The Computational Research on the Ancient near East

(CRANE) Project: An Archaeological Data Integration, Simulation

and Data Mining

Stephen Batiuk

, Tim Harrison

, Lynn Welton

, Darren Joblonkay

and Lemonia Ragia

Department of Near & Middle Eastern Civilizations and the Archaeology Centre of the University of Toronto, Canada

Department of Near and Middle Eastern Civilizations University of Toronto, Canada

The Oriental Institute, The University of Chicago, U.S.A.

Geneva School of Economics and Management/Information Science Institute & University Center of Informatics

(CUI)/Institute of Services Sciences, University of Geneva, Switzerland

Keywords: Data Mining, Archaeological Database, Data Analysis, Spatial Analysis, Information Retrieval, Simulation

Modelling.

Abstract: Archaeology has emerged as one of the most dynamic and innovative disciplines in the humanities and social

sciences, employing a truly interdisciplinary, collaborative approach and a continually expanding array of

analytical research tools. Computer aided analysis of archaeological data is remarkably challenging given the

heterogeneous nature of the material. Archaeologists generally aim to discover patterns, spatial relationships

and other associations between different traits of the archaeological record. However, given the idiosyncratic

and highly personal nature in which archaeological data is collected and analyzed, identifying these patterns

and relationships offers many challenges. The Computational Research on the Ancient Near East (CRANE)

initiative seeks to build an international multidisciplinary research collaboration, comprised of archaeologists,

computer scientists, and paleo-environmental specialists, with the capacity to leverage a burgeoning corpus

of data from a number of archaeological sites and fundamentally transform our knowledge of the civilizations

of the ancient Middle East. The CRANE initiative is developing a sustainable, scalable, user-driven vehicle

for large-scale data management and cross-project data integration, to harness the full evidentiary range

produced by this uniquely rich cultural legacy. At the same time we are developing tools for data mining

techniques, and to analyze simulate ancient societies using agent-based models of behavior.

1 INTRODUCTION

Over a century and a half of archaeological research

in the Near East has documented the emergence of the

first sedentary communities, the origins of

agriculture, the development of the first state-level

societies, and the first interregional commercial and

political networks (Redman, 1978; Wilkinson, 1994;

Akkermans and Schwartz, 2003; Yoffee, 2005; Edens

and Kohl, 1993; Marfoe, 1987; Stein and Blackman,

1993; Wattenmaker, 1994; Wattenmaker, 1998a;

Wattenmaker, 1998b; Mazzoni, 2003). Yet its

contribution to a deeper understanding of the long-

term growth and development of human communities

and their interaction with the natural environment has

been hindered by a less-than-ideal publication record

and the lack of any real analytical framework that

incorporates the full array of data produced by this

uniquely rich cultural legacy. Furthermore, the

present wars in Syria and Iraq have left the

completion of many projects impossible for the

foreseeable future, further hindering final

publications, leaving data sets in limbo.

Advances in the collection and analysis of

archaeological data mean that, in many respects, we

have never been in a better position to pull together

the often heterogeneous and idiosyncratic published

and unpublished datasets, and understand the nature

and scope of these social, political, economic, and

ideological transformations in the ancient world

(Kansa, 2005; Kansa, 2010; Kansa et al., 2005;

Kansa et al., 2007; Petrovic et al., 2011). Yet such

efforts are often hampered by the challenges of

integrating the datasets (which are often at varied

Batiuk, S., Harrison, T., Welton, L., Joblonkay, D. and Ragia, L.

The Computational Research on the Ancient near East (CRANE) Project: An Archaeological Data Integration, Simulation and Data Mining.

DOI: 10.5220/0006213401530160

In Proceedings of the 3rd International Conference on Geographical Information Systems Theory, Applications and Management (GISTAM 2017), pages 153-160

ISBN: 978-989-758-252-3

153

spatial and temporal scales) which would be capable

of resolving short term actions or long term processes

spanning the millennia of data we have in the Ancient

Near East.

