20 International Journal of Applied Geospatial Research, 2(3), 20-31, July-September 2011

A Neural Network for

Modeling Multicategorical
Parcel Use Change
Kang Shou Lu, Towson University, USA
John Morgan III, Towson University, USA
Jeffery Allen, Clemson University, USA

ABSTRACT
This paper presents an artificial neural network (ANN) for modeling multicategorical land use changes.
Compared to conventional statistical models and cellular automata models, ANNs have both the architecture
appropriate for addressing complex problems and the power for spatio-temporal prediction. The model consists
of two layers with multiple input and output units. Bayesian regularization was used for network training in
order to select an optimal model that avoids over-fitting problem. When trained and applied to predict changes
in parcel use in a coastal county from 1990 to 2008, the ANN model performed well as measured by high
prediction accuracy (82.0-98.5%) and high Kappa coefficient (81.4-97.5%) with only slight variation across
five different land use categories. ANN also outperformed the benchmark multinomial logistic regression by
average 17.5 percentage points in categorical accuracy and by 9.2 percentage points in overall accuracy.
The authors used the ANN model to predict future parcel use change from 2007 to 2030.
Keywords:

GIS, Land Use, Neural Networks, Parcel Use, Spatial Modeling

INTRODUCTION
Land use change has been a major cause of many
environmental problems. Changes are often
necessary to accommodate population growth
and economic development. Degraded environments, however, threaten sustainable development. As more states and local governments are
willing to create and implement smart growth
strategies, planners and policy makers need to

DOI: 10.4018/jagr.2011070102

know the impacts of future land use change and

related regulatory decisions. Predictive modeling is not only a learning tool to understand
causal factors and dynamic changes of a land
use system, but also an important mechanism
to predict future changes and simulate the potential effects under different growth scenarios
(Pijanowski et al., 2002).
Despite the emergence of numerous predictive models over the last half-century, our
ability to accurately predict land use change
remains limited. Recently, 18 scientists jointly
conducted an evaluation of the performance of

Copyright 2011, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

International Journal of Applied Geospatial Research, 2(3), 20-31, July-September 2011 21

nine land cover/land use models applied in 13

regions (Pontius et al., 2008). These models
included conventional logistic regression (McConnell, Sweeney, & Mulley, 2004), cellular
automata based SLEUTH (Dietzel & Clarke,
2004; Silva & Clarke, 2002), multiple agent
based SAMMBA (Boissau & Castella, 2003;
Castella, Trung & Boissau, 2005), multistage
model CLUE and its variant CLUE-S (Duan
et al., 2004; Verburg et al., 2002; Veldkamp
& Fresco, 1996; Verburg & Veldkamp, 2004),
and multifunctional LTM (Pijanowski et al.,
2005), multiple objective GEOMOD (Pontius,
Cornell & Hall, 2001; Pontius & Malanson,
2005; Pontius & Spencer, 2005). It was found
that prediction accuracy, as measured in percent
of the correctly predicted against the observed,
falls within a range of 1-73 percent, falling below
30 percent in seven cases and above 50 percent
only in three cases. Some of the assessments
were against the sample datasets used for model
calibration or training. But judging on these
results, how much can we trust the predictions
of the models?
Pontius et al. (2008) point out that something must be wrong with the mechanics of these
models. We attribute the poor performances
more to the oversimplification of complex
land use systems in both semantics and syntax.
Semantically, most models, particularly cellular
automata models, tend to overemphasize parsimony and use too few predictive variables
to truly represent complex reality. It may not
be a coincident that SLEUTH, constructed with
only three effective predictive variables, is the
worst performer among all the models examined
by Pontius et al. (2008). Although there is no
suggested threshold for how many predictive
variables are deemed appropriate, a good model
should include variables that measure key drivers of changes in land use such as population,
economy, and technology (Turner & Meyer,
1994). More importantly, the model should be
able to generate meaningful predictions, and
pass the reality test.
From the syntax perspective, most existing
models, particularly conventional statistical
models, lack the multilayered, hierarchical,

