Post-classification Change Detection Research Articles

Modeling of built-up lands expansion in Gaza Strip, Palestine using Landsat data and CA-Markov model

In Gaza Strip, Built-up lands expansion have reached critical level due to speed in population growth and high demand for new houses especially since the establishment of the Palestinian national authority (PNA) in 1994. In this context, more agricultural and arable lands have been transformed to built-up areas. Thus, monitoring and modelling this expansion is a fundamental task for sustainable management of available resources and long-term urban planning purposes. Against this background, the primary objective of this research is modelling and predicting the future expansion of built-up lands that would take place in the study area by the year 2036. The research was conducted based on times series satellite images that taken in (1992, 2003, 2014) by Landsat and Cellular Automata Markov (CA_Markov) model integrated with GIS and multi criteria evaluation technique. In this research, land cover maps have been prepared based on the satellite images and the post classification change detection technique has been employed for quantitative analysing of the past land cover changes among the study area. Then, CA_Markov model has been implemented and validated. Later, the land cover map for the year 2036 has been predicted. The results illustrate that if the trend of change in the future period continue as the same the built-up lands would cover 45.3% of the total area in Gaza Strip by 2036. Moreover, the expansion of the built-up lands occurred at the expense of the agricultural and arable lands. In conclusion, this research demonstrated that Gaza Strip face serious crisis if the same pattern followed. Therefore, focus on urban planning is essential to control the expansion of built-up lands and minimize the negative impacts of urbanization in Gaza Strip.

Effects of Tree-crop Farming on Land-cover Transitions in a Mosaic Landscape in the Eastern Region of Ghana

Tree crops such as cocoa and oil palm are important to smallholders’ livelihoods and national economies of tropical producer countries. Governments seek to expand tree-crop acreages and improve yields. Existing literature has analyzed socioeconomic and environmental effects of tree-crop expansion, but its spatial effects on the landscape are yet to be explored. This study aims to assess the effects of tree-crop farming on the composition and the extent of land-cover transitions in a mixed cocoa/oil palm landscape in Ghana. Land-cover maps of 1986 and 2015 produced through ISODATA, and maximum likelihood classification were validated with field reference, Google Earth data, and key respondent interviews. Post-classification change detection was conducted and the transition matrix analyzed using intensity analysis. Cocoa and oil palm areas have increased in extent by 8.9% and 11.2%, respectively, mainly at the expense of food-crop land and forest. The intensity of forest loss to both tree crops is at a lower intensity than the loss of food-crop land. There were transitions between cocoa and oil palm, but the gains in oil palm outweigh those of cocoa. Cocoa and oil palm have increased in area and dominance. The main cover types converted to tree-crop areas are food-crop land and off-reserve forest. This is beginning to have serious implications for food security and livelihood options that depend on ecosystem services provided by the mosaic landscape. Tree-crop policies should take account of the geographical distribution of tree-commodity production at landscape level and its implications for food production and ecosystems services.

Detection and impact of land encroachment in El-Beheira governorate, Egypt

Mainly, the high fertile land of Egypt is limited and threatened by the problem of land dwindling. In this context, three temporal satellite imagers were utilized to generalize the land cover changes. This is to reliable monitoring the urban sprawl changes and its action on farming area in El-Beheira governorate, Egypt, after the revolution of January 25th. The two algorithms of supervised maximum likelihood and post-classification change detection were implemented through cross tabulation for monitoring the urban sprawl to achieve change detection. Implementing ancillary data, digital interpretation and the area expert knowledge further refined the classification results. GIS utilities assist to argue out the risk of urban expansion at the expense of highly productive units. The output results showed that the rapid imbalance changes occurred among three land cover classes (urban, desert and cultivated land). During the (1985–2013) period, the urban land cover area was increased from 137.9 to 579.4 km2 (23.8%). Nevertheless, in just 3 years (2010–2013) urban sprawl expanded from 381.9 to 579.4 km2 (65.9%) as a total loss of cultivated land, during the insecure situation of the 25th revolution. Exclusively, these changes strengthened the land fragmentation processes over the green land as a result of urban encroachment. Information on urban growth, land use/cover change are essential for local government and urban planners for the amelioration of future sustainable development.