Large-scale data analysis has become increasingly

common in humanities scholarship, with researchers

increasingly disappointed by the impoverished results

they receive when querying multiple datasets that

have only superficially shared data structures, an all

too familiar problem when using internet search

engines such as Google. The poor quality of large-

scale query results, typically of textual data, reflects

the difficulties inherent in machine processing of

natural language and other kinds of ‘artificial

intelligence’ (Abiteboul et al., 2000; Ling and

Dobbie, 2004; Dreyfus, 1992). The Computational

Research on the Ancient Near East (or CRANE)

Project, directed by Tim Harrison of the University of

Toronto and funded primarily by the Social Sciences

and Humanities Research Council of Canada, is an

international collaboration that takes up these

challenges through the integration and analysis of

data from a number of archaeological projects

working within the Orontes Watershed of modern

Southeastern Turkey and Northwestern Syria.

The underlying rationale for the CRANE Project

is to build an international collaboration of

researchers who will leverage these data to model and

visualize the interplay of social, economic and

environmental dynamics at various spatial and

temporal scales in order to shed light on the rise and

development of complex societies in this important

region. This research will also provide insight into a

number of pressing contemporary issues, including

the ecological impact of human activities, the

socioeconomic and political impact of climate

change, the long-term health consequences of human

dietary practices and subsistence strategies, and the

role of cultural conflict in affecting social and

political change.

The work of the CRANE Project is guided by a

number of specific research objectives, including the

integration of digital data from multiple

archaeological research projects - both legacy and

active - that use different terminologies stemming

from different research traditions and

methodologies; the development of a core cultural,

paleo environmental and chronological sequence for

the Orontes Watershed; the creation of protocols and

analytical tools to facilitate broad access to this

information; the modeling of emergent and inverse

simulations of ancient social practices and related

human-environment dynamics based on parameters

supplied by empirical data; the creation of spatially

accurate and realistic 3D visualizations of

reconstructed ancient landscapes and human activity

based on empirical data and the output of simulated

scenarios; the creation of research opportunities and

training in advanced archaeological analysis for

university students at all levels and junior scholars.

2 THE ORONTES WATERSHED

In its current stage, the CRANE Project is addressing

these objectives through a focus on the Orontes

Watershed in southeast Turkey and northwest Syria.

The Orontes valley represents the northern most

extension of the Greta Rift Valley, and is dominated

by the Orontes river, which finds its headwaters in the

Lebanese mountains, flowing north reaching the

Mediterranean Sea in the Hatay region of south

Eastern Turkey, which is in turn fed by a hydrological

system fed from as far north as the Maraş plain,

encompassing a drainage basin of around 24,000 km

(Fig. 1).

Figure 1: The Orontes Watershed.

Over a century and a half of archaeological survey

and excavation throughout this region has brought to

light one of the most important cultural sequences in

the ancient Near East. As a cohesive geographical

unit and a cultural microcosm of the broader Near

East, it represents an exceptional initial test case. Our

present efforts are concentrating on the integration of

data from five important sites in this region, Tell

Acharneh, Tell Nebi Mend, Qatna, Tell Tayinat and

Zinçirli Höyük, as well as a number of archaeological

surveys, and is presently set to expanding to include

other sites in the greater region. These projects

GISTAM 2017 - 3rd International Conference on Geographical Information Systems Theory, Applications and Management

154

represent a diverse set of not only of archaeological

data, but excavation and recording methodologies,

different taxonomies for the collected data, in which

the level of detail and quality of the data varies greatly

within the individual projects, let alone between the

projects.

2.1 OCHRE Data Integration

Data integration is an essential component of CRANE

and presents a significant challenge in trying to

incorporate the heterogeneous datasets from various

projects into a single query able environment without

imposing a uniform taxonomy. Archaeological data

can be quite diverse and significantly variable;

including architectural, artefactual, or ceramic data,

which can be represented by drawings, photos,

vector, or textual data of measurements and/ or

descriptions. Furthermore this data is highly

interpretive, which can change over an excavation

season, with post-excavations analysis, or with

changes in theoretical approaches, all of which must

be coherently documented. Making meaningful links

between these disparate datasets is an immense

challenge, and one that can only be undertaken with

The Present Advances in Computing. the Collection

of This Data in a Centralized Networked Legacy

Protected Location Allows for the Preservation of the

Record of Archaeological Excavations in an

Electronic Format for Present and Future Scholars or

Even Eventually the Public to Utilize.

