Date of submission: 12
Download 0.72 Mb.
|
- Navigate this page:
- 7.1 Future Research
- References
7. ConclusionIn this study an attempt was made to monitor urban growth over the Austin urban area and make a prediction for future urban sprawl. A methodology was successfully devised and GIS systems, Landsat data, change detection methods and a multi-layer perceptron neural network were employed to monitor and analyse urban sprawl patterns and make a prediction for the future. The study has highlighted the use of freely available Landsat data to capture synoptic views of urban development and as the Landsat satellite archive continues to grow its use in this field becomes ever more valuable. The NDVI differencing change detection method was successfully utilised to monitor NDVI over the time-series of images. After testing for its accuracy it proved a reliable method and I was able to use a decline in NDVI as a proxy for urban growth. I was able to track the change in urban growth over time and assess the amount, location and direction of the changes. The distance of urban growth from the CBD showed an increase over time, which fits in with observed urban sprawl patterns. A highly significant correlation was observed between distance from roads and amount of sprawl, which is another commonly observed feature with urban sprawl. Patterns were also observed within census tracts, suggesting certain areas expanding at certain times and a link with the population of Austin was considered, noting that the period with the steepest rise in population also tied in to the epoch which experienced the greatest extent of urban growth. In the second part of the study the Idrisi Land Change Modeler was utilised to test the efficacy of using change detection maps to provide an input and estimate for urban growth in Austin in 2015. The previous decrease in NDVI was used and two explanatory variables, distance from roads and distance from past sprawl, were input in order to create transition potentials using the Multi-Layer Perceptron neural network. A Markov chain was then used to predict future land cover and two maps were created, one for 2010, which could be compared against the actual change for that period to validate the model and another for 2015, to predict the urban growth for that year. The validated 2010 model provided a very close prediction in terms of total amount of urban growth, however it did not perform so well in terms of location. The prediction for 2015 provides an interesting insight into potential future sprawl and although this cannot be validated at this point in time it could prove a useful tool in planning and mitigating against future sprawl. The findings in this study highlight that Austin is a sprawling city, despite smart growth efforts in the city. The amount, location and patterns of sprawl over the past 22 years have been assessed and the findings should be useful to those studying urban dynamics and managing against sprawl. Urban sprawl is a phenomena that has been acknowledged to cause many problems and is something faced by countless cities across the world. The framework developed in this study could be applicable to many other areas facing urban sprawl and used to quantify and analyse trends of past sprawl to help plan for the future. 7.1 Future ResearchIn terms of future research, imagery with a higher spatial resolution would be desirable in order to more accurately classify pixels, as at the 30 metre resolution there is likely to have been spectral confusion in pixels at the urban boundary. The NDVI differencing method has proved effective in capturing change to urban land, though the thresholds need to be carefully set. Whilst in this study it took an element of trial and error, developing an automated way to set the change thresholds would be preferable. Change detection is widely used and although this study used a fairly simple image differencing method based on the NDVI there are a number of other methods that could be explored, including