فصلنامه سنجش از دور و GIS ایران
پیاپی 3 (پاییز 1388)

The aim of this paper, is designing and evaluating an agent based GIS to identify the environmental risk areas based on the smoke plumes, derived from NOAA satellite images, and the online modeling of impacts over an environmental phenomenon. Air pollution is an event that produces risk areas and effects on the environment in many ways. Therefore, it is difficult to determine full impacts of this phenomenon for risks. Whereas, several aspects of this phenomenon such as growth change of vegetation covers, can be considered as an urgent application to make the spatial decisions. To solve this problem, it can be considered the application of environmental damages of the smoke plumes of Kuwait's oil well fire on the southwest forest lands of Iran's territory during the 1991 Persian Golf war. By checking of NOAA-AVHRR midday images, it could be confirmed the movement of oil pollution via south west of Iran territory. The polluted inland areas can be outlined as natural environmental resources. Then, it is necessary to online track, quick estimate and evaluate of risk values in terms of natural forest covers due to the mentioned atmospheric pollution. This purpose will be accessible, if an integrated intelligent system was designed for making decision. Thus, GIS and Remote sensing tools and data, are used to identify dangerous sites prior to undertaking further analyses or field investigations. In this paper, one of objectives is to evaluate different methods in a spatial agent based system in order to assess environmental risks for air pollution application. In this system, different genetic learning methods are evaluated to determine proper rules for reasoning. With respect to the uncertain nature and indeterminate boundaries of input spatial data (pollution plumes and risk area), it is necessary to use predictive mode of knowledge base for inference. Then, for each snapshot, the stored inference rules are learned and tuned based on the uncertain conditions. Thus, it is essential to design an appropriate agent based system to use in the final inference process to obtain risk areas. Therefore, risk areas are determined, and different genetic learning methods are evaluated using Landsat TM satellite images sample points.

The process of Remote Sensing is affected by several errors such as geometrical deterioration, radiometric imbalance and atmospheric effects among which the former has significant role. In this work using Radiosonde data of 5 years, a mean profile of the atmosphere for the region of the study were calculated. Then introducing this profile to 6S code, the images of the region were corrected for the effects of the atmosphere. The results were compared with those of corrected by predefined profiles such as Midsummer, Midwinter and Subtropical. The results show significant improvement in band 17 of MODIS. To compare the output images, the NDVI products of the region were used. It shows that the NDVIs of less than 0.4 decreases while those of more than 0.5 increases. This is in accordance with the results of other researchers.

In this paper an algorithm for classification of land cover from remote sensing data based on the combination of supervised and unsupervised neural networks is presented. The proposed algorithm composed of Self- Organizing Map (SOM) and Multi-Layer Perceptron (MLP) algorithms. Since the SOM is an unsupervised algorithm, it can’t determine the accurate label of image pixels by itself; therefore, in this paper, the MPL was used to determine the final label. The proposed algorithm includes two steps. First, the image segmented is performed using the SOM algorithm; second, the labels of all SOM’s neurons are determined using MLP and training data to produce the land cover thematic map. In this paper the different numbers of neurons were considered in SOM structure for reducing the number of mathematics operations. In this case, the PCA algorithm was applied for initialization SOM and the result of this part shows that the number of operations was reduced significantly. The algorithm performed on Landsat (ETM+) and Ikonos images to demonstrate its capability. Different combination algorithms were preformed in this work. All these algorithms were used to produce land cover map and then the obtained result were compared with SOM-MLP results. The obtained results showed the ability of SOM-MLP algorithm for land cover classification. In this regard, the result of maximum likelihood classifier, minimum distance algorithm and MLP were compared to proposed algorithms result. Finally, it is concluded that the SOM-MLP improves the accuracy of classification, and it is suitable to remote sensing data when there is not enough ground truth data for training.

