
tical
p
o
in
t
o
f
v
iew.
T
h
e
o
v
e
r
all
g
r
a
d
e
d
is
tr
ib
u
tio
n
ch
ar
ac
ter
is
tics
wer
e
m
ain
tain
ed
,
a
n
d
o
u
tlier
clip
p
in
g
to
t
h
e
1
s
t
-
9
9
t
h
p
er
ce
n
tile
r
an
g
e
h
as
b
ee
n
p
er
f
o
r
m
ed
,
th
e
r
eb
y
elim
in
atin
g
th
e
ef
f
ec
t
o
f
ex
tr
em
e
v
alu
es.
I
t
is
r
ec
o
g
n
ized
th
at
th
e
r
e
is
s
o
m
e
b
ias
as
v
alu
es
b
elo
w
th
e
m
ax
im
u
m
ar
e
n
o
t
r
ec
o
r
d
ed
an
d
alter
n
ativ
e
r
o
b
u
s
t
p
r
e
-
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
s
h
o
u
ld
b
e
in
v
esti
g
ate
d
in
th
e
f
u
tu
r
e
.
T
h
e
g
o
ld
g
r
ad
e
d
is
tr
ib
u
tio
n
is
p
lo
tted
in
a
h
is
to
g
r
am
a
n
d
b
o
x
p
lo
t
in
Fig
u
r
e
3
.
T
h
e
s
p
atial
co
o
r
d
in
ates w
er
e
s
ca
led
b
y
St
an
d
ar
d
Scaler
p
r
io
r
t
o
m
o
d
ellin
g
.
Fig
u
r
e
3
.
Dis
tr
ib
u
tio
n
o
f
g
o
ld
g
r
ad
e
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Hyb
r
id
g
eo
s
ta
tis
tica
l a
n
d
ma
c
h
in
e
lea
r
n
in
g
f
o
r
g
o
ld
g
r
a
d
e
e
s
tima
tio
n
(
Ta
n
ya
r
a
d
z
w
a
Mir
ia
m
Mtetw
a
)
397
3
.
4
.
G
eo
s
t
a
t
is
t
ica
l
m
o
dellin
g
T
h
e
s
p
at
ial
b
asel
i
n
e
o
f
t
h
e
h
y
b
r
i
d
f
r
am
ew
o
r
k
u
s
ed
was
OK
.
T
o
u
n
d
e
r
s
t
an
d
th
e
s
p
a
tial
a
u
t
o
-
co
r
r
el
ati
o
n
s
tr
u
ct
u
r
e
o
f
th
e
g
o
l
d
g
r
ad
e
f
ie
ld
,
an
e
x
p
e
r
i
m
e
n
t
al
v
a
r
i
o
g
r
am
was
c
alc
u
l
ate
d
u
s
i
n
g
t
h
e
d
r
il
l
-
h
o
l
e
d
at
a.
T
h
e
p
a
r
a
m
e
te
r
s
o
f
n
u
g
g
et
,
s
i
l
l
a
n
d
r
a
n
g
e
w
er
e
d
e
te
r
m
i
n
ed
th
r
o
u
g
h
t
h
e
le
ast
-
s
q
u
ar
es
f
itt
i
n
g
o
f
a
t
h
eo
r
e
tic
al
m
o
d
el
t
o
t
h
e
e
x
p
er
im
en
tal
v
a
r
i
o
g
r
am
[
6
]
,
[
8
]
.
T
h
e
v
a
r
i
o
g
r
a
m
s
h
o
we
d
a
l
ar
g
e
n
u
g
g
e
t
e
f
f
e
ct
t
y
p
i
ca
l
o
f
s
h
o
r
t
-
r
a
n
g
e
g
r
ad
e
v
ar
iat
io
n
f
o
u
n
d
i
n
s
t
r
u
ct
u
r
all
y
f
o
r
m
e
d
g
o
l
d
d
e
p
o
s
its
i
n
Z
im
b
a
b
w
e.
T
h
e
f
i
tte
d
v
ar
i
o
g
r
a
m
m
o
d
el
is
s
h
o
wn
i
n
Fi
g
u
r
e
4
.
F
o
r
t
h
is
p
ar
t
ic
u
la
r
d
a
tas
et
,
t
h
e
s
ta
n
d
a
r
d
v
a
r
i
o
g
r
am
-
b
as
ed
Kr
ig
in
g
was
ad
e
q
u
ate
a
n
d
a
ls
o
m
a
n
a
g
e
a
b
le
d
u
e
t
o
a
d
v
a
n
c
es
i
n
t
h
e
K
r
i
g
i
n
g
m
e
th
o
d
o
l
o
g
y
o
f
r
ec
e
n
t
y
ea
r
s
s
u
c
h
as
T
h
e
ta
-
r
eg
u
l
ar
ize
d
K
r
i
g
i
n
g
[
1
6
]
a
n
d
R
at
io
n
al
Kr
ig
in
g
[
1
7
]
w
h
ic
h
a
r
e
m
o
r
e
u
s
e
f
u
l i
n
t
h
e
c
ase
o
f
ill
-
c
o
n
d
iti
o
n
e
d
c
o
v
a
r
ia
n
ce
m
a
tr
ices
.
Fig
u
r
e
4
.
E
x
p
er
im
e
n
tal
an
d
f
itted
v
ar
io
g
r
am
m
o
d
el
3
.
5
.
M
a
chine
lea
rning
m
o
de
llin
g
GB
was c
h
o
s
en
b
ec
au
s
e
it h
as
p
r
o
v
e
d
to
b
e
s
u
cc
ess
f
u
l o
n
tab
u
lar
r
eg
r
ess
io
n
task
s
wh
er
e
th
e
v
ar
ian
c
e
is
n
o
t
h
o
m
o
g
en
eo
u
s
[
12
]
.
I
t
f
i
ts
a
s
u
m
o
f
s
h
allo
w
r
e
g
r
ess
io
n
tr
ee
s
,
o
n
e
f
o
r
th
e
n
e
g
ativ
e
g
r
ad
ien
t
o
f
th
e
lo
s
s
f
u
n
ctio
n
at
a
tim
e,
to
g
r
ad
u
all
y
d
ec
r
ea
s
e
p
r
ed
ictio
n
e
r
r
o
r
s
.
T
h
e
in
p
u
t
was
n
o
r
m
alize
d
s
p
a
tial
co
o
r
d
in
ates
an
d
th
e
o
u
tp
u
t
wer
e
th
e
r
esid
u
als
o
f
th
e
Kr
ig
in
g
.
T
h
e
tr
ain
in
g
an
d
test
s
et
s
h
av
e
b
ee
n
s
p
li
t
in
a
m
an
n
er
th
at
en
s
u
r
es
th
e
f
u
ll
r
an
g
e
o
f
r
esid
u
al
m
ag
n
itu
d
e
is
co
v
er
ed
.
T
h
e
m
o
d
el
r
esu
lts
wer
e
a
s
s
es
s
ed
b
ased
o
n
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
an
d
c
o
ef
f
icien
t o
f
d
eter
m
in
atio
n
(
R
²)
.
3
.
6
.
G
eo
g
r
a
ph
ic
info
rm
a
t
io
n sy
s
t
em
(
G
I
S
)
-
ba
s
ed
s
pa
t
ia
l v
is
ua
liza
t
io
n
Mo
d
el
o
u
tp
u
ts
f
r
o
m
b
o
th
m
o
d
els we
r
e
g
r
id
d
ed
an
d
tr
an
s
f
o
r
m
ed
to
co
n
tin
u
o
u
s
s
p
atial
lay
er
s
to
cr
ea
te
is
o
lin
e
m
ap
s
o
f
g
r
ad
e
d
is
tr
ib
u
tio
n
s
.