interconnected structure needed for modeling

complex land use systems as Batty and Torrens
(2005) have suggested. Multiple layers mimic
the processes of land use changes that involve
land transaction, speculation, and development;
whereas interconnections through these layers
capture the interrelationships and interactions
between dependent and independent variables,
whether they are observable, quantifiable or
comprehensible. The CLUE (-S) model is to
some degree structured in this way and thus
performed relatively well (Pontius et al., 2008).
Batty and Torrens (2005) did not provide specific suggestions about what algorithms to use
and how to derive them in order to describe
such interrelationships and implement the
framework. The structure of the conceptual
model, however, implicitly points to an artificial
neural network (ANN) approach which does
offer such capabilities.
This paper presents an artificial neural
network (ANN) for modeling multi-categorical
parcel use changes. We intended to improve
the model by: 1) incorporating more effective
predictor variables for a better semantic representation; 2) expanding the model structure for a
multiclass land use system; 3) using a multilayer
neural network to enhance predictive power;
and 4) applying a Bayesian regularization (BR)
training algorithm to avoid the over-fit problem.
We applied the model in Beaufort County, South
Carolina, to predict and simulate future land
use changes from 2000 to 2030 under different
growth scenarios.

BACKGROUND
ANNs have been around since the early 1940s,
but it was not until the mid 1990s that they were
introduced into the geosciences for spatial interaction, interregional telecommunication, resource management, suitability assessment, and
image classification (Fischer & Gopal, 1994;
Openshaw, 1993). Openshaw and Openshaw
(1997) identified four major benefits of neural
networks for modeling: better performance,
greater representational flexibility and freedom

Copyright 2011, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

22 International Journal of Applied Geospatial Research, 2(3), 20-31, July-September 2011

from current model design constrains, the opportunity to handle explicitly noisy data, and
the incorporation of spatial dependency in the
net representation (which is currently ignored).
Researchers in land use modeling have been
a half-decade slower in realizing such benefits.
Pioneering studies mainly focus the use of
ANNs for simulating the change in urbanization
patterns (Li & Yeh, 2001; Pijanowski, Gage, &
Long, 2000; Pijanowski et al., 2002; Yeh & Li,
2002). Pijanowski et al. (2005) later incorporated an ANN as one of the three components
of the Land Transformation Model (LTM), and
applied it in several other areas. Allen and Lu
(2004, 2006) found that ANN models not only
attained fair to high prediction accuracy but also
outperformed the logistic regression in several
applications in coastal regions. They also found
that ANN models were capable of discerning
isolated, sparsely distributed features or events
that other models often fail to predict. Land
use systems modeled in these studies are all
binary. It remains to be tested whether ANNs
can achieve similar success in predicting multicategory land use change.

Figure 1 provides both a graphic illustration

and mathematic notations (MatLab) of a twolayer feedforward neural network appropriate
for land use prediction. The network has R
input units, S1 hidden units and S2 output units.
The connectors between the input units and the
hidden units are input weights, collectively
denoted by IW1,1, which is a R x S1 matrix. The
superscripts represent the destination and source
of a connector. The connectors between hidden
units and output units (second layer) are layer
weights, denoted by LW2,1, which is a S1x S2
matrix. Each unit in the hidden layer or output
layer has a bias term, b1 or b2. They together
form a bias vector, b1 or b2. The input vector is
p, whereas a1 and a2 are the output vectors for
the hidden layer and output layer, respectively.
The vector a2 is also the output of the whole
network; f1and f2 are transfer functions for the
hidden layer and output layer, respectively. A
logistic function is often used as transfer function for classification problems.
The prediction starts from left to right.
First, each hidden unit sums with its own bias
b1 the product of the input value and correspond-

Figure 1. A two-layer feedforward neural network for modeling multi-categorical land uses

Copyright 2011, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

International Journal of Applied Geospatial Research, 2(3), 20-31, July-September 2011 23