to Meet This Challenge, Our Current Data

Integration Efforts Focus on the Use and

Enhancement of the Online Cultural and Historical

Research Environment, or OCHRE, a Powerful,

Multi-User, XML Database System Developed by

David and Sandra Schloen of the University of

Chicago (Schloen 2001). in the Figure 2 the OCHRE

System Architecture Is Presented. OCHRE’s Item-

based Approach Is Highly Flexible, and as Relatively

Few Concepts and Relationships Are Predefined, It

Enables It to Operate at a Much Higher Level of

Abstraction than Formal Ontologies Employed by

Other Such Data Frameworks. Its Generic Ontology

Is Also Inherently Extendible, Allowing CRANE

Researchers to Construct Their Own Lists and

Hierarchies of Data Items, and Their Own

Taxonomies to Describe Those Items, but More

Important for Us Allows Us to Create Thesauri to

Link Equivalent Categories across Participating

Projects. OCHRE Displays and Manages Data Items

Spatially through the Use of an Embedded Java SDK

by ESRI Which Allows for the Full Visualization of

All Data Housed within the Database. CRANE Is

Collecting and Integrating Data from the Orontes

Region at an Unprecedented Level and Developing

New Tools to Leverage These Data. Modern Data

Mining, Modeling/Simulation and Visualization

Techniques Are Being Used to Transform the Data

into Information That Helps Researchers Better

Understand What Happening in the Region in the past

and Present It in More Meaningful Ways to the

General Public.

Figure 2: The OCHRE System Architecture.

2.2 Crane Subprojects

The over-arching nature of CRANE results in a

number of inter-related sub projects. What follows is

a brief description of a few of the relevant subprojects

that focus on Geographical Information Systems. For

a full description of the various CRANE subprojects

and how they are integrated, see (CRANE 2016). One

of the primary projects initiated was a comprehensive

inventory of all sites identified in the Orontes

Watershed to serve as a backbone to the project, a

scaffold upon which many of the sub-projects hang.

We presently have identified over 4100 sites in the

greater Orontes region, delineated by their geographic

location, chronological periods, linked to an

exhaustive bibliography. OCHRE’s API Integration

with the French PaleoSyr Project (ANR-PALEOSYR

2014), has given us access to an incredible array of

additional data for the various sites, including

descriptive, chronological and other archaeological

metadata. These data have been shared with ASOR’s

Cultural Heritage Initiative (ASOR 2014) – to aide in

the construction of a more comprehensive database

of sites in Syria and Iraq to help with management of

the destruction of Cultural heritage monuments from

the civil wars in the region. Integrating remotely

sensed imagery, historical maps of the regions, along

with thematic maps (including soil, geology,

hydrology, elevation and slope etc) were all

The Computational Research on the Ancient near East (CRANE) Project: An Archaeological Data Integration, Simulation and Data Mining

155

integrated into OCHRE, and utilizing the GIS

capabilities of OCHRE (Fig. 3).

Figure 3: A map with GIS.

2.3 Simulation Modeling

One important objective of the CRANE project was

to ultimately be able to utilize the various assembled

georeferenced archaeological and environmental

datasets from within the Orontes watershed to

examine human-environment interaction through the

modeling of both natural systems and social

processes, as well as investigate the interplay and

interaction between these two sets of variables in

contributing to emergent social complexity.

As a result, a secondary sub-project developed as

part of CRANE was to implement a program of agent-

based simulation modelling built on an earlier

research initiative entitled “Modeling Ancient

Settlement Systems” (Wilkinson et al., 2007), which

used holistic agent-based simulation techniques to

explore socio-ecological questions in ancient

Mesopotamia. Agent-based modelling is used to

simulate the emergence and functioning of complex

systems through the actions and interactions of

autonomous agents, who are programmed to behave

according to certain defined rules. These agents can

either be individuals, or can represent collective

entities such as organizations or groups. While it has

been more consistently used in other fields such as

computational sociology and ecology, it has not been

frequently applied to archaeological questions. The

ways in which the results of agent-based modelling in

archaeology have been interpreted in the past have

been problematic, sometimes leading its value to the

discipline to be misconstrued. The outcomes and

goals of simulation modeling have often been

conceptualized in terms of the idea that the ultimate

goal of an agent-based model is simply to run it and

have it approximate reality as closely as possible, and

therefore that its ability to do so represents its ultimate

value to archaeology. When the endeavour is viewed

this way, the criticisms are obvious; it is impossible

to account for every single possible factor that could

affect the outcomes of processes in complex systems

like ancient societies, and the idea that we can

adequately account for random variation is also

problematic.