Pre
d
icted
g
r
a
d
es
wer
e
allo
ca
ted
to
th
r
ee
ca
teg
o
r
ies
to
d
ef
in
e
th
e
ex
tr
ac
tio
n
p
r
io
r
ity
a
r
ea
s
-
h
ig
h
-
g
r
ad
e
o
r
e
s
h
o
o
t
(
Prio
r
ity
1
)
;
m
in
e
r
alize
d
en
v
elo
p
e
(
Prio
r
ity
2
)
;
an
d
s
u
b
-
ec
o
n
o
m
ic
waste
(
Prio
r
ity
3
)
.
T
h
e
s
p
atial
d
is
tr
ib
u
tio
n
o
f
p
r
e
d
icted
g
o
ld
g
r
ad
es
an
d
ex
tr
ac
tio
n
p
r
io
r
it
y
zo
n
es a
r
e
s
h
o
wn
i
n
Fig
u
r
es 5
an
d
6
.
Fig
u
r
e
5
.
Sp
atial
d
is
tr
ib
u
tio
n
m
ap
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
:
3
9
4
-
403
398
Fig
u
r
e
6
.
E
x
tr
ac
tio
n
p
r
io
r
ity
z
o
n
es
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
4
.
1
.
K
rig
ing
re
s
ult
s
T
h
e
OK
g
a
v
e
a
s
p
a
tia
ll
y
c
o
h
e
r
e
n
t
g
r
a
d
e
p
r
ed
ict
io
n
s
u
r
f
a
ce
t
h
at
m
a
tc
h
e
d
t
h
e
v
a
r
i
o
g
r
am
s
t
r
u
ct
u
r
e
t
h
at
was
f
i
tte
d
.
S
m
o
o
t
h
i
n
g
,
as
e
x
p
ec
t
ed
f
o
r
a
n
u
g
g
e
t
-
d
o
m
i
n
at
ed
d
e
p
o
s
it
,
was
s
e
e
n
in
t
h
e
p
r
e
d
i
cti
o
n
s
w
h
i
c
h
we
r
e
f
la
tte
n
e
d
t
o
w
ar
d
s
t
h
e
l
o
c
al
m
e
an
wi
th
h
i
g
h
-
g
r
a
d
e
i
n
t
er
s
ec
t
io
n
s
in
t
h
e
m
ai
n
o
r
e
s
h
o
o
t
b
ei
n
g
u
n
d
e
r
-
g
r
ad
ed
,
a
n
d
wid
er
p
o
r
t
io
n
s
o
f
s
u
b
-
e
co
n
o
m
i
c
m
at
er
ial
b
ei
n
g
o
v
e
r
-
g
r
a
d
ed
.
T
h
is
s
m
o
o
t
h
i
n
g
d
i
r
ec
tl
y
i
m
p
ac
ts
o
n
t
h
e
s
el
ec
ti
v
it
y
o
f
d
e
p
o
s
its
an
d
r
esu
lts
i
n
u
n
d
e
r
est
im
ati
o
n
o
f
t
h
e
m
i
ll f
e
ed
g
r
ad
e
a
n
d
p
r
o
d
u
c
ti
o
n
s
h
o
r
t
f
al
l [
3
]
.
T
h
e
r
esu
lts
o
f
t
h
e
p
e
r
f
o
r
m
a
n
c
e
m
e
asu
r
es
a
r
e
s
u
m
m
a
r
iz
e
d
i
n
T
ab
le
2
.
T
h
e
s
p
at
ia
l
d
is
t
r
i
b
u
ti
o
n
m
a
p
is
s
h
o
w
n
in
Fig
u
r
e
7
.
T
ab
le
2
.
OK
p
er
f
o
r
m
an
ce
m
et
r
ics
M
o
d
e
l
R
M
S
E
R²
OK
0
.
3
6
4
5
0
.
5
2
4
8
Fig
u
r
e
7
.
OK
s
p
atial
d
is
tr
ib
u
ti
o
n
m
ap
4
.
2
.
M
a
chine
lea
rning
re
s
ult
s
T
h
e
s
tan
d
alo
n
e
GB
m
o
d
el
o
u
t
p
er
f
o
r
m
ed
OK
o
n
th
e
h
eld
-
o
u
t
test
s
et
,
as
s
h
o
wn
in
T
ab
le
3
.
Fig
u
r
e
8
co
m
p
ar
es
ac
tu
al
an
d
p
r
e
d
icted
g
r
a
d
e
f
o
r
t
h
e
m
o
d
el
an
d
ill
u
s
tr
ates
th
at
th
e
m
o
d
el
ca
p
t
u
r
es
th
e
g
r
a
d
e
tr
en
d
s
an
d
is
ab
le
to
b
etter
r
ec
o
v
er
th
e
h
ig
h
-
g
r
ad
e
zo
n
es
th
at
ar
e
u
n
d
er
p
r
ed
icted
b
y
Kr
ig
in
g
.
T
h
e
m
o
s
t
im
p
o
r
tan
t
v
ar
iab
les
f
o
r
s
p
atial
co
o
r
d
in
at
e
v
ar
iab
les
(
x
an
d
y
)
b
y
im
p
o
r
tan
ce
an
aly
s
is
wer
e
f
o
u
n
d
to
b
e
th
e
h
ig
h
est
an
d
ar
e
ex
p
ec
ted
to
b
e
im
p
o
r
tan
t
f
o
r
th
e
g
r
ad
e
v
ar
iatio
n
in
a
s
tr
u
ctu
r
ally
c
o
n
tr
o
lled
m
in
e
r
aliza
tio
n
tr
en
d
in
Fig
u
r
e
9
.
Fo
r
GB
,
ev
en
th
o
u
g
h
th
e
p
r
ed
ictio
n
s
wer
e
m
o
r
e
ac
cu
r
ate,
th
ey
s
h
o
wed
s
p
at
ial
in
co
h
er
en
ce
wh
en
p
lo
tted
as
a
m
ap
,
with
n
o
v
ar
io
g
r
am
-
b
ased
co
n
tin
u
ity
co
n
s
tr
ain
ts
.
I
n
en
s
em
b
le
m
eth
o
d
s
,
GB
,
XG
B
o
o
s
t
,
an
d
r
an
d
o
m
f
o
r
est
m
o
d
els
h
av
e
b
ee
n
f
o
u
n
d
to
p
e
r
f
o
r
m
in
a
co
m
p
ar
ab
le
f
ash
io
n
in
tab
u
la
r
s
p
atial
r
eg
r
ess
io
n
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Hyb
r
id
g
eo
s
ta
tis
tica
l a
n
d
ma
c
h
in
e
lea
r
n
in
g
f
o
r
g
o
ld
g
r
a
d
e
e
s
tima
tio
n
(
Ta
n
ya
r
a
d
z
w
a
Mir
ia
m
Mtetw
a
)
399
p
r
o
b
lem
s
,
with
GB
b
ei
n
g
th
e
m
o
s
t
s
u
itab
le
am
o
n
g
th
e
t
h
r
e
e
in
ter
m
s
o
f
ac
cu
r
ac
y
as
wel
l
as
in
ter
p
r
etab
ilit
y
wh
en
ap
p
lied
to
h
eter
o
g
en
e
o
u
s
g
r
ad
e
d
atasets
[
1
8
]
.
T
ab
le
3
.
GB
p
er
f
o
r
m
an
ce
m
et
r
ics
M
o
d
e
l
R
M
S
E
R²
GB
0
.
1
6
4
2
0
.
7
5
4
5
Fig
u
r
e
8
.