Emergency management requires precise and reliable information about the current situation of emergency. Considering the time sensitive nature of emergency situations, it is necessary to collect and use spatial information of the current state of the emergency within the minimum waste of time. This will be achieved if in the context of a collaborative effort, each of the parties involved in emergency management, takes responsibilities for collecting some parts of spatial information required for emergency management and sharing them to be accessible for wider emergency management community.In this regard, former researches have illustrated that Spatial Data Infrastructure (SDI) and Web-based GIS are an appropriate framework to facilitate such collaboration in spatial data collection and sharing and to manage this spatial data in emergency situations. Although SDI conceptual models have been developed in the field of emergency management, paying attention to application of wireless networks and dependent technologies such as Mobile GIS, it is necessary to expand such SDI conceptual models based on the characteristics of the wireless networks and related technologies. In this research, first the developed SDI conceptual model for disaster management was expanded to support wireless and its related technologies such as mobile GIS environments in emergency management. Afterwards, based on the expanded SDI conceptual model, a pilot mobile GIS was designed, developed and implemented to be utilized by in-field emergency workers. Moreover, the implemented system was assessed and evaluated. In this regard, a hypothetical scenario for emergency management was explained. Then the system efficiency in complying with the requirements having been mentioned in the scenario was evaluated. Consequently, based on the proposed scenario and evaluating the developed mobile GIS application, utilization of wireless environments and mobile GIS together in the SDI framework result in facilitating and improving the quality of emergency management.

Every year hundreds of fires are occurring in our country; So that thousands hectare of forests, pastures and vegetables are being destroyed. Fires, in addition to economic damages cause environmental effects. In spite of effective factors in fire occurrence, monitoring, controlling and evaluating damages are of great importance. Frequent fire occurrence in different regions of Iran in the past few years cause natural resources researchers to conduct new research about forests in order to prevent from occurring and expanding fire or to differ its time. After launching Remote Sensing satellites, collecting information from earths surface become possible and by developing these technology, monitoring natural arena in short time become possible. Monitoring and evaluating damages are some of the Remote Sensing applications. In this research, different satellite images for detecting and determining fired region in the Khour palms in the Esfahan province were used. MODIS sensor recorded a fire on 1/8/2008, which the enhanced fire detection algorithm specified location of this fire. In the proposed fire detection algorithm, water and cloud mask is applied to eliminate thecorresponding pixels and then an appropriate threshold is applied to identify the potential fire regions. Afterwards, the pixels which have brightness temperature, spectral reflectance and temperature difference values smaller than 293 K in band 22, 0.3 in band 2 and 10 K between bands 22 and 31 respectively, will be labeled as potential fire pixels. Then using different thresholds and tests, fire pixels are extracted. The results indicate that based on global scale, using threshold value of 310 K for band 22 is not useful for detection of small and cold fires. Thus an optimized threshold has been used. Also, for evaluating damages and determining the area of burnt regions, a Landsat ETM+ satellite image was used which maximum likelihood classification is performed to identify the burned area. The achieved results show that about 9 hectare of the palms are burnt due to the occurred fire.

Today, Airborne laser scan has an important role in acquiring 3-d information from earth surfaces. Manually feature extraction from laser scan data is too time-consuming and expensive. Roads are the most fundamental linear features and extracting of their information is very important for related organizations in each country. The main aim of this research is to present an approach for detecting roads from LiDAR data, which exclusively uses data produced by LiDAR system (Range and Intensity). For this purpose, First the intensity data and then, both of range and intensity data were classified by Support Vector Machine. Next, high objects were removed by using slope-based filtering algorithm and Digital Terrain Model and Digital Non-Terrain Model layers were obtained and Then the result of classification step was modified by making use of Digital Non-Terrain Model layer. Next, by post processing includes five steps of "morphological cleaning", "eliminating small components", "connecting discontinuity in the roads Network", "deleting disconnected components" and "morphological closing" roads were identified from LiDAR data.By comparing the results of implementation the algotithm with ground truth data,values of 84.35% for completeness, 71.61% for correctness and 63.22% for quality were achieved.

Urban air quality control and monitoring are major concerns throughout the world. Real-time accessing and processing of air quality observations are key components for successful environmental monitoring and management. The emergence of air quality monitoring sensors and geospatial services are providing the fundamental infrastructure to begin building interactive analysis environment for planning better urban conditions. One of the applied solutions to monitor and mange the air pollution problem is the use of the sensor networks which are connected to Internet using various communicational channels. While air quality observations have tremendous scientific values, their potentials are not fully explored. In this case, the difficulties in information dissemination across heterogeneous computing platforms are the most important issues to be resolved. In other words, the lack of standard data structure and access methods for transporting and exchanging observations from one system to another in heterogeneous computing environments are the challenges to be addressed. With this in mind, this paper aims at using geospatial services in conjunction with Observation and Measurement (O&M) model to provide an efficient air quality dissemination framework for Tehran. Based on our practical tests, the framework proved to be an efficient solution for interoperable accessing and disseminating air quality sensor observations.