ing weight lw1,1 from every input unit p. Then,

a transfer function, f1, is applied to the sum n1
before its output a1 is sent to every unit of the
output layer. Each unit of the output layer repeats
the process, but uses the output of every hidden
unit as the input. The result is the output, a2, or
prediction of the network. This process is also
called feedforward prediction. For this approach, the determination of the weights and
biases for multilayer networks used to be a
challenge until recently.
A backpropagation training algorithm
(Rumelhart et al., 1986) makes it possible to
automatically derive the weights and bias for
a neural network by learning from a sample.
It starts with random weights and bias and
proceeds with the feedforward prediction.
The prediction error, the difference between
the output value and the observed value (often
called the target value), is then calculated.
The error is redistributed backward to every
hidden unit based on a gradient descent rule.
The information is then used for updating the
corresponding weight and bias for every unit at
a certain correction rate before starting another
cycle for the next input-target pair. The entire
process that goes through every pair in a sample
dataset is an epoch. It usually takes many epochs
before a network achieves a desirable goal and
stops training. The backpropagation method has
revitalized neural network sciences and marks
the second generation of neural computation
(Penny et al., 1999).
Many new algorithms have been developed
for increasing the training speed, maximizing
approximation capability, or avoiding overfitting problems. One such innovative algorithm
is the Bayesian Regularization (BR) developed
by MacKay (1992). Instead of minimizing
just sum of squared error (SSE) as the training
objective, BR incorporates sum of squared
weights (SSW) into the performance function
by using two additional parameters ( and )
for regularizing SSE and SSW, respectively.
Built upon Bayesian probability framework,
BR is capable of 1) determining all parameters
based on the posterior probabilities conveyed in
the sample data, 2) automatically selecting an

optimal model that avoids over-fitting problems

for better generalization, and 3) retaining great
approximation power once sufficiently trained.
It is no longer necessary to split a sample into
three subsets for training, testing, and validation
as an essential technique to avoid over-fitting
problems.

METHODS
Study Area
Beaufort County, South Carolina, was selected
as the study area. It is a well-known coastal
tourist destination. The county covers 923 mi2 in
area, with 63 percent land and 37 percent water.
Driven by tourism development, new immigration, service sector expansion, and military
demand, Beaufort County has seen tremendous
growth in population, urban area, and impervious surface over the past two decades. From
1990 to 2000, its population increased by 39.93
percent, from 86,425 to 120,935. This growth
rate triples the national average (13 percent)
and leads all counties in South Carolina. From
1990 to 2008, the total number of built parcels
increased by 136.4 percent from 23,446 to
56,929. Impervious surface almost quadrupled
(380 percent) in the fast growing Bluffton area.
The land conversion rate has been high, with an
average of 2,575 parcels (1,500 acres) per year
over the last decade. As one of the top seven
retiree communities in the US, the county is
expected to continue growing at a rapid pace.
These changes impose tremendous pressure on
natural environments, local infrastructure, and
public services. There is a tremendous demand
for predictions and impact assessments needed
for smart growth decisions.

Neural Network Specification

We used a two-layer, feedforward neural network with 18 x 18 x 5 architecture to model a
five-class parcel use system. The five output
units included commercial, urban residential,
rural residential, recreation (golf course), and
undeveloped, all of which are binary (1 or 0).

Copyright 2011, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

24 International Journal of Applied Geospatial Research, 2(3), 20-31, July-September 2011

Each parcel is assigned to one type of use, and

each parcel is encoded by a vector of five elements. For example, if a parcel was developed
for commercial use, it was coded as (1, 0, 0, 0,
0). Input units represent 18 independent variables listed in Table 1. The number of hidden
units was initially set to 18, but may change,
depending on the BR training result.
We used a logistic function, f = 1 / (1+ exp
(- x)), as the transfer function for all layers, and
a softmax function, yj = exp (- xj) / exp (- xk),
for land transition probability and output classification. The former allows us to simulate
parcel changes under different scenarios. The
BR algorithm is available in the Neural Network
Toolbox of Simulink 8 (MatLabtm). We wrote
scripts to enable data input, classification, and
error assessment. Several ArcGIS-based submodules were developed for sample extraction,
data processing, and spatial prediction.
Performance of the ANN was assessed in
measures of: 1) mean squared error (MSE),
sum of squared error (SSE), and sum of squared
weights (SSW); 2) prediction accuracy; and
3) the Kappa coefficient. Multinomial logistic
regression was used as a benchmark model for

comparisons. We have also assessed the effects

of predictor variables.

