Robert Gilmore Pontius Jr, PhD

Professor

950 Main Street

Worcester MA 01610-1477

USA

OFFICE PHONE 001 508 793 7761

OFFICE FAX 001 508 793 8881

Updated 17 March 2013.

Welcome to Gil Pontius’ home page from which you can obtain copies of the publications below. If you would like other publications, please see Gil’s CV, and then send your request and postal address to Gil (rpontius@clarku.edu).

Obtain computer programs and learn about Intensity Analysis, including optimal aggregation of categories, by visiting the Intensity Analysis website here.

See the new video concerning recent ideas in Land Change Modeling by clicking here.

Listen to my interview on University of Lagos by clicking here. The first four minutes are music, then the half-hour interview begins.

PUBLICATIONS AS JOURNAL ARTICLES:

N M Giner, C Polsky, R G Pontius Jr, and D M Runfola. 2013. Understanding the social determinants of lawn landscapes: A fine-resolution spatial statistical analysis in suburban Boston, Massachusetts, USA. Landscape and Urban Planning 111: 25-33. Left click to request a copy.
J Huang, Q Li, R G Pontius Jr, V K, and H Hong. 2013. Detecting the dynamic linkage between landscape characteristics and water quality in a subtropical coastal watershed, southeast China. Environmental Management 51(1): 32-44. Left click to request a copy.
V Gutierrez-Velez and R G Pontius Jr. 2012. Influence of carbon mapping and land change modelling on the prediction of carbon emissions from deforestation. Environmental Conservation 39(4): 325-336. Left click to request a copy.
S Aldwaik and R Pontius Jr. 2012. Intensity Analysis to unify measurements of size and stationarity of land changes by interval, category, and transition. Landscape and Urban Planning 106: 103-114. Left click to request a copy. For more information, click https://sites.google.com/site/intensityanalysis/. You can also download a free 8MB computer program to perform the analysis by right clicking here.
J Huang, R G Pontius Jr, Q Li, and Y Zhang. 2012. Use of Intensity Analysis to Link Patterns with Processes of Land Change from 1987 to 2007 in a Coastal Watershed of Southeast China. Applied Geography 34: 371-384. Left click to request a copy.
H Chen and R G Pontius Jr. 2011. Sensitivity of a land change model to pixel resolution and precision of the independent variable. Environmental Modeling & Software 16: 37-52. Left click to request a copy.
Y Gao, P Marpu, I Niemeyer, D M Runfola, N M Giner, T Hamill, and R G Pontius Jr. 2011. Object-based classification with features extracted by a semi-automatic feature extraction algorithm - SEaTH. Geocarto International 26(3): 211-226. Left click to request a copy. Table 4 has an error in the total column but the corresponding figure 5 is correct.
R G Pontius Jr, S Peethambaram and J-C Castella. 2011. Comparison of three maps at multiple resolutions: a case study of land change simulation in Cho Don District, Vietnam. Annals of the Association of American Geographers 101(1): 45-62. Left click to request a copy.
R G Pontius Jr and M Millones. 2011. Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment. International Journal of Remote Sensing 32(15): 4407-4429. Left click to request a copy. Download an Excel file to perform the calculations by clicking the link highlighted in green below. Click here to see the video.
