Iranian Journal of Remote Sensing & GIS
Year:2010 | Volume:2 | Issue:3|Papers Count:8

Spatial data in Geographic Information Systems (GIS) are inherently uncertain; and therefore a system that can handle and infer from such uncertain data is of vital importance. Fuzzy Inference System (FIS) is one of the well-known inference systems that have been considered by many scientists in the recent decades. The objective of this paper is to propose and implement a new framework for extracting fuzzy membership functions and fuzzy rules that can be used for allocating gas stations in the city of Tehran. In this research, some of the fuzzy membership functions and fuzzy rules were extracted by using training data, and the rest were estimated by interviewing experts and loading the results manually. A combination of fuzzy clustering algorithm and Genetic Algorithm (GA) were used to extract fuzzy membership functions and fuzzy rules automatically. In the first step, initial fuzzy membership functions and rules were extracted by clustering data and mapping them onto the axes of the coordinate systems. The fuzzy C-Means (FCM) algorithm was used for data clustering. Although the FCM is an efficient means, but it requires being define of the number of clusters (C) by an expert. Since C has a close relation with the number of rules and membership functions, so estimating it in advance is important. The mathematical formula used to determine the optimal number of clusters is referred to a cluster validity index. Fukuyama and Sugeno cluster validity index (VFS) were used to determine the optimum number of clusters in this paper. In the second step the GA, which is a member of the family of evolutionary techniques, was employed to find the optimum form of fuzzy membership functions and fuzzy rules. The purpose of this step was to obtain a suitable set of parameter values that described the fuzzy rules and fuzzy membership functions according to the optimization criterion. At the end, the fuzzy inference system was improved by adding experts’ knowledge in the form of fuzzy membership functions and fuzzy rules. The proposed system was used for allocating gas stations in Tehran, capital of Iran. According to the knowledge of safety and fuel experts, 10 governing factors in site selection of fuel stations are identified and organized in 10 GIS layers such as proximity to the main streets, proximity to highways, etc. The results of this research showed that the accuracy of the fuzzy inference system increased 53% by using GA. Also, by examining the histograms of the land suitability map for allocating gas stations, it was inferred that 9% of the region had a high potential for constructing gas stations.

An environmental increasing problem of the air pollution –as well as the pollutants - in megacities is the most prominent issue for urban decision makers. An important cause of air pollution in Tehran, the capital of Iran, is the engine exhausts of about 2 million motor vehicles operating in an extremely congested road space and 70, 000 industrial units. The dissemination of air quality information can be efficient in controlling ambient air pollution and minimizing related health threats. Public access to up-to-date and reliable data is considered as one of the key components of a successful environmental management. Moreover, it is necessary to provide on-demand processing functionalities in the context of environmental modeling. These requirements can be met by establishing suitable environmental monitoring systems. Such systems are data-intensive and time-sensitive ones.  They need to exchange and process heterogeneous data among multiple sensors deployed in a sensor network. Data from such sensors play an important role to improve notifying the pollution sources, preventing the health threats, and reducing the number of people affected by environmental pollution. But, the use of such data is hampered in many ways. Lack of easily available and usable metadata about the presence and capabilities of sensors, lack of common data formats that can be used by data producers and data consumers, lack of interoperability between dissemination and acquisition systems, and lack of interoperability between processing systems are some technical challenges in this context. In this research, the authors address these aforementioned technical challenges through developing a service-oriented architecture to facilitate accessing, processing, and visualizing of different types of sensors and observations. They discuss how the use of Web services technology and OGC framework can address such geospatially oriented challenges in an open standard way. The authors have designed and implemented standards-based, interoperable services that provide sensor observation delivery mechanism and processing capabilities in an environmental monitoring context. The services were deployed in a Web-based environmental monitoring system application, named Tehran Air Quality Reporter. It provides realtime air quality information through a Sensor Observation Service and generates on-demand air pollution maps, using a Web Processing Service. The standard specifications of the SWE and the WPS standard interface along with Web services technology were used to implement the components of the proposed system. The use of such standards can provide interoperability among geospatial processing systems. Since sensor observation data are offered to users in O& M and map generation process result provided in KML, data interoperability is achieved.  Furthermore, as Web service technologies along with SOS and WPS interfaces are utilized for the development of the system, no problems regarding the interaction between clients and the services deployed in server side are observed. Microsoft.NET Framework 3.5 was utilized to implement the server-side components of the proposed system. Web client technologies (Dynamic HTML, CSS, and JavaScript) were used in the client-side to provide user-friendly environment. AJAX technology is also used to provide more interactivity and rich user experience.