Data Preparation
Parcel use in 2008 was derived from the parcel
shape file (ESRI, Inc., Redlands, California)
and Tax Assessors Table provided by Beaufort
County. We grouped parcel uses into five general
categories: 1) commercial, including all commercial, industrial, institutional, and service/
utility uses; 2) urban residential, including all
developed accommodation use < 5 ac; 3) rural
residential, with parcel size falling between 5-10
ac; 4) recreational (only golf courses); and 5)
undeveloped, including wetlands, open space,
forestlands, croplands, parks and reserves,
and other preserved and protected lands. Of
a total 99,781 parcels, 33,250 (33.32 percent)
were developed or built between 1990 and
2008. We call this new development or net
change for model validation. Because of rich
temporal information, we were able to derive
changes on an annual or decadal basis for different land uses, periods, and regions. We used
the growth rates for three different lengths of

Table 1. Predictor variables

Group

Independent Variables

Physical properties

land area
wetland ratio
slope
distance to water front
forest wetland

Road accessibility

cost distance to major road

distance to local street

Proximity to utilities

distance to waterline
and distance to sewer line

Neighborhood effects

cost distance to central business district

developed parcels
distance to built parcels
agricultural use

Demographic features

block population
block neighborhood population

Land value

parcel land value

total property values

Land ownership

private ownership

Copyright 2011, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

International Journal of Applied Geospatial Research, 2(3), 20-31, July-September 2011 25

periods to simulate future changes: 1980-2008,

1990-2008, and 2000-2008.
We prepared two sets of data for all predictive variables, 1990 for model training, and 2008
for future prediction. National Wetland Inventory data from 1989 were used to extract forested
wetland, land area, and wetland ratio. Slope
was derived from the 30 m DEM downloaded
from USGSs National Map Seamless Server.
Block population data were from Census Data
1990 and 2000. Beaufort County provided the
updated data for roads and streets from which
proximity and coast distance variables were
derived. Waterline and sewerline layers were
from South Carolina Department of Commerce.
Protected lands were downloaded from the
Natural Resources GIS Data Clearinghouse of
the South Carolina Department of and updated
by using the 2008 parcel data. The tax assessor
file was the source for building counts, built
year, parcel size, land price, land value, and
land ownership at the finest spatial units. Since
the coastal area is highly fragmented by water
bodies and wetlands, we constructed two cost
distance variables to measure the influences of
major roads and central business district over a
cost surface created by weighting these natural
barriers more as frictional factors.
All data were aggregated in parcel units
and the parcel shape file was joined with the tax
assessors table. Most distances were measured
from the centroid of a parcel, but distance to
waterfront is the zonal average of the grids
Euclidian distances to a parcel. Data for each
independent variable were scaled to a range
between 0 and 1 by using the same set of minmax values for both training and prediction sets.
The training dataset was extracted by using
a pseudo-stratified systematic random sampling
method. The strata are five land use classes, but
subsample size for each stratum is not purely
proportional to the total number of parcels,
but proximately proportional to the total area
of the stratum in concern. The sample size (S)
for the entire training set was estimated based
on the formula S=Nw / Et where Nw is the total
number of weights including biases, and Et is
the targeted error threshold. The final training

sample includes 7,812 parcels, accounting for

nearly 8 percent in number and 17 percent in
area of all parcels in the county. We also prepared four more datasets for model validation
and testing. They included two sample sets, a
net change set, and the full dataset. The first
three sets accounted for 20 percent, 10 percent,
and 33 percent of the total number of parcels
in the county respectively.

RESULTS
Model Performance
We performed multinomial regression analysis
in a preliminary study to screen predictive
variables. Eighteen of the variables included in
the preliminary study were found statistically
significant and thus used to construct the ANN
model. Based on the 4:2:2 ratios, the training
sample was split into three subsets for training,
validation, and testing, respectively, during the
training process. The training process stopped
within 100 epochs in several runs. MSE is
0.018 for the training subset and 0.038 for both
testing and validation subsets. Results of BR
suggest that an optimal model with 415 effective
parameters (18 x 17 x 5) would be adequate.
The ANN model performed well against
the training dataset (Table 2). The prediction
accuracy, overall or categorical, is quite impressive as measured in terms of correct percent
(82.0-98.5 percent) and Kappa coefficients
(0.81-0.98), particularly for a change of 33.3
percent over newly two decades. Kappa coefficient is considered a conservative measure of
agreement with chance corrected, and a value
above 0.80 suggests an excellent prediction.
Although both accuracy and Kappa tend to
increase with the total number of parcels within
the category, their variations across different
land uses are relatively small.
The benchmark MLR was also statistically significant based on the likelihood ratio
tests (Chi-square = 11,100, df = 76, p < 0.001).
It was, however, outperformed by the ANN
model in all measurements (Tables 2 and 3).
The ANN model improved prediction accuracy