H Chen and R G Pontius Jr. 2010. Diagnostic tools to evaluate a spatial land change projection along a gradient of an explanatory variable. Landscape Ecology 25: 1319-1331. Left click to request a copy.
R Manandhar, Inakwu O A Odeh and R G Pontius Jr. 2010. Analysis of twenty years of categorical land transitions in the Lower Hunter of New South Wales, Australia. Agriculture Ecosystems and Environment, 135: 336-346. Left click to request a copy.
R G Pontius Jr and X Li. 2010. Land transition estimates from erroneous maps. Journal of Land Use Science 5(1): 31-44. Left click to request a copy.
R G Pontius Jr and N Neeti. 2010. Uncertainty in the difference between maps of future land change scenarios. Sustainability Science. Left click to request a copy. Click here to see the video!
R G Pontius Jr and S Petrova. 2010. Assessing a predictive model of land change using uncertain data. Environmental Modeling & Software 25(3): 299-309. Left click to request a copy.
R G Pontius Jr and J Connors. 2009. Range of categorical associations for comparison of maps with mixed pixels. Photogrammetric Engineering & Remote Sensing, 75(8): 963-969. Left click to request a copy.
R G Pontius Jr, W Boersma, J-C Castella, K Clarke, T de Nijs, C Dietzel, Z Duan, E Fotsing, N Goldstein, K Kok, E Koomen, C D Lippitt, W McConnell, A Mohd Sood, B Pijanowski, S Pithadia, S Sweeney, T N Trung, A T Veldkamp, and P H Verburg. 2008. Comparing input, output, and validation maps for several models of land change. Annals of Regional Science, 42(1): 11-47. Left click to request a copy. The same document is available at www.springerlink.com. For color figures, see Pontius et al. (2007) listed under the conference proceedings on this web page.
R G Pontius Jr, O Thontteh and H Chen. 2008. Components of information for multiple resolution comparison between maps that share a real variable. Environmental and Ecological Statistics, 15(2): 111-142. Left click to request a copy. The same document is available at www.springerlink.com.
C Alo and R G Pontius Jr. 2008. Identifying systematic land cover transitions using remote sensing and GIS: The fate of forests inside and outside protected areas of Southwestern Ghana. Environment and Planning B, 35(2): 280-295. Left click to request a copy.
K Kuzera and R G Pontius Jr. 2008. Importance of matrix construction for multiple-resolution categorical map comparison. GIS and Remote Sensing, 45(3): 249-274. Left click to request a copy. Equation 11 has an error; the numerator of equation 11 should be [Prgij – (Prgi+ × Prg+j)]².
R G Pontius Jr, R Walker, R Yao-Kumah, E Arima, S Aldrich, M Caldas and D Vergara. 2007. Accuracy assessment for a simulation model of Amazonian deforestation. Annals of Association of American Geographers, 97(4): 677-695. Left click to request a copy. The same document is available at www.blackwell-synergy.com.
R G Pontius Jr, A J Versluis and N R Malizia. 2006. Visualizing certainty of extrapolations from models of land change. Landscape Ecology 21(7) p.1151-1166. Left click to request a copy.
R G Pontius Jr and C D Lippitt. 2006. Can error explain map differences over time? Cartography and Geographic Information Science 33(2) p.159-171. Right click to download.
R G Pontius Jr and M L Cheuk. 2006. A generalized cross-tabulation matrix to compare soft-classified maps at multiple resolutions. International Journal of Geographical Information Science 20(1) p.1-30. Left click to request a copy.
