Hostname: page-component-78c5997874-j824f Total loading time: 0 Render date: 2024-11-18T01:10:07.077Z Has data issue: false hasContentIssue false
  • English
  • Français

Predictive Modeling for Site Detection Using Remotely Sensed Phenological Data

Published online by Cambridge University Press:  16 January 2017

Scott Detrich Kirk ,
Amy E. Thompson  and
Christopher D. Lippitt
Scott Detrich Kirk
Affiliation:
Department of Anthropology, University of New Mexico, Albuquerque, NM 87131 (kirks@unm.edu)
Amy E. Thompson
Affiliation:
Department of Anthropology, University of New Mexico, Albuquerque, NM 87131 (athomp04@unm.edu)
Christopher D. Lippitt
Affiliation:
Department of Geography, University of New Mexico, Albuquerque, NM 87131 (clippitt@unm.edu)
Get access Rights & Permissions [Opens in a new window]

Abstract

This paper examines the potential of remote sensing–derived metrics of vegetation phenology and a Multi-Layer Perceptron neural network to model the most likely locations of large, agglomerated archaeological sites. Focusing on two different environments in central New Mexico, the Galisteo Basin and the Sandia-Manzano Mountain range, this pilot study distinguishes between archaeological sites and their surroundings based on differential growth in vegetation. Using data derived from Landsat Thematic Mapper, a time series of Normalized Difference Vegetation Indices were created to characterize vegetation phenology in the study areas. Distinguishing between archaeological sites and their surroundings, the neural network was trained on a series of known sites to develop an output activation layer indicating the possible locations of other, previously unknown sites. This output activation layer, treated as a site suitability model, was validated using the receiver operating characteristic area under the curve using known sites excluded from the training procedure. Results show promise in large, open areas such as basin environments. While differences in vegetation type have relatively little effect, differences in elevation, or more directly the changes in phenology that go along with them, negatively impact the ability to infer the presence of archaeological sites using this approach.

Este artículo examina la potencial de métricas de teledetección de fenología vegetal y una red neural de Multi-Layer Perceptron para modelar las ubicaciones más probables de sitios arqueológicas grandes y aglomerados. Este estudio preliminar enfoque en dos localidades diferentes en el centro de Nueva México, el Cuenco de Galisteo y la cordillera de Sandia-Manzano y distingue entre sitios arqueológicos y sus entornos basado en crecimiento diferencial en vegetación. Un serie temporal del índice de vegetación diferencial normalizado (NDVI) fue creada de datos derivado de Landsat Thematic Mapper para caracterizar la fenología de las plantas en los áreas de estudio. La red neural distingue entre sitios arqueológicos y sus entornos y fue entrenando en un serie de sitios conocidos para desarrollar una capa de activación de salida que indique las ubicaciones posibles de sitios desconocidos. Tratado por un modelo de idoneidad del sitio, la capa de activación de salida fue validada con sitios conocidos excluidos del proceso de entrenamiento usando el área de operador receptor característico bajo de la curva. Los resultados son prometedores para áreas abiertas tal como cuencos. Diferencias en vegetación tienen relativamente poco efecto. Sin embargo, diferencias en elevación y los cambios concomitantes en fenología afectan negativamente la utilidad de este enfoque para inferir sitios arqueológicos.

Type
Research Article
Information
Advances in Archaeological Practice , Volume 4 , Issue 1 , February 2016 , pp. 87 - 101
Copyright
Copyright © Society for American Archaeology 2016

