Machine learning methods for classification of the green infrastructure in city areas

Rapid urbanization in cities can result in a decrease in green urban areas. Reductions in green urban infrastructure pose a threat to the sustainability of cities. Up-to-date maps are important for the effective planning of urban development and the maintenance of green urban infrastructure. There are many possible ways to map vegetation; however, the most effective way is to apply machine learning methods to satellite imagery. In this study, we analyze four machine learning methods (support vector machine, random forest, artificial neural network, and the naive Bayes classifier) for mapping green urban areas using satellite imagery from the Sentinel-2 multispectral instrument. The methods are tested on two cities in Croatia (Varaždin and Osijek). Support vector machines outperform random forest, artificial neural networks, and the naive Bayes classifier in terms of classification accuracy (a Kappa value of 0.87 for Varaždin and 0.89 for Osijek) and performance time.

[1]  V. Rodriguez-Galiano,et al.  Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines , 2015 .

[2]  Daniel L. Civco,et al.  Artificial Neural Networks for Land-Cover Classification and Mapping , 1993, Int. J. Geogr. Inf. Sci..

[3]  Konstantinos Tzoulas,et al.  Mapping Urban Green Infrastructure: A Novel Landscape-Based Approach to Incorporating Land Use and Land Cover in the Mapping of Human-Dominated Systems , 2018 .

[4]  Tie-Yan Liu,et al.  On the Depth of Deep Neural Networks: A Theoretical View , 2015, AAAI.

[5]  Ian Mell,et al.  Can green infrastructure promote urban sustainability , 2009 .

[6]  Michael K Stenstrom,et al.  Using satellite imagery for stormwater pollution management with Bayesian networks. , 2006, Water research.

[7]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[8]  Jian Zheng,et al.  Combination of Tree Configuration with Street Configuration for Thermal Comfort Optimization under Extreme Summer Conditions in the Urban Center of Shantou City, China , 2018, Sustainability.

[9]  Ulf G. Sandstro¨m.  Green Infrastructure Planning in Urban Sweden , 2002 .

[10]  D. Botkin,et al.  Cities as environments , 1997, Urban Ecosystems.

[11]  Weiqi Zhou,et al.  Comparing Machine Learning Classifiers for Object-Based Land Cover Classification Using Very High Resolution Imagery , 2014, Remote Sensing.

[12]  Erwan Scornet,et al.  Tuning parameters in random forests , 2017 .

[13]  Massimiliano Pittore,et al.  Performance Evaluation of Machine Learning Algorithms for Urban Pattern Recognition from Multi-spectral Satellite Images , 2014, Remote. Sens..

[14]  Martin Kappas,et al.  Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery , 2017, Sensors.

[15]  A. Viera,et al.  Understanding interobserver agreement: the kappa statistic. , 2005, Family medicine.

[16]  Pat Langley,et al.  Induction of Selective Bayesian Classifiers , 1994, UAI.

[17]  Barnali M. Dixon,et al.  Application of Support Vector Machines for Landuse Classification Using High-Resolution RapidEye Images: A Sensitivity Analysis , 2015 .

[18]  Richard E. Neapolitan,et al.  Probabilistic reasoning in expert systems - theory and algorithms , 2012 .

[19]  I. V. Muralikrishna,et al.  An Approach for the Segmentation of Satellite Images Using Moving KFCM and Naive Bayes Classifier , 2013 .

[20]  Mahdi Hasanlou,et al.  A COMPARISON STUDY OF DIFFERENT KERNEL FUNCTIONS FOR SVM-BASED CLASSIFICATION OF MULTI-TEMPORAL POLARIMETRY SAR DATA , 2014 .

[21]  Damir Medak,et al.  Support Vector Machine Accuracy Assessment for Extracting Green Urban Areas in Towns , 2019, Remote. Sens..

[22]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[23]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

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

[25]  Colin Campbell,et al.  Learning with Support Vector Machines , 2011, Learning with Support Vector Machines.

[26]  Giles M. Foody,et al.  Status of land cover classification accuracy assessment , 2002 .

[27]  F. Gómez,et al.  Green zones, bioclimatics studies and human comfort in the future development of urban planning , 2001 .

[28]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.

[29]  Cardona Alzate,et al.  Predicción y selección de variables con bosques aleatorios en presencia de variables correlacionadas , 2020 .

[30]  Ingmar Nitze,et al.  COMPARISON OF MACHINE LEARNING ALGORITHMS RANDOM FOREST, ARTIFICIAL NEURAL NETWORK AND SUPPORT VECTOR MACHINE TO MAXIMUM LIKELIHOOD FOR SUPERVISED CROP TYPE CLASSIFICATION , 2012 .

[31]  Steven E. Franklin,et al.  A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery , 2012 .