E Fedorko, R G Pontius Jr, S Aldrich, L Claessens, C Hopkinson Jr, and W Wolheim. 2005. Spatial distribution of land type in regression models of pollutant loading. Journal of Spatial Hydrology 5(2) p.60-80. Right click to download.
R G Pontius Jr and J Malanson. 2005. Comparison of the structure and accuracy of two land change models. International Journal of Geographical Information Science 19(2) p.243-265. Left click to request a copy.
R G Pontius Jr and J Spencer. 2005. Uncertainty in extrapolations of predictive land change models. Environment and Planning B 32 p.211-230. Right click to download. This paper won the Michael Breheny Prize for the Best Paper in Environment and Planning B in 2005.
R G Pontius Jr, D Huffaker and K Denman. 2004. Useful techniques of validation for spatially explicit land-change models. Ecological Modelling 179(4) p.445-461. Left click to request a copy.
R G Pontius Jr and N R Malizia. 2004. Effect of category aggregation on map comparison. Lecture Notes in Computer Science 3234 p.251-268 in M J Egenhofer, C Freska, and H J Miller (eds): GIScience2004. Right click to download.
R G Pontius Jr, E Shusas and M McEachern. 2004. Detecting important categorical land changes while accounting for persistence. Agriculture, Ecosystems & Environment 101(2-3) p.251-268. Right click to download.
R G Pontius Jr and Pablo Pacheco. 2004. Calibration and validation of a model of forest disturbance in the Western Ghats, India 1920-1990. GeoJournal 61(4) p.325-334. Left click to request a copy.
R G Pontius Jr and K Batchu. 2003. Using the relative operating characteristic to quantify certainty in prediction of location of land cover change in India. Transactions in GIS 7(4) p.467-484. Right click to download. The PDF of Pontius and Batchu (2003) is an electronic version of an article published in Transactions in GIS: complete citation information for the final version of the paper, as published in the print edition of Transactions in GIS, is available on the Blackwell Synergy online delivery service, accessible via the journal’s website at http://www.blackwellpublishing.com/tgis or http://www.blackwell-synergy.com.
R G Pontius Jr, A Agrawal and D Huffaker. 2003. Estimating the uncertainty of land-cover extrapolations while constructing a raster map from tabular data. Journal of Geographical Systems 5(3) p.253-273. Right click to download.
R G Pontius Jr. 2002. Statistical methods to partition effects of quantity and location during comparison of categorical maps at multiple resolutions. Photogrammetric Engineering & Remote Sensing 68(10) p.1041-1049. Right click to download.
R G Pontius Jr, J Cornell and C Hall. 2001. Modeling the spatial pattern of land-use change with GEOMOD2: application and validation for Costa Rica. Agriculture, Ecosystems & Environment 85(1-3) p.191-203. Right click to download.
L Schneider and R G Pontius Jr. 2001. Modeling land-use change in the Ipswich watershed, Massachusetts, USA. Agriculture, Ecosystems & Environment 85(1-3) p.83-94. Right click to download.
R G Pontius Jr and L Schneider. 2001. Land-use change model validation by a ROC method for the Ipswich watershed, Massachusetts, USA. Agriculture, Ecosystems & Environment 85(1-3) p.239-248. Right click to download.
R G Pontius Jr. 2000. Quantification error versus location error in the comparison of categorical maps. Photogrammetric Engineering & Remote Sensing 66(8) p.1011-1016. Right click to download. You can do the calculations described in this paper with PontiusMatrix23.xlsx.