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

References Cited

Adams, E. Charles, and Duff, Andrew I. (editors) 2004. The Protohistoric Pueblo World, A.D. 1275–1600. University of Arizona Press, Tucson.Google Scholar
Agapiou, Athos, Hadjimitsis, Diofantos G., and Alexakis, Dimitrios D. 2012. Evaluation of Broadband and Narrowband Vegetation Indices for the Identification of Archaeological Crop Marks. Remote Sensing 4:3892–3919.Google Scholar
Agapiou, Athos, Hadjimitsis, Diofantos G., and Alexakis, Dimitrios D. 2013. Development of an Image-Based Method for the Detection of Archaeological Buried Relics Using Multi-temporal Satellite Imagery. International Journal of Remote Sensing. 34:5979–5996.Google Scholar
Agapiou, Athos, Hadjimitsis, Diofantos G., Alexakis, Dimitrios, and Sarris, Apostolos 2012. Observatory Validation of Neolithic Tells (Magoules) in the Thessalian Plain, Central Greece, Using Hyperspectral Spectroradiometric Data. Journal of Archaeological Science 39:1499–1512.Google Scholar
Bahn, Paul, and Renfrew, Colin 2008. Archaeology: Theories, Methods, and Practice. 5th ed. Thames and Hudson, London.Google Scholar
Barrett, Elinore M. 2012. The Spanish Colonial Settlement Landscape of New Mexico, 1598–1680. University of New Mexico Press, Albuquerque.Google Scholar
Bewley, Robert H. 2003. Aerial Survey for Archaeology. The Photogrammetric Record 18:273–292.Google Scholar
Cavalli, Rosa Maria, Colosi, Francesca, Polombo, Angelo, Pignatti, Steffano, and Poscolieri, Maurizio 2007. Remote Hyperspectral Imagery as a Support to Archaeological Prospection. Journal of Cultural Heritage 8:272–283.Google Scholar
Center for New Mexico Archaeology 2014 Galisteo Basin Archaeological Sites Protection Act. Electronic resource, http://galisteo.nmarchaeology.org/index.html, accessed November 13, 2015.Google Scholar
Chase, Arlen F., Chase, Diane Z., Fisher, Christopher T., Leisz, Stephen J., and Weishampel, John F. 2012. Geospectral Revolution and Remote Sensing LiDAR in Mesoamerican Archaeology. PNAS 109:12916–12921.Google Scholar
Current, John R., and Schilling, David A. 1990. Location Modeling: Perspective and Overview. Geographical Analysis 22:1–3.Google Scholar
Custer, Jay F., Eveleigh, Timothy, Klemas, Vytautas, and Wells, Ian 1986. Application of LANDSAT Data and Synoptic Remote Sensing to Predictive Models for Prehistoric Archaeological Sites: An Example from the Delaware Coastal Plain. American Antiquity 51:572–588.Google Scholar
Eastman, J. Ronald 2015. TerrSet Manual. Clark Labs, Worcester.Google Scholar
Findlow, Frank, and Confeld, Linda 1980. Landsat Imagery and the Analysis of Archaeological Catchment Territories: A Test of the Method of Catchment Analysis. In Catchment Analysis: Essays on Prehistoric Resource Space, edited by Findlow, Frank J. and Ericson, Jonathon E., pp. 31–52. University of California, Los Angeles.Google Scholar
Flannery, Kent (editor) 1982. The Early Mesoamerican Village. Academic Press, Waltham.Google Scholar
Foody, G.M. 2003. Uncertainty, Knowledge Discovery and Datamining in GIS. Progress in Physical Geography 27:113–121.Google Scholar
Hamilton, Scott, Graham, James, and Nicholson, B.A. 2007. Archaeological Site Distributions and Contents: Modeling Late Precontact Blackduck Land Use in the Northeastern Plains. Canadian Journal of Archaeology/ Journal Canadien d’Archéologie 31(3):93–136.Google Scholar
Heege, Thomas, Kiseleva, Viacheslav, Wettlea, Magnus, and Hungb, Nguyen Nghia 2014. Operational Multi-Sensor Monitoring of Turbidity for the Entire Mekong Delta. International Journal of Remote Sensing 35:2910–2926.Google Scholar
Hejcman, M., Karlík, P., Ondráček, J., and Klír, T. 2013. Short-Term Medieval Settlement Activities Irreversibly Changed Forest Soils and Vegetation in Central Europe. Ecosystems 16:652–663.Google Scholar
Hritz, Carrie 2014. Contributions of GIS and Satellite-based Remote Sensing to Landscape Archaeology in the Middle East. Journal of Archaeological Research 22:229–276.Google Scholar
Kennedy, David, and Bishop, M.C. 2011. Google and the Archaeology of Saudi Arabia. A Case Study from the Jeddah Area. Journal of Archaeological Science 38:1284–1293.Google Scholar
Kohler, Timothy A., Bocinsky, R. Kyle, Cockburn, Denton, Crabtree, Stefani A., Varien, Mark D., Kolm, Kenneth E., Smith, Schaun, Ortman, Scott G., and Kobti, Ziad 2012. Modelling Prehispanic Pueblo Societies in Their Ecosystems. Ecological Modeling 241:30–41.Google Scholar
Kruse, Melissa 2007. The Agricultural Landscape of Perry Mesa: Modeling Residential Site Location in Relation to Arable Land. Kiva 73(1):85–102.Google Scholar
