{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:26:20Z","timestamp":1760235980215,"version":"build-2065373602"},"reference-count":27,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2021,10,12]],"date-time":"2021-10-12T00:00:00Z","timestamp":1633996800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OCE-1637630"],"award-info":[{"award-number":["OCE-1637630"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>The profession debates how to encode a categorical variable for input to machine learning algorithms, such as neural networks. A conventional approach is to convert a categorical variable into a collection of binary variables, which causes a burdensome number of correlated variables. TerrSet\u2019s Land Change Modeler proposes encoding a categorical variable onto the continuous closed interval from 0 to 1 based on each category\u2019s Population Evidence Likelihood (PEL) for input to the Multi-Layer Perceptron, which is a type of neural network. We designed examples to test the wisdom of these encodings. The results show that encoding a categorical variable based on each category\u2019s Sample Empirical Probability (SEP) produces results similar to binary encoding and superior to PEL encoding. The Multi-Layer Perceptron\u2019s sigmoidal smoothing function can cause PEL encoding to produce nonsensical results, while SEP encoding produces straightforward results. We reveal the encoding methods by illustrating how a dependent variable gains across an independent variable that has four categories. The results show that PEL can differ substantially from SEP in ways that have important implications for practical extrapolations. If users must encode a categorical variable for input to a neural network, then we recommend SEP encoding, because SEP efficiently produces outputs that make sense.<\/jats:p>","DOI":"10.3390\/ijgi10100686","type":"journal-article","created":{"date-parts":[[2021,10,13]],"date-time":"2021-10-13T06:38:41Z","timestamp":1634107121000},"page":"686","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Encoding a Categorical Independent Variable for Input to TerrSet\u2019s Multi-Layer Perceptron"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7671-3467","authenticated-orcid":false,"given":"Emily","family":"Evenden","sequence":"first","affiliation":[{"name":"Graduate School of Geography, Clark University, Worcester, MA 01610, USA"},{"name":"Department of International Development, Community, and Environment, Clark University, Worcester, MA 01610, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7287-5875","authenticated-orcid":false,"given":"Robert Gilmore","family":"Pontius Jr","sequence":"additional","affiliation":[{"name":"Graduate School of Geography, Clark University, Worcester, MA 01610, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,10,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1007\/s002679900095","article-title":"Using dynamic modeling to scope environmental problems and build consensus","volume":"22","author":"Costanza","year":"1998","journal-title":"Environ. Manag."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/s10708-004-4946-y","article-title":"Land-use change modeling: Current practice and research priorities","volume":"61","author":"Verburg","year":"2004","journal-title":"GeoJournal"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.envsoft.2013.09.010","article-title":"Inductive pattern-based land use\/cover change models: A comparison of four software packages","volume":"51","author":"Mas","year":"2014","journal-title":"Environ. Model. Softw."},{"key":"ref_4","unstructured":"Eastman, J.R., Van Fossen, M., and Solorzano, L. (2005). Transition potential modeling for land cover change. GIS, Spatial Analysis and Modeling, ESRI Press."},{"key":"ref_5","unstructured":"Eastman, J.R. (2020). TerrSet Geospatial Monitoring and Modeling System, Clark University. Available online: https:\/\/clarklabs.org."},{"key":"ref_6","first-page":"61","article-title":"Modeling REDD+ baselines using mapping technologies: A pilot study from Balpakram-Baghmara Landscape (BBL) in Meghalaya, India","volume":"9","author":"Areendran","year":"2013","journal-title":"Int. J. Geoinformat."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Gong, H., Simwanda, M., and Murayama, Y. (2017). An Internet-based gis platform providing data for visualization and spatial analysis of urbanization in major Asian and African cities. ISPRS Int. J. Geo-Inf., 6.","DOI":"10.3390\/ijgi6080257"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Kefi, M., Mishra, B.K., Kumar, P., Masago, Y., and Fukushi, K. (2018). Assessment of tangible direct flood damage using a spatial analysis approach under the effects of climate change: Case study in an urban watershed in Hanoi, Vietnam. ISPRS Int. J. Geo-Inf., 7.","DOI":"10.3390\/ijgi7010029"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Megahed, Y., Cabral, P., Silva, J., and Caetano, M. (2015). Land cover mapping analysis and urban growth modelling using remote sensing techniques in greater Cairo Region\u2014Egypt. ISPRS Int. J. Geo-Inf., 4.","DOI":"10.3390\/ijgi4031750"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Nath, B., Wang, Z., Ge, Y., Islam, K., Singh, R.P., and Niu, Z. (2020). Land use and land cover change modeling and future potential landscape risk assessment using Markov-CA