PUBLICATIONS AS CONFERENCE PROCEEDINGS:

PUBLICATION AS BOOK CHAPTER:

PUBLICATION AS SOFTWARE MANUAL:

R G Pontius Jr and H Chen. 2006. GEOMOD Modeling. Chapter of help system in J Ronald Eastman. Idrisi 15: The Andes Edition. Worcester MA: Clark Labs. Right click to download.

You may be interested in the links below.

SUMMARY OF PONTIUS’ INTELLECTUAL CONTRIBUTIONS:

Robert Gilmore Pontius Jr has developed quantitative methods that have contributed greatly to Geographic Information Science (GIS) and Remote Sensing. Pontius began his career as an applied statistician and environmental scientist with expertise in geographic information science (GIS), ecological modeling, and land change science. The applied nature of his diverse activities has inspired him to derive mathematical proofs for generally applicable concepts concerning spatial measurements that are essential in GIS and Remote Sensing. He has presented these ideas in ways that have persuaded the professional culture to shift. Several of these methods have been incorporated into the GIS & Image Processing software Idrisi, which has over 100,000 users worldwide.

Pontius’ most important intellectual creation is a conceptual philosophy to compare maps mathematically in ways that visually match intuition. One can understand the philosophy in the context of comparison of two maps that share the same set of categories, such as the comparison of maps of land classes from two time points or the comparison between ground information versus a classified map. The philosophy focuses on the disagreement between the maps because it is more important to understand the disagreement than the agreement for practical purposes, such as characterizing land change or improving a classifier. Pontius’ approach separates the overall disagreement between the maps into two components: quantity disagreement and allocation disagreement. Quantity disagreement is the amount of difference between the reference map and a comparison map that is due to the less than perfect match in the proportions of the categories. Allocation disagreement is the amount of difference between the reference map and a comparison map that is due to the less than optimal match in the spatial allocation of the categories, given the proportions of the categories in the reference and comparison maps. It is important to separate overall disagreement into these two components, because these two components have different interpretations and implications for practical applications. For example, if the purpose is to estimate change over time in overall forest area on a landscape, then quantity disagreement is much more important than allocation disagreement. Pontius (2000 & 2002) were the first publications in the sequence to establish this approach, while Pontius and Millones (2011) is the most recent and clearest articulation of this philosophy. Pontius, Shusas, and McEachern (2004) used the philosophy to derive new measurements to characterize transitions among categories in a manner that offers an alternative to conventional inferential statistics. His philosophy formed the basis of Pontius and Spencer (2005), which won the Michael Brehney prize for best paper of the year in Environment and Planning B. Pontius and Cheuk (2006) used the philosophy to derive a cross-tabulation matrix that can analyze maps of categories where the pixels have categorical memberships that are mixed, soft or fuzzy. That paper was the most highly cited paper in its journal, IJGIS, during its first years of publication. Pontius and Connors (2009) built on that paper to show how associations among categories are sensitive to modifications in the spatial resolution of the maps. Pontius, Peethambaram, and Castella (2011) extended the philosophy to derive a method that compares simultaneously three maps of mixed pixels, which is essential for the validation of land change simulation models at multiple-resolutions. The approach has inspired additional methods to estimate land change over time from remotely sensed maps for the common case where map error is suspected but not measured due to lack of ground reference information (Pontius and Li 2010, Pontius and Lippitt 2006). Pontius, Thontteh and Chen (2008) unified the philosophy for a categorical variable with the philosophy for a real continuous variable. Pontius and his doctoral students are now using his philosophy to design novel methods to construct rigorous methods for accuracy assessment of object-based classifications. His Bachelors, Masters, and Doctoral advisees have won awards from the Association of American Geographers 15 times. Pontius’ philosophy presents a new way of thinking, while his equations are elegant in their clarity.

Pontius spreads this philosophy in a variety of ways. He has presented it in workshops that he has given 18 times since 2003 in Ecuador, France, Greece, India, Japan, Mexico, Namibia, Russia, Portugal, The Netherlands (twice), and seven cities in the USA. The workshop teaches the approach in the context of land change modeling using Pontius’ model Geomod (Pontius, Cornell, and Hall 2001), which has become a standard model to predict land change especially for management of the global carbon cycle in the context of Reduced Emissions due to Deforestation and Degradation (REDD) projects. Pontius’ method has become popular in part because he has designed an easy-to-use spreadsheet, which is freely available from his web site www.clarku.edu/~rpontius. The electronic spread sheet is especially useful for accuracy assessment in Remote Sensing because the outputs derive from a single confusion matrix that users enter.

Pontius presents his philosophy strategically and theatrically to inspire a shift in the scientific culture from where scientists previously strived to report levels of accuracy that are better than random to where scientists now strive to report clearly the sizes of various types of disagreement that show how maps are less than perfect. This cultural shift in the mentality of scientists is as important as any particular quantitative method, because the shift in mentality is necessary for clear communication among scientists, hence is necessary for advancement in all aspects of GIS and Remote Sensing. Pontius has induced this shift in the profession by showing how his own maps have various types of errors, and then by demonstrating that his work is typical of the situation of many others (Pontius et al. 2008). Pontius designs all of his professional presentations at conferences to show these characteristics, with the direct purpose to serve as an example to others that it is necessary and advantageous to expose openly the disagreements among maps and to adopt more informative methodologies that are either compliments to or alternatives to conventional statistical schools of thought.

He serves on the editorial boards of seven journals and has been a reviewer for 79 different journals. He is presently on a National Research Council Committee concerning the Needs and Research Requirements for Land-Change Modeling.