A Comparative Study of Machine Learning Techniques to Simulate Land Use Changes

Design and development of a practical land use change (LUC) model require both a high prediction accuracy, to predict the future changes, and a well-fitted model reflecting and monitoring real world. In this regard, many models follow the three phases: training, testing and validating, in the modelling process to maximise both the accuracy and fitness. Therefore, the choice of model for different applications is still a valid and important question. This paper applies and compares three widely used data mining models: classification and regression tree (CART), multivariate adaptive regression spline (MARS) and random forest (RF), to simulate urban LUCs of Shirgah in Iran. The results of these three phases for the three models: CART, MARS and RF, for the study area of Shirgah, in the north of Iran, verify that having the highest accuracy in the testing run does not necessarily guarantee the highest accuracy in the validating run. And so, with respect to the purpose of each project, such as modelling the current situation or predicting the future, the best model with the highest accuracy at the relevant phase or a combination of some/all should be selected. For example, in this study, MARS can provide the best accuracy in the validating run while the lowest level of accuracy in the testing run. RF provides the highest accuracy in the testing run and the lowest level of accuracy in the validating run.

[1]  Jie Shan,et al.  Genetic Algorithms for the Calibration of Cellular Automata Urban Growth Modeling , 2008 .

[2]  M. Ahmadlou,et al.  Multiple Land Use Change Modeling Using Multivariate Adaptive Regression Spline and Geospatial Information System , 2015 .

[3]  B. Pijanowski,et al.  Using neural networks and GIS to forecast land use changes: a Land Transformation Model , 2002 .

[4]  R. Gil Pontius,et al.  Land-cover change model validation by an ROC method for the Ipswich watershed, Massachusetts, USA , 2001 .

[5]  Jonah Gamba,et al.  Simulating Urban Growth Using a Random Forest-Cellular Automata (RF-CA) Model , 2015, ISPRS Int. J. Geo Inf..

[6]  Jacob Cohen,et al.  Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit. , 1968 .

[7]  Keith C. Clarke,et al.  Cellular automata modeling approaches to forecast urban growth for adana, Turkey: A comparative approach , 2016 .

[8]  Hossein Shafizadeh-Moghadam,et al.  USING MULTIVARIATE ADAPTIVE REGRESSION SPLINE AND ARTIFICIAL NEURAL NETWORK TO SIMULATE URBANIZATION IN MUMBAI, INDIA , 2015 .

[9]  Agung Wahyudi,et al.  Cellular Automata for Urban Growth Modelling: A Review on Factors defining Transition Rules , 2016 .

[10]  Edward J. Rykiel,et al.  Testing ecological models: the meaning of validation , 1996 .

[11]  Elizabeth Deakin,et al.  Inhalation of motor vehicle emissions: effects of urban population and land area , 2006 .

[12]  David L. Olson,et al.  Introduction to Business Data Mining , 2005 .

[13]  Y. Jeffrey Yang,et al.  Predicting plausible impacts of sets of climate and land use change scenarios on water resources , 2012 .

[14]  Thomas Koellner,et al.  Global land use impact assessment on biodiversity and ecosystem services in LCA , 2013, The International Journal of Life Cycle Assessment.

[15]  T. Koellner,et al.  Land use impacts on biodiversity in LCA: a global approach , 2013, The International Journal of Life Cycle Assessment.

[16]  Zhiyong Hu,et al.  Modeling urban growth in Atlanta using logistic regression , 2007, Comput. Environ. Urban Syst..

[17]  Qiongyu Huang,et al.  Future habitat loss and extinctions driven by land‐use change in biodiversity hotspots under four scenarios of climate‐change mitigation , 2015, Conservation biology : the journal of the Society for Conservation Biology.

[18]  Ahmadlou,et al.  Comparing ANN and CART to model Multiple Land Use Changes : A Case Study of Sari and Ghaem-Shahr Cities in Iran , 2022 .

[19]  Z. Hao,et al.  The impacts of climate change and land cover/use transition on the hydrology in the upper Yellow River Basin, China , 2013 .

[20]  Jerome H. Friedman.  Multivariate adaptive regression splines (with discussion) , 1991 .

[21]  J. Gareth Polhill,et al.  Agent-based land-use models: a review of applications , 2007, Landscape Ecology.

[22]  Daniel G. Brown,et al.  A review of current calibration and validation practices in land-change modeling , 2016, Environ. Model. Softw..

[23]  Manfred F. Buchroithner,et al.  LAND USE/LAND COVER CHANGE ANALYSIS AND ITS IMPACT ON SOIL PROPERTIES IN THE NORTHERN PART OF GADARIF REGION, SUDAN , 2013 .

[24]  Eric Koomen,et al.  Comparing the input, output, and validation maps for several models of land change , 2008 .

[25]  Xia Li,et al.  Cellular automata for simulating land use changes based on support vector machines , 2008, Comput. Geosci..

[26]  S. An,et al.  Assessing the impact of urbanization on regional net primary productivity in Jiangyin County, China. , 2007, Journal of environmental management.

[27]  J. Friedman,et al.  FLEXIBLE PARSIMONIOUS SMOOTHING AND ADDITIVE MODELING , 1989 .

[28]  Robert Gilmore Pontius,et al.  The total operating characteristic to measure diagnostic ability for multiple thresholds , 2014, Int. J. Geogr. Inf. Sci..

[29]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[30]  Mahdi Hasanlou,et al.  Integration of genetic algorithm and multiple kernel support vector regression for modeling urban growth , 2017, Comput. Environ. Urban Syst..

[31]  Robert Gilmore Pontius,et al.  Using the Relative Operating Characteristic to Quantify Certainty in Prediction of Location of Land Cover Change in India , 2003, Trans. GIS.

[32]  Hossein Shafizadeh-Moghadam,et al.  MODELING URBAN DYNAMICS USING RANDOM FOREST: IMPLEMENTING ROC AND TOC FOR MODEL EVALUATION , 2016 .

[33]  C. F. Lee,et al.  GIS-based geo-environmental evaluation for urban land-use planning: A case study , 2001 .

[34]  I. Masser,et al.  Urban growth pattern modeling: a case study of Wuhan city, PR China , 2003 .

[35]  Bryan C. Pijanowski,et al.  Comparing three global parametric and local non-parametric models to simulate land use change in diverse areas of the world , 2014, Environ. Model. Softw..

[36]  Y. Hayashi,et al.  Application of an integrated system dynamics and cellular automata model for urban growth assessment: A case study of Shanghai, China , 2009 .

[37]  D. Mengistu,et al.  Monitoring land use/land cover change impacts on soils in data scarce environments: a case of south-central Ethiopia , 2016 .