The outputs of computer-based simulations can be

compared to the archaeological record, but this is

generally best done as a means of testing specific

hypotheses about explanations for the appearance or

behaviour of certain phenomena and the investigation

of new research avenues (for a recent attempt in

biomedicine, see Kammash, 2008). ENKIMDU is a

modeling framework with the capability to create a

virtual world in which to run simulations based on

various environmental and social parameters

(Christiansen, 2005; Christiansen and Altaweel

2006a; Christiansen and Altaweel, 2006b).

ENKIMDU’s approach is holistic and agent-based,

and represents a “bottom up” method of modeling.

This means that its simulated historical trajectories

appear as the cumulative outcomes of a host of small-

scale activities and interactions, for instance as a

result of actions by individual persons, households,

crop fields, and domesticated animals. ENKIMDU

was developed with the intention of testing the idea

that the appearance of urban centres in Mesopotamia

was an emergent phenomenon that was ultimately

regulated by positive feedback loops that encouraged

population agglomeration and settlement growth, and

negative feedback loops that constrained growth and

kept it within certain limits.

For much of its environmental modelling,

ENKIMDU relies on communicating with third-party

software called SWAT, the Soil and Water

Assessment Tool, developed jointly by the USDA

Agricultural Research Service and Texas A&M

University (Neitsch et al., 2002; Arnold and Fohrer,

2005). This software was developed to model a

variety of natural processes, such as basic weather

patterns, hydrology (including surface runoff and

water table dynamics), soil evolution and erosion,

plant nutrient cycling, and vegetation growth

(including both the natural environment and human-

managed crop growth). SWAT’s internal weather

generation abilities are augmented by using ClimGen,

a Markov-chain weather generator (Stöckle et al.,

1999). This SWAT-based environmental model is

then positioned in a larger social model, whose

original focus was on subsistence economy,

agricultural processes and sustainability in relation to

GISTAM 2017 - 3rd International Conference on Geographical Information Systems Theory, Applications and Management

156

Figure 4: The simulation modelling.

environmental conditions and the demographic

structure of the population. The model focused on the

performance of detailed aspects of the agricultural

cycle, including planting, irrigation, harvesting, crop

processing, storage and consumption (Fig. 4).

Although the ENKIMDU model creates individual

people as agents, the primary decision-making social

agent for agricultural processes is the Household.

Households can allocate labor and other resources,

and plan both short-term and long-term agricultural

operations. Households can also identify situations of

short-term, medium-term and long-term food stress,

and deploy a variety of different coping strategies for

dealing with each of these situations.

Another important area of CRANE’s interest has

been in the implementation of paleoclimate

modelling using General Circulation Models, in

particular, the models of the Coupled Model

Intercomparison Project (Taylor et al., 2011) and the

Paleoclimate Modelling Intercomparison Project

(Argus and Peltier, 2010; Tarasov et al., 2012;

Lambeck et al., 2010).

These projects model various climate-related

variables both forward and backward in time,

including temperature and precipitation, but also a

host of other factors relating to issues like ocean

currents and temperatures, wind patterns, snow

coverage, and vegetation patterns. CMIP5’s standard

modelling time frames include 6kya (the mid-

Holocene, ca. 4000 BC), while PMIP runs

experiments for additional time frames including the

Early Holocene and the 8.2 kya climatic event (ca.

6200 BC).

2.3 Data Mining

Archaeologists are frequently pursuing new

techniques and tools to analyze their data. In an effort

to identify relationships for interpretation, they have

utilized a number of different approaches. Data

analysis and information retrieval is explicitly

described in Richards and Ryan, 1985. Statistics is

not a new topic for archaeology and is extensively

analyzed by Kimball 1997. The differences between

qualitative and quantitative analysis is also covered

using examples in Drennan, 2008. In another

approach it is explained how statistical techniques can

clarify ambiguous patterns in an historical application

(Kelly-Buccellati and Elster, 1973). It is

The Computational Research on the Ancient near East (CRANE) Project: An Archaeological Data Integration, Simulation and Data Mining

157

demonstrated that the application of statistical

thinking and techniques can aid the archaeologist in

retrieving as much information as possible from

artifacts (Bentley and Schneider, 2000).

