* Author to whom correspondence should be addressed; E-Mail: firstname.lastname@example.org. Received: 29 January 2012; in revised form: 7 February 2012 / Accepted: 8 February 2012 / Published: 23 February 2012
Abstract: The primary objective of this research is to predict and analyze the future urbangrowth of Dhaka City using the Landsat satelliteimages of 1989, 1999 and 2009. Dhaka City Corporation (DCC) and its surrounding impact areas have been selected as the study area. At the beginning, a fisher supervised classification method has been applied to prepare the base maps with five landcover classes. In the next stage, three different models have been implemented to simulate the landcover map of Dhaka city of 2009. These have been named as “Stochastic Markov (St_Markov)” Model, “Cellular Automata Markov (CA_Markov)” Model and “Multi Layer Perceptron Markov (MLP_Markov)” Model. Then the best-fitted model has been selected by implementing a method to compare landcover categories in three maps: a reference map of time 1, a reference map of time 2 and a simulation map of time 2. This is how the “Multi Layer Perceptron Markov (MLP_Markov)” Model has been qualified as the most appropriate model for this research. Later, using the MLP_Markov model, the landcover map of 2019 has been predicted. The MLP_Markov model extrapolates that built-up area increases from 46% to 58% of the total study area during 2009–2019.
Today, the population of the world is more than 7 billion and more than 60 percentages of it is working in primary sector. This ever increasing population has altered and modified most of earth’s land surfaces. Remote sensing data with auxiliary techniques provide dependable, updated and precise information for LULC mapping and future planning. The monitoring and mapping of LULC changes through the multi-temporal digital (satellite) data provides detailed information. In order to monitor the pattern, distribution and trend of urbanland use/ landcover change, it is necessary to integrate polarization, spatial, spectral and multi- temporal remotely sensed data to assess the spatial pattern and dynamics changes of urban areas in both the spatial and the temporal dimensions. This research paper aims to monitor the land use and landcover classes for the years 2006-07 and 2009-10 and their temporal analysis for Rania block of Sirsa district. Agriculture land, wastelands, built-up, plantation and water body are main classes observed in study area at first level classification. At second level double crop, rabi only, kharif only, current fallow, sand desertic, waterlogged seasonal and degraded pasture & grazing land are observed in both years.
Due to inappropriate planning and management, accelerated urbangrowth and tremendous loss in land, es- pecially cropland, have become a great challenge for sustainable urban development . Detection of such changes may help decision makers and planners to understand the factors in land use and landcover changes in order to take effective and useful measures. Remote sensing and GIS techniques may be used as efficient tools to detect and assess land use changes.In recent years, a considerable land use changes have occurred in the greater Zanjan area. In order to understand the type and rate of changes in this area, Landsat TM images captured in 1984 and 2011 have been selected for comparison.First, geometric correction and contrast stretch are applied. In order to detect and evaluate land use changes, image differencing, principal component analyses and Fuzzy ARTMAP classification method are applied. Finally, the results of landcover classifica- tion for three different times are compared to reveal land use changes.Then, combined Cellular Automata with Markov Chain analysis is employed to forecast of human impacts on land use change until 2020 in Zanjan area. The results of the present study disclose that about 44 percents of the total area changed their land use, e.g., changing agricultural land, orchard and bare land to settlements, construction of industrial areas and highways. The crop pattern also changes, such as orchard land to agricultural land and vice versa. The mentioned changes have occurred within last 27 years in Zanjan city and its surrounding area.
This study revealed land use/cover change of Manikganj Sadar Upazila concerning with urbaniza- tion of Dhaka city. The study area also offers better residential opportunity and food support for Dhaka city. The major focus of this study is to find out the spatial and temporal changes of land use/cover and its effects on urbanization while Dhaka city is an independent variable. For analyz- ing land use/cover change GIS and remote sensing technique were used. The maps showed that, between 1989 and 2009 built-up areas increased approximately +12%, while agricultural land decreased −7%, water bodies decreased about −2% and bare land decreased about −2%. The sig- nificant change in agriculture land use is observed in the south-eastern and north eastern site of the city because of nearest distance and better transportation facilities with Dhaka city. This study will contribute to the both the development of sustainable urbanland use planning decisions and also for forecasting possible future changes in growth patterns.
tant RS research has been conducted to date, particularly in urban change analysis and the modeling of growth [9,15-17], LULC evaluation [2,18-21], and urban heat- island research [19,22-24]. In particular, RS-based multi- temporalland use change data provide information that can be used for assessing the structural variation of LULC pattern. In addition, accurate and comprehensive land use change statistics are useful for devising sus- tainable urban and environmental planning strategies [3,25]. It is therefore very important to estimate the rate, pattern and type of LULC changes in order to predict future changes in urban development . Thus this study will attempt to identify the spatio-temporal pattern of LULC changes which occurred in Delhi usingsatelliteimages periodically from 1997 to 2008 in conjunction with the various master plans from 1962-2021 along with various socio-economic factors such as population, road density, vehicle population, Gross State Domestic Prod- uct (GSDP)”etc. to understand the dynamical pattern of urbanization and identify key features for sustainable environmental management of Delhi.
Structuring Waterfront: Waterside spaces perform multiple urban functions, structuring cities’ development along history. At the same time, these zones are the most dynamic and sensible ones of the water basin, playing essential environmental functions (Mello & Holenda, 2009). The urban waterfront and its relation to the city have undergone through various cycles of structural change: front door, isolation from the city, deterioration and neglect and redevelopment. (Shrestha, 2009). Waterfront of Buriganga River has already passed through these first three phases and waiting for future development to reconnect with the city. The previous relation between the river ‘Jati’ and ‘ Lal bagh fort’ is now totally disconnected due to unplanned chaotic development in between. The other side of this canal along study area is also facing tremendous pressure of rapid urbangrowth and disconnects its inhabitants with water. Roads and settlement come towards water on such a way that it seems these illegal encroachments will capture all the remaining water and be a part of the city very soon (Figure 5-A). This waterfront needs to develop as more dynamic and responsive urban space to regain the water retention area and stop further encroachments. On the other hand, most of the historical buildings and monuments of Dhaka city has developed along the river Buriganga. Although unstructured congested development of ‘Old city’ destroy the relation between river and these build forms, but still they work as major touristic spots for Dhaka city. These historical monuments allows the water front adjacent shaid nagar to develop as an area of culture, leisure, combined with a system of water retention ponds and urban void. Respecting existing road lines as major vehicular access roads towards site; new roads as bicycle tracks, pedestrian lane as well as green open spaces have proposed to create an environment friendly productive urban void for the city (Figure 4-B). With the motivation of ensuring sustainable living environment, this research has proposed to remove all illegal encroachments beside riverbank and reinforce the water retention area, which have mentioned in DMDP (Figure 4-C). Developing clean clear waterfront with recreational spaces instead of black narrow canal will give the city a breathing space, which the city is suffering for many years. It can be also a great touristic hub, as it already linked some importation heritage structures of old Dhaka. Proposed new river-front development connected with proposed Boulevard along western embankment and well-developed water infrastructure can also help to increase the economy by raising public activities and enhancing touristic business.
used to derive snow cover maps. The images in ENVI 4.8 software were classified by using the maximum likelihood algorithm. Other spatial analyses were performed in ARC-GIS 9.3 software. The maximum likelihood method was accuracy assessed by operation points of testing. The least and the average of overall accuracy of produced maps were found to be 91% and 98%, respec- tively. This demonstrates that the maximum likelihood method has high performance in the clas- sification of images. Overall snow cover and the review of terrain through the years 2008-2009 and 2009-2010 showed that snow cover begins to accumulate in November and reaches its highest magnitude in February. Finally, no trace of snow can be observed on the surface of the ba- sin in the month of May. By average, 34% of the basin is covered in snow from November through to May.
Shahjahanabad, as well as Delhi, is researched in the stream of inner city research, (Datta, 1983; Datta and Jha, 1983; Banerjee, 1975; Shrivastav, 1982; Nath, 1993; Dupont and Tingal, 1997; Sivam, 2003; Jain, 2004; Garella, 2006; Yamane et al., 2008; Dutta and Bandyopadhyay, 2012; Thaper, 1980). However, research that coverurban blight and renewal approaches are very few in number (Verma, 1993; Mehra, 1991). With the extract of literature on various issues, it can be argued that South and South- East Asian context urban problems, including the inner city distress are different, in various ways, compared to those in the Global North. The unprecedented growth of southern cities of recent decades coupled with economic and political changes make it difficult for urban planners to cope with, and the urban development perspective is to provide quantity rather than quality (Verma, 1993). And thus, development of new areas has become typical for the planning agencies in the developing world. Generally, such planning agencies are elitist in terms of formation, perspective and operation (Mehra, 1991). Like the planning agencies, also other service providing act in the same way. Consequently, the inner cities are left neglected in a way that perpetuate the inner cities as deprived and place for the deprived population (Verma, 1993; Roy, 2009b; Roy, 2009c; Watson, 2009; Leonard, 1986; Tunas, 2008). The trend of out migration from inner city with increased social and economic status (Khatun, 2003), which is observed in most of the cities worldwide, simply aggravates the misery of the city center which is further accentuated by its lack of or non-participation in the decision making arena.
As options for piped networks (predominantly non-conventional for LICs) are identified, planned and implemented, it may be necessary to allow the improved tanks to continue to discharge effluent into the drains (open surface and deep stormwater drains), without prosecution, until a piped network (conventional or non-conventional) is available and functioning for the users to connect into. This could be by way of offering a “grace period” to customers, before which penalties will not be applied providing the containment facilities are correctly operated and maintained (i.e. regularly desludged), and with clear guidance about the conditions under which penalties would be imposed once sewer connections become feasible. In the interim, households discharging to stormwater drains could be charged on the basis of using the drains as a form of combined sewer. Basic treatment would need to be provided at the drain outlets (primary screening and management of the discharge points as a minimum) to reduce impacts on the environment and public health risks. Special attention would be important to those drains most at risk of discharging into living environments, especially in low-lying areas. This sort of approach, though unconventional and requiring careful management to ensure transitioning as soon as feasible, would allow the development of sewered networks to be planned in line with changes to urban settlements, as the city develops and sewers can be introduced throughout the city, or new forms of sanitation are identified.
In the Mega-City Dhaka, with a population of 14 million (may rise to 22-25 million by 2020), rapid urban population growth has far outstripped the capacity of urban infrastructure, leading to low level of service delivery. The transport conditions in Dhaka are characterized by chronic traffic congestion and delays, high rate of accidents, low quality of public transport service, lack of comfort and safety for pedestrians and growing air pollution. In Dhaka, nearly fifty percent of the people are walking dependent, both for economic and efficiency reasons. A significant number of trips are made by bicycles and non-motorized three wheeler rickshaws. There is a high level of conflicts between motorized and non- motorized transport. Also, seventy seven percent of traffic accident fatalities were previously found to be pedestrians and fifty percent of these fatalities involved buses . At the current growth rate, the number of vehicles in the country is expected to double in the next ten years. This factor along with the high proportion of two-and three-wheeler motorized and non- motorized vehicles in the city and the relatively young age of the majority of the population, are contribute to the serious road accident casualties . In urban areas, the traffic roadway system is more complex where a mixed road user environment prevails and greater perceptual demands are placed on the road users. The heterogeneity of traffic, plying of modes with varying speed and maneuvering time makes the roads and intersections of cities of Bangladesh even more complex . These specific natures make Dhaka city unique and
Change detection is a technique used in remote sensing to measure surface processes for volumetric change such as map erosion and deposition. Methods of change detection are usually divided into pixel comparison directly and post- classification comparison . Change detection is useful in many applications related to LC changes, such as shifting cultivation and landscape changes, land degradation and desertification, coastal change and urban development Image pre-processing, deforestation, habitat fragmentation and other cumulative changes.. Some studies have indicated that human-induced landcover change (LCC) contributes significantly to the initiation and reactivation of landslides especially in populated regions, where landslides represent a major risk to infrastructure, human settlements and people .
Deep learning techniques are the valuable tool for classifying multispectral images into various landcover classes and it has been using in the field of LULC and produced better result than machine learning techniques . DBN is one of the kind of deep learning technique and it is proposed by Hinton et al in the year of 2006. DBN is an unsupervised neural network, and each layer is created by restricted Boltzmann machine (RBM). RBM was initially proposed by Paul Smolensky in the year of 1986 and it was extended by Geoffrey Hinton and collaborators in the year of mid-2000 for fast learning process. It has been successfully used in feature extraction, classification, pattern recognition  etc. The organization of this paper is as follows, section 2 describes about study area and data description, section 3 illustrates about methodology, section 4 explain about experimental result, section 5 present the conclusion and section 6 describes about reference.
Md. Sanaul Haque Mondal 2895
A good number of literatures were found on informal economy of developing countries. But the literatures on informal economy of Bangladesh are scanty. Huda et al. (2009) studied on measuring the effect of informal sector on women. The role of informal sector in economic development of Asian countries and urban environmental management was focused in several studies (Amin, 2005; Amin & Singh, 2002; Amin, 2001). The study of McKernan et al. (2005) exclusively examined the gender based formal and informal financial sectors of rural Bangladesh. Barmon (2011) studied on consumption patterns and saving rate of vendors of informal sectors in Bangladesh. Rouse (2004) studied on the effect of urban development on informal-sector enterprises. Although many researchers identified several types informal economic activities in Bangladesh, still there is a dearth of academic literature on socio- economic contribution of urban informal economy from a qualitative methods perspective. In developing countries including Bangladesh, informal economy pays little attention among the policy makers. As a result, this sector is still lag behind. No doubt urban formal sector cannot run smoothly without support from informal activity. Realizing the above significance of informal sector, this research was an effort to understand household level contribution of urban informal economic activities of Dhaka city. The research question of the study was: how does vegetable selling (as an informal business) contribute to improving socioeconomic conditions of vegetable vendors in Dhaka city and what obstacles they face as informal businessman?
According to the present analysis of Landsat data, paddy area (in km 2 ) in 2009 in each of the Gazipur sub-dis- tricts is 130.1 (Gazipur Sadar), 101.3 (Kaliakair), 90.3 (Kaliganj), 107.3 (Kapasia) and 158.8 (Sreepur). The BBS statistics, on the other hand, report that in 2009-2010, rice area (in km 2 ) and production (in metric ton) were 113.7/32,767 (Gazipur Sadar), 43.2/26,735 (Kaliakair), 31.7/26,552 (Kaliganj), 147.8/29,298 (Kapasia), and 153.2/30,106 (Sreepur) . On average, the paddy areas account for 27.1% of the total area, which is slightly smaller than the satellite result of 36.5% (588 km 2 ). Nonetheless, the present analysis of satellite data has re- vealed that paddy area increased by around 7% during the period from 2001 to 2009. This recovery in the paddy area can be associated with the adoption of modern rice varieties. Although regional statistical numbers are un- available, rice production increased by 6.4% from 2001 to 2008 in accordance with the social statistics in the whole country . The change of three rice types in 2008-2009 was 6% to 6% (Aus, no change), 41% to 37% (Aman), and 53% to 57% (Boro). In the harvesting periods of 2004-2005, 2005-2006 and 2006-2007, rice pro- duction was 251.57, 265.30 and 273.18 million metric tons, respectively . These changes indicate the recent improvement in the food security condition, especially in availability aspect. Records say that in the 1970s, 70% of the population were under the food consumption of poverty line in Bangladesh. In 2005, however, this went down to under half of the population. As such, nutrition situation in Bangladesh has improved, as manifested in per capita energy supply from 1800 kcal in 1970s to 3055 kcal in 2009 .
KEY WORDS: Remote Sensing, LandCover, Classification, Image Analysis, Data Mining, Knowledge Base, High resolution.
Nowadays, the availability of high-resolution images has increased the number of researches on urbanland use and landcover classification. Most of them have used object oriented image analysis with successful results. Although object oriented analysis offers effective tools to represent the knowledge of the scene, the tasks of building semantic network and selecting attributes are time-consuming. These processes demand considerable prior knowledge of the scene and of the urban object characteristics. Therefore, we propose to use the C4.5 decision tree algorithm to help semantic network construction and attribute selection processes. This algorithm selects the best subset of attributes based on an entropy measure and organizes the classes in a decision tree structure. To evaluate the performance of C4.5 algorithm, we conduced a landcover classification in an urban area of São José dos Campos (São Paulo state, Brazil). Two experiments were performed, one based on specialist knowledge using E-Cognition 4.1™ system and the other based on the decision tree generated by C4.5 algorithm . Both provided similar results although the C4.5 experiment was faster than the other.
formed by two types of X RL i j , , one is the class changed, the other is the class not.
3. Experimental results and analysis
In order to verify rightness of the algorithm, two groups of remote sensing images are adopted to compare the algorithm which the PCA-KMEANS algorithm proposed by dissertation . Figure (a) and (b) in figure 2 have four small map in all. Figure 1 is a reference, figure 2 is a detection map, figure 3 is the change detection algorithm result map of PCA-KMEANS algorithm proposed by dissertation . Figure 4 is the proposed change detection algorithm result in this paper. Using algorithm (a4, b4) and comparison algorithm (a3, b3) to detect the changes of images (a1, a2, b1, b2) at the same area, but different time phases, from the visual point of view, this algorithm is better. Thus, the detection accuracy of the algorithm in this paper is better than the comparison algorithm.
A spokesman for the district administration told the author that Katchi abadis are only acknowledged by the government if over 100 dwelling units in a cluster are located on government land, while slums can be located on public or private lands but they are not legally acknowledged by local, provincial or federal governments. According to him, katchi abadis are a subset of slums—ones whose existence is acknowledged by the government. Squatter settlements are again another subset of slums and refer to settlements where the occupants have unilaterally occupied land without permission or payment. Thus to get the status of being legally accepted as “katchi abadis” the residents of illegal slums sometimes manoeuvre things with the help of politicians. Usually with the help of lower government staff, these slums are shown in the government records as the dwellings that were growing very fast to force the district administration to give them the status of legal Katchi abadis, and further, after getting this status, to include them within the jurisdictional limits of city. In this way the urban limits of any city increases legally or illegally. While government interventions such as land regulations, property rights, and taxation and infrastructure investments are necessary for residents of urban areas, these slums, which are exempt in the sense of being outside the system, become serious obstacles to the development of cities. All of the participants admitted that the socio-economic conditions of the inhabitants of these squatter settlements are quite different from those of normal settlements. Some FG representatives, who belonged to big slums of Rawalpindi such as Shah Jewan colony, Sawan colony, Sadiq colony, Ahmadabad and Quaid-i-Azam colony, responded to my question about how life is in slums as follows: “Life is not treating us very kindly.” A woman (Rashida) during a visit to slum responded “Although life here’s not fair, but we do not have any other option”.
accuracy is increased with the help of cloud-shadow projection approach as a new solution to this problem which uses the geometrical relation between cloud and shadow. Cloud and shadow classification results are compared to Fmask method. Although, both methods have sufficient recall rates for cloud and shadow classification, region growing rate used by Fmask method to increase confidence interval causes non-cloud and non-shadow areas classified as cloud and shadow on many regions. Testing our algorithm with other satellites is also possible, if satellites have thermal and infrared bands. One of the restrictions of the proposed algorithm is the necessitiy of thermal infrared bands to find cold regions to compare clouds with other cold regions. Using only visible bands to find cloud regions is not possible in our algorithm, but using techniques like deep learning can yield good results with three bands images. Transferability of this method is tested with the same parameters by using different images from different study areas. In addition to algorithm like ACCA and Fmask, the usability and transferability of the algorithm developed here is proven in terms of simplification of processing steps and decreasing computational workload because of its superpixel-based approach.
In addition, the parameter setting is more convenient in the proposed framework than in CD_PCA_PCA [ 1 ], CD_MLS [ 2 ], and Semi_FCM [ 3 ]. One free-parameter is required in the proposed framework. Furthermore, the second technique of the proposed framework automatically provided a range for its parameter determination, which is valuable for parameter selection, especially for an inexperienced practitioner. In Figure 16 , the pairwise green line marked the threshold range predicted by the proposed framework for each experiment. The first minimum and maximum were captured automatically and referenced to the prediction threshold range. The binary threshold could be determined easily with the suggested auxiliary range, although the predicted range cannot directly determine a rational binary threshold for dividing a CMI into a BCDM. Furthermore, the relationship between detection accuracy and parameters varied within the suggested range, as illustrated in Figure 17 . MA is increased with the increment of parameter (T) in each experiment. By contrast, FA and OE are decreased with the increment in parameter (T) in each experiment. Furthermore, FA and OE inclined gradually to the horizontal line with the increment in parameter (T) and the constraints of the predicted range. This finding is essential for the parameter determination of the proposed framework. The growth performance of the third proposed technique, namely, RGA, is illustrated in Figure 18 to demonstrate the effectiveness of this method. In Figure 18 , the pixels of the growing area were along the change area and were continuously spatial despite the small size of the growing area. The quantitative comparison between the results of the second and third techniques (RGA) is presented in Table 5 ; this comparison was performed to investigate the advantages of the proposed method. In Table 5 , the detection accuracy was relatively improved in terms of the four experimental datasets when the proposed RGA is applied to optimize the initial binary change detection result, which was obtained using the second technique.
Land use and landcover (LULC) represent the ongoing challenge of envi- ronmental variation. The understanding of the level and process of its change is the basis for any environmental planning and management. In Morocco, as everywhere in the world, human population densities are constantly increas- ing on the coastal zones. This results in a continuous and rapid acceleration of the use of coastal space and an increase in pressures on ecosystems and the different species they contain. The purpose of this study is the analysis of the changes in LULC from 1985 to 2017 in the coastal area of Sebou estuary, si- tuated in the Northwest of the Moroccan Atlantic coast. The changes were identified and assessed after classifying a series of Landsat images taken dur- ing 1985, 2002 and 2017. The algorithm used for the classification is the Sup- port Vector Machine (SVM), which yielded results with accuracy higher than 85%. The results of the land use landcover change describe phenomenal ur- banization and deforestation, as well as an evolution of the agricultural sector, indicating the impact of anthropization in this vulnerable environment.