Integration of Local and Global Support Vector Machines to Improve Urban Growth Modelling
The use of local information for the classification and modelling of spatial variables has increased with the application of statistical and machine learning algorithms, such as support vector machines (SVMs). This study presents a new local SVM (LSVM) model that was developed to model the probabili...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-08-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2220-9964/7/9/347 |
| _version_ | 1811327239840595968 |
|---|---|
| author | Babak Mirbagheri Abbas Alimohammadi |
| author_facet | Babak Mirbagheri Abbas Alimohammadi |
| author_sort | Babak Mirbagheri |
| collection | DOAJ |
| description | The use of local information for the classification and modelling of spatial variables has increased with the application of statistical and machine learning algorithms, such as support vector machines (SVMs). This study presents a new local SVM (LSVM) model that was developed to model the probability of urban development and simulate urban growth in a subregion in the southwestern suburb of the Tehran metropolitan area, Iran, for the periods of 1992–1996 and 1996–2002. Based on the focal training sample, the model was calibrated using the cross-validation method, and the optimal bandwidth was determined. The results were compared with those of a nonlinear global SVM (GSVM) model that was calibrated based on the ten-fold cross-validation method. This study then evaluated an integrated SVM model (LGSVM) obtained based on a weighted combination of the local and global urban development probabilities. A comparison of the probability maps showed a higher accuracy for the LGSVM than for either the LSVM or GSVM model. To assess the performance of the LSVM, GSVM and LGSVM models in the simulation of urban growth, probability maps were employed as the transition rules for urban cellular automata. The results show that a trade-off between local and global SVM models can enhance the performance of urban growth modelling. |
| first_indexed | 2024-04-13T15:03:08Z |
| format | Article |
| id | doaj.art-4788bd0df0f94310a8c668a18a03aac7 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-04-13T15:03:08Z |
| publishDate | 2018-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-4788bd0df0f94310a8c668a18a03aac72022-12-22T02:42:14ZengMDPI AGISPRS International Journal of Geo-Information2220-99642018-08-017934710.3390/ijgi7090347ijgi7090347Integration of Local and Global Support Vector Machines to Improve Urban Growth ModellingBabak Mirbagheri0Abbas Alimohammadi1Faculty of Geodesy and Geomatics Engineering, K.N. Toosi University of Technology, Tehran 19967-15433, IranFaculty of Geodesy and Geomatics Engineering, K.N. Toosi University of Technology, Tehran 19967-15433, IranThe use of local information for the classification and modelling of spatial variables has increased with the application of statistical and machine learning algorithms, such as support vector machines (SVMs). This study presents a new local SVM (LSVM) model that was developed to model the probability of urban development and simulate urban growth in a subregion in the southwestern suburb of the Tehran metropolitan area, Iran, for the periods of 1992–1996 and 1996–2002. Based on the focal training sample, the model was calibrated using the cross-validation method, and the optimal bandwidth was determined. The results were compared with those of a nonlinear global SVM (GSVM) model that was calibrated based on the ten-fold cross-validation method. This study then evaluated an integrated SVM model (LGSVM) obtained based on a weighted combination of the local and global urban development probabilities. A comparison of the probability maps showed a higher accuracy for the LGSVM than for either the LSVM or GSVM model. To assess the performance of the LSVM, GSVM and LGSVM models in the simulation of urban growth, probability maps were employed as the transition rules for urban cellular automata. The results show that a trade-off between local and global SVM models can enhance the performance of urban growth modelling.http://www.mdpi.com/2220-9964/7/9/347support vector machinescellular automataprobability mapsurban development |
| spellingShingle | Babak Mirbagheri Abbas Alimohammadi Integration of Local and Global Support Vector Machines to Improve Urban Growth Modelling ISPRS International Journal of Geo-Information support vector machines cellular automata probability maps urban development |
| title | Integration of Local and Global Support Vector Machines to Improve Urban Growth Modelling |
| title_full | Integration of Local and Global Support Vector Machines to Improve Urban Growth Modelling |
| title_fullStr | Integration of Local and Global Support Vector Machines to Improve Urban Growth Modelling |
| title_full_unstemmed | Integration of Local and Global Support Vector Machines to Improve Urban Growth Modelling |
| title_short | Integration of Local and Global Support Vector Machines to Improve Urban Growth Modelling |
| title_sort | integration of local and global support vector machines to improve urban growth modelling |
| topic | support vector machines cellular automata probability maps urban development |
| url | http://www.mdpi.com/2220-9964/7/9/347 |
| work_keys_str_mv | AT babakmirbagheri integrationoflocalandglobalsupportvectormachinestoimproveurbangrowthmodelling AT abbasalimohammadi integrationoflocalandglobalsupportvectormachinestoimproveurbangrowthmodelling |