A majority of urban planning problems include spatial or natural components. However, in many urban planning researches, the spatial relationship factors are ignored or modeled poorly and therefore the results have not accurate enough. Moreover, a variety of factors such as land use, transportation, environment, culture and economy together with their spatial effects and relationships should be considered for a comprehensive urban planning. But, current researches have paid less attention to such comprehensive modeling. Multi-objective evolutionary algorithms are proper solutions for simultaneous optimization of urban planning factors as well as suitable urban planning. Meanwhile evolutionary algorithms by themselves, which ignore spatial relationships between real world features, cannot lead to proper solutions. In this paper, a multi-objective evolutionary algorithm with innovative operators for optimization of urban design and planning is developed. The model uses a cell-tree structure to encode the search space and then uses innovative cross-over and mutation operators to solve the spatial problems. The innovative model is used for design and planning of a new city, by simultaneous optimization of land use and transportation objectives, as a case study. NSGA-II was used as the multi-objective optimization algorithm. The results showed the suitability of the proposed approach for urban planning, especially, designing new towns.

Although fuzzy logic methods are of great interest in many GIS applications, the traditional fuzzy logic has two important deficiencies. First, applying the fuzzy logic is needed to assign, to every property and for every value, a crisp membership function. Second, fuzzy logic does not distinguish between the situation in which there is no knowledge about a certain statement and a situation that the belief to the statement in favor and against is the same. Due to this fact, it is not recommended for problems with missing data and where grades of membership are hard to define. Uncertainty and vagueness are parts and parcels of many geographical phenomena. In general there is rarely a clear boundary between such different natural phenomena. In this paper a simple fuzzy region and fundamental concepts for uncertainty modeling of spatial relationships are analyzed from the view point of intuitionistic fuzzy (IF) logic. The authors demonstrated how it could provide model for fuzzy region; i.e., regions with indeterminate boundaries. They introduced a new theoretical framework and discussed possible contribution to remote sensing. As a proof of their idea, the paper discusses the use of suggested model for different kind of uncertainty.

The Existence of important agricultural structure, civil, industrial and urban projects, needs of the sides of Karoon river, damages of geomorphologic changes, wide change of the meander in rout of the river and the role of them in natural Changes as well as the economical and social ones are the theories of survive of the intensity, type and amount of changes on Karoon river. The case study area is a part of Karoon river located in Khuzestan province in southwest of Iran. The length of this reach is about 364 km from the north of Shoshtar to the Arvandrod. In this research by using of satellite images (Land sat, IRS, Terra), GIS layers, Arial photos and field studies of the changes in Karoon river have been survived. In this reach the geomorphologic changes have been analyzed during a period of 52 years from 1955 to 2007. The purpose of this research is recognizing the most important geomorphologic land forms of the Karoon river sides and determining the amount of the changes during the study. The results show that the rate of changes and the length of river channel have been increased.

Land Surface Temperature (LST) is an important factor in global changing studies; to estimate the radiation budgets in heat balance studies and urban climatology researches. This research evaluates the potential of multispectral satellite data for retrieving the biophysical parameters to estimate the land surface temperature in Tehran city using ETM+satellite data. LST is investigated for different Land use/Land cover (LULC) types and LULC classification accuracy is evaluated as well. The classification results improve using MNF components in comparison with using of the Maximum Likelihood Classification (MLC). Emissivity and LST values are estimated using SEBAL algorithm. The results indicated that in city level, LULC has high impact on surface temperature regimes as well as NDVI and FVC are closely correlated with LST in several LULC categories. Using the regression analysis indicated that the used method in this research to estimate the emissivity and LST in heterogeneous urban area was suitable and it could be used in order to estimate urban temperature changes in city level for specific time period.

One of the major applications of high resolution satellite imagery is planning for the green areas in urban management. The number of trees and their attributes play a major role in urban green area management. Traditional methods used for counting the trees are too time - consuming and costly where usually are subject to error due to the human mistakes where in many cases it will come up with no spatial data. In this research, a new method is developed which uses high resolution satellite images. In this case study, a Panchromatic and a multispectral image of Quick bird from Bandar Abbas city, Iran, is used. There are various arrangements of the trees like dense groups, row of trees and individual trees in the study area. The most of them are ten years old and more. The Panchromatic and the multispectral images are fused and a NDVI map is produced. The potential seeds of the tree positions are then obtained applying a couple of morphological operators including Erosion and Regional Max. The result is, finally, adjusted by eliminating duplicated points and non-tree points. The method output shows good correlation with the ground truth data with an accuracy of about 90%.