model and analytical hierarchy process. ISPRS Int. J. Geo-Inf., 9.","DOI":"10.3390\/ijgi9020134"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Rimal, B., Zhang, L., Keshtkar, H., Haack, B.N., Rijal, S., and Zhang, P. (2018). Land Use\/land cover dynamics and modeling of urban land expansion by the integration of cellular automata and Markov chain. ISPRS Int. J. Geo-Inf., 7.","DOI":"10.3390\/ijgi7040154"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1080\/13658810410001713416","article-title":"Calibrating a neural network-based urban change model for two metropolitan areas of the upper Midwest of the United States","volume":"19","author":"Pijanowski","year":"2005","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1037\/h0042519","article-title":"The perceptron: A probabilistic model for information storage and organization in the brain","volume":"65","author":"Rosenblatt","year":"1958","journal-title":"Psychol. Rev."},{"key":"ref_14","unstructured":"Rumelhart, D.E., Hinton, G.E., and Williams, R.J. (1986). Learning internal representations by error propagation. Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1: Foundations, MIT Press."},{"key":"ref_15","first-page":"7","article-title":"A Comparative study of categorical variable encoding techniques for neural network classifiers","volume":"175","author":"Potdar","year":"2017","journal-title":"Int. J. Comput. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1186\/s40537-020-00305-w","article-title":"Survey on categorical data for neural networks","volume":"7","author":"Hancock","year":"2020","journal-title":"J. Big Data"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1007\/s10980-012-9710-y","article-title":"Land cover change in the Bolivian Amazon and its implications for REDD+ and endemic biodiversity","volume":"27","author":"Sangermano","year":"2012","journal-title":"Landsc. Ecol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1215","DOI":"10.1007\/s40808-017-0376-y","article-title":"An ensemble of spatially explicit land-cover model projections: Prospects and challenges to retrospectively evaluate deforestation policy","volume":"3","author":"Bradley","year":"2017","journal-title":"Model. Earth Syst. Environ."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zheng, X., He, G., Wang, S., Wang, Y., Wang, G., Yang, Z., Yu, J., and Wang, N. (2021). Comparison of machine learning methods for potential active landslide hazards identification with multi-source data. ISPRS Int. J. Geo-Inf., 10.","DOI":"10.3390\/ijgi10040253"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Jayne, C., Yue, S., and Iliadis, L. (2012). Evaluating the impact of categorical data encoding and scaling on neural network classification performance: The case of repeat consumption of identical cultural goods. Engineering Applications of Neural Networks, Springer.","DOI":"10.1007\/978-3-642-32909-8"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/S0167-8809(01)00183-9","article-title":"Modeling the spatial pattern of land-use change with GEOMOD2: Application and validation for Costa Rica","volume":"85","author":"Pontius","year":"2001","journal-title":"Agric. Ecosyst. Environ."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"101332","DOI":"10.1016\/j.ecoinf.2021.101332","article-title":"The utility of a hybrid GEOMOD-Markov Chain model of land-use change in the context of highly water-demanding agriculture in a semi-arid region","volume":"64","author":"Andaryani","year":"2021","journal-title":"Ecol. Inform."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1080\/15481603.2019.1658420","article-title":"Intensity analysis to communicate land change during three time intervals in two regions of Quanzhou City, China","volume":"57","author":"Quan","year":"2020","journal-title":"GIScience Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Amadlou, M., Karimi, M., and Pontius, R.G. (2021). A new framework to deal with the class imbalance problem in urban gain modeling based on clustering and ensemble models. Geocarto Int.","DOI":"10.1080\/10106049.2021.1923826"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Hsieh, W.W. (2009). Machine Learning Methods in the Environmental Sciences: Neural Networks and Kernels, Cambridge University Press.","DOI":"10.1017\/CBO9780511627217"},{"key":"ref_26","unstructured":"(2021, October 01). Commonwealth of Massachusetts. Available online: https:\/\/www.gismanual.com\/lookup\/MassGISLandUse.html."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1016\/j.ecolind.2019.01.057","article-title":"Intensity analysis and the figure of merit\u2019s components for assessment of a Cellular Automata\u2014Markov simulation model","volume":"101","author":"Varga","year":"2013","journal-title":"Ecol. Indic."}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/10\/10\/686\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:12:13Z","timestamp":1760166733000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/10\/10\/686"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,12]]},"references-count":27,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,10]]}},"alternative-id":["ijgi10100686"],"URL":"https:\/\/doi.org\/10.3390\/ijgi10100686","relation":{},"ISSN":["2220-9964"],"issn-type":[{"type":"electronic","value":"2220-9964"}],"subject":[],"published":{"date-parts":[[2021,10,12]]}}}