Copyright 2011, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

26 International Journal of Applied Geospatial Research, 2(3), 20-31, July-September 2011

Table 2. Prediction accuracy of the ANN model against the training sample
Observed

Predicted
I

II

III

IV

Row Total

Accuracy
(%)

Kappa

511

24

24

574

89.0

0.88

II

12

2815

30

14

2877

97.8

0.97

III

10

22

866

38

943

91.8

0.91

IV

218

34

266

82.0

0.81

16

11

18

3105

3152

98.5

0.98

Column total

553

2877

943

242

3197

7812

96.2

0.94b

Notes: I=Commercial, II=Urban residential, III=Rural residential, IV=Golf course, and V=Other use.
a. Overall prediction accuracy, b. Overall kappa coefficient.

by an average of 17.5 percentage points across

the five uses and by 9.2 percentage points in
overall. The two numbers are even more impressive for Kappa coefficients (0.19 and 0.14). The
greatest improvement occurred where MLR
failed to generate satisfactory results, by 33.6
and 32.2 percentage points for commercial and
rural residential respectively.
Results of model validation against four
different datasets are summarized in Table 4.
Overall accuracy is high in all cases (> 94.9
percent) with only little variation (< 1.3 percentage points) across different cases. For all but
net change validation, prediction accuracy
dropped only by average 2.4 percentage points
in all 19 measurements with a range of 0.8-2.6
percentage points. The net change case is an
exception because we observed three extreme

discrepancies: the largest jump (+12.2), the

smallest drop (-1.2), and the largest drop (-11.1)
in prediction accuracy from those for the training set. ANNs predictive ability did not show
a consistent decay pattern which was not expected.

Predicted Changes
The predicted long-term trajectories for parcel
development are shown in Figure 2. They reflect
quantitative demands at three different growth
rates. We used 2008 data as the new input of
the trained ANN model to predict land transition probabilities for five parcel uses. These
two types of information were used to map
future change through 2030. Figure 3 shows
the distribution of predicted parcel use changes

Table 3. Prediction accuracy of the MLR model against the training sample
Observed

Predicted

Row Total

Accuracy
(%)

Kappa

35

574

55.4

0.53

II

III

IV

318

197

12

12

II

19

2659

50

146

2877

92.4

0.88

III

74

147

562

156

943

59.6

0.56

IV

13

24

177

47

266

66.5

0.66

52

3083

3152

97.8

0.96

Column total

429

3079

637

200

3467

7812

87.0a

0.80b

Notes: I=Commercial, II=Urban residential, III=Rural residential, IV=Golf course, and V=Other use.
a. Overall prediction accuracy, b. Overall kappa coefficient.

Copyright 2011, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

International Journal of Applied Geospatial Research, 2(3), 20-31, July-September 2011 27

Table 4. Prediction accuracy (%) of the ANN model in four validations

Parcel Use
Category

Training Set

Validation Sets
Use-based

Area-based

Net Change a

Full Set

89.0

86.6

83.8

79.2

87.1

II

97.8

96.5

96.5

96.6

96.2

III

91.8

88.5

84.9

80.7

87.4

IV

82.0

79.8

77.6

94.2

80.6

98.5

97.7

97.6

Overall

96.2

96.4

96.1

97.7
94.9

96.2

Notes: I=Commercial, II=Urban residential, III=Rural residential, IV=Golf course, and V=Other use.
a
Category V or Other use is treated as the background category and is thus not applicable in this case.

for selected classes and areas under selected

growth rates and constraints. Table 5 provides
a quantitative summary of simulated regional
development with and without a growth boundary constraint.