Actu
al
v
s
.
p
r
ed
icted
g
o
ld
g
r
ad
es
Fig
u
r
e
9
.
Featu
r
e
im
p
o
r
ta
n
ce
p
lo
t
4
.
3
.
H
y
brid
m
o
del r
esu
lt
s
T
h
e
h
y
b
r
id
m
o
d
el
ac
h
iev
ed
th
e
h
ig
h
est
ex
p
lan
ato
r
y
p
o
wer
(
R
²=
0
.
8
7
9
5
)
am
o
n
g
th
e
ev
alu
ated
m
o
d
els,
in
d
icatin
g
im
p
r
o
v
e
d
p
r
ed
ictio
n
p
er
f
o
r
m
a
n
ce
co
m
p
ar
ed
to
th
e
s
tan
d
alo
n
e
ap
p
r
o
a
ch
es
,
as
s
h
o
wn
in
T
ab
le
4
.
T
h
e
ac
tu
al
v
s
.
p
r
ed
ic
ted
s
ca
tter
p
lo
t
in
Fig
u
r
e
1
0
was
m
o
r
e
tig
h
tly
clu
s
ter
ed
ar
o
u
n
d
th
e
1
:1
lin
e
th
an
eith
er
s
tan
d
alo
n
e
m
o
d
el,
in
d
ic
atin
g
r
ed
u
ce
d
s
y
s
tem
atic
b
ias
an
d
lo
wer
r
an
d
o
m
er
r
o
r
.
Hig
h
-
g
r
ad
e
p
r
e
d
ictio
n
s
m
o
r
e
clo
s
ely
m
atch
ed
m
ea
s
u
r
ed
v
alu
es,
co
n
f
ir
m
in
g
th
at
r
esid
u
al
co
r
r
ec
tio
n
s
u
cc
ess
f
u
lly
r
e
co
v
er
s
g
r
ad
e
p
ea
k
s
s
u
p
p
r
ess
ed
b
y
Kr
i
g
in
g
s
m
o
o
th
in
g
.
T
h
e
r
esid
u
al
p
lo
t
a
f
ter
h
y
b
r
i
d
co
r
r
ec
tio
n
in
Fig
u
r
e
1
1
s
h
o
ws
a
m
o
r
e
s
y
m
m
etr
ical
er
r
o
r
d
is
tr
ib
u
tio
n
ar
o
u
n
d
ze
r
o
with
less
clu
s
ter
in
g
in
h
i
g
h
-
g
r
ad
e
z
o
n
es
co
m
p
ar
ed
to
s
tan
d
alo
n
e
Kr
ig
in
g
r
esid
u
als.
T
h
e
s
p
at
i
al
d
is
tr
ib
u
tio
n
o
f
th
e
h
y
b
r
id
m
o
d
el
p
r
ed
ictio
n
s
is
p
r
esen
ted
in
Fig
u
r
e
1
2
.
T
h
e
r
esu
ltin
g
m
ap
p
r
eser
v
es
th
e
o
v
er
all
g
eo
lo
g
ical
co
n
ti
n
u
ity
estab
lis
h
ed
b
y
OK
wh
ile
en
h
an
cin
g
lo
ca
l
h
ig
h
-
g
r
ad
e
v
ar
ia
b
ilit
y
th
r
o
u
g
h
GB
r
esid
u
al
co
r
r
ec
tio
n
.
C
o
m
p
ar
ed
with
th
e
s
ta
n
d
alo
n
e
Kr
ig
in
g
m
o
d
el,
th
e
h
y
b
r
id
p
r
ed
ictio
n
p
r
o
v
id
e
s
clea
r
er
d
elin
ea
tio
n
o
f
m
in
e
r
alize
d
zo
n
es
an
d
m
o
r
e
r
ea
lis
tic
r
ep
r
esen
tatio
n
o
f
g
r
ad
e
v
a
r
iab
ilit
y
,
m
ak
i
n
g
it m
o
r
e
s
u
itab
le
f
o
r
m
in
e
p
lan
n
in
g
an
d
ex
tr
ac
tio
n
p
r
io
r
itizatio
n
.
T
ab
le
4
.
Hy
b
r
id
m
o
d
el
p
e
r
f
o
r
m
an
ce
m
etr
ics
M
o
d
e
l
R
M
S
E
R²
H
y
b
r
i
d
(
O
K
+
G
B
)
0
.
1
8
3
6
0
.
8
7
9
5
Fig
u
r
e
10
.
Hy
b
r
id
m
o
d
el
a
ctu
al
v
s
.
p
r
ed
icted
g
o
ld
g
r
ad
es
Fig
u
r
e
11
.
R
esid
u
al
p
lo
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
:
3
9
4
-
403
400
Fig
u
r
e
12
.
Sp
atial
d
is
tr
ib
u
tio
n
o
f
p
r
e
d
icted
g
o
ld
g
r
a
d
es
4
.
4
.
M
o
del
co
m
pa
riso
n
T
h
e
p
e
r
f
o
r
m
an
ce
i
n
d
ex
es
o
f
a
ll
th
r
ee
m
o
d
els
ar
e
s
h
o
wn
in
T
ab
le
5
,
wh
er
e
p
r
o
g
r
ess
iv
e
im
p
r
o
v
em
e
n
t
is
o
b
s
er
v
ed
f
r
o
m
OK
to
th
e
s
tan
d
alo
n
e
GB
m
o
d
el,
an
d
th
en
to
th
e
h
y
b
r
id
m
o
d
el.
T
h
is
is
in
lin
e
with
th
eo
r
etica
l
r
esu
lts
:
Kr
ig
in
g
is
g
o
o
d
f
o
r
s
p
atial
co
h
er
en
ce
b
u
t
b
ad
f
o
r
s
am
p
le
-
by
-
s
am
p
le
ac
cu
r
ac
y
;
GB
is
g
o
o
d
f
o
r
s
am
p
le
-
by
-
s
am
p
le
ac
c
u
r
ac
y
b
u
t
b
ad
f
o
r
s
p
atial
co
h
er
en
c
e;
th
e
co
m
b
i
n
atio
n
o
f
b
o
th
is
g
o
o
d
.
T
h
e
o
b
jectiv
e
o
f
th
is
f
ig
u
r
e
is
to
d
ir
ec
tly
c
o
m
p
ar
e
th
e
R
MSE
an
d
R
²
v
alu
e
s
o
f
all
th
r
ee
m
o
d
els
,
as
s
h
o
wn
in
Fig
u
r
e
1
3
.
T
ab
le
5
.
Mo
d
el
co
m
p
ar
is
o
n
M
o
d
e
l
R
M
S
E
R²
OK
0
.
3
6
4
5
0
.
5
2
4
8
GB
0
.
1
6
4
2
0
.
7
5
4
5
H
y
b
r
i
d
(
O
K
+
G
B
)
0
.
1
8
3
6
0
.
8
7
9
5
Fig
u
r
e
13
.
R
MSE
an
d
R
²
co
m
p
ar
is
o
n
A
co
m
p
ar
is
o
n
o
f
R
MSE
an
d
R
²
v
alu
es
f
o
r
th
e
th
r
ee
m
o
d
els.
T
h
ese
f
in
d
in
g
s
ar
e
co
m
p
ar
ed
with
p
u
b
lis
h
ed
f
i
n
d
in
g
s
,
p
lacin
g
th
em
in
th
e
c
o
n
tex
t
o
f
o
th
e
r
p
u
b
lis
h
ed
liter
atu
r
e
.
Ma
n
iteja
et
a
l.
[
1
9
]
r
e
p
o
r
ted
an
R
²
o
f
0
.
