Integrating machine learning with Markov chain and cellular automata models for modelling urban land use change

Abstract Modelling urban land use change is of profound concern to environmental scientists who have found cellular automata models very attractive for simulating urban dynamics. The quest for suitable predictive models to improve realistic simulation of urban land use change has resulted in the use of several notable cellular automata calibrations. Cellular automata model has become very attractive and one of the strongest models for urban growth simulation due to its simplicity and possibility of evolution. However, the inability of cellular automata to include driving forces of urban growth in the simulation process has warranted further cellular automata calibrations to minimize this weakness. To address this problem, and contrary to previous cellular automata calibrations, this research presents a novel integration of support vector machine, Markov chain and cellular automata for urban change modelling. Support vector machine is introduced as a machine learning technique to mine the impact of the explanatory variables that drive urban change. Markov chain is employed to mine the urban transition probabilities between the various urban epochs while cellular automata are used to implement the incremental discrete time steps based on neighbourhood interaction from an initial time to a future time. This modelling is implemented using Landsat data acquired in 1984, 2000 and 2015 over Lagos in Nigeria; Africa’s most populous city. Urban transitions (1984-2000 and 2000-2015) are used to simulate future urban state in 2030 and validation metrics include McNemar's test. The introduction of stochasticity into the model helps create the typical randomness inherent in the real world for deriving future urban forms through discrete cellular automata iterations. The high accuracy obtained in this experiment implies a substantial fit between the predicted and reference data, which proves the robustness of this method for modelling urban change.

[1]  Xiaohua Tong,et al.  A new cellular automata framework of urban growth modeling by incorporating statistical and heuristic methods , 2020, Int. J. Geogr. Inf. Sci..

[2]  Suzana Dragicevic,et al.  Enhancing a GIS Cellular Automata Model of Land Use Change: Bayesian Networks, Influence Diagrams and Causality , 2007, Trans. GIS.

[3]  Yue Li,et al.  Simulation method of concrete chloride ingress with mesoscopic cellular automata , 2020 .

[4]  Junliang Fan,et al.  Comparison of Support Vector Machine and Extreme Gradient Boosting for predicting daily global solar radiation using temperature and precipitation in humid subtropical climates: A case study in China , 2018 .

[5]  Vadlamani Ravi,et al.  Churn prediction using comprehensible support vector machine: An analytical CRM application , 2014, Appl. Soft Comput..

[6]  Keith C. Clarke,et al.  Calibrating SLEUTH with big data: Projecting California's land use to 2100 , 2020, Comput. Environ. Urban Syst..

[7]  Huiling Chen,et al.  Chaotic multi-swarm whale optimizer boosted support vector machine for medical diagnosis , 2020, Appl. Soft Comput..

[8]  Wei Cai,et al.  Evacuation simulation and layout optimization of cruise ship based on cellular automata , 2017 .

[9]  Beniamino Murgante,et al.  Fuzzy definition of Rural Urban Interface: An application based on land use change scenarios in Portugal , 2018, Environ. Model. Softw..

[10]  Lotfi A. Zadeh,et al.  MAKING COMPUTERS THINK LIKE PEOPLE , 1984 .

[11]  Jiejun Huang,et al.  An Integrated Approach based on Markov Chain and Cellular Automata to Simulation of Urban Land Use Changes , 2015 .

[12]  S. Abdullah,et al.  Identifying factors and predicting the future land-use change of protected area in the agricultural landscape of Malaysian peninsula for conservation planning , 2020 .

[13]  Clifford T. Brown,et al.  The fractal geometry of ancient Maya settlement , 2003 .

[14]  Atsushi Nara,et al.  A meta-modeling approach for spatio-temporal uncertainty and sensitivity analysis: an application for a cellular automata-based Urban growth and land-use change model , 2018, Int. J. Geogr. Inf. Sci..

[15]  Anthony Gar-On Yeh,et al.  Neural-network-based cellular automata for simulating multiple land use changes using GIS , 2002, Int. J. Geogr. Inf. Sci..

[16]  Xiaoling Zhang,et al.  Urban spatial growth modeling using logistic regression and cellular automata: A case study of Hangzhou , 2020 .