DISCUSSION AND
CONCLUSION
A neural network was applied to predict parcel
use change in Beaufort County, South Carolina.
The model is not only theoretically appropriate

for addressing complex problems, but also has

demonstrated improved predictive capability.
The accuracy ranges from fairly good to excellent in all 29 measurements, regardless of variations in land use category, sample set, parcel
size, and time span. The ANN outperformed
both benchmark MLR and models evaluated by
Pontius et al. (2008). A critique of ANNs is the
over-fitting problem. But this problem, if present, might have been kept to minimal in our case,
due to the use of BR and large training sample.
Cross-validations do not show any substantial

Figure 2. Predicted trajectories of parcel development in Beaufort County at three different

growth rates

Copyright 2011, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

28 International Journal of Applied Geospatial Research, 2(3), 20-31, July-September 2011

Figure 3. Predicted parcel use changes in Beaufort County from 2000 to 2030 under different
growth scenarios

drops in prediction accuracy nor suggest any

pattern of variations across different sample sets
and land uses. It was found again that ANNs
enable us to predict rare, sparsely distributed
events with the level of accuracy other models
often fail to reach (Allen & Lu, 2006).
The use of parcels as objects to be modeled
and as units of analysis has brought both benefits
and issues. This approach adds more realism to
our modeling practice because of the use of real

world units for land transaction and development (Landis, 1994). Many parcel attributes
are predictive variables with measurements
that can be readily incorporated into a model
to improve model semantics and prediction
accuracy. Also, many property variables are
spatially well-defined by parcel boundaries and
no additional error is induced by aggregation
or disaggregation. For the same reason, it is
less difficult to interpret the modeling results.

Copyright 2011, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

International Journal of Applied Geospatial Research, 2(3), 20-31, July-September 2011 29

Table 5. Potential impact of the growth boundary on regional development in Beaufort County
Growth Boundary
Region

Yes

Gain (or Loss)

No

Yes-No

Area

Area

N%

Area%

5132

4592

-100

-100

S Beaufort Islands

2726

2038

1664

875

64

133

Hilton Head

5239

3968

4884

3035

31

NE Corner

958

1341

-100

-100

Port Royal-City of Beaufort

10332

8148

9631

5945

37

Bluffton

9404

7318

8687

5677

Entire County

27701

21472

30956

21466

-11

St Henna Island

29
a

<1a

Notes: Prediction is based on the 1990-2008 growth rate. Area units are acres.
a
Discrepancies are caused by variable parcel sizes due to the use of area-based demand.

Four issues we have encountered are related to

large parcel partitioning, vector data processing,
parcel use classification, and data availability.
How to model the large parcel partitioning
process remains to be a technical challenge.
The predicted trajectories and growth patterns have policy implications. The anticipated
urban growth ratio is relatively moderate (2:13:1) compared to that (6:1) for the Charleston
area (Allen & Lu, 2003). Potential impacts
of land development can be relatively severe
because Beauforts physical environment is
very fragmented and ecological systems are
quite vulnerable. While new development is
continuously spreading in the urban fringe areas,
infill development is expected to intensify in
previously sprawled regions. Over time, development will change the image of the county as
a well vegetated, properly landscaped tourist
destination. The simulation results suggest
caution in implementation of a growth boundary. The policy may be able to preserve natural
areas and farm lands in North Beaufort, but it
has a potential risk of driving land conversion
and environmental change in many peripheral
islands in South Beaufort too fast for coastal
terrestrial and aquatic life to adapt. Incentives
should be in place in order to regulate such
developments.

ACKNOWLEDGMENT
We would like to thank South Carolina Sea
Grant and NOAAs National Centers for Coastal
Ocean Science for funding this project.

REFERENCES
Allen, J. S., & Lu, K. S. (2006). Predicting trajectories
of urban growth in the coastal Southeast. In G. S.
Kleppel, M. R. Devoe & M. V. Rawson (Eds.), Changing land use patterns in the coastal zone: Managing
environmental quality in rapidly developing regions
(pp. 47-67). New York, NY: Springer.
Allen, J. S., & Lu, K. S. (2003). Modeling and prediction of future urban growth in the Charleston region
of South Carolina: A GIS-based integrated approach.
Conservation Ecology, 8(2), 120.
Allen, J. S., & Lu, K. S. (2004). Artificial neural
network vs. binary logistic regression: Two alternative models for predicting urban growth in the Myrtle
Beach region. Paper presented at the NOAAs Land
Use-Coastal Ecosystem Study (LU-CES) Program.
Batty, M., & Torrens, P. M. (2005). Modeling and
prediction in a complex world. Futures, 37(7),
745766. doi:10.1016/j.futures.2004.11.003