8
1
f
o
r
a
h
y
b
r
id
OK
-
M
L
ap
p
r
o
ac
h
ap
p
lied
t
o
ir
o
n
o
r
e
g
r
a
d
e
esti
m
atio
n
.
Similar
ly
,
J
af
r
asteh
et
a
l.
[
1
4
]
d
em
o
n
s
tr
ated
th
at
ML
m
eth
o
d
s
ca
n
o
u
tp
er
f
o
r
m
co
n
v
en
tio
n
al
g
eo
s
tatis
tical
tech
n
iq
u
es
i
n
co
p
p
e
r
o
r
e
g
r
ad
e
esti
m
atio
n
,
h
ig
h
lig
h
ti
n
g
th
e
ef
f
ec
tiv
en
ess
o
f
d
ata
-
d
r
iv
e
n
ap
p
r
o
ac
h
es
f
o
r
im
p
r
o
v
in
g
p
r
ed
ict
io
n
ac
cu
r
ac
y
.
T
a
k
e
f
o
r
in
s
tan
ce
th
e
s
tu
d
y
b
y
Han
an
d
Su
h
[
2
0
]
wh
ich
s
h
o
wed
th
at
th
e
in
teg
r
ativ
e
ap
p
r
o
ac
h
es
o
f
ML
-
Kr
ig
in
g
wer
e
alwa
y
s
s
u
p
er
io
r
to
th
e
g
eo
s
tatis
tical
ap
p
r
o
ac
h
es
f
o
r
m
in
er
al
e
x
p
lo
r
atio
n
s
p
at
ial
p
r
ed
ictio
n
an
d
Mo
h
am
m
ad
p
o
u
r
et
a
l.
[
2
1
]
co
n
f
ir
m
ed
th
at
ML
-
Kr
ig
in
g
b
etter
r
ep
r
esen
ted
th
e
s
p
atial
v
ar
iab
ilit
y
o
f
g
eo
p
h
y
s
ical
d
ata
th
an
th
e
g
eo
s
tatis
t
ic
ap
p
r
o
ac
h
es.
Vale
r
i
o
et
a
l.
[
2
2
]
u
s
ed
a
h
y
b
r
id
r
eg
r
ess
io
n
-
Kr
ig
in
g
-
ML
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Hyb
r
id
g
eo
s
ta
tis
tica
l a
n
d
ma
c
h
in
e
lea
r
n
in
g
f
o
r
g
o
ld
g
r
a
d
e
e
s
tima
tio
n
(
Ta
n
ya
r
a
d
z
w
a
Mir
ia
m
Mtetw
a
)
401
m
o
d
el
to
f
ill
in
m
is
s
in
g
s
p
atial
d
ata,
an
d
o
b
tain
ed
s
i
m
ilar
ac
cu
r
ac
y
i
m
p
r
o
v
em
en
t
s
as
in
th
is
wo
r
k
.
An
v
ar
i
et
a
l.
[
2
3
]
u
s
ed
a
co
m
b
in
ed
g
eo
s
tatis
tical
an
d
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
f
o
r
g
eo
ch
e
m
ical
m
ap
p
in
g
an
d
f
o
u
n
d
th
e
s
p
atial
b
o
u
n
d
ar
ies
o
f
c
o
n
tam
in
atio
n
ar
ea
s
wer
e
b
etter
ca
p
t
u
r
ed
.
R
esu
lts
wer
e
s
im
ilar
to
th
o
s
e
p
u
b
lis
h
ed
b
y
o
th
er
r
esear
ch
er
s
an
d
s
h
o
wed
th
e
h
y
b
r
id
m
o
d
el
in
th
is
s
tu
d
y
to
h
av
e
a
n
R
²
o
f
0
.
8
7
9
5
with
an
R
MSE
r
ed
u
ctio
n
o
f
a
r
o
u
n
d
5
0
%,
c
o
m
p
a
r
ed
t
o
th
e
s
tan
d
alo
n
e
Kr
ig
in
g
m
o
d
el.
Ov
er
all,
p
r
ev
io
u
s
s
tu
d
ies
co
n
s
is
ten
tly
d
em
o
n
s
tr
ate
th
at
ML
an
d
h
y
b
r
id
g
eo
s
tatis
tical
–
ML
ap
p
r
o
ac
h
es
ca
n
im
p
r
o
v
e
p
r
ed
ictio
n
ac
cu
r
ac
y
co
m
p
ar
ed
with
c
o
n
v
en
tio
n
al
g
e
o
s
tatis
tical
m
eth
o
d
s
ac
r
o
s
s
v
ar
io
u
s
s
p
atial
p
r
e
d
ictio
n
ap
p
licatio
n
s
[
1
3
]
,
[
1
4
]
,
[
1
9
]
–
[
2
4
]
.
T
h
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
co
n
s
is
ten
t
with
th
is
g
en
er
al
tr
en
d
,
wh
er
e
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
ac
h
iev
ed
a
n
R
²
o
f
0
.
8
7
9
5
an
d
s
u
b
s
tan
tially
r
ed
u
ce
d
p
r
e
d
ictio
n
er
r
o
r
c
o
m
p
ar
ed
with
OK
.
T
h
e
p
r
o
p
o
s
ed
f
r
am
ew
o
r
k
d
e
m
o
n
s
tr
ated
co
m
p
etitiv
e
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
,
ac
h
iev
in
g
a
n
R
²
o
f
0
.
8
7
9
5
wh
ile
p
r
eser
v
in
g
s
p
atial
co
n
tin
u
ity
a
n
d
r
e
d
u
cin
g
p
r
ed
ictio
n
er
r
o
r
.
T
h
e
r
esu
lts
d
em
o
n
s
tr
ate
th
at
t
h
e
p
r
o
p
o
s
ed
h
y
b
r
id
g
eo
s
tatis
tical
–
ML
f
r
am
ewo
r
k
ca
n
en
h
an
ce
t
h
e
ac
cu
r
ac
y
o
f
o
r
e
g
r
a
d
e
esti
m
atio
n
i
n
h
i
g
h
ly
v
ar
iab
le
g
r
ee
n
s
to
n
e
b
elt
d
ep
o
s
its
,
th
er
eb
y
s
u
p
p
o
r
tin
g
m
o
r
e
r
eliab
le
m
in
e
p
lan
n
i
n
g
an
d
d
ec
is
io
n
-
m
ak
i
n
g
.
4
.
5
.
L
im
it
a
t
io
ns
a
nd
im
pli
ca
t
io
ns
T
h
e
r
esu
lts
ar
e
f
r
o
m
o
n
e
g
o
ld
d
ep
o
s
it
in
Z
im
b
ab
we.
Ap
p
lic
atio
n
o
f
th
is
to
s
itu
atio
n
s
with
d
if
f
er
in
g
s
tr
u
ctu
r
al
co
n
tr
o
ls
,
m
in
e
r
aliza
tio
n
s
ty
les,
o
r
d
ata
d
e
n
s
ity
ar
e
r
eq
u
ir
ed
t
o
b
e
test
ed
f
ir
s
t
b
ef
o
r
e
it
ca
n
b
e
u
s
ed
in
an
o
p
er
atio
n
al
s
itu
atio
n
.
T
h
e
ex
tr
em
e
v
alu
es
r
em
o
v
ed
in
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
(
1
s
t
-
9
9
t
h
p
e
r
ce
n
tile)
s
u
b
ject
to
o
u
tlier
clip
p
in
g
an
d
in
tr
o
d
u
c
e
b
ias
b
y
th
r
esh
o
ld
in
g
tr
u
e
h
ig
h
-
g
r
a
d
e
v
alu
es
-
o
th
er
p
r
e
-
p
r
o
ce
s
s
i
n
g
m
eth
o
d
s
s
h
o
u
ld
b
e
in
v
esti
g
ated
.