Figure 5: A diagram with association rules.

Data mining is a scientific topic of information

technology widely used in many applications.

Handling different data types data mining techniques

result in automatic knowledge discovery and decision

support (Han et al. 2011), (Olson and Delen

2008). The association rules establish relationships

between variables in a given data set. Mining

association rules were first introduced in Agrawal et

al. 1993. Since then they received much attention in

academic and industrial applications (Jiao, et al.

2006).

There is an approach deals with data mining

techniques on heterogeneous archaeological

databases on smaller scales to that of CRANE

(Zweig, 2006). Data mining techniques have been

also used for historical manuscripts and cultural

artifacts (Zhu, 2011). It has been proposed the

application of Association Mining algorithms (in

particular an updated form of the Apriori algorithm as

initially conceived by Agrawal et., 1993), in order to

reveal heretofore unrecognized associations between

artifacts in archaeological contexts, as itemized in

archaeological data warehouse environments, such as

OCHRE. The Apriori algorithm is utilized to detect

those items (i.e. artifacts) which are frequently

associated with one another in context, the

relationships between which are indicative of past

commonly attested practices within the community

under analysis. The output results in a series of

association “rules” (lists of the frequency with which

items are found together in context), which may be

graphed to provide a visual representation of the past

organization/structure of a community (Fig. 5). The

methodology has been applied to a small Iron Age

settlement (ca. 9th century BCE) in northwest Syria,

in order to produce a more nuanced characterization

of the community, based upon commonly attested

practices amongst households at the site.

The archaeological data are described by

attributes with their values. A value can be numerical

and non-numerical. An attribute is an individual

characteristic of an artifact which represents the

archaeological finding. In our sample the artifact is an

item and can be further subdivided by its attributes.

The attributes have non-numerical values describing

different traits such as color, texture, form, shape. As

an example the attribute form can have as values

"Bowl", "Cooking Pot" or "Store Jar". Relationships

between variables can be found using logical

operations as an expression. The items are discovered

in different location of the excavation and the whole

excavation area is split into 11 rooms. There is also

an attribution based on a spatial relationship

representing the location of the items. The location of

the item is defined by the value "Room" with its

number, e.g. "Room 5". The spatial relationship

"included_by" can also be used to identify the

location.

3 CONCLUSIONS

The rapid proliferation of digitally generated

archaeological data (both new and digitized legacy

data) represents a profound opportunity for our

discipline to contribute meaningfully to issues of

pressing contemporary concern, while providing

deeper insight and understanding about the world in

which we live. However this can only be achieved

through the development and utilization of robust

computational tools. Near Eastern Archaeology

represents an ideal test case for developing a

computational framework capable of integrating the

complex, heterogeneous, or “messy”, datasets that

typify our world, and defy the homogenizing

algorithms of machine-driving learning. Thus, the

most successful collaborative data-sharing ventures

in this effort are likely to be those that accommodate

multiple, diverse taxonomic structures and

hierarchies of knowledge and meaning. To ensure the

full exploitation of these datasets by both

archaeologist as well as public stakeholders (such as

Cultural Heritage Management Groups), more

powerful tools that maximize the potential of the

computational tools available to us today.

GISTAM 2017 - 3rd International Conference on Geographical Information Systems Theory, Applications and Management

158

ACKNOWLEDGEMENTS

We wish to acknowledge the very real collaborative

contribution of our CRANE colleagues, from

universities worldwide, as well as non-academic

partners. A special thanks goes out to our

hardworking students who play an integral role in the

success of our work, and finally the generous support

of the Social Sciences and Humanities Research

Council of Canada who makes all the work possible.

REFERENCES

Abiteboul, S., Buneman, P., and Suciu, D., 2000. Data on

the Web: from relations to semistructured data and

XML. Morgan Kaufmann.

Agrawal, R., Imieliński, T., and Swami, A., 1993, June.

Mining association rules between sets of items in large

databases. In Acm sigmod record, Vol. 22, No. 2, 207-

216. ACM.

Akkermans, P.M.M.G. and Schwartz, G.M., 2003. The

Archaeology of Syria: From Complex Hunter-

Gatherers to Early Urban Societies (ca. 16,000-300

BC). Cambridge: Cambridge University Press.