Lasaponara, Rosa and Masini, Nicola 2005. Quickbird-Based Analysis for the Spatial Characterization of Archaeological Sites: Case Study of the Monte Serico Medieval Village. Geophysical Research Letters 32(12):L12313.Google Scholar
Lasaponara, Rosa and Masini, Nicola 2006. Identification of Archaeological Buried Remains Based on the Normalized Difference Vegetation Index (NDVI) from QuickBird Satellite Data. IEEE Geoscience and Remote Sensing Letters 3:325–328.Google Scholar
Lasaponara, Rosa, and Masini, Nicola 2007. Detection of Archaeological Crop Marks by Using Satellite QuickBird Multispectral Imagery. Journal of Archaeological Science 24:214–221.Google Scholar
Legg, Robert J., and Anderton, John B. 2010. Using Paleoshoreline and Site Location Modeling in the Northern Great Lakes: Geoarchaeological Approaches to Prehistoric Archaeological Survey in the Pictured Rocks National Lakeshore. Geoarchaeology 25:772–783.Google Scholar
Lippitt, Christopher D., Rogan, John, Li, Zhe, Eastman, J. Ronald, and Jones, Trevor G. 2008. Mapping Selective Logging in Mixed Deciduous Forest: A Comparison of Machine Learning Algorithms. Photogrammetric Engineering and Remote Sensing 74:1201–1211.Google Scholar
Lippitt, Christopher D., Rogan, John, Toledano, James, Sangermano, Florencia, Eastman, J. Ronald, Mastro, Victor, and Sawyer, Alan 2008. Incorporating Anthropogenic Variables into a Species Distribution Model to Map Gypsy Moth Risk. Ecological Modeling 210:339–350.Google Scholar
Lu, Dengsheng, Tian, Hanqin, Zhou, Guomo, and Ge, Hongli 2008. Regional Mapping of Human Settlements in Southeastern China with Multisensory Remotely Sensed Data. Remote Sensing of Environment 112:3668–36679.Google Scholar
Manzano Mountains State Park 2004. Manzano Mountains State Park Management Plan 2004–2008. Electronic document, http://www.emnrd.state.nm.us/SPD/documents/ManzanoStatePark_000.pdf, accessed November 13, 2015.Google Scholar
Mehrer, Mark, and Wescott, Konnie 2006. GIS and Archaeological Site Location Modeling. Taylor and Francis, Boca Raton.Google Scholar
Menze, Bjoern H., and Ur, Jason A. 2014. Multitemporal Fusion for the Detection of Static Spatial Patterns in Multispectral Satellite Images—With Application to Archaeological Survey. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 7:3513–3524.Google Scholar
Montufo, Antonio M. 1997. The Use of Satellite Imagery and Digital Image Processing in Landscape Archaeology: A Case Study from the Island of Mallorca, Spain. Geoarchaeology 12:71–85.Google Scholar
Myers, Adrian 2010. Camp Delta, Google Earth, and the Ethics of Remote Sensing in Archaeology. World Archaeology 42:455–467.Google Scholar
National Park Service 2014. Salinas Pueblo Missions. Electronic document, http://www.nps.gov/sapu/index.htm, accessed November 13, 2015.Google Scholar
Parry, John T. 1992. The Investigative Role of Landsat-TM in the Examination of Pre and Proto Historic Water Management sites in Northeast Thailand. Geocarto International 7(4):5–24.Google Scholar
Reeves, Dache M. 1936. Aerial Photography and Archaeology. American Antiquity 2:102–107.Google Scholar
Sadr, Karin, and Rodier, Xavier 2012. Google Earth, GIS and Stone-walled Structures in Southern Gauteng, South Africa. Journal of Archaeological Science 39:1034–1042.Google Scholar
St. Joseph, J.K. 1945. Air Photography and Archaeology. The Geographical Journal 105:47–59.Google Scholar
Stirn, Matthew 2014. Modeling Site Location Patterns Amongst Late-Prehistoric Villages in the Wind River Range, Wyoming. Journal of Archaeological Science 41:523–532.Google Scholar
United States Geological Service (USGS) 2014a USGS Earth Explorer. USGS. 01 July 2014. Electronic document, http://earthexplorer.usgs.gov/, accessed November 13, 2015.Google Scholar
United States Geological Service (USGS) 2014b Landsat Processing Details. USGS. 08 December 2014. Electronic document, http://landsat.usgs.gov/Landsat_Processing_Details.php, accessed November 13, 2015.Google Scholar
Upex, Stephen 1996. Leicestershire Headlands: Some Cropmarks in the Midlands. Current Archaeology 13:191–193.Google Scholar
Verhoeven, Kris, and Dales, L. 1994. Remote Sensing and Geographical Information Systems (GIS for Archaeological Research (Applied in Mesopotamia). In Cinquante-deux reflexions sur le Proche-Orient ancien, edited by Gasche, Hermann, Tanret, Michel, Janssen, C., and Degraeve, A., pp. 519–539. Peeters, Ghent.Google Scholar
Wilson, Chris 1994. Historic Resources Reconnaissance Survey of the Manzano and Sandia Mountain Villages. State Historic Preservation Division of Cultural Affairs, Santa Fe.Google Scholar