Fo
r
r
e
g
io
n
s
with
s
tr
u
ctu
r
al
co
m
p
lex
ity
,
r
esid
u
al
p
atter
n
s
co
u
ld
ac
tu
ally
b
e
r
elate
d
t
o
g
eo
lo
g
ical
tr
an
s
itio
n
s
an
d
m
a
y
ac
ce
n
tu
ate
r
ath
er
th
an
r
e
m
o
v
e
th
e
s
ig
n
al
in
th
e
r
eg
io
n
af
f
ec
ted
b
y
th
e
GB
co
r
r
ec
tio
n
.
H
y
b
r
id
p
r
ed
ictio
n
s
an
d
Kr
ig
i
n
g
v
a
r
ian
ce
m
ap
s
ar
e
to
b
e
u
s
ed
to
g
eth
er
to
f
in
d
ar
ea
s
wh
er
e
a
co
r
r
ec
tio
n
s
h
o
u
ld
b
e
m
ad
e
co
n
s
er
v
ativ
el
y
[
2
5
]
.
T
h
e
u
n
ce
r
tain
ty
q
u
a
n
tific
atio
n
p
r
o
b
lem
in
AI
-
b
ased
p
r
o
s
p
ec
tiv
ity
m
o
d
els
r
em
ain
s
an
ac
tiv
e
ar
ea
o
f
r
esear
c
h
[
2
5
]
.
T
h
e
ap
p
r
o
ac
h
wo
u
ld
b
e
m
o
r
e
in
f
o
r
m
ativ
e
if
th
e
an
aly
s
is
o
f
th
e
d
ata
wer
e
d
o
n
e
b
y
lith
o
lo
g
ical
u
n
it,
alter
atio
n
zo
n
e
o
r
s
tr
u
ctu
r
al
d
o
m
ain
.
Po
licy
-
wis
e,
a
v
alid
ated
h
y
b
r
id
esti
m
atio
n
m
eth
o
d
c
o
u
ld
p
r
o
v
id
e
g
u
id
an
ce
f
o
r
u
p
d
atin
g
n
atio
n
al
m
in
er
al
r
eso
u
r
ce
esti
m
atio
n
g
u
id
elin
es,
an
d
co
u
ld
b
e
u
s
ed
to
p
r
o
v
id
e
m
o
r
e
cr
ed
ib
le
r
eso
u
r
ce
d
ec
lar
atio
n
s
to
r
ep
o
r
tin
g
co
d
es
th
at
ar
e
alig
n
ed
with
jo
in
t
o
r
e
r
eser
v
es
co
m
m
ittee
(
J
OR
C
)
,
So
u
th
Af
r
ican
co
d
e
f
o
r
th
e
r
ep
o
r
tin
g
o
f
ex
p
lo
r
atio
n
r
esu
lts
,
m
in
er
al
r
e
s
o
u
r
ce
s
an
d
m
in
e
r
al
r
eser
v
es
(
SAMREC
),
an
d
co
m
m
ittee
f
o
r
m
in
er
al
r
eser
v
es
in
ter
n
atio
n
al
r
e
p
o
r
tin
g
s
tan
d
ar
d
s
(
C
R
I
R
SC
O
)
.
5.
CO
NCLU
SI
O
N
T
h
e
p
r
esen
t
s
tu
d
y
aim
ed
to
d
esig
n
,
d
ev
elo
p
,
an
d
ev
al
u
ate
a
h
y
b
r
id
g
eo
s
tatis
tical
an
d
ML
f
o
r
g
o
ld
g
r
ad
e
esti
m
atio
n
in
a
Z
im
b
a
b
wea
n
g
r
ee
n
s
to
n
e
b
elt
d
e
p
o
s
it
.
OK
was
u
s
ed
f
o
r
th
e
s
p
atial
b
aselin
e
an
d
th
e
s
y
s
tem
atic
r
esid
u
al
er
r
o
r
s
wer
e
co
r
r
ec
ted
b
y
GB
.
T
h
e
h
y
b
r
id
m
o
d
el
y
ield
e
d
th
e
h
ig
h
est R
²
an
d
p
r
o
d
u
ce
d
m
o
r
e
g
eo
lo
g
ically
r
ea
lis
tic
s
p
atial
p
r
ed
ictio
n
s
wh
ile
m
ain
tain
in
g
co
m
p
etitiv
e
R
MSE
p
er
f
o
r
m
an
ce
.
T
h
is
r
esid
u
al
co
r
r
ec
tio
n
f
r
am
ewo
r
k
ca
n
p
r
o
v
id
e
th
e
d
esire
d
g
r
ad
e
r
eso
lu
ti
o
n
th
at
is
ty
p
ically
lo
s
t
b
y
s
m
o
o
th
in
g
in
K
r
ig
in
g
an
d
s
im
u
ltan
eo
u
s
ly
k
ee
p
th
e
s
p
atial
co
h
er
en
ce
p
r
o
v
id
ed
b
y
a
p
u
r
ely
d
ata
-
d
r
i
v
en
ap
p
r
o
ac
h
f
r
o
m
ML
m
eth
o
d
s
.
T
h
e
ex
tr
ac
ti
o
n
p
r
io
r
ity
zo
n
e
m
ap
s
cr
ea
ted
u
s
in
g
h
y
b
r
id
p
r
ed
ictio
n
s
ar
e
o
p
e
r
atio
n
ally
u
s
ef
u
l
in
th
e
s
eq
u
en
ce
o
f
e
x
tr
ac
tio
n
,
b
last
p
atte
r
n
d
esig
n
,
a
n
d
o
r
e/w
aste
clas
s
if
icatio
n
.
Oth
er
f
u
t
u
r
e
d
ir
ec
tio
n
s
ar
e:
in
clu
d
in
g
m
o
r
e
g
eo
lo
g
ical
p
r
ed
icto
r
v
ar
iab
les,
in
clu
d
i
n
g
lith
o
lo
g
y
,
alter
atio
n
in
ten
s
ity
an
d
p
r
o
x
im
ity
to
s
tr
u
ctu
r
e;
ex
ten
d
in
g
to
th
r
ee
-
d
im
en
s
io
n
al
b
lo
c
k
m
o
d
el
esti
m
atio
n
;
im
p
lem
en
tin
g
u
n
ce
r
t
ain
ty
q
u
an
tific
atio
n
with
Kr
ig
in
g
v
a
r
ian
ce
an
d
G
B
p
r
ed
ictio
n
in
ter
v
als;
ex
ten
d
in
g
to
m
u
lti
-
y
ea
r
d
atasets
o
f
d
r
ill
-
h
o
le
g
r
ad
es
f
o
r
u
s
e
as
lo
n
g
itu
d
in
al
v
alid
atio
n
;
an
d
in
co
r
p
o
r
atin
g
d
o
wn
s
tr
e
am
ex
tr
ac
tio
n
ef
f
icien
cy
o
u
tc
o
m
es
o
f
m
ill
f
ee
d
g
r
ad
e
v
a
r
ian
ce
,
o
r
e
r
ec
o
v
er
y
r
ates a
n
d
d
ilu
tio
n
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
s
wo
u
l
d
lik
e
to
e
x
p
r
ess
th
an
k
s
to
Har
ar
e
I
n
s
titu
te
o
f
T
ec
h
n
o
l
o
g
y
f
o
r
ac
ad
e
m
ic
s
u
p
p
o
r
t
an
d
s
u
p
er
v
is
io
n
.