[17]  A. Braimoh,et al.  Spatial determinants of urban land use change in Lagos, Nigeria , 2007 .

[18]  Bart De Moor,et al.  Cellular automata models of road traffic , 2005, physics/0509082.

[19]  K. Lahiri,et al.  Confidence Bands for ROC Curves With Serially Dependent Data , 2015 .

[20]  David O'Sullivan,et al.  Exploring Spatial Process Dynamics Using Irregular Cellular Automaton Models , 2010 .

[21]  Liang Yuan,et al.  A comparative approach to modelling multiple urban land use changes using tree-based methods and cellular automata: the case of Greater Tokyo Area , 2018, Int. J. Geogr. Inf. Sci..

[22]  O. Okwuashi,et al.  GIS-based simulation of land use change , 2014 .

[23]  Nazma Naskar,et al.  A survey of cellular automata: types, dynamics, non-uniformity and applications , 2016, Natural Computing.

[24]  Mariana Belgiu,et al.  Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis , 2018 .

[25]  Qi Lu,et al.  Exploring the potential climate change impact on urban growth in London by a cellular automata-based Markov chain model , 2017, Comput. Environ. Urban Syst..

[26]  Dipendra Nath Das,et al.  A neural network and landscape metrics to propose a flexible urban growth boundary: A case study , 2018, Ecological Indicators.

[27]  Xiaobin Jin,et al.  Reconstruction of historical arable land use patterns using constrained cellular automata: A case study of Jiangsu, China , 2014 .

[28]  Sudhir Kumar Singh,et al.  Modelling land use and land cover dynamics of Dedza district of Malawi using hybrid Cellular Automata and Markov model , 2020 .

[29]  David O'Sullivan.  Complexity science and human geography , 2004 .

[30]  Zhong-ren Peng,et al.  LandSys: an agent-based Cellular Automata model of land use change developed for transportation analysis , 2012 .

[31]  A. Benyoussef,et al.  Cognitive anticipation cellular automata model: An attempt to understand the relation between the traffic states and rear-end collisions. , 2020, Accident; analysis and prevention.

[32]  Duoqian Miao,et al.  Three-way confusion matrix for classification: A measure driven view , 2020, Inf. Sci..

[33]  B. Praba,et al.  Application of the graph cellular automaton in generating languages , 2020, Math. Comput. Simul..

[34]  L. Shchur,et al.  Dynamic fractals in spatial evolutionary games , 2017, Physica A: Statistical Mechanics and its Applications.

[35]  Yoshihiko Kayama,et al.  Characteristics of fractal cellular automata constructed from linear rules , 2019, Artificial Life and Robotics.

[36]  Xia Li,et al.  A Constrained CA Model for the Simulation and Planning of Sustainable Urban Forms by Using GIS , 2001 .

[37]  Mustapha Ouardouz,et al.  Cellular automata approach for modelling climate change impact on water resources , 2019, Int. J. Parallel Emergent Distributed Syst..

[38]  Rachel Whitsed,et al.  A hybrid genetic algorithm with local optimiser improves calibration of a vegetation change cellular automata model , 2017, Int. J. Geogr. Inf. Sci..

[39]  Fulong Wu,et al.  Calibration of stochastic cellular automata: the application to rural-urban land conversions , 2002, Int. J. Geogr. Inf. Sci..

[40]  Yuk Feng Huang,et al.  Support vector machine enhanced empirical reference evapotranspiration estimation with limited meteorological parameters , 2020, Comput. Electron. Agric..

[41]  Shaoying Li,et al.  Simulating urban dynamics in China using a gradient cellular automata model based on S-shaped curve evolution characteristics , 2018, Int. J. Geogr. Inf. Sci..

[42]  Zahari Taha,et al.  The identification of high potential archers based on fitness and motor ability variables: A Support Vector Machine approach. , 2018, Human movement science.

[43]  Roger White,et al.  Cellular Automata and Fractal Urban Form: A Cellular Modelling Approach to the Evolution of Urban Land-Use Patterns , 1993 .

[44]  Hailu Worku,et al.  Simulating urban land use and cover dynamics using cellular automata and Markov chain approach in Addis Ababa and the surrounding , 2020 .

