Urban Growth Modeling Considering Educational Institutions In Qazvin, Iran: An Investigation Into The Performance of Three ANFIS Methods

Due to increasing urbanization, the rapid expansion of urban spaces has become a major environmental concern over the last few decades. Therefore, modeling the urban expansion as a complex system has been scrutinized in recent years; however, determining the rules that lead to the expansion of urban areas has always been a challenging factor in this field, especially for disaggregated models like cellular automata (CA). To overcome this issue, in this research, an Adaptive Network-based Fuzzy Inference System (ANFIS) is proposed to enhance the simulation of urban growth through the automatic production of transition rules. The ANFIS can be associated with several inputs division methods, such as ANFIS accompanied by grid partitioning (ANFIS-GP), subtractive clustering (ANFIS-SC), and fuzzy c-means clustering (ANFIS-FCM). Hence, twenty-two ANFIS models based on Landsat images for the time interval from 2000 to 2010 and using different division methods were trained to investigate their effect on the efficiency of ANFIS in urban growth modeling. To examine the efficiency, the Cellular Automata-based Markov Chain (CA-MC) as a popular method was developed, and the simulation accuracy of CA-MC and the most accurate ANFIS models were obtained through comparison with observed data. The most accurate ANFIS-SC model had a Kappa of 0.76 and an overall accuracy of 93.41% for the 2019 simulated map. The results from this study reveal that the ANFIS model is effective at simulating urban expansion and the ANFIS-SC is superior to CA-MC, ANFIS-GP, and ANFIS-FCM models in urban expansion modeling.

Urban Growth Modeling Considering Educational Institutions: An Investigation Into the Performance of Three Anfis Methods

Due to increasing urbanization, the rapid expansion of urban spaces has become a major environmental concern over the last few decades. Therefore, modeling the urban expansion as a complex system has been scrutinized in recent years; however, determining the rules that lead to the expansion of urban areas has always been a challenging factor in this field, especially for disaggregated models like cellular automata (CA). To overcome this issue, in this research, an Adaptive Network-based Fuzzy Inference System (ANFIS) is proposed to enhance the simulation of urban growth through the automatic production of transition rules. The ANFIS can be associated with several inputs division methods, such as ANFIS accompanied by grid partitioning (ANFIS-GP), subtractive clustering (ANFIS-SC), and fuzzy c-means clustering (ANFIS-FCM). Hence, twenty-two ANFIS models based on Landsat images for the time interval from 2000 to 2010 and using different division methods were trained to investigate their effect on the efficiency of ANFIS in urban growth modeling. To examine the efficiency, the Cellular Automata-based Markov Chain (CA-MC) as a popular method was developed, and the simulation accuracy of CA-MC and the most accurate ANFIS models were obtained through comparison with observed data. The most accurate ANFIS-SC model had a Kappa of 0.76 and an overall accuracy of 93.41% for the 2019 simulated map. The results from this study reveal that the ANFIS model is effective at simulating urban expansion and the ANFIS-SC is superior to CA-MC, ANFIS-GP, and ANFIS-FCM models in urban expansion modeling.

The Influence of the Calibration Interval on Simulating Non-Stationary Urban Growth Dynamic Using CA-Markov Model

The temporal non-stationarity of land use and cover change (LUCC) processes is one of the main sources of uncertainty that may influence the calibration and the validation of spatial path-dependent LUCC models. In relation to that, this research aims to investigate the influence of the temporal non-stationarity of land change on urban growth modeling accuracy based on an empirical approach that uses past LUCC. Accordingly, the urban development in Rennes Metropolitan (France) was simulated using fifteen past calibration intervals which are set from six training dates. The study used Idrisi’s Cellular Automata-Markov model (CA-Markov) which is an inductive pattern-based LUCC software package. The land demand for the simulation year was estimated using the Markov Chain method. Model validation was carried out by assessing the quantity of change, allocation, and spatial patterns accuracy. The quantity disagreement was analyzed by taking into consideration the temporal non-stationarity of change rate over the calibration and the prediction intervals, the model ability to reproduce the past amount of change in the future, and the time duration of the prediction interval. The results show that the calibration interval significantly influenced the amount and the spatial allocation of the estimated change. In addition to that, the spatial allocation of change using CA-Markov depended highly on the basis land cover image rather than the observed transition during the calibration period. Therefore, this study provides useful insights on the role of the training dates in the simulation of non-stationary LUCC.

Modeling of Urban Growth Using Cellular Automata and GIS Case of Benslimane in Morocco

In this study, our goal was to research land-use change by combining spatio–temporal land use/land cover monitoring (LULC (1989–2019) and urban growth modeling (1999–2039) in Benslimane, Morocco, to determine the effect of urban growth on different groups based on cellular automata (CA) and geospatial methods. A further goal was to test the reliability of the AC algorithm for urban expansion modeling. To do this, four years of satellite data were used at the same time as population density, downtown distance, slope, and ground road distance. The LULC satellite reported a rise of 3.8 km2 (318% variation) during 1989–2019. Spatial transformation analysis reveals a good classification similarity ranging from 89% to 91% with the main component analysis (PCA) technique. The statistical accuracy between the satellite scale and the replicated built region of 2019 gave 97.23 %t of the confusion matrix overall accuracy, and the region under the receiver operational characteristics (ROC) curve to 0.94, suggesting the model's high accuracy. Although the constructed area remains low relative to the total area of the municipality's territory, the LULC project shows that the urban area will extend to 5,044 km2 in 2019, principally in the western and southwestern sections. In 2019–2039, urban development is expected to lead to a transformation of the other class (loss of 1,364 km2), followed by vegetation cover (loss of 0.345 km2). In spatial modeling and statistical calculations, the GDAL and NumPy Python 3.8 libraries were successful.