T
h
a
n
k
s
ar
e
d
u
e
to
th
e
g
eo
lo
g
is
ts
an
d
o
t
h
er
o
r
g
a
n
izatio
n
s
wh
o
m
a
d
e
g
eo
lo
g
ical
d
ata
an
d
ad
v
ic
e
av
ailab
le
d
u
r
in
g
th
e
s
tu
d
y
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
:
3
9
4
-
403
402
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
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
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
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
T
an
y
ar
ad
zwa
Mir
iam
Mte
twa
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Mo
n
ik
a
Go
n
d
o
✓
✓
✓
✓
✓
✓
✓
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
Au
th
o
r
s
s
tate
n
o
k
n
o
wn
co
m
p
etin
g
f
i
n
an
cial
in
ter
ests
o
r
p
er
s
o
n
al
r
elatio
n
s
h
ip
s
th
at
co
u
ld
h
a
v
e
ap
p
ea
r
ed
t
o
in
f
lu
e
n
ce
th
e
wo
r
k
r
ep
o
r
ted
in
t
h
is
p
ap
er
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
is
s
tu
d
y
co
m
p
lies
with
eth
ical
s
tan
d
ar
d
s
f
o
r
r
esear
ch
in
v
o
lv
in
g
g
eo
lo
g
ical
d
atasets
.
No
h
u
m
an
s
u
b
jects
wer
e
d
ir
ec
tly
in
v
o
l
v
ed
.
Data
wer
e
u
s
ed
with
in
s
titu
tio
n
al
ap
p
r
o
v
al
f
r
o
m
Har
ar
e
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
ailab
le
f
r
o
m
th
e
c
o
r
r
esp
o
n
d
in
g
a
u
th
o
r
,
[
TMM
]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
R
e
p
u
b
l
i
c
o
f
Z
i
mb
a
b
w
e
,
“
V
i
si
o
n
2
0
3
0
:
t
o
w
a
r
d
s
a
n
u
p
p
e
r
mi
d
d
l
e
-
i
n
c
o
me
e
c
o
n
o
m
y
b
y
2
0
3
0
,
”
H
a
r
a
r
e
,
Zi
m
b
a
b
w
e
,
2
0
1
8
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
z
i
m
e
m
b
a
ss
y
d
c
.
o
r
g
/
w
p
-
c
o
n
t
e
n
t
/
u
p
l
o
a
d
s
/
2
0
2
3
/
1
2
/
Zi
m
b
a
b
w
e
-
V
i
si
o
n
-
2
0
3
0
.
p
d
f
[
2
]
M
i
n
i
s
t
r
y
o
f
I
C
T,
P
o
s
t
a
l
a
n
d
C
o
u
r
i
e
r
S
e
r
v
i
c
e
s
,
G
o
v
e
r
n
m
e
n
t
o
f
Z
i
m
b
a
b
w
e
,
“
Th
e
sm
a
r
t
Zi
m
b
a
b
w
e
2
0
3
0
mas
t
e
r
p
l
a
n
,
”
H
a
r
a
r
e
,
Zi
m
b
a
b
w
e
,
2
0
1
9
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
i
c
t
m
i
n
i
st
r
y
.
g
o
v
.
z
w
/
a
sse
t
s/
d
o
c
u
me
n
t
s
/
S
mar
t
%
2
0
Zi
m
b
a
b
w
e
%
2
0
2
0
3
0
%2
0
M
a
s
t
e
r
%
2
0
P
l
a
n
.
p
d
f
[
3
]
M
.
E.
R
o
ssi
a
n
d
C
.
V
.
D
e
u
t
s
c
h
,
Mi
n
e
ra
l
re
so
u
rc
e
e
st
i
m
a
t
i
o
n
.
D
o
r
d
r
e
c
h
t
:
S
p
r
i
n
g
e
r
N
e
t
h
e
r
l
a
n
d
s,
2
0
1
4
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
1
-
4
0
2
0
-
5
7
1
7
-
5.
[
4
]
H
.
A
.
Jel
sm
a
a
n
d
P
.
H
.
G
.
M
.
D
i
r
k
s
,
“
N
e
o
a
r
c
h
a
e
a
n
t
e
c
t
o
n
i
c
e
v
o
l
u
t
i
o
n
o
f
t
h
e
Zi
m
b
a
b
w
e
C
r
a
t
o
n
,
”
G
e
o
l
o
g
i
c
a
l
S
o
c
i
e
t
y
,
L
o
n
d
o
n
,
S
p
e
c
i
a
l
P
u
b
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
9
9
,
p
p
.
183
–
2
1
1
,
2
0
0
2
,
d
o
i
:
1
0
.
1
1
4
4
/
g
s
l
.
s
p
.
2
0
0
2
.
1
9
9
.
0
1
.
1
0
.
[
5
]
J.
R
i
d
l
e
y
,
O
re
d
e
p
o
si
t
g
e
o
l
o
g
y
,
C
a
mb
r
i
d
g
e
,
U
.
K
.
:
C
a
m
b
r
i
d
g
e
U
n
i
v
e
r
si
t
y
P
r
e
ss,
2
0
1
3
.
[
6
]
G
.
M
a
t
h
e
r
o
n
,
“
P
r
i
n
c
i
p
l
e
s
o
f
g
e
o
st
a
t
i
st
i
c
s
,
”
E
c
o
n
o
m
i
c
G
e
o
l
o
g
y
,
v
o
l
.
5
8
,
n
o
.
8
,
p
p
.
1
2
4
6
–
1
2
6
6
,
D
e
c
.
1
9
6
3
,
d
o
i
:
1
0
.
2
1
1
3
/
g
s
e
c
o
n
g
e
o
.
5
8
.
8
.
1
2
4
6
.
[
7
]
I
.
C
l
a
r
k
,
Pr
a
c
t
i
c
a
l
g
e
o
s
t
a
t
i
s
t
i
c
s
,
1
st
e
d
.
L
o
n
d
o
n
,
U
.
K
.
:
A
p
p
l
i
e
d
S
c
i
e
n
c
e
P
u
b
l
i
sh
e
r
s,
1
9
7
9
.
[
8
]
P
.
G
o
o
v
a
e
r
t
s,
G
e
o
s
t
a
t
i
s
t
i
c
s
f
o
r
n
a
t
u
r
a
l
res
o
u
rc
e
s e
v
a
l
u
a
t
i
o
n
.
N
e
w
Y
o
r
k
,
N
Y
:
O
x
f
o
r
d
U
n
i
v
e
r
s
i
t
y
P
r
e
s
s,
1
9
9
7
.
[
9
]
F
.
A
t
a
l
a
y
,
“
Es
t
i
m
a
t
i
o
n
o
f
F
e
g
r
a
d
e
a
t
a
n
o
r
e
d
e
p
o
si
t
u
si
n
g
e
x
t
r
e
me
g
r
a
d
i
e
n
t
b
o
o
st
i
n
g
t
r
e
e
s
(
X
G
B
o
o
s
t
)
,
”
M
i
n
i
n
g
,
M
e
t
a
l
l
u
rg
y
&
Ex
p
l
o
ra
t
i
o
n
,
v
o
l
.
41
,
n
o
.
4
,
p
p
.
2
1
1
9
–
2
1
2
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
4
6
1
-
0
2
4
-
0
1
0
1
0
-
5.
[
1
0
]
T.
C
h
e
n
a
n
d
C
.
G
u
e
s
t
r
i
n
,
“
X
G
B
o
o
s
t
:
a
s
c
a
l
a
b
l
e
t
r
e
e
b
o
o
st
i
n
g
s
y
st
e
m
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
2
n
d
A
C
M
S
I
G
K
D
D
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
K
n
o
w
l
e
d
g
e
D
i
s
c
o
v
e
r
y
a
n
d
D
a
t
a
Mi
n
i
n
g
,
A
u
g
.