change-vector analysis or principal components analysis. The MLP neural network has a large scope for future exploration, in particular inputting further explanatory variables for the algorithm to train on in order to more accurately describe and predict changes in the future. It is also possible to introduce a number of constraints (such as places where urban growth cannot take place, i.e. conservation areas) and also dynamic road building in the Land Change Modeler which could be explored further. When producing a prediction there is an option for a ’soft prediction’, which provides an assessment of change potential. This gives an indication of not what has changed, but what has the right conditions to precipitate change. Given the somewhat random nature of urban sprawl, this would be a good option for mapping. Due to time constraints these options were not explored but could prove very useful in improving the future prediction results. ReferencesAlig, R.J. (1986) Econometric analysis of the factors influencing forest acreage trends in the southeast, Forest Science, 32, pp. 119-134 Benedict, M.A. and McMahon, E.T. (2002) Green Infrastructure: Smart Conservation for the 21st Century, Sprawl Watch Clearinghouse Monograph Series Bernell, S., Plantinga, A.J. and Wu, J. (2003) Urban Sprawl and Obesity. In: American Agricultual Economics Association Meeting, July 2003, Montreal Bruekner, J.K. (2000) Urban Sprawl: Diagnosis and Remedies, International Regional Science Review, 23(2), pp. 160-171 Catalán, B., Sauri, D. and Serra, P. (2008) Urban sprawl in the Mediterranean? Patterns of growth and change in the Barcelona Metropolitan Region 1993-2000, Landscape and Urban Planning, 85, pp. 174-184 Centre for Remote Imagery, Sensing & Processing - CRISP (2001) Interpreting Optical Remote Sensing Images, Available at: http://www.crisp.nus.edu.sg/~research/tutorial/opt_int.htm [Accessed 30/08/2012] Chang, K.T. (2010) Introduction to Geographic Information Systems, Fifth Edition, Singapore, McGraw-Hill International City of Austin GIS (2012) City of Austin GIS Data Sets. Available at: ftp://ftp.ci.austin.tx.us/GIS-Data/Regional/coa_gis.html [Accessed 04/09/2012]
Clark Labs (2009) Land Change Modeler Overview, Available at: http://www.clarklabs.org/products/Land-Change-Modeler-Overview.cfm [Accessed 04/09/2012] CNN Money (2007) The fastest growing U.S. Cities, Available from: http://money.cnn.com/2007/06/27/real_estate/fastest_growing_cities/ [Accessed 04/09/2012] Dai, X.L. and Khorram, S. (1999) Remotely Sensed Change Detection Based on Artificial Neural Networks, Photogrammetric Engineering & Remote Sensing, 65(10), pp. 1187-1194 Downs, A. (1998) The Costs of Sprawl Revisited, Transportation Cooperative Research Program Report. DTREG (2012) Multilayer Perceptron Neural Networks. Available from: http://www.dtreg.com/mlfn.htm [Accessed 04/09/2012] Eastman, J.R. (2009) IDRISI Guide to GIS and Image Processing (Manual Version 16.02), Worcester, Clark University Elvidge, C.D., Sutton, P.C., Wagner, T.W. (2004) Urbanization: In Gutman, G., Janetos, A.C., Justice, C.O., Moran, E.F., Mustard, J.F., Rindfuss, R.R., Skole, D., Turner, B.L., Cochrane, M.A. (eds) Land change science: Observing, monitoring, and understanding trajectories of change on the earth’s surface (pp. 315-328), Dordrecht, Nethrelands: Kluwer Academic Publishers Ewing, R., Schmid, T., Killingsworth, R., Zlot, A. and Raudenbush, S. (2008) Relationship Between Urban Sprawl and Physical Activity, Obesity and Morbidity, Urban Ecology, 5, pp. 567-582 Frumkin, H. (2002) Urban Sprawl and Public Health, Public Health Reports, 117, pp. 201-217 Gairola, S. and Noresah, M. S. (2010) Emerging trend of urban green space research and the implications for safeguarding biodiversity: a viewpoint, Nature and Science, 8(7) pp. 43-49 Geller, A.L. (2003) Smart Growth: A Perspective for Livable Cities, American Journal of Public Health, 93(9), pp. 1410-1415 Goetz, S.J., Smith, A.J., Jantz, C., Wright, R.K., Prince, S.D. Mazzacato, M.E., Melchoir, B. (2003) Monitoring and predicting urban land use change: applications of multi-resolution multi-temporal satellite data. In: 2003 International Geoscience and Remote Sensing Symposium (IGARSS), Institute of Electrical and Electronics Engineers (IEEE),Toulouse, France, pp. 1567-1569 Griffiths, G.H. (1988) Monitoring urban change from Landsat TM and SPOT satellite imagery by image differencing, Proceeds of IGARSS 1988 Symposium, Edinburgh (Piscataway, NJ:IEEE), pp. 493-497 Griffiths, P., Hostert, P., Gruebner, O. and van der Linden, S. (2010) Mapping megacity growth with multi-sensor data, Remote Sensing of Environment, 114, pp. 426-439 Howarth, P.J. and Boasson, E. (1983) Landsat digital enhancements for change detection in urban environments, Remote Sensing of Environment, 13, pp. 149-160 Huang, J., Lu, X. X. and Sellers, J. M. (2007) A global comparative analysis of urban form: Applying spatial metrics and remote sensing, Landscape and Urban Planning, 82, pp. 184-197 Ji, W., Ma, J., Twibell, R. W. and Underhill, K. (2006) Characterizing urban sprawl using multi-stage remote sensing images and landscape metrics, Computers, Environment and Urban Systems, 30, pp. 861-879 Kaźmierczak, A. and Cavan, G. (2011) Surface Water flooding risk to vulnerable communities: Analysis of vulnerability, hazard and exposure. Landscape and Urban Planning, 103(2) pp. 185-197 Kneebone, E. (2009) Job Sprawl revisited: The changing geography of metropolitan employment. Washington DC, Brookings Institution Kraas, F. (2007) Megacities and Global Change in East, Southeast and South Asia, ASIEN, 103, pp. 9-22 Li, X. and Yeh, A.G. (2002) Neural-network-based cellular automata for simulating multiple land use changes using GIS, International Journal of Geographical Information Science, 16(4), pp. 323-343 Ligtenberg, A., Bregt, A.K. and van Lammeren, R. (2001) Multi-actor-based land-use modelling: Spatial planning using agents, Landscape and Urban Planning, 56, pp. 21-33 Lillesand, T.M. and Kiefer, R.W. (2000) Remote Sensing and Image Interpretation. Fourth Edition. New York: John Wiley & Sons, Inc. Martinuzzi, S., Gould, W.A. and Ramos Gonźalez, O.M. (2007) Land development, land use, and urban sprawl in Puerto Rico integrating remote sensing and population census data, Landscape and Urban Planning, 79, pp. 288-297 Masek, J.G., Lindsay, F.E. and Goward, S.N. (2000) Dynamics of urban growth in the Washington DC metropolitan area, 1973-1996, from Landsat observations, International Journal of Remote Sensing, 21(18), pp. 3473-3486 McMahan, J.B., Weber, K.T. and Sauder, J.D. (2002) Using Remotely Sensed Data in Urban Sprawl and Green Space Analyses, Intermountain Journal of Sciences, 8(1), pp. 30-37 Nechyba, T.J. and Walsh, R.P. (2004) Urban Sprawl, Journal of Economic Perspectives, 18(4), pp. 177-200 Neuroph – Java Neural Network Framework (2012) Multi-layer Perceptron, Available from: http://neuroph.sourceforge.net/tutorials/MultiLayerPerceptron.html [Accessed 04/09/2012] Parker, D.C., Manson, S.M., Janssen, M.A., Hoffman, M.J. and Deadman, P. (2003) Multi-Agent Systems for the Simulation of Land-Use and Land-Cover Change: A Review, Annals of the Association of American Geographers, 93(2), pp. 314-337 Pijanowski, B.C., Brown, D.G., Shellito, B.A., Manik, G.A. (2001) Using neural networks and GIS to forecast land use changes: a Land Transformation Model, Computers, Environment and Urban Systems, 26(6), pp. 553-575 Pontius Jr, R.G and Chen, H. (2006) GEOMOD Modeling, Chapter of help system, In: Eastman, J.R. Idrisi 15: The Andes Edition, Worcester, Clark Labs Prakash, A. and Gupta, R.P.