ANR-PALEOSYR 2014

http://www.archeorient.mom.fr/recherche-et-

activites/appels-d-offre-et-contrats/ANR-PALEOSYR

Argus, D. F. and Peltier, W. R., 2010. Constraining models

of postglacial rebound using space geodesy: a detailed

assessment of model ICE-5G (VM2) and its relatives.

Geophysical Journal International 181 (2), 697–723.

Arnold, J.G., Fohrer, N., 2005. SWAT2000: current

capabilities and research opportunities in applied

watershed modelling. Hydrological. Process. 19 (3),

563–572.

ASOR 2014. http://www.asor-syrianheritage.org/

Bentley, J., Schneider, T. J., 2000. Statistics and

archaeology in Israel. Computational statistics & data

analysis, 32(3), 465-483.

Christiansen, J.H., 2005. A Practical Approach for

Constructing Flexible and Robust Simulations for

Complex, Heterogeneous Problem Domains. Paper

presented at the Santa Fe Institute Workshop: Next

Generation Simulations of Human-Environment

Interactions, Tucson, AZ, December 12-15, 2005.

Christiansen, J.H., Altaweel. M., 2006a. Understanding

Ancient Societies: A New Approach Using Agent-

Based Holistic Modeling. Structure and Dynamics:

eJournal of Anthroplogical and Related Sciences Vol.

1: No. 2, Article 7.

Christiansen, J. H., Altaweel, M., 2006b. Simulation of

natural and social process interactions: An example

from Bronze Age Mesopotamia. Social Science

Computer Review, 24(2), 209-226.

CRANE 2016: www.crane.utoronto.ca

Drennan, R. D., 2008. Statistics in archaeology. Pearsall,

Deborah M. Encyclopedia of Archaeology. Elsevier

Inc, 2093-2100.

Dreyfus, H.L., 1992. What Computers Still Can’t Do: A

Critique of Artificial Reason. Cambridge, MA: MIT

Press.

Edens, C.M., Kohl, P.L., 1993. Trade and World Systems

in Early Bronze Age Western Asia. In Trade and

Exchange in Prehistoric Europe. Edited by C. Scarre

and F. Healy. Oxford: Oxbow Books, 17-34.

Han, J., Pei, J., and Kamber, M., 2011. Data mining:

concepts and techniques. Elsevier.

Jiao, J. R., Zhang, Y., and Helander, M., 2006. A Kansei

mining system for affective design. Expert Systems

with Applications, 30(4), 658-673.

Kammash, M., 2008. Reverse Engineering: The

Architecture of Biological Networks. Biotechniques 44

(3):323-29.

Kansa, E.C., 2005. A Community Approach to Data

Integration: Authorship and Building Meaningful Links

across Diverse Archaeological Data Sets. Geosphere

1/2: 97-109.

Kansa, E.C, 2010. Open Context in Context:

Cyberinfrastructure and Distributed Approaches to

Publish and Preserve Archaeological Data. The SAA

Archaeological Record 10 (5): 12-16.

Kansa, E.C, Schultz, J., and Bissell, A. N., 2005. Protecting

Traditional Knowledge and Expanding Access to

Scientific Data. International Journal of Cultural

Property 12/3: 285-314.

Kansa, S.W., Kansa, E.C., and Schultz, J.M., 2007. An

Open Context for Near Eastern Archaeology. Near

Eastern Archaeology 70/4: 188- 201.

Kelly-Buccellati, M., Elster, S., 1973. Statistics in

archaeology and its application to ancient Near Eastern

data. Orientalia, 42, 195-211.

Kimball, L. R., 1997. Statistics for Archaeologists: A

Commonsense Approach. American Antiquity, 62(3),

568-570.

Lambeck, K., Purcell, A., Zhao, J., and Svensson, N.-O.

2010. The Scandinavian Ice Sheet: from MIS 4 to the

end of the Last Glacial Maximum. In Boreas, 39, 410–

435

Ling, T. W., Dobbie, G., 2004. Semistructured database

design (Vol. 1). Springer Science & Business Media.

Marfoe, L. 1987. Cedar Forest to Silver Mountain: Social

Change and the Development of Long-Distance Trade

in Early Near Eastern Societies. In Centre and

Periphery in the Ancient World, 25-35.