2
0
1
6
,
p
p
.
7
8
5
–
794
,
d
o
i
:
1
0
.
1
1
4
5
/
2
9
3
9
6
7
2
.
2
9
3
9
7
8
5.
[
1
1
]
Z.
F
u
e
t
a
l
.
,
“
T
h
e
e
v
o
l
u
t
i
o
n
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
l
a
r
g
e
-
s
c
a
l
e
mi
n
e
r
a
l
p
r
o
s
p
e
c
t
i
v
i
t
y
p
r
e
d
i
c
t
i
o
n
:
a
d
e
c
a
d
e
o
f
i
n
n
o
v
a
t
i
on
(
2
0
1
6
–
2
0
2
5
)
,
”
M
i
n
e
ra
l
s
,
v
o
l
.
1
5
,
n
o
.
1
0
,
p
.
1
0
4
2
,
S
e
p
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
mi
n
1
5
1
0
1
0
4
2
.
[
1
2
]
L.
B
r
e
i
m
a
n
,
“
R
a
n
d
o
m
f
o
r
e
st
s
,
”
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
,
v
o
l
.
4
5
,
n
o
.
1
,
p
p
.
5
–
3
2
,
O
c
t
.
2
0
0
1
,
d
o
i
:
1
0
.
1
0
2
3
/
A
:
1
0
1
0
9
3
3
4
0
4
3
2
4
.
[
13
]
U
.
E
.
K
a
p
l
a
n
a
n
d
E
.
To
p
a
l
,
“
A
n
e
w
o
r
e
g
r
a
d
e
e
s
t
i
m
a
t
i
o
n
u
s
i
n
g
c
o
m
b
i
n
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
Mi
n
e
r
a
l
s
,
v
o
l
.
10
,
n
o
.
1
0
,
p
.
8
4
7
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
mi
n
1
0
1
0
0
8
4
7
.
[1
4
]
B
.
Jafr
a
st
e
h
,
N
.
F
a
t
h
i
a
n
p
o
u
r
,
a
n
d
A
.
S
u
á
r
e
z
,
“
C
o
m
p
a
r
i
so
n
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s
f
o
r
c
o
p
p
e
r
o
r
e
g
r
a
d
e
e
s
t
i
m
a
t
i
o
n
,”
C
o
m
p
u
t
a
t
i
o
n
a
l
G
e
o
s
c
i
e
n
c
e
s
,
v
o
l
.
22
,
n
o
.
2
,
p
p
.
1
3
7
1
–
1
3
8
8
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
5
9
6
-
018
-
9
7
5
8
-
0.
[1
5
]
I
.
M
.
K
i
š
,
“
C
o
m
p
a
r
i
so
n
o
f
o
r
d
i
n
a
r
y
a
n
d
u
n
i
v
e
r
sal
k
r
i
g
i
n
g
i
n
t
e
r
p
o
l
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
o
n
a
d
e
p
t
h
v
a
r
i
a
b
l
e
(
a
c
a
se
o
f
l
i
n
e
a
r
sp
a
t
i
a
l
t
r
e
n
d
)
,
c
a
s
e
s
t
u
d
y
o
f
t
h
e
Š
a
n
d
r
o
v
a
c
F
i
e
l
d
,
”
R
u
d
a
rs
k
o
-
g
e
o
l
o
šk
o
-
n
a
f
t
n
i
zb
o
r
n
i
k
,
v
o
l
.
3
1
,
n
o
.
2
,
p
p
.
4
1
–
5
8
,
2
0
1
6
,
d
o
i
:
1
0
.
1
7
7
9
4
/
r
g
n
.
2
0
1
6
.
2
.
4
.
[1
6
]
X
.
X
i
e
a
n
d
X
.
L
u
,
“
T
h
e
t
a
-
r
e
g
u
l
a
r
i
z
e
d
K
r
i
g
i
n
g
:
mo
d
e
l
i
n
g
a
n
d
a
l
g
o
r
i
t
h
m
s
,
”
Ap
p
l
i
e
d
Ma
t
h
e
m
a
t
i
c
a
l
M
o
d
e
l
l
i
n
g
,
v
o
l
.
1
3
6
,
p
.
1
1
5
6
2
7
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
p
m.
2
0
2
4
.
0
7
.
0
3
4
.
[1
7
]
V
.
R
.
J
o
se
p
h
,
“
R
a
t
i
o
n
a
l
K
r
i
g
i
n
g
,
”
J
o
u
rn
a
l
o
f
t
h
e
Am
e
ri
c
a
n
S
t
a
t
i
st
i
c
a
l
Ass
o
c
i
a
t
i
o
n
,
v
o
l
.
1
2
0
,
n
o
.
5
4
9
,
p
p
.
5
4
8
–
5
5
8
,
J
a
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
8
0
/
0
1
6
2
1
4
5
9
.
2
0
2
4
.
2
3
5
6
2
9
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Hyb
r
id
g
eo
s
ta
tis
tica
l a
n
d
ma
c
h
in
e
lea
r
n
in
g
f
o
r
g
o
ld
g
r
a
d
e
e
s
tima
tio
n
(
Ta
n
ya
r
a
d
z
w
a
Mir
ia
m
Mtetw
a
)
403
[1
8
]
Y
.
M
.
I
n
d
a
h
,
R
.
A
r
i
st
a
w
i
d
y
a
,
A
.
F
i
t
r
i
a
n
t
o
,
E.
Er
f
i
a
n
i
,
a
n
d
L
.
M
.
R
.
D
.
J
u
m
a
n
s
y
a
h
,
“
C
o
mp
a
r
i
s
o
n
o
f
r
a
n
d
o
m
f
o
r
e
st
,
X
G
B
o
o
s
t
,
a
n
d
Li
g
h
t
G
B
M
me
t
h
o
d
s
f
o
r
t
h
e
h
u
m
a
n
d
e
v
e
l
o
p
me
n
t
i
n
d
e
x
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
J
a
m
b
u
r
a
J
o
u
r
n
a
l
o
f
M
a
t
h
e
m
a
t
i
c
s
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
1
4
–
1
8
,
2
0
2
5
,
d
o
i
:
1
0
.
3
7
9
0
5
/
j
j
o
m.
v
7
i
1
.
2
8
2
9
0
.
[1
9
]
M
.
M
a
n
i
t
e
j
a
e
t
a
l
.
,
“
A
d
v
a
n
c
i
n
g
i
r
o
n
o
r
e
g
r
a
d
e
e
st
i
ma
t
i
o
n
:
a
c
o
m
p
a
r
a
t
i
v
e
st
u
d
y
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
O
r
d
i
n
a
r
y
K
r
i
g
i
n
g
,
”
Mi
n
e
r
a
l
s
,
v
o
l
.
1
5
,
n
o
.
2
,
p
.
1
3
1
,
Ja
n
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
m
i
n
1
5
0
2
0
1
3
1
.
[
20
]
H
.
H
a
n
a
n
d
J.
S
u
h
,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
–
K
r
i
g
i
n
g
i
n
t
e
g
r
a
t
i
v
e
a
p
p
r
o
a
c
h
e
s
f
o
r
e
n
h
a
n
c
e
d
sp
a
t
i
a
l
p
r
e
d
i
c
t
i
o
n
o
f
mi
n
e
r
a
l
e
x
p
l
o
r
a
t
i
o
n
d
a
t
a
,
”
I
S
P
RS
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
G
e
o
-
I
n
f
o
rm
a
t
i
o
n
,
v
o
l
.
1
5
,
n
o
.
4
,
p
.
1
7
5
,
A
p
r
.
2
0
2
6
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
g
i
1
5
0
4
0
1
7
5
.
[2
1
]
M
.
M
o
h
a
mm
a
d
p
o
u
r
,
H
.
R
o
sh
a
n
,
M
.
A
r
a
sh
p
o
u
r
,
a
n
d
H
.
M
a
s
o
u
mi
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
ss
i
st
e
d
K
r
i
g
i
n
g
t
o
c
a
p
t
u
r
e
sp
a
t
i
a
l
v
a
r
i
a
b
i
l
i
t
y
i
n
p
e
t
r
o
p
h
y
s
i
c
a
l
p
r
o
p
e
r
t
y
m
o
d
e
l
l
i
n
g
,
”
M
a
ri
n
e
a
n
d
P
e
t
r
o
l
e
u
m
G
e
o
l
o
g
y
,
v
o
l
.
1
6
7
,
p
.
1
0
6
9
6
7
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
a
r
p
e
t
g
e
o
.
2
0
2
4
.
1
0
6
9
6
7
.
[2
2
]
A
.
V
a
l
e
r
i
o
,
Y
.
-
C
.
C
h
e
n
,
C
.
-
Y
.
Li
u
,
Y
.
-
Y
.
C
h
e
n
,
a
n
d
C
.
-
Y
.
Li
n
,
“
A
h
y
b
r
i
d
r
e
g
r
e
ss
i
o
n
–
K
r
i
g
i
n
g
–
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
f
o
r
i
mp
u
t
i
n
g
mi
ss
i
n
g
TR
O
P
O
M
I
N
O
2
d
a
t
a
o
v
e
r
Ta
i
w
a
n
,
”
Re
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
7
,
n
o
.
1
2
,
p
.
2
0
8
4
,
J
u
n
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
7
1
2
2
0
8
4
.
[2
3
]
K
.
A
n
v
a
r
i
,
J.
B
e
n
n
d
o
r
f
,
G
.
G
e
r
b
e
r
,
a
n
d
U
.
A
l
i
s
c
h
,
“
H
y
b
r
i
d
g
e
o
s
t
a
t
i
s
t
i
c
a
l
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
f
o
r
g
e
o
c
h
e
mi
c
a
l
c
h
a
r
a
c
t
e
r
i
z
a
t
i
o
n
i
n
h
i
s
t
o
r
i
c
a
l
mi
n
e
t
a
i
l
i
n
g
s,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
5
,
n
o
.
1
,
p.
3
5
0
0
4
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
5
-
1
9
4
4
1
-
5.
[2
4
]
G.
E
.
Er
t
e
n
,
K
.
M
o
k
d
a
d
,
C
.
Z
.
d
a
S
i
l
v
a
,
J
.
N
i
s
e
n
s
o
n
,
G
.
B
r
a
n
d
a
o
,
a
n
d
J
.
B
o
i
s
v
e
r
t
,
“
E
n
se
m
b
l
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
g
e
o
st
a
t
i
st
i
c
a
l
h
y
b
r
i
d
m
o
d
e
l
s
f
o
r
g
r
a
d
e
c
o
n
t
r
o
l
,
”
M
a
t
h
e
m
a
t
i
c
a
l
G
e
o
s
c
i
e
n
c
e
s
,
v
o
l
.
5
7
,
n
o
.
3
,
p
p
.
4
9
9
–
5
2
2
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
0
4
-
024
-
10172
-
3.
[2
5
]
D
.
K
o
l
d
a
s
b
a
y
e
v
a
,
P
.
Tr
e
g
u
b
o
v
a
,
M
.
G
a
san
o
v
,
A
.
Za
y
t
se
v
,
A
.
P
e
t
r
o
v
s
k
a
i
a
,
a
n
d
E.
B
u
r
n
a
e
v
,
“
C
h
a
l
l
e
n
g
e
s
i
n
d
a
t
a
-
d
r
i
v
e
n
g
e
o
s
p
a
t
i
a
l
mo
d
e
l
i
n
g
f
o
r
e
n
v
i
r
o
n
m
e
n
t
a
l
r
e
s
e
a
r
c
h
a
n
d
p
r
a
c
t
i
c
e
,
”
N
a
t
u
r
e
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
1
5
,
n
o
.
1
,
p
.
1
0
7
9
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
4
6
7
-
0
2
4
-
5
5
2
4
0
-
8.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ta
n
y
a
r
a
d
z
wa
Mi
r
ia
m
Mt
e
twa
re
c
e
iv
e
d
th
e
Ba
c
h
e
l
o
r
o
f
Tec
h
n
o
l
o
g
y
(Ho
n
o
u
rs)
d
e
g
re
e
in
S
o
f
twa
re
En
g
in
e
e
ri
n
g
f
ro
m
Ha
ra
re
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
Zi
m
b
a
b
we
,
in
2
0
2
3
a
n
d
is
c
u
rre
n
tl
y
p
u
rsu
in
g
a
M
a
ste
r
o
f
Tec
h
n
o
l
o
g
y
d
e
g
re
e
in
Da
ta
S
c
ien
c
e
a
n
d
An
a
ly
ti
c
s
a
t
th
e
sa
m
e
in
stit
u
ti
o
n
.
He
r
re
se
a
rc
h
i
n
tere
sts
in
c
lu
d
e
d
a
ta
sc
ien
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
g
e
o
sta
ti
stics
,
m
in
e
ra
l
re
so
u
rc
e
e
stim
a
ti
o
n
,
a
n
d
s
p
a
ti
a
l
d
a
ta
a
n
a
l
y
ti
c
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
tetwa
tan
ia@
g
m
a
il
.
c
o
m
.
Mo
n
ik
a
G
o
n
d
o
is
a
lec
tu
re
r
in
th
e
De
p
a
rtme
n
t
o
f
o
f
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
a
n
d
c
u
rre
n
tl
y
re
sp
o
n
si
b
le
f
o
r
M
Tec
h
p
ro
g
ra
m
m
e
s
u
n
d
e
r
t
h
e
S
c
h
o
o
l
o
f
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
a
t
Ha
ra
re
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
.
He
r
p
re
v
i
o
u
s
re
se
a
rc
h
in
c
lu
d
e
s
In
fo
rm
a
ti
o
n
S
e
c
u
rit
y
,
In
f
o
rm
a
ti
o
n
Risk
M
a
n
a
g
e
m
e
n
t
a
n
d
In
f
o
rm
a
ti
o
n
S
e
c
u
ri
ty
Ad
m
in
istrati
o
n
(Ac
c
e
ss
to
Co
rp
o
ra
te
In
fo
rm
a
ti
o
n
,
In
f
o
rm
a
ti
o
n
Rig
h
ts
,
a
n
d
In
f
o
rm
a
ti
o
n
P
r
iv
a
c
y
)
,
a
n
d
Web
De
v
e
l
o
p
m
e
n
t.
He
r
re
se
a
rc
h
in
tere
sts
a
re
Io
T,
AI
,
a
n
d
e
th
ics
,
d
i
g
it
a
l
tra
n
sfo
r
m
a
ti
o
n
,
ICT
4
D,
s
o
ftwa
re
e
n
g
in
e
e
rin
g
,
c
o
m
p
u
ter v
isio
n
,
a
n
d
i
n
fo
rm
a
ti
o
n
se
c
u
rit
y
t
o
m
e
n
t
io
n
a
fe
w.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
g
o
n
d
o
@h
it
.
a
c
.
z
w
.
Evaluation Warning : The document was created with Spire.PDF for Python.