( 1998) Land-use mapping and change detection in a coal mining area – a case study in the Jharia coalfield, India, International Journal of Remote Sensing, 19(3), pp. 391-410 Putnam, R. (2000) Bowling alone: the collapse of the American Community. New York, Simon & Schuster. Rafiee, R., Mahiny A.S. and Khorasani, N. (2009) Assessment of changes in urban green spaces of Mashad city using satellite data, International Journal of Applied Earth Observation and Geoinformation, 11, pp. 431-438 Ridd, M.K. and Liu, J.A. (1998) A comparison of four algorithms for change detection in an urban environment, Remote Sensing of Environment, 63, pp. 95-100 Rosenblatt, F. (1958) The perceptron: a probabilistic model for information storage and organisation in the brain, Psychological Review, 65, pp. 386-408 Rusk, D. (1999) Inside Game, Outside Game: Winning Strategies for Saving Urban America. Harrinsonburg, Virginia, R.R. Donnelley & Sons Schöpfer, E., Lang, S. and Blaschke, T. (2004) A “Green Index” incorporating remote sensing and citizen’s perception of green space, International Society for Photogrammetry and Remote Sensing, Joint Symposia URBAN-URS 2005 Tempe Arizona March 14-16th 2005, Conference Paper Sierra Club (1998) Sprawl Report, the dark side of the American dream: the costs and consequences of suburban sprawl. Available from http://www.sierraclub.org/sprawl/report98/austin.asp [Accessed 04/09/2012] Squires, G.D. (2002) Urban Sprawl and the Uneven Economic Development of Metropolitan America. In Squires, G.D. (eds) Urban Sprawl: Causes, Consequences and Policy Responses, Washington DC, Urban Press Institute, pp. 1-23 Sudhira, H.S., Ramachandra, T.V. and Jagadish, K.S. (2004) Urban Sprawl: metrics, dynamics and modelling using GIS, International Journal of Applied Earth Observation and Geoinformation, 5, pp. 29-39 Summerville, J. (2011) 2011 Assessment of Smart Growth in Austin, Texas, Unpublished Thesis (MSc), Texas State University-San Marcos Tateishi, R. (2002) Land cover mapping of Asia – problems and solutions of continental/global land cover mapping, Tropical Ecology, 43(1), pp. 3-8 Torrens, P.M. (2001) Can geocomputation save urban simulation? Throw some agents into the mixture, simmer and wait…., Publication 32, London: University College London US Census Bureau (2011) State & County QuickFacts – Austin, Texas, Available from: http://quickfacts.census.gov/qfd/states/48/4805000.html [Accessed 26/08/2012] US Census Bureau (2010) 2010 Census TIGER/Line® Shapefiles, Available from http://www.census.gov/geo/www/tiger/tgrshp2010/tgrshp2010.html [Accessed 23/08/2012] USGS (2012) Earth Explorer. Available from: http://earthexplorer.usgs.gov/ [Accessed 02/09/2012] Václavík, T. and Rogan, J. (2009) Identifying Trends in Land Use/Land Cover Changes in the Context of Post-Socialist Transformation in Central Europe: A Case Study of the Greater Olomouc Region, Czech Republic, GIScence & Remote Sensing, 46(1), pp. 1548-1603 Wikimedia Commons (2012) Melbourne2.jpg, Available from: http://en.wikipedia.org/wiki/File:Melbourne2.jpg [Accessed: 04/09/2012] Williams, D.L., Goward, S. and Arvidson, T. (2006) Landsat: Yesterday, Today and Tomorrow, Photogrammetric Engineering & Remote Sensing, 72(10), pp. 1171-1178 Wolter, P.T., Mladenoff, D.J., Host, G.E. (1995) Improved forest classification in the Northern Lake States using multi-temporal Landsat imagery, Photogrammetric Engineering and Remote Sensing, 68(7), pp. 725-734 Xian, G. and Crane, M. (2005) Assessments of urban growth in the Tampa Bay watershed using remote sensing data, Remote Sensing of Environment, 97, pp. 203-215 Yang, X. (2002) Satellite Monitoring of Urban Spatial Growth in the Atlanta Metropolitan Area, Photogrammetric Engineering and Remote Sensing, 68(7), pp. 725-734 Yuan, F., Sawaya, K.E., Loeffelholz, B.C. and Bauer, M.E. (2005) Land cover classification and change analysis of the Twin Cities (Minnesota) Metropolitan Area by multitemporal Landsat remote sensing, Remote Sensing of Environment, 98, pp. 317-328 Zhao, Z. and Kaestner, R. (2010) Effects of Urban Sprawl On Obesity, Journal of Health Economics, 29(6), pp. 779-787 Zhou, W., Troy, A. and Grove, M. (2008) Object-based Land Cover Classification and Change Analysis in the Baltimore Metropolitan Area Using Multi-temporal High Resolution remote Sensing Data, Sensors, 8, pp. 1613-1636
Download 0.72 Mb. Share with your friends:
|