Omid Ashkriz; Babak Mirbagheri; Ali Akbar Matkan; Alireza Shakiba
Abstract
Introduction: Urban growth has accelerated in recent decades, therefore, predicting the future growth pattern of the city is very important to prevent environmental, economic, and social problems. The city of Tabriz has also experienced rapid growth of urban lands due to significant demographic changes, ...
Read More
Introduction: Urban growth has accelerated in recent decades, therefore, predicting the future growth pattern of the city is very important to prevent environmental, economic, and social problems. The city of Tabriz has also experienced rapid growth of urban lands due to significant demographic changes, which requires accurate simulation of urban growth to prevent negative environmental and economic consequences. The purpose of this study was to evaluate the performance accuracy of the proposed machine learning algorithms by spatial cross-validation method in combination with the cellular automata model to simulate urban growth.Material and methods: In this study, to analyze urban land-use changes, Landsat satellite images related to the years 1997, 2006, and 2015 were classified using the support vector machine algorithm. In the next step, change potential maps of non-urban to urban areas were produced using random forest algorithms, support vector machine, and multilayer perceptron neural network for two periods of calibration (1997 and 2006) and validation (2006 and 2015) based on distance from the main roads, distance from the city center, distance from built-up areas, distance from the rivers and railways, as well as slope, elevation, and two-class (agricultural/barren) land use layer as effective factors in the growth of the city. Finally, using the cellular automata model, the growth simulation of Tabriz city based on land use and change potential maps obtained from machine learning algorithms for the mentioned periods was performed. To prevent over-fitting of algorithms to training samples and to obtain optimistic results, in the process of extracting optimal parameters of machine learning algorithms, the spatial cross-validation method was used to reduce the spatial correlation between training and test data.Results and discussion: The results showed that the random forest algorithm with the area under the ROC curve of 0.9228 compared to the support vector machine and multilayer perceptron neural network algorithms with 0.8951 and 0.8726, respectively, had a better performance in estimating the change potential of non-urban to urban areas. Furthermore, in comparison with others, the random forest also clearly showed local variations in potential change. Finally, the growth of Tabriz city was simulated using the cellular automata model based on the obtained change potential maps. Comparison of the prediction map in the validation period with the current situation of urban areas in 2015 showed that the accuracy of an urban growth simulation model based on random forest with a Figure of Merit index of 0.3569 compared to models based on support vector machine and artificial neural network was more accurate in allocating non-urban to urban lands with 0.3496 and 0.3434, respectively.Conclusion: As machine learning algorithms such as artificial neural networks, support vector machines, and random forest are capable of solving non-linear problems, using them is strongly recommended for urban growth simulation. Also, among the algorithms used in this research, the random forest algorithm based on ensemble learning has a higher advantage than the two-support vector machine and the artificial neural network algorithms.
ِAshkan Mohammadi; Naser Shafiei Sabet; Alireza Shakiba
Abstract
Introduction: One of the major implications of accelerated urbanization is the spatial expansion of urban sprawl and the corrosive of villages and peripheral lands that have been numerous in metropolitan areas. The irregular sprawl and extension of the Tehran metropolis into surrounding areas have led ...
Read More
Introduction: One of the major implications of accelerated urbanization is the spatial expansion of urban sprawl and the corrosive of villages and peripheral lands that have been numerous in metropolitan areas. The irregular sprawl and extension of the Tehran metropolis into surrounding areas have led to disturbances and imbalances in the social, economic, and spatial organization of peripheral villages. In recent decades, urban growth analysis has started from a variety of perspectives. Over the past half century this phenomenon has been prominent in Iran. It originally took place in metropolises and large cities, but gradually moved to middle cities due to the centralized policies of the settlement .The study area has been expanding rapidly in the last three decades and has caused many environmental problems and rapid changes in the economic performance of villages and the transformation of valuable natural resources. Therefore, this research intends to investigate the manner and extent of land use changes in the study area by analyzing and accurately analyzing the phenomenon of creep and reducing the adverse effects by providing scientific solutions. Therefore, this research is intended by look up and accurate analysis of the sprawl phenomenon, study the method and extent of land use change in the study area and reduces its adverse effects by providing scientific solutions. Material and methods: For accurate analysis of the effects of sprawl phenomena, descriptive and analytical methods have been used. In this method, after collecting data contains Land sat satellite images with TM, ETM and OLI sensors and after visual interpretation of satellite images due to the absence of stroke errors, cloud spots by using remote sensing techniques and spatial information systems, the land use change process began in 1986, 2002, 2018, and divided into four residential and non-residential construction, vegetation, rangelands and roads. After that, the supervised classification operation was monitored by the SVM algorithm and the detection and determination of the sprawl pattern in the study area. Results and discussion: The calculations indicate that in the region of Tehran -Damavand, due to the crawling growth in discrete form and in some points continuous, the most changes in terms of increase is related to the use of residential construction 9.69% and the use of the road 1%, that this growing trend has reduced the use of pasture and vegetation by about 9.07% and 0.1%, respectively. After field operation and harvesting of samples with two-frequency GPS receivers and introducing it to the software, the classification of complications was performed by support vector machines with a mean total accuracy of 62.69% and a mean Kappa coefficient of 85.33%. Most changes were related to residential and non-residential classes and roads and in the study area, most vegetation coverings and agricultural land became industrial estates and recreational villas. This led to an increase the migration from villages to Tehran's metropolis, followed by the need for urban landscapes and finally fragility and instability of environmental resources. In Tehran- Damavand axis, these changes have been made by various factors and forces during its uneven spatial expansion. Conclusion: In the study of spatial and land use changes, it is important to pay attention to which side effects are slowly changing and which side effects change more quickly. In this research, it was revealed that the study of vegetation compared to other lands had the greatest change. Therefore, if there is no precise planning and policies and continuous monitoring to prevent this trend, there will be harmful and irreparable environmental impacts.