Mazzoni, S., 2003. Ebla: Crafts and Power in an Emergent

State of 3rd Millennium Syria. Journal of

Mediterranean Archaeology 16: 173-91.

Neitsch, S.L., Arnold, J.G., Kiniry, J.R., Srinivasan, R.,

Williams, J.R., 2002. Soil and Water Assessment Tool.

Users Manual. Version 2005. GSWRL Report 02-02,

BRC Report 2-06, Temple, Texas, USA

Olson, D. L., Delen, D., 2008, Advanced data mining

techniques. Springer Science & Business Media.

Petrovic, V., Gidding, A., Wypych, T., Kuester, F.,

DeFanti, T., and Levy, T., 2011. Dealing with

The Computational Research on the Ancient near East (CRANE) Project: An Archaeological Data Integration, Simulation and Data Mining

159

Archaeology’s Data Avalanche. Computer, 44(7), 56-

60.

Redman, C., 1978. The Rise of Civilization; From Early

Farmers to Urban Society in the Ancient Near East. San

Francisco: W.H. Freeman and Co.

Richards, J. D., Ryan, N. S., 1985. Data processing in

archaeology. CUP Archive.

Schloen, J. D., 2001. Archaeological data models and web

publication using XML. Computers and the

Humanities, 35(2), 123-152.

Schloen, J.D., Schloen S.R., 2012. OCHRE An Online

Cultural and Historical Research Environment.

Stein, G., Blackman M.J., 1993. The Organizational

Context of Specialized Craft Production in Early

Mesopotamian States. Research in Economic

Anthropology 14: 29-59.

Stöckle, C.O., Campbell G.S., Nelson R., 1999. ClimGen

Manual. Biological Systems Engineering Department,

Washington State University, Pullman, WA

Tarasov, L., Dyke, A. S., Neal, R. M., and Peltier, W.

R.,2012. A data-calibrated distribution of deglacial

chronologies for the North American ice complex from

glaciological modeling. In Earth and Planetary

Science Letters., 315, 30–40.

Taylor, K. E., Stouffer, R. J., and G. A. Meehl, G.A.,

2011. An overview of CMIP5 and the experiment

design, Bull. Am. Meteorol. Soc., 93(4), 485–498.

Wattenmaker, P., 1994. Political Fluctuations and Local

Exchange Systems in the Ancient Near East: Evidence

from the Early Bronze Age Settlements at Kurban

Hoyuk. In Chiefdoms and Early States in the Near East;

The Organizational Dynamics of Complexity. Ed. By G.

Stein and M. S. Rothman. Madison: Prehistory Press,

193-208.

Wattenmaker, P., 1998a. Craft production and social

identity in northwest Mesopotamia. Archeological

Papers of the American Anthropological

Association, 8(1), 47-55.

Wattenmaker, P., 1998b. Household and State in Upper

Mesopotamia: Specialized Economy and the Social

Uses of Goods in an Early Complex Society.

Washington: Smithsonian Institute Press.

Wilkinson, T.J., 1994. The Structure and Dynamics of Dry-

Farming States in Upper Mesopotamia.” Current

Anthropology 35: 483-520.

Wilkinson, T.J., Gibson, M., Christenson, J., Widell, M.,

Woods, C., Kouchoukos, N., and Paulette, T., 2007.

Modeling Settlement Systems in a Dynamic

Environment: Case Studies from Mesopotamia. In The

Model-Based Archaeology of Socionatural Systems.

Ed. by T.A. Kohler and S.E. van der Leeuw. Santa Fe,

NM: School for Advanced Research Press, 175-208.

Yoffee, N., 2005. Myths of the Archaic State: Evolution of

the Earliest Cities, States and Civilizations. Cambridge:

Cambridge University Press.

Zhu, Q., 2011. Data Mining Historical Manuscripts and

Culture Artifacts. UC Riverside: Computer Science.

Retrievefrom:

http://escholarship.org/uc/item/2jx150v7

Zweig, Z., 2006. Using Data Mining Techniques for

Analyzing Pottery Databases (Doctoral dissertation,

Department of Land of Israel Studies & Archaeology,

Bar-Ilan University. Ramat-Gan, Israel 2006).

GISTAM 2017 - 3rd International Conference on Geographical Information Systems Theory, Applications and Management

160