Relationship in metastasis of coal fire and land use/cover using thermal imagery and support vector machine classifier

The objective of the present study was to delineate temporal and spatial changes in the coal fire and land use/cover within Bastacolla area of Jharia coal field. Studying this variation helped to decipher interconnection among the dynamics of the coal fire and concomitant changes in land use/cover. The detection of coal fires during a span of 14 years along with transitioning land use/cover was cost-effective and enabled planning for management of coal resources and environment. Landsat series of satellite data of 2002, 2009, 2013, and 2016 were processed for generating land surface temperature profiles vis-a-vis classified land use/cover of the study area. A single cut-off temperature was derived for mapping of coal fires using land surface temperature profile from 2002 to 2016. The satellite images were classified using support vector machines, and for depicting land use/cover change, post-classification change detection was done. Classification accuracy obtained was excellent with kappa coefficient ranging from 0.897 for classified image of 2002 to 0.799 for classified image of 2016. Results revealed that coal fires had shifted to the central west part of the area. Furthermore, pockets of coal fire from northern and eastern part of the study area have diminished. OB dumps and coal quarry/coal dump may be attributed towards the spatial change in coal fire while; OB dumps showed connotation with the highest temperature zones. Ground verifications for temperature profiles and coal fires were carried out using thermal camera which enunciated good agreement with results.

Time Series Land Cover Mapping and Change Detection Analysis Using Geographic Information System and Remote Sensing, Northern Ethiopia

Land use planners require up-to-date and spatially accurate time series land resources information and changing pattern for future management. As a result, assessing the status of land cover change due to population growth and arable expansion, land degradation and poor resource management, partial implementation of policy strategies, and poorly planned infrastructural development is essential. Thus, the objective of the study was to quantify the spatiotemporal dynamics of land use land cover change between 1995 and 2014 using 5 multi-temporal cloud-free Landsat Thematic Mapper images. The maximum likelihood (ML)-supervised classification technique was applied to create signature classes for significant land cover categories using means and variances of the training data to estimate the probability that a pixel is a member of a class. The final Bayesian ML classification resulted in 12 major land cover units, and the spatiotemporal change was quantified using post-classification and statistical change detection techniques. For a period of 20 years, there was a continuously increasing demand for arable areas, which can be represented by an exponential growth model. Excepting the year 2009, the built-up area has shown a steady increase due to population growth and its need for infrastructure development. There was nearly a constant trend for water bodies with a change in slope significantly less than +0.01%. The 2014 land cover change statistics revealed that the area was mainly covered by cultivated, wood, bush, shrub, grass, and forest land mapping units accounting nearly 63%, 12%, 8%, 6%, 4%, and 2% of the total, respectively. Land cover change with agro-climatic zones, soil types, and slope classes was common in most part of the area and the conversion of grazing land into plantation trees and closure area development were major changes in the past 20 years.

Coastal wetland change detection using high spatial resolution KOMPSAT-2 imagery

Coastal wetlands store terrestrial carbon and conserve biodiversity, thus playing an essential ecological role. Reliable regional-scale assessments of wetland dynamics, such as analysis of land use and land cover (LULC), and coastal monitoring, provide important hydrographical and socio-geographical information. Remote sensing images, such as Earth Observation satellite data, are useful for examining temporal LULC changes and providing environmental monitoring data. This study presents a method of mapping and monitoring changes in coastal LULC using classified multispectral images acquired by the Korea Multi-Purpose Satellite-2 (KOMPSAT-2). Wetland changes are monitored in three different protected tidal flats areas on the coastal boundary of the Korean Peninsula with the Yellow Sea, for the period of 2008 - 2015. High overall accuracy and Kappa coefficient values for the accuracy assessment indicate the suitability of LULC classification using high spatial resolution KOMPSAT imagery, even when an unsupervised classification approach is adopted. The LULC maps were analyzed and evaluated using post-classification change detection methods. Results showed spatial decreases of 6 and 20% for mixed forest and wetlands in the Gyeonggi area, respectively, but no significant changes over time for Jeonbuk and Jeonnam. There was a 12% increase in developed areas for Gyeonggi but only 1.9 and 6% for Jeonbuk and Jeonnam, respectively. LULC change is thus easily identified through a pixel-based analysis of multispectral KOMPSAT-2 images over time. Such data are useful for environmental and policy managers when developing advanced coastal management strategies.

