docx (preprint)

ticketdonkeyΤεχνίτη Νοημοσύνη και Ρομποτική

25 Νοε 2013 (πριν από 4 χρόνια και 11 μήνες)

258 εμφανίσεις


1


Mining Urban Land U
se Patterns from Volunteered Geographic
Information Using Genetic Algorithms and Artificial Neural
Networks


Julian Hagenauer

and

Marco Helbich


GIScience,
Institute

of Geography,

University

of
Heidelberg
,
Germany


K
eywords:

Volunteered Geography,
OpenStreetMap, Spatial Data Quality,
Spatial Data Mining



This is an Author’s Original Manuscript of an article whose final and definitive form,

the Version of Record, has been published in the International Journal of Geographical

Information Science [
14 Nov 2011
] [copyright Taylor & Francis], available online at:

http://www.tandfonline.com/doi/abs/10.1080/13658816.2011.619501
.


Abstract


OpenStreetMap

(OSM)
, as one of the
most promising
crow
d sourced initiative,
provides
volunteered
mapped
spatial data.
At once, t
his bears several
spatial data quality
problems
,
inter alia

completeness, which
on the one hand
induces data omission errors and commission e
rror
s

on the
other hand
. Using European
-
wide urban land use patterns
,

this study
investigates
the first issue and
aims at

predict
ing

currently not mapped or partially mapped

urban areas based on
OSM
. For this
purpose
,

a
machine learning approach
consisting

of g
enetic
a
lgorithms and
a
rtificial
n
eural
n
etworks

is applied

to estimated urban areas
.
Under the premise
of

existing
OSM
data

the model
estimates
missing urban areas with
an overall
squared correlation coefficient

(R
2
)
of 0.6
.

Nevertheless,
interregional comparisons
of European regions
confirm spatial heterogeneity in model quality
(R
2

ranges from
0.2

up to
0.8
)
and thus the
inherent varying
completeness of OSM.
Hence
, this
verifies
the hypothesis that more active volunteers
wi
thin a region
enhance the content of OSM.


1
Introduction


The emergence of internet technologies facilitates the generation and distribution of manifold digital
content

(e.g., Flickr
,

Wikipedia
) and thus
makes
collaborative efforts common

and present in
everyday life
. The enablement of participatory collaboration caused a paradigm shift, blurring the
distinction between consumers and producers

that has been existent in the W
eb since its early days.
O’Reilly (2005)
terms

these developments
Web 2.0.


2



Because of the
high
costs related to
the process of
gathering

and

maintaining as well as efforts
involved in sharing and distributing spatial data, these have been almost solely the domain of either
official land surveying offices or commercial companies.

Nowadays, the availability of mobile devices
endowed
with satelli
te navigation has enabled people to collect geographic data
on
their own, at low
costs, and high precision levels, formerly not
conceivable
for non
-
experts.
Citizens
have become
human
sensors
(
Goodchild 2007
).

Web 2.0
-
technologies permit volunteers to aggr
egate
,

share
and
,

edit
their collected geographic data in a collaborative manner.
This phenomenon is usually referred
to as Volunteered Geograp
hic Information (VGI; Goodchild

2007; Elwood 2008)
, whereas
Sui (2008)
calls

it

in terms of GIS

metaphorically

the "wikification of GIS".


Among a broad list of initiatives
dealing with

VGI, OpenStreetMap (OSM) is one of the most
promising
activities
.

Since its
initiation

in 2004
,

its primary goal
is the generation of
a free map of the
world through volunteered
co
ntributions
.
A
lthough
,

the generation of maps
is
still
the primary
intention
, the collected spatial data is
also
made publicly available and may thus be used for
individual
purposes

(e.g.,
OpenRouteService.org

(Neis and Zipf 2008)
, 3D city models
(Over et
al.
2010
)
)
.
U
ser generated
GPS tracks
,
out of copyright maps
,

and

more recently aerial images

(e.g., Bing

M
aps
)
serve as primary data source
. The data itself
are

distributed under a license that guarantees
freedom of use
, but enforces
that
all
derived data

are distributed under the same license

(Haklay and
Weber
2008
, Ramm and Topf 2010
)
.


In general, awareness concerning the limitations of spatial data is essential and in particular
data
quality

issues
,
which are
a
comprehensive

and ongoing
active
research
field
(
e.g.,

Chrisman

19
84;
Buttenfield 1993;
Goodchild and Hunter
1996
;
Goodchild 1998;
Shi et al. 2002,
Devillers
et al.

20
10
)
.
Evaluating spatial data quality is an
impo
r
tant
part in the process of assessing the "fitness
for use"
(Chrisman 1993
) of a data set for a particular application (van Oort

20
03).
Further
more
,

spatial data
quality has also

been addressed by
a set of standard definitions
and quality criteria proposals
from
various
organizations

such as the National Committee on Digital Car
tographic Data Standards
(NCDCDS, Moellering 1987), the International Cartographic Association (ICA, Guptill and Morrison
1995) or the International Standardization Organization (ISO, Kresse and Fadaie 2004
).
Based on the
definitions of the Technical Commi
ttee 211 of the
ISO
,
the following elements of spatial data quality
can be identified (Kresse and Fadaie

20
04
):

-

Positional accuracy
: concerns the accordance of positioning and geometry
of
an
object
to
it
s

represent
ation

in the real world
,

-

Attribute
accuracy
: measures the correctness of attributes assigned to a geographic object
,


3


-

Completeness: measures the absence
and excess
of data
,

-

Logical consistency
: describes the topological correctness and
the
relationships between
objects in respect to their i
nternal consistency
,

-

Semantic accuracy
: evaluates the correspondence of the interpretation of spatial object
s

to
their
meaning
s

in the real world
,

-

Temporal accuracy
: describes the
data
actuality in relation to real world changes
,

-

Lineage
: concerns the hist
ory of a data set, how it was collected and derived to its
actual

state
,

-

Usage
: assesses the extent of a data set to serve its intended purpose.


This
contribution
focuses on
the
completeness

criterion

of spatial quality
.
Completeness
describes

the presence and absence of objects in a data set. Brassel et al. (1995) distinguish between data
completeness

and model completeness
.
Former

refers to the measureable errors between the data
set and its specification.

Errors may be caused by lack of data

that is formally expected to be present
in the database (omission

errors
) or
otherwise
, present in the database but not intended to be
included (commission

errors
).
The la
tter

is measurable and independent of the application.
In
contrast

to data completen
ess
, m
odel completeness considers the intended use, i.e. how well
the
model of a dataset fulfills the requirements of an application
(
Brassel et al. 1995
). To evaluate
completeness in terms of fitness for use, it is
advisable
to
consider both

data complete
ness
as well as
model completeness.

T
he
appropriateness

of spatial data quality usually depends on the availability
and quality of reference i
nformation (Servigne et al.

20
10
).

Concerning VGI in general and OSM in
particular spatial data quality, namely sp
atial accuracy, is an important issue (Haklay et al.

20
10
) and
following Goodchild (2008) the same is valid for completeness.


Studies of OSM data quality have previously been
conducted
in several recent studies

(
Girres and
Touya 2010
;
Haklay 20
10
; Haklay
et al. 2010)
.

Haklay (2010) evaluates
the positional accuracy of OSM
in reference to Ordnance Survey data for Great Britain

based on the methodology of Goodchild and
Hunter (1996)
, by analyzing the percentage of overlaps between both data sets within a
buffer
distance
. Girres and Touya (2010)
similarly

evaluated

different aspects of OSM data quality in France.
Both

studies

showed that in terms of positional accuracy the quality of OSM data is comparable to
traditional geographic datasets from national ma
pping agencies or commercial
provide
r
s
.

Nevertheless,
comprehensive
studies concerning completeness of OSM are lacking so far

and
thus
re
present a compelling area of
research
, which is
the main objective of

this paper
.




4


The
m
easurement of
VGI
completeness

is a complex task and
bears several difficulties.
First,
VGI
activities address a large user
-
base, whose motivations for participating, contributing
,

and using
spatial data differ substantially (Heipke

20
10).
Second, a

strictly defined dataset specificati
on may be
contradicting the plurality of a user community, but without a precise specification of the dataset it is
not possible to detect errors of completeness (v
a
n Oort

20
06; Servigne et al.

20
10
).
Third,
in OSM
anybody is permitted to add, delete
,

or modify data
. However
, mapping guidelines
exist
that are
recommended to
be
follow
ed

by contributors
. The guidelines

are

communicated, discussed and
modified through a wiki
, and
reflect the consensus of the community
.
Because this specification is
not au
thoritative, it is not possible to measure completeness of OSM in a strict sense. Anyhow,
several studies comparing the completeness of OSM to other datasets exist (
e.g.,
Girres and Touya
2010
;
Haklay 2010
;

Haklay et al.
2010
;

Zielstra and Zipf
2010
).
Howe
ver, those studies
only consider
objects of certain types
(
e.g.
,

roads or rivers
)
for
descriptive
measurement
s
.


For OSM

i
t i
s no
t

guarantee
d

that a certain object will ever be mapped. On a global scale the digital
divide is an important factor for incompl
ete mapping of less developed countries (
Goodchild 2008;
Maue and Schade

20
08). On a local scale the absence of voluntary contributors in disadvantaged
areas
is

a primary cause for omission errors (e.g.
,

Haklay

20
10
).
In particular
,

it appears that
completeness in the sense of present features not only
depends
on the density of information within
an area, but also on the number of contributors, which is generally high in densely populated areas
(Girres and Touya

20
10).

Third
-
party co
ntributions to OSM
,

such as the import of the TIGER data
from the US Census Bureau
and
the availability of cadastral data from French authorities
,

improve
the situation of missing data. Beyond that, it
is

expected that intelligent tools and
powerful

visual
izations might further be helpful in detecting and fixing spatial data quality issues

(e.g.,
see
the
prototype of the web
-
base
d

attribute visualization tool
OSMatrix
1

(Roick and Hagenauer 2011)
.
However, t
he
absence of data may unbearabl
y

affect the fitnes
s for use
. For instance,

incomplete or
wrong
ly

mapped representations of road networks and the surrounding environment may induce
inaccurate route proposals of a navigation application

(e.g., Neis and Zipf 2008)
. This in turn

negatively
affect
s

the users’
activity space and time schedule. In particular, this is true for larger
urban areas,
affected

by traffic jams, speed limits, and one
-
way streets
, where it is

often advisable to
take an alternative bypass route
.


OSM
exhibits
implicit information that can
be used to fill the gap between the contents of the data
set and information needed for the intended application.

Urban areas are generally not
delineated

in
OSM, but there are various possibilities to derive them from existing data.
A
straightforward
solu
tion



1

http://
osmatrix.uni
-
hd.
de


5


is to aggregate land
use information to form urban areas.
However, especially in sparsely mapped
areas

and for small rural communities
such
land use

information is
mostly

absent in OSM.

Based on
the method of Rozenfeld et al. (2008),
Jiang and Jia (20
1
1
)
propose
a clustering algorithm

to
deriv
e
city
boundaries

from

OSM street nodes. Their method
ology

aggregates
street nodes
within a certain
distance
to clusters. The choice of the distance has a
crucial

affect on the result.
Their approach
validates Z
ipf’s law
, which relates the s
ize of cities with their ranking
s.
However, their approach

ignore
s

other

OSM data

and
inherent

non
-
linear relationships.

Furthermore
, both approaches
derive
only crisp urban areas, but

in urban geography
there
is
strong
eviden
ce that

metropolitan areas are
nowadays
shaped by sub
-

and post
suburbanization processes

(e.g.
,

Helbich and Leitner 2009,
2010)
,
causing a
continuous transition

between urban and rural areas,

and cannot be
delineated
by a crisp
and
dichotomous
classificati
on scheme (Leung 1987)
.
A
continuously
and

density
-
based
representation of u
rban areas
is

more

suitable

but
is
difficult to obtain

due to complex relationships
of urbanization processes
.


Developments in
artificial intelligence find remedy and bear potential to solve
g
eographical problems

that were previously difficult to solve
(
Smith 1984,
Gahegan

20
03)
.
In particular,
Artificial Neural
Networks (ANNs) are appealing for spatial analysis

(Openshaw and Open
shaw 1997)
, because of their
computation
al speed
, representational flexibility, ability to model non
-
linear relationships
,

and
computational adaptivity (Fischer

19
97). ANNs perform
particularly
well compared to conventional
statistical models if the data
a
re
incomplete or inconsistent (Fischer and Gopal

19
94), which is often
the case with
complex
spatial data

such as

OSM.
In GIScience
,

ANNs have already shown high
potential for modeling
complex
geographic processes (
e.g.,
Fischer and Gopal

19
94;
Pijanowski
et al.

20
02
;

Mas et al.

20
04
).


This

paper makes an initial empirical contribution and charts current urban patterns

on the basis of
VGI
.
Therefore, the objective of this study is to develop a
density
-
based

methodological framework
to delimitate
continuous
urban areas using the whole information diversity of OSM. To capture
possible
non
-
linear relationships
, interactions
,

and spatial effects within the
GIS
-
based
data
,

ANN

techniques

are applied.
The framework mitigates data completeness issues of
OSM and thus helps to
improve the fitness
for
use of OSM for individual applications.
The usefulness
is

demonstrated
on a
set of selected
European
urban
regions.


The paper is structured as follows
:

S
ection
2 provides an overview concerning

the
study area

and

the
data sets.
Section 3 introduces

t
he methodology used
to detect
urban patterns
.

R
esults of the

6


empirical analysis are discussed

in section 4

and t
he
paper concludes
(section 5)
with a

discussion of
the results and

identifies future work
.


2 Materia
ls

2.1
Study Site and Data


Training of ANNs requires reference information for learning. For the European Union

(EU)
, t
wo
public
ly

available
urban land use
datasets

are
predominant
: CORINE (Coordination of information on
the environment)
Land
-
C
over
(CLC)
data

and Global Monitor
ing or Environment and Security

Urban
Atlas
(GMESUA)
data.

The former has the advantage that it is fully available for the whole territory of
the EU but has
a
minimum mapping unit of 25
hectare

and a minimum width of linear elements
of
100 meters. Therefore, it is only suitable for small scale mapping applications. The second
alternative, the GMESUA data,
are a product of
a joint initiative of the European Commission and the
European Space Agency.
During the first quarter of 2011,
The

GMESUA data set covers 242 urban
regions within Europe
,
which

differ in socio
-
economic and demographic factors
.



The acquisition of GMESUA
is
based on
SPOT
-
5 satellite imag
e
s
w
ith a 10

m
multispectral and 2.5

m
panchromatic pixel resolution.

The m
ultispe
ctral data includes
a
near
-
infrared band.

Compared to
CL
C
, t
he data has a
considerably
finer resolution:
linear elements
with a width of
10

m
are mapped
and the minimum mapping unit for urban areas
is
0.25 and 0.5
5

ha

for non
-
urban areas. Thereby, 44
different land use categories are
distinguish
ed.
The advantage of high spatial and thematic resolution
is reduced by the fact
that
the
data
set i
s

only available for
selected
urban areas with more than
100.000 habitants in 2
7 different co
untries at a scale of 1:10.000
.
Figure 1

illustrates the
selected

urban regions
.

A

random
sampling was
indispensable

to keep computation feasible and consists of a
subset of about 20%, corresponding to 42 regions, to generate the training and

validation data set
.





7



Figure 1

C
ountries

covered by
GMESUA
(
dark
gray) and
the
42 randomly selected GMSEU
A

urban
regions (black).


3
Methodology


The proposed
research design

for estimation of urban land use patterns comprises application of
three
major
consecutive steps
:

1.

Data preparation
:
As a first step

it is necessary to prepare the OSM and GMESUA data such
that
both are

valuable for model building.
In particular,
a large set of potential
attributes are
derived from OSM for inductive
learning

and

the desired output
is

calculated from GMESUA

(Section 3.1)
.

2.

Selection and model building
: Second, a gen
etic algorithm (GA) is used to reduce the total set
of attributes to a reasonable subset and an artificial neural network (ANN) is
trained with
these su
bset

(Section 3.2 and 3.3)
.


8


3.

Sensitivity a
nalysis

and model performance
:

Finally,
due to the unknown
contribution of the
attributes to the model, their significance
is analyzed (Section 3.4) and the model
performance for the different
areas are

investigated
.


3.1 Data preparation


Training data for ANNs consists of a set of training samples. Each sample is a pair of an input vector
and a desired output. Therefore, it is necessary to derive input vectors from OSM data and the
desired output from the reference GMSEUA data set to learn

the intra
-
relationship between them.
However, both datasets consist of manifold and diverse information that need to be aggregated to a
normalized representation, where the choice of the areal units for aggregation is crucial and possibly,
like regression

analysis (Fotheringham
and Wong

1991
), affected by the
modifiable areal unit
problem
(Openshaw 1984). In this study, aggregation is carried out on a hexagonal raster
representation. This seems more reasonable than squarely shaped cells because hexagonal s
hapes
can better imitate European urban patterns at every scale. The side length of every hexagonal cell is
250

m
for this European
-
wide analysis, which seems a trade
-
off between computational burden and
spatial resolution, but allows the derivation of fin
e scaled urban patterns.


3
.
1
.1 GMESUA
Urban Regions as Desired Output


GMESUA subsumes continuous and discontinuous urban fabric of built
-
up areas and its respective
associated land according to its primary use. The latter is further distinguished between

degrees of
soil sealing (EEA 2010).
To derive urban areas from land use
classification
, reclassification of the
original data is required, which is an ambiguous and subjective process. While for few classes of
GMESUA a clear distinction between urban and
non
-
urban areas is obvious (e.g., category 1.1.1:
continuous urban fabric with sealing level above 80%), most classes require additional information to
achieve a clear class membership. Here, primary aerial images and local
knowledge

were used to
reclassif
y the GMESUA datasets. For each cell the overlap between the cell and the resulting urban
areas is computed and assigned as an attribute, representing the desired output for the ANN.


3
.
1
.2
D
erivation

of
OSM
Attributes (Input data)


B
asically
, OSM presents

three different types of information: geometric information, attributive
information
,

and meta
-
data

(Ramm
and Topf

2010)
. These types potentially
contain

implicitly or

9


explicitly information that can be used for urban pattern detection.

A spatial o
bject i
n OSM is
characterized by its geometric
primitive

and a set of assigned tags. A tag is a pair of a key and
additional
value
s that

represent the attributive information of
a specific

object, e.g.
a linear
geometry with the assigned
tags highway =”primary”
and oneway=”true” describe
s

a major highway
that is only accessible in one direction. Although
,

the data model of OSM is strictly specified, in
the
sense that

every user is permitted to assign arbitrary tags to an
y

objec
t.


I
t cannot be expected to signifi
cantly improve the total model performance

by including information
about sparsely mapped objects
, but instead bears the risk of overfitting. Highways and places are
assumed to be generally well mapped for most regions. However, due to the freedom of users

to
assign keys and tags at will, the
potential
number of different highway and place categories is
arbitrarily large

and thus requires certain generalization. Therefore, highways and places with a
reasonable high occurrence in OSM
2

are
exclusively conside
r
ed
. Most objects in OSM have meta
-
information assigned (e.g., the time of the last edit or the name of the user that has modified an
object
at
last). Hacklay (2010) indicated that mapping habits of people within urban areas differ from
people residing in
rural areas. Thus, it can be expected that this difference is reflected in the meta
-
information of spatial objects. The basic descriptive statistics (e.g., minimum, maximum, average) are
calculated from the meta
-
information of all considered objects raster

cell.
According to
concept

of
spatial autocorrelation, geographically close observations depend on each other

(Tobler 1970).
Thus
,

the distance
to an object predominantly

found in urban areas relates to the urbanization of an actual
raster cell

and implic
itly includes autocorrelated processes in the model
.

Hence, it is reasonable to
comprise the nearest distance to different objects, e.g. nearest highways, as an attribute for each
raster cell. For derivation of geometric and topologic attributes, it is nec
essary to distinguish
between the geometric primitives of OSM.

Of special interest are the properties of lines, mostly
representing roads. It is hypothesized that urban areas show a higher amount of total road length,
junctions, curves, and right angles be
cause of the necessity of dense traffic infrastructures in
densely
populated areas, and are consequently included as the raster cell’s attributes. Further, graph
centrality (Nieminen 1974) measures the number of nodes that link a given node. Previous studi
es by
Yang and Harry (2004) and Bak et al. (2010) have documented the
capability

of this index for street
network analysis. In conclusion, table 1
gives an overview of the
102
derived statistics

and attributes
for each cell.





2

Frequently used tags: a) highway
-
tags: residential, unclassified, tertiary, secondary, primary, motorway,
motorway_link, steps, trunk, path, track, footway, service, living_street, cycleway; b) place
-
tags:

town, hamlet,
village, suburb, locality
.


10


Table 1

Derived
OSM
attributes

for each cell

3

Attributes for
selected
highway types

Aggregated
attributes


for
selected
highways

Attributes for
selected p
lace
types

Aggregated
attributes

for
selected
highways and places

Length

Number of junctions

Number points

Number of objects

Distance

Number of junctions with at
least one right angle curve

Distance

Min./Max./Avg. version
number(s)

Curviness

Number or roads with right
angle curves

Earliest/Latest/Avg. time of
modification(s)

Number of
waypoints

Number of road endings

Total/Min./Max./Avg. number
of user contributions

M
in
.
/
Max.
/
Total
/
Avg.

a
ngle
(
s
)

Min./Max./Total/Avg. number
of object tags

M
in
./Max.
/
Total/Avg.
centrality



3.
2

Genetic Algorithm for
Attribute Selection


As
outlined
in
S
ection
2
several cell
-
based
OSM
attributes

are calculated
.
The
performance

of
ANN

models

when learning a regression function depends on the choice of attributes

(Pyle

19
99)
.

The
attributes implicitly define a pattern language (Yang and Honavar

19
97). If the language is not
e
xpressive

enough, a model will fail to capture the
information necessary
to approximate the target
function.

Contrary, i
f the language is t
o
o expressive, the computational time to learn the model
increases and
is vulnerable to overfit
t
ing
.

Due to

the large number o
f attribute
s

and the non
-
linear
relationships between th
e attributes, heuristics
are
promising
to obtain
near
-
optimal attribute sets
for
ANN
model building (
Siedlecki and Sklansky

19
89
).


Attribute
selection
approaches

can be categorized
as follows
(Liu
and Yu

20
04
)
:
The filter approach
uses statistics to measure the relevance of attributes. It
is total
ly

independent

of the learning
algorithm,
thus

it is computationally more efficient than the wrapper approach, which involves
computational overhead by exe
cuting the training algorithm for every presented attribute set

and
evaluating the results
.
Attribute selection may
not
be
independent of the

learning algorithm, which is
ignored by the filter approach.
In contrast, the wrapper approach takes the propertie
s and biases of



3

For se
lected highways and places see 2


11


the inductive
learning
algorithm into account.

B
ecause the wrapper approach is generally
computational demanding,
g
enetic algorithms
(GA)
are especially promising for attribute selection
(Siedlecki and Sklansky

19
89).


A
GA

is a heuristic o
ptimization method
,

simulating natural evolution processes
in analogy to biology
(Holland 1975; Goldberg

19
89).
GAs
represent
a potential solution as an individual.
Each individual is
encoded
by a chromosome, comprised of a set of genes.
The c
hromosomes ar
e often
coded

as a
binary string.
A set of individuals constitutes a population
.

This
population iteratively evolves, until a
stop criterion is reached.

At
each
iterative step

of the GA

the fitness of the individuals
of
the current

population
is measured
.
Afterwards, the
population for the next iterative
step

is

built by selecting,
recombining
,

and mutating t
he most promising

individuals of the current population

(Mitchell 1998)
.
Because only promising individuals take part in the evolutionary process,
it i
s likely that near
-
optimal
solutions emerge.

The final solution is chosen from the individuals of the last population.

In contrast
to
g
radient
-
d
ecent
o
ptimization
, multiple solutions are maintained in parallel within a
population
,
allowing interactions amo
ng them to explore regions in the search space between
them
(Qi et al.

19
94). The goodness of a solution, respectively fitness of an individual, is numerically evaluated by a
fitness function, which depends on the optimization objective.

To utilize GAs for

attribute selection
following the wrapper approach,
it is necessary to represent different attribute sets as individuals.
For each individual of a
population

an ANN
is trained
and its performance is
measured
, representing
the goodness of the individual
.


3.3 Artificial Neural Network


Artificial neural networks (ANNs) model an interconnected system of neurons, enabling computers to
imitate the brain’s ability to detect patterns and learn relationships within data (Fischer 1998). The
multi
-
layer perceptron

(MLP), introduced by Rumelhart et al. (1986), is one of the most widely used
ANNs (e.g.,
Fischer and Gopal

19
94; Pijanowski et al.

20
02; Mas et al.

20
04
). The MLP usually consists
of three different layers of neurons: the input layer, the hidden layer, and the output layer. Every
connection between neurons of different layers has an assigned weight, scaling input signals passing
through. The input data is

first presented to the input layer, and then subsequently passed to the
hidden layer and to the output layer in a feed forward manner. A neuron receiving the weighted
signals from connected neurons of the preceding layer, sums the signals, and calculates
an output
signal according to its inner activation function (Bishop 1996).



12


The crucial part of ANNs is the adaption of the weights, so that the model is capable to represent a
target function. The most popular way of training an ANN is by modifying its weight using the back
propagation algorithm (Rumelhart et al. 1986). This algo
rithm randomly sets the weights and
calculates the resulting output. After all data samples are presented to the network, the sum of the
mean squared error is calculated and the weights are modified according to a generalized delta rule
(Rumelhart et al. 1
986), so that the total error is distributed among the various nodes in the network.
This process of feeding forward input signals and back propagating the errors is repeated iteratively,
until a terminating condition is fulfilled (e.g. the error
-
rate fall
s below a certain threshold).


It has been shown that ANNs with one hidden layer can theoretically approximate any function
(Hornik et al. 1989). However, a certain degree of freedom must be supplied, i.e. the layer must
consist of a sufficient number of
hidden neurons. Generally, the number of hidden neurons is chosen
to minimize a trade
-
off between network bias and variance (Bishop 1995). A limitation in the use of
ANNs is that they provide a “black box” model. It is difficult to gain deep insight into t
he interior
working of an ANN by interpreting the weights of the network. Nevertheless, numerical analysis of
different input settings may help to gain insights into the importance of attributes. One primary
advantage of ANNs, compared to the more easily i
nterpretable decision trees, is the ability to model
unknown interactions between input variables, the relationship between such interactions, and any
output pattern (Pyle 1999).


3.4

Significance Analysis


Although the total set of input variables for
ANN

training are reduced by a
GA
, the relative
contribution of the remaining attributes on the total model performance is not known. However,
being aware of
the importance of
the

attribute
s

can
advance the

understanding
of
the model and its
explanatory capabi
lities. To evaluate the relative contribution of
each
attribute to the output
,

several
methods have been proposed (
Gevrey et al.

20
03;
Olden et al. 2004
).


Because of the convergence of the GA to an optimal solution, the genetic diversity of the individual
s
within a generation is generally decreasing. Consequently, it

is

hypothesize
d
that genes important to
the survival of individuals are present in most chromosomes of individuals within a generation, while
unimportant genes are spare and diverse. Thus
,

by
counting the frequency of the attributes
represented within a generation, the importance of the attributes to the output of the ANN can be
estimated. Another method to measure the importance of an attribute is to measure the change

of
root mean square erro
r

(RMSE)
when
sequentially
and
stepwise
setting input neurons to their mean

13


value

(SSMV)
.
The resulting change indicates the relative importance of each attribute

(Gevrey et al.

20
03).

Because the two

techniques
can lead to diverse conclusions, both
are ap
plied
and compared
in the next section.


4
Results

4.1 Model Specification and Overall Quality


For variable selection purposes
a non
-
dominated sorting genetic algorithm

(NSGA
-
1; Srinivas and

Deb

19
94
) was used. The algorithm was allowed to run at most 1000 iterations, but stops
earlier
if the
performance for 25 iterations does not
significantly
improve. Each generation consisted of 100
individuals. To reduce the computation time and to limit the resul
ting model to a reasonable size, the
maximum number of attributes was
set to

20 for each individual

and

is represented by

a trained ANN
model
. The training data consist of a subset of 20,000
, cells

(
4
% of the whole dataset)
, randomly
selected from all regi
ons of the dataset

(see Sec. 2)
.
The remaining cells are used for testing and
validation.
After empirical tests, t
he
final
ANN consists of a single hidden layer with








hidden
neurons, where


is the number of attributes
,
even though

the optimal num
ber of hidden neurons is
not
known. The ANN
is trained for 1,000 cycles by backpropagation with a learning rate of 0.3. The
final model is selected from the last
GA
generation, based on
the RMSE
,
the
squared correlation
coefficient (R
2
)
, Spearman’s rho

(R
S
)
,

and the number of attributes
.

The resulting model of the GA
optimization consists of 11 remaining attributes

(
d
istance to nearest residential road, length of
residential roads, number of waypoints of primary roads, length of motorways, cycleway curvines
s,
distance to nearest pedestrian road, distance to nearest track, length of tracks, number of junctions,
distance to nearest village,
and
number of attributes)
.
Overall, t
he model

showed moderate
performance with a
RMSE of 0.12, a R
2

of 0.6
,

and a R
S

of 0
.5
9
.

Applying the model on the remaining
data, which
are independent of

model building,
allows
the
investigation of

its generalization
capabilities
.
The
result

yields
a similar performance with
a RMSE of 0.12, a R
2

of 0.59
,

and a R
S

of
0.58.
A further resi
dual inspection shows a mean of
-
0.05 and standard deviation of 1.03
and
confirms

a nearly Gaussian distribution. Thus, it
attests full model
capability
.


4.
2
Regional

Model Performance


Due to the spatial heterogeneity of geographic processes, it
is
assumed

that the performance of local
model
s

changes if applied to distinct
areas
.
R
eason
s are
,

on the one hand
,

differences in
urbanization,
economic power, as well as
cultur
al issues
,

and
,

on the other hand
,

the varying quality

14


of OSM data underlying the

model. To assess the influence of locality to
the
model performance, it is
applied to each
GMESUA
region

and its generalization capabilities are examined separately
. The
results are
summarized
in Table
2
.


Table
2

Model performance for selected regions
wi
thin the

study area

Urban Region

GMESUA

Regions
4

%

of c
ells
intersecting
urban areas

RMSE

R
2

R
S

Linz

At003l

48.8

0.121

0.695

0.650

Varna

Bg003l

28.7

0.194

0.353

0.554

Ruse

Bg006l

18.4

0.125

0.440

0.483

Brno

Cz002l

31.6

0.114

0.646

0.637

Ústí nad Labem

Cz005l

35.9

0.127

0.583

0.649

Jihlava

Cz014l

21.3

0.070

0.700

0.628

Leibzig

De008l

38.6

0.135

0.627

0.700

Bremen

De012l

36.0

0.103

0.709

0.626

Darmstadt

De025l

35.8

0.126

0.757

0.710

Mönchengladbach

De036l

80.4

0.186

0.701

0.837

Koblenz

De042l

37.8

0.118

0.743

0.720

Odense

Dk003l

45.3

0.118

0.580

0.476

Valencia

Es003l

53.1

0.185

0.534

0.678

Toledo

Es016l

12.1

0.075

0.337

0.275

Cordoba

Es020l

16.5

0.108

0.538

0.492

Bordeaux

Fr007l

45.0

0.167

0.528

0.628

Rennes

Fr013l

55.0

0.119

0.590

0.449

Besançon

Fr025l

31.4

0.101

0.632

0.666

Patrai

Gr003l

26.1

0.110

0.667

0.620

Miskolc

Hu002l

24.1

0.167

0.423

0.500

Debrecen

Hu005l

25.1

0.185

0.313

0.423

Győr

Hu007l

24⸸

0⸱.4

0⸴.3

0⸵.3

䙩牥湺e

䥴I07l

40⸵

0⸱.7

0⸶.7

0⸶.9

䉯汯gna

䥴I09l

42⸱

0⸱.7

0⸴.3

0⸴.9

††††††††††††††††††††
†††††††††

4

This code allows a

clear

assignment

to the data sets.

The first two characters correspond to the particular
country according to the ISO 3166 standard.



15


Trieste

It015l

57.1

0.169

0.590

0.773

Panevėžys

L琰03l

15⸸

0⸱.1

0⸲.0

0⸲.4

Lu硥mbou牧

Lu001l

32⸱

0⸰.5

0⸶.3

0⸶.8

Liepāja

Lv002l

0⸰.

0⸰.0

0⸳.1

0⸲.2

副瑴敲摡m

N氰l3l

62⸱

0⸱.3

0⸵.8

0⸷.5

呩汢u牧

N氰l6l

60⸱

0⸲.6

0⸵.9

0⸶.8

Wrocław

P氰04l

29⸲

0⸱.9

0⸴.0

0⸵.9

Poznań

P氰05l

32⸰

0⸱.2

0⸵.9

0⸵.9

卥瓺S慬

P琰06l

57⸳

0⸲.6

0⸱.5

0⸳.0

䅶A楲o

P琰08l

52⸸

0⸲.2

0⸱.9

0⸳.0

Brăila

副008l

17⸶

0⸱.3

0⸶.6

0⸴.4

Călăraşi

副012l

19⸱

0⸱.3

0⸴.2

0⸴.0

啭日

卥S05l

0⸰.

0⸰.4

0⸴.8

0⸲.5

䉡B獫By獴物捡

卫〰3l

17⸴

0⸰.2

0⸷.0

0⸵.0

Žilina

卫〰6l

26⸸

0⸱.9

0⸵.9

0⸵.7

卨敦晩敬e

啫U10l

47⸵

0⸱.5

0⸷.9

0⸷.1

L敩捥獴sr

啫U14l

47⸹

0⸱.9

0⸷.2

0⸶.9

坯lv敲桡mpWon

啫U28l

53⸶

0⸱.8

0⸷.8

0⸷.5


䙯爠 mo獴s r敧eons 瑨W moT
敬e p敲eo牭
s

comp慲慢汹 睥汬, 睩瑨 愠 f敷 牥m慲a慢汥l 數捥灴con献

For
楮獴慮捥Ⱐ瑨攠牥杩on of
Liepāja
, Latvia
,

has

a very low RMSE

(0.06
0
)
, which means that the model
mostly predicts well. However, the

low R
2

(0.361)

and R
S

(0.202)

indicate,
that
the low RMSE

is not a
result of a good prediction of urban areas, but
certainly
cause
d

by the sparse urbanization in that
region.
The
largest
city in this region is Liepaja with a population of about 60,000, and only 3 further
towns are located in that region with mor
e than 1,000 residents.
In fact, only
8
% of all cells

are

cover
ed

at least partially
by
urban
areas
.
Additionally, OSM data is mostly absent, except for the city
Liepaja itself, thus the model necessarily failed to predict urban areas.


As a second exampl
e, t
he region of Aveiro, Portugal
,

has an exceptional high RMSE (0.242)
. The high
RMSE is caused by a discrepancy between a hi
gh density of urbanization and

sparse

OSM data in that
region.

Actually,

53% of the cells
for that re
g
i
on
are

at least partially

covered by urban structures.

Figure
2
depi
cts a

section

from this region
,

including
the city

of

Ílhavo
.
Ílhavo
has
approximately
16,800 residents. However, virtually no OSM data
are
mapped for this city

(Fig. 2 lower panel)
.

Only
the place and a single pr
imary highway
exist
, although the comparison to GMSEUA reveals, that the

16


region is densely settled

(Fig. 2 upper panel)
.

Such a

discrepancy

is, of course, reflected

in

the

performance

of the model
.




Figure 2

Urban areas
of Aveiro (Portugal)
according to
GMESUA
(
upper panel) and OSM data (lower
panel
)


However, for several regions the model performs exceptionally well.
E
specially
,

for the region of
Jihlava, Czech Republic
,

the model results
in
a very low RMSE
(0.07)
and also
a
considerably hig
h R
2

(0.7)
and R
S

(0.682)
, even though
21% of the cells are at least partially covered by urban structures

T
he good perform
an
ce
for this region indicate
s

that the quality of the OSM data suffice
the
data
requirements

of the
ANN
model.



The OSM data qualit
y of the United Kingdom is well
-
understood and it
is empirically verified
that at
least urban areas are well
-
covered in the sense of completeness (Hacklay

20
10
;

Hacklay et al.

20
10
).

17


These results are also supported by this study
as well. Generally,
high
R
2

and R
S

for all urban regions
of the
United Kingdom

are revealed
.

One
stated
key motivation of this work is to improve
completeness of OSM by machine learning, and thus improve
its
fitness for use. The developed
model is able to predict urban pattern
s
,
ba
sed on a set of attributes derived from OSM data.
Figure
3
(lower panel)
shows a successful prediction of
urban patterns

for Great Gl
e
n
(
United Kingdom
)
,
where

the model
distinguish
es

different
degrees of urbanization

based on the

underlying OSM data
.




Figure 3

Comparison between the real urban pattern based on
GMESUA
(upper panel)

and the
predicted results (lower panel) for
Great Glen, south
-
east of Leicester,
United Kingdom
.


4.2
Significance Analysis


T
o
gain
further insights into the model, the importance of the models’ attributes is evaluated.
The
respective ranks for the
two
proposed methods
(Sec. 3)
are
presented
in table
4
.


18



Table
3

Ranking of attribute importance by
SSMV

and
GA

Attribute

SSMV

GA


Change
of RMSE

Rank

Frequency

Rank

Distance to nearest residential road

0.0195

1

100

1

Length of residential roads

0.0196

2

100

1

Number of Attributes

0.0103

3

90

6

Number of junctions

0.0095

4

32

9

Distance to nearest village

0.0080

5

85

7

Distance to
nearest pedestrian road

0.0054

6

92

5

Length of tracks

0.0001

7

100

1

Number of waypoints of primary roads

-
0.0001

8

7

11

Distance to nearest track

-
0.0003

9

99

4

Length of motorways

-
0.0006

10

23

10

Cycleway curviness

-
0.0014

11

58

8



The results for both methods are
widely comparable. Both identif
y

the length of residential roads
and their distance as most significant

input variables
.
Both methods are also comparable at
identifying
less
important attributes, except the number of juncti
ons and distance to nearest tracks
,
whose ranks are complementary.
For
SSMV it is notable, that attributes with a rank less than 7 are
rather unimportant because s
etting them stepwise to constant values even improved the results.

However
, there exist also
significant
differences in the measurement of importance.

SSMV ranked
the number of attributes as very important, while for GA this attribute is only of average importance.

Anot
her major

difference between
SSMV

and GA is the ranking
of track
-
related attrib
utes.

For GA the
length of tracks and the distance to the nearest track is very important,
while for SSMV these
attributes are rather irrelevant.

Further
more
, the importance of junctions is not emphasized by GA.

4.3 Discussion


Data production in VGI is carried out by many independent contributors, increasing the chance for
occurring repetitions. It can be expected that a large number of repetitions increases the chance of
errors being detected and fixed in the data, and thus imp
roves the data quality in general (Heipke
2010). For OSM data Haklay et al. (2010) showed, that there is in fact a non
-
linear relationship
between the number of contributors and the positional accuracy. This assumption holds not for

1
9


every aspect of spatial

data quality. For completeness it is anticipated, that the number of omission
errors negatively correlates with the number of commission errors because of the diversity of user
requirements. However, the proposed methodology is based on neural computing a
nd aims to detect
urban areas using OSM data. It enables users to derive information implicitly stored in OSM,
superseding explicit storage, and thus making commission errors less likely.


The performance of the developed model varied considerably applied
to the 42 different European
regions, emphasizing the spatial heterogeneity of the data. Local models may provide better results
for individual geographic regions, but do not capture general properties of the data well. Although
the developed model depends

on data that is mostly mapped in OSM, it necessarily fails, if such data
is missing at all. Therefore, to apply the presented methodology it is necessary to make assumptions
on the presence of valuable information. Delineating urban patterns is subject to

individual
considerations. Thus, the validity of the presented methodology for predicting density
-
based
patterns of urban areas is a difficult task, although the results are coherent and visually appealing. In
general, the validity of the results must be
evaluated with respect to the intended application.


Machine Learning can only respond to geographic characteristics if those are encoded in the data
(Gahegan 2003). It is
a priori
unclear how to encode information in the dataset to give reasonable
result
s. Furthermore, t
he
settings

of

the ANN and GA in this study are
primarily

chosen a priori.
However, a detailed inspection and sensitivity analysis of the different settings bear potential for
making the model more robust and yield better results (see Patu
elli et al. 2010).

A fundamental
problem of spatial data analysis on lattice data is the dependence of the results on the underlying
scale and zoning (Openshaw 1984). The influence of the cell size on the results of prediction was not
subject of this study
, but needs more research.


6

Conclusion
s

and Future Work


In this study a methodological framework is proposed for the delineation of continuous urban areas
from OSM data.
Each of the framework’s components provides solely distinct capabilities. The
ANN

enables the non
-
linear estimation of urban patterns from a set of attributes. The
GA

reduces the
total set of attributes to a reasonable size for inductive learning following the wrapper approach,
thus that no
precise

understanding of the processes is
man
datory
. The usefulness of the
methodology was demonstrated by applying it to the estimati
on of urban patterns of Europe.



20


It was shown, that urban patterns can be predicted to a large extend. Explicit information about
urban patterns and urban density is u
seful for manifold applications, e.g. navigation
and spatial
planning
tasks, but is
currently
mostly absent in OSM. By estimating the urban density with the
proposed framework the
fitness for use

in OSM for applications
is
improved, leading to additional
b
enefit for users.


Future work will elaborate on the application of machine learning to OSM data. OSM offers a rich
and
manifold
source of

spatial data, offering a profound pool of implicit information. Extracting this
information
from OSM
and making it explicit
improve
s

the fitness for

use

and overwhelm
completeness issues in the data

for manifold applications and requirements. Additionally, machine
learning bears potential for detection of
other data quality issues, e.g. positional or sema
ntic errors
.

From a methodological point of view it seems fruitful to include further machine learning techniques
that
in particular
take
into
account the spatial and t
emporal properties of OSM data.

Acknowledgements


We acknowledge the valuable feedback r
eceived from
our
colleague
s
Georg Walenciak
,
Marcus Götz
,
Bernhard Höfle, and
Alexander Zipf on an early draf
t

of this paper. In addition, we want to thank
Hannes T
aubenb
ö
ck

(German Aerospace Center,
DLR
) for his useful hints for appropriate remote
sensing

data.


Reference


Bak P, Omer I and Schreck T 2010 Geospatial thinking. Painho, M, Santos, M Y & Pundt, H, (eds)
Geospatial Thinking
. Springer, Berlin: 25
-
42


Bishop C M 1996
Neural Networks for Pattern Recognition
. New York, Oxford University Press


Bra
ssel K, Bucher F and Stephan E
-
M 1995 Elements of Spatial Data Quality. . Pergamon, Oxford: 81
-
108


Buttenfield B 1993 Representing data quality.
Cartographica: The International Journal for
Geographic Information and Geovisualization

30: 1
-
7


Delavar M R and Devillers R 2010 Spatial data quality: From process to decisions.
Transactions in GIS

14: 379
-
386


Devillers R, Stein A, Bédard Y, Chrisman N, Fisher P and Shi W 2010 Thirty years of research on spatial
data quality: Achievements, failures,

and opportunities.
Transactions in GIS

14: 387
-
400


EEA 2010 Mapping guide for a European urban atlas. WWW document,

21


http://www.eea.europa.eu/data
-
and
-
maps/data/urban
-
atlas/mapping
-
guide


Elwood S 2008 Volunteered geographic information: Key questions, co
ncepts and methods to guide
emerging research and practice.
GeoJournal

72: 133
-
135


Fischer M M 1998 Computational neural networks: A new paradigm for spatial analysis.
Environment
and Planning A

30: 1873
-
1891


Fischer M M and Gopal S 1994 Artificial neural networks: A new approach to modelling interregional
telecommunication flows.
Journal of Regional Science

34: 503
-
527


Fotheringham A S and Wong D W S 1991 The modifiable areal unit problem in multivariate stat
istical
analysis.
Environment and Planning A

23: 1025
-
1044


Gahegan M 2003 Is inductive machine learning just another wild goose (or might it lay the golden
egg)?
International Journal of Geographical Information Science

17: 69
-
92


Gevrey M, Dimopoulos I a
nd Lek S 2003 Review and comparison of methods to study the
contribution of variables in artificial neural network models.
Ecological Modelling

160: 249
-
264


Girres J
-
F and Touya G 2010 Quality assessment of the French OpenStreetMap dataset.
Transactions
i
n GIS

14: 435
-
459


Goldberg D E 1989
Genetic Algorithms in Search, Optimization and Machine Learning
. Boston, MA,
Addison
-
Wesley Longman Publishing Co., Inc.


Goodchild M F 2008 Spatial accuracy 2.0. In
Proceedings of the Eighth International Symposium on
Spatial Accuracy Assessment in Natural Resources and Environmental Sciences
. Liverpool, World
Academic Union: 1
-
7


Goodchild M F 2007 Citizens as sensors: The world of volunteered geography.
GeoJournal

69: 211
-
221


Goodchild M F and Hunter G J 1997 A simple positional accuracy measure for linear features.
International Journal of Geographical Information Science

11: 299
-
306


Haklay M 2010 How good is volunteered geographical information? A comparative study of
OpenSt
reetMap and Ordnance Survey datasets.
Environment and Planning B: Planning and Design

37: 682
-
703


Haklay M, Basiouka S, Antoniou V and Ather A 2010 How many volunteers does it take to map an
area well? The validity of Linus’ law to volunteered geographic
information.
The Cartographic Journal

47: 315
-
322


Haklay M and Weber P 2008 OpenStreetMap: User
-
generated street maps.
IEEE Pervasive Computing

7: 12
-
18


Heipke C 2010 Crowdsourcing geospatial data.
ISPRS Journal of Photogrammetry and Remote Sensing

65: 5
50
-
557


Helbich H and Leitner M 2010 Postsuburban spatial evolution of Vienna's urban fringe: Evidence from
point process modeling.
Urban Geography

31: 1100
-
1117


22



Helbich M and Leitner M 2009 Spatial analysis of the urban
-
to
-
rural migration determinants in

the
Viennese metropolitan area. A transition from suburbia to postsuburbia?.
Applied Spatial Analysis
and Policy

2: 237
-
260


Holland J 1992
Adaptation in Natural and Artificial Systems: An Introductory Analysis with
Applications to Biology, Control, and A
rtificial Intelligence
. Cambridge, MA, MIT Press


Hornik K, Stinchcombe M and White H 1989 Multilayer feedforward networks are universal
approximators.
Neural Networks

2: 359
-
366


Jiang B and Harrie L 2004 Selection of streets from a network using self
-
org
anizing maps.
Transactions in GIS

8: 335
-
350


Jiang B and Jia T 2011 Zipf’s law for all the natural cities in the United States: A geospatial
perspective.
International Journal of Geographical Information Science

(accepted)


Kresse W and Fadaie K 2004
ISO
Standards for Geographic Information
. Berlin, Springer


Leung Y 1987 On the imprecision of boundaries.
Geographical Analysis

19: 125
-
151


Mas J F
,

Puig H
,

Palacio J L and Sosa
-
López A 2004 Modelling deforestation using GIS and artificial
neural networks.
Environmental Modelling & Software

19: 461
-
471


Maué P and Schade S 2008 Quality of geographic information patchworks. In

11th AGILE
International Conference on Geographic Information Science
.


Neis P and Zipf A 2008 OpenRouteService.org is three times "Op
en": Combining OpenSource, OpenLS
and OpenStreetMaps. In

GIS Research UK
. Manchester


Nieminen J 1974 On centrality in a graph.
Scandinavian Journal of Psychology

15: 322
-
336


Olden J D
,

Joy M K and Death R G 2004 An accurate comparison of methods for quan
tifying variable
importance in artificial neural networks using simulated data.
Ecological Modelling

178: 389
-
397


van Oort P 2006 Spatial Data Quality: From Description to Application. PhD thesis, Wageningen
University


Openshaw S and Openshaw C 1997
Arti
ficial Intelligence in Geography
. New York, NY, Wiley


Over

M,

Schilling A
,

Neubauer S and Zipf A 2010 Generating web
-
based 3D city models from
OpenStreetMap: The current situation in Germany.
Computers, Environment and Urban Systems

34:
496
-
507


Patuelli
R
,
Reggiani A
,
Nijkamp P and Schanne N 2011 Neural networks for regional employment
forecasts: Are the parameters relevant?
Journal of Geographical Systems

13: 67
-
85


Pijanowski B C
,
Brown D G
,

Shellito B A and Manik G A 2002 Using neural networks and GIS to
forecast land use changes:
A

land transformation model.
Computers, Environment and Urban
Systems

26: 553
-
575


Pyle D 1999
Data preparation for data mining
. San Francisco, CA, Morgan Kaufmann

Publishers Inc.


23



Qi X and Palmieri F 1994 Theoretical analysis of evolutionary algorithms with an infinite population
size in continuous space. Part I: Basic properties of selection and mutation.
Neural Networks, IEEE
Transactions on

5: 102
-
119


Ramm

F

an
d
Topf J 2010
OpenStreetMap: Using and Enhancing the Free Map of the World
. UIT
Cambridge


Roick O and Hagenauer J 2011 OSMatrix
-

Grid
-
based analysis and visualization of
OpenStreetMap.
State of the Map 2011 The 5th Annual International OpenStreetMap
Conference
,
Vienna, Austria

(submitted)


Rozenfeld

H D, Rybski D, Gabaix X and Makse H A 2009 The area and population of cities: New
insights from a different perspective on cities. National Bureau of Economic Research, Inc., NBER
Working Papers

No
15409


Rumelhart D E, Hinton

G E and Williams R J 1986 Learning representations by back
-
propagating
errors.
Nature

323: 533
-
536


Servigne S, Lesage N and Libourel, T 2010
Quality Components, Standards, and Metadata
Fundamentals
In Devillers R and Jeansoulin R
(e
d
s
) Fundamentals of Spatial Data Quality
.

London,
ISTE: 179
-
210


Shi

W,

Goodchild M and Fisher P 2002
Spatial data quality
. New York, Taylor & Francis


Siedlecki W and Sklansky J 1989 A note on genetic algorithms for large
-
scale feature selection.
Pattern
Recognition Letters

10: 335
-
347


Smith T R 1984 Artificial intelligence and its applicabilty to geographical problem solving.
The
Professional Geographer

36: 147
-
158


Srinivas N and Deb K 1994 Multiobjective optimization using nondominated sorting in genet
ic
algorithms.
Evolutionary Computation

2: 221
-
248


Tobler W R 1970 A computer movie simulating urban growth in the Detroit region.
Economic
Geography

46: 234
-
240


Yang J and Honavar V 1998 Feature subset selection using a genetic algorithm.
Intelligent Sy
stems
and their Applications, IEEE

13: 44
-
49


Zielstra D and Zipf A 2010 A comparative study of proprietary geodata and volunteered geographic
information for Germany.
13th AGILE International Conference on Geographic Information Science
,
Guimaraes, Portug
al


Guptill S C and Morrison J L (eds) 1995
Elements of Spatial Data Quality
. Oxford, Pergamon


Moellering H (ed) 1987
A Draft Proposed Standard for Digital Cartographic Data
. Columbus, OH,
National Committee for Digital Cartographic Standards