[45]  F. Wu,et al.  Simulating urban encroachment on rural land with fuzzy-logic-controlled cellular automata in a geographical information system , 1998 .

[46]  Mark Brussel,et al.  Logistic regression and cellular automata-based modelling of retail, commercial and residential development in the city of Ahmedabad, India , 2014 .

[47]  G. Foody.  Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy , 2004 .

[48]  Huayi Wu,et al.  Coupling cellular automata with area partitioning and spatiotemporal convolution for dynamic land use change simulation. , 2020, The Science of the total environment.

[49]  Yongjiu Feng,et al.  How current and future urban patterns respond to urban planning? An integrated cellular automata modeling approach , 2019, Cities.

[50]  Ambalika Sharma,et al.  DCWI: Distribution descriptive curve and Cellular automata based Writer Identification , 2019, Expert Syst. Appl..

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

[52]  P. Gong,et al.  Integrated Analysis of Spatial Data from Multiple Sources: Using Evidential Reasoning and Artificial Neural Network Techniques for Geological Mapping , 1996 .

[53]  A. Poursaee.  Application of agent-based paradigm to model corrosion of steel in concrete environment , 2018 .

[54]  Roger White,et al.  Urban systems dynamics and cellular automata: Fractal structures between order and chaos , 1994 .

[55]  Shanshan Shi,et al.  Effects of household features on residential window opening behaviors: A multilevel logistic regression study , 2020, Building and Environment.

[56]  A. Antunes,et al.  A Cellular Automata Model Based on Irregular Cells: Application to Small Urban Areas , 2010 .

[57]  Jamal Jokar Arsanjani,et al.  ntegration of logistic regression , Markov chain and cellular automata odels to simulate urban expansion amal , 2012 .

[58]  Ye Tian,et al.  Maximizing receiver operating characteristics convex hull via dynamic reference point-based multi-objective evolutionary algorithm , 2020, Appl. Soft Comput..

[59]  Huayi Wu,et al.  A novel cellular automata model integrated with deep learning for dynamic spatio-temporal land use change simulation , 2020, Comput. Geosci..

[60]  Chris Webster,et al.  Coase, Spatial Pricing and Self -organising Cities , 2001 .

[61]  Christopher E. Ndehedehe,et al.  Tide modelling using support vector machine regression , 2016 .

[62]  B. Amiri,et al.  Simulating urban expansion and scenario prediction using a cellular automata urban growth model, SLEUTH, through a case study of Karaj City, Iran , 2015 .

[63]  Soohong Park,et al.  Incorporating Cellular Automata simulators as analytical engines in GIS , 1997, Trans. GIS.

[64]  A. Soffianian,et al.  Modeling Land Use/Cover Changes by the Combination of Markov Chain and Cellular Automata Markov (CA-Markov) Models , 2015 .

[65]  Liping Wang,et al.  Multi-agent based modeling of spatiotemporal dynamical urban growth in developing countries: simulating future scenarios of Lianyungang city, China , 2014, Stochastic Environmental Research and Risk Assessment.

[66]  Haijun Wang,et al.  Delineating early warning zones in rapidly growing metropolitan areas by integrating a multiscale urban growth model with biogeography-based optimization , 2020 .

[67]  Nur Shafira Nisa Shaharum,et al.  Oil palm mapping over Peninsular Malaysia using Google Earth Engine and machine learning algorithms , 2020, Remote Sensing Applications: Society and Environment.

[68]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[69]  Wenkai Li,et al.  Multiple land use change simulation with Monte Carlo approach and CA-ANN model, a case study in Shenzhen, China , 2015, Environmental Systems Research.

[70]  Yuek Ming Ho,et al.  The simulation and prediction of spatio-temporal urban growth trends using cellular automata models: A review , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[71]  Andrew Crooks,et al.  Projecting cropping patterns around Poyang lake and prioritizing areas for policy intervention to promote rice: A cellular automata model , 2018 .

[72]  M. Macy,et al.  FROM FACTORS TO ACTORS: Computational Sociology and Agent-Based Modeling , 2002 .

[73]  E. Pardo‐Igúzquiza,et al.  Estimation of the spatiotemporal dynamics of snow covered area by using cellular automata models , 2017 .