Copyright 2011, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

30 International Journal of Applied Geospatial Research, 2(3), 20-31, July-September 2011

Boissau, S., & Castella, J. (2003). Constructing a common representation of local institutions and land use
systems through simulation-gaming and multi-agent
modeling in rural areas of Northern Vietnam: The
SAMBA-Week methodology. Simulation & Gaming,
34(3), 342347. doi:10.1177/1046878103255789
Castella, J., Boissau, S., Trung, T. N., & Quang, D.
D. (2005). Agrarian transition and lowland-upland
interactions in mountain areas in northern Vietnam:
Application of a multi-agent simulation model. Agricultural Systems, 86(3), 312332. doi:10.1016/j.
agsy.2004.11.001
Dietzel, C. K., & Clarke, K. C. (2004). Spatial differences in multi-resolution urban automata modeling.
Transactions in GIS, 8, 479492. doi:10.1111/j.14679671.2004.00197.x
Duan, Z., Verburg, P. H., Zhang, F., & Yu, Z. (2004).
Construction of a land-use change simulation model
and its application in Haidian District, Beijing. Acta
Geographica Sinica, 59(6), 10371046.
Fischer, M. M., & Gopal, S. (1994). Artificial neural
networks: A new approach to modeling interregional
telecommunication flows. Journal of Regional Science, 34(4), 503527. doi:10.1111/j.1467-9787.1994.
tb00880.x
Landis, J. (1994). The California urban futures model:
A new generation of metropolitan simulation models.
Environment and Planning. B, Planning & Design,
21, 399420. doi:10.1068/b210399
Li, X., & Yeh, A. G. O. (2001). Calibration of cellular
automata by using neural networks for the simulation
of complex urban systems. Environment & Planning
A, 33(8), 14451462. doi:10.1068/a33210
Lu, K. S., & Allen, J. S. (in press). Neural networks
for modeling urban growth patterns and potential
ecosystem impact in the coastal zone . In Brouwer,
F., & Goetz, S. J. (Eds.), The dynamics of land use
and ecosystem interactions: A transatlantic, multidisciplinary and comparative approach. New York,
NY: Springer.
MacKay, D. J. C. (1992). Bayesian interpolation.
Neural Computation, 4(3), 415447. doi:10.1162/
neco.1992.4.3.415
Openshaw, S. (1993). Modeling spatial interaction
using a neural net . In Fischer, M. M., & Nijkamp,
P. (Eds.), GIS spatial modeling and policy (pp.
147164). Berlin, Germany: Springer-Verlag.

Penny, W. D., Husmeier, D., & Roberts, S. J. (1999).

Introduction . In Lisboa, P. J. G., Ifeachor, E. C.,
& Szczepaniak, P. S. (Eds.), Artificial neural networks in biomedicine (pp. 19). Berlin, Germany:
Springer-Verlag.
Pijanowski, B. C., Brown, D. G., Manik, G., &
Shellito, B. A. (2002). Using neural nets and GIS
to forecast land use changes: A land transformation model. Computers, Environment and Urban
Systems, 26(6), 553575. doi:10.1016/S01989715(01)00015-1
Pijanowski, B. C., Pithadia, S., Shellito, B. A., &
Alexandrids, K. (2005). Calibrating a neural networkbased urban change model for two metropolitan areas
of the Upper Midwest of the United States. International Journal of Geographical Information Science,
19, 197215. doi:10.1080/13658810410001713416
Pontius, R. G. Jr, Boersma, W., Castella, J., Clarke,
K., de Nijs, T., & Dietzel, C. (2008). Comparing
the input, output, and validation maps for several
models of land change. The Annals of Regional Science, 24(1), 1137. doi:10.1007/s00168-007-0138-2
Pontius, R. G. Jr, Cornell, J., & Hall, C. (2001).
Modeling the spatial pattern of land-use change with
GEOMOD2: Application and validation for Costa
Rica. Agriculture Ecosystems & Environment, 85(13), 191203. doi:10.1016/S0167-8809(01)00183-9
Pontius, R. G. Jr, & Spencer, J. (2005). Uncertainty
in extrapolations of predictive land change models. Environment and Planning B, 32, 211230.
doi:10.1068/b31152
Rumelhart, D. E., Hinton, G. E., & Williams, R. J.
(1986). Learning internal representations by error
propagation. In J. L. McClelland & D. E. Rumelhart
(Eds.), Parallel distributed processing: Explorations
in the microstructure of cognition: Vol. 1. Foundations (pp. 318-362). Cambridge, MA: MIT Press.
Silva, E., & Clarke, K. C. (2002). Calibration of
the SLEUTH urban growth model for Lisbon and
Porto, Portugal. Computers, Environment and
Urban Systems, 26, 525552. doi:10.1016/S01989715(01)00014-X
Turner, B. L., & Meyer, W. B. (1994). Global land-se
and land-cover change: An overview . In Meyer, W.
B., & Turner, B. L. II, (Eds.), Change in land use
and land cover: A global perspective (pp. 110).
Cambridge, UK: Cambridge University Press.

Openshaw, S., & Openshaw, C. (1997). Artificial

intelligence in geography. Chichester, UK: John
Wiley & Sons.

Copyright 2011, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.

International Journal of Applied Geospatial Research, 2(3), 20-31, July-September 2011 31

Veldkamp, T. A., & Fresco, L. (1996). CLUECR: An integrated multi-scale model to simulate
land use change scenarios in Costa Rica. Ecological Modelling, 91, 231248. doi:10.1016/03043800(95)00158-1
Verburg, P. H., Soepboer, W., Veldkamp, T. A., Limpiada, R., Espaldon, V., & Mastura, S. A. S. (2002).
Modeling the spatial dynamics of regional land use:
The CLUE-S model. Environmental Management,
30(3), 391405. doi:10.1007/s00267-002-2630-x

Verburg, P. H., & Veldkamp, T. A. (2004). Projecting

land use transitions at forest fringes in the Philippines at two spatial scales. Landscape Ecology, 19,
7798. doi:10.1023/B:LAND.0000018370.57457.58
Yeh, A. G. O., & Li, X. (2002). Urban simulation
using neural networks and cellular automata for land
use planning . In Richardson, D., & van Osterom,
P. (Eds.), Advances in spatial data handling (pp.
451464). Berlin, Germany: Springer-Verlag.

Kang Shou Lu is an associate professor of geography at Towson University in Baltimore, Maryland,

USA. He received his PhD from Clemson University. His academic experiences include serving
as a program director at Shaanxi Normal University, Xian, China, editor-in-chief of Geography
for Secondary Education, a visiting scholar at California State University at Northridge, and
a research scientist at the Strom Thurmond Institute of Government and Public Affairs. Kang
Shou is one of the authors for the award-wining Charleston Urban Growth study funded by the
National Oceanic and Atmospheric Administration (NOAA). He has published more than 30
peer-reviewed papers and book chapters in diverse fields. His current teaching and research foci
are on land use modeling, urban growth simulation, geographic information systems, artificial
neural networks, and watershed impairment assessment.
John Morgan III (Jay) is a professor in the Department of Geography and Environmental
Planning at Towson University in Baltimore, MD. Prior to joining the faculty at Towson in 1984,
Jay worked with state and local government agencies in Maryland. His experience includes
serving as the first systems analyst and programmer on the Maryland Automated Geographic
Information Systems (1974 to 1977). Jay has sponsored an annual GIS conference since 1987,
founded and served as the director of the Center for GIS for 13 years, and has been the principal
investigator on over $13 million of grants and contracts. Jays teaching and research interests
include geographic information systems, remote sensing, homeland security and emergency
management, and outdoor recreation planning and management.
Jeff Allen is the Director of the South Carolina Water Resources Center at the Strom Thurmond
Institute of Government and Public Affairs at Clemson University. He serves on the faculty of
the Policy Studies Program and is also an Adjunct Assistant Professor in the Department of
Forestry and Natural Resources at Clemson University. Jeff received a PhD in Policy Studies
from Clemson University with an emphasis in natural resources policy. His work involves coordinating water research with a national network of water institutes and identifying and pursuing
critical water research needs for South Carolina. Jeff has served as the principle investigator
on multiple grants from government agencies and private foundations. He has organized and
sponsored several state-wide meetings on GIS mapping and water resources. His recent work
includes mapping structures within South Carolinas beach setback zone to determine impacts
of sea level rise and beach erosion and building urban growth prediction models to describe
potential future development patterns in South Carolina.

Copyright 2011, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.