Google Earth Engine Based Three Decadal Landsat Imagery Analysis for Mapping of Mangrove Forests and Its Surroundings in the Trat Province of Thailand

Monitoring and understanding the changes in mangrove ecosystems and their surroundings are required to determine how mangrove ecosystems are constantly changing while influenced by anthropogenic, and natural drivers. Cosistency in high spatial resolution (30 m) satellite and high performance computing facilities are limiting factors to the process, with storage and analysis requirements. With this, we present the Google Earth Engine (GEE) based approach for long term mapping of mangrove forests and their surroundings. In this study, we used a GEE based approach: 1) to create atmospheric contamination free data from 1987-2017 from different Landsat satellite imagery; and 2) evaluating the random forest classifier and post classification change detection method. The obtained overall accuracy for the years 1987 and 2017 was determined to be 0.87 and 0.96, followed by a Kappa coefficient 0.80 and 0.94. The change detection results revealed a significant decrease in the agricultural area, while there was an increase in mangrove forest, shrimp/fish farm, and bareland area. The results suggest that interconversion of land use and land cover is affecting the landscape dynamics within the study area.

Change Detection Analysis of Water Pollution in Coimbatore Region using Different Color Models

The data acquired through remote sensing satellites furnish facts about the land and water at varying resolutions and has been widely used for several change detection studies. Apart from the existence of many change detection methodologies and techniques, emergence of new ones continues to subsist. Existing change detection techniques exploit images that are either in gray scale or RGB color model. In this paper we introduced color models for performing change detection for water pollution. Here the polluted lakes are classified and post-classification change detection techniques are applied to RGB images and results obtained are analysed for changes to exist or not. Furthermore RGB images obtained after classification when converted to any of the two color models YCbCr and YIQ is found to produce the same results as that of the RGB model images. Thus it can be concluded that other color models like YCbCr, YIQ can be used as substitution to RGB color model for analysing change detection with regard to water pollution.

Monitoring the spatiotemporal dynamics of waterlogged area in southwestern Bangladesh using time series Landsat imagery

Waterlogging is becoming a major environmental problem and challenge for socio-economic development in the southwestern part of Bangladesh. In this study, the Satkhira district was selected as the study area to quantify waterlogging area delineation. To portray these dynamics, Landsat imageries from 1973, 1989, 1995, 2000, 2005, 2010 and 2015 were used. A training dataset was generated in ArcGIS, and a supervised classification was carried out using the random forest algorithm in the R Studio. The overall classification accuracy and kappa statistics was 95% and 91% respectively. Post-classification change detection comparisons were made in QGIS to calculate the transformations of the respective land cover areas in the study site. Areas of approximately 832, 3033, 13,562, 11,547, 27,162, 40,056, and 35,606ha were observed as waterlogged in the above mentioned years, respectively, which indicates that the acreage of waterlogged areas increased approximately 43 fold from 1973 to 2015. Moreover, the Land Use Land Cover (LULC) change matrix showed that waterlogged area was increased from 5% to 12% during 2000–2005, further rose from 12% to 18% during 2005–2010 and decreased from 18% to 16% during 2010–2015. The most water logged sub-district was Debhata (38%) while Koloroa has the lowest (4%) waterlogged area. The study is an effort to reconstruct the history to understand the dynamics of the waterlogging as past ground monitoring information is absent. Regarding environmental degradation, the government and development agencies should consider these results a critical issue in the entire southwestern part of Bangladesh.

ASSESSING LAND COVER CHANGES CAUSED BY GRANITE QUARRYING USING REMOTE SENSING

Abstract. Dimension stone quarrying in the area between Rustenburg and Brits in the North West Province of South Africa has been in existence for over 70 decades. The unique characteristics of the granite deposits in South Africa resulted in making the country a global producer of the granite rocks. This led to intensified quarrying activities between Rustenburg and Brits town. However, this surface mining method, has a potential to impact the environment in a negative way causing loss in vegetation, depletion of natural resources, loss of scenic beauty and contamination of surface water resources. To assess the land cover changes caused by granite quarrying activities, remotely sensed data in the form of Landsat images between 1998 and 2015 were used. Supervised classification was used to create maps. Accuracy assessment using Google EarthTM as a reference data yielded an overall accuracy of 78 %. The post classification change detection method was used to assess land cover changes within the granite quarries. Granite quarries increased by 1174.86 ha while formation of quarry lakes increased to 5.3 ha over the 17-year period. Vegetation cover decreased by 1308 ha in area while 18.3 ha bare land was lost during the same period. This study demonstrated the utility of remote sensing to detect changes in land cover within granite quarries.

Wetland cover change detection using multi-temporal remotely sensed data

Lake Urmia, located in northwest Iran, contains a number of wetlands significantly affecting the environmental, social, and economic conditions of the region. The ecological condition of Lake Urmia has degraded during the past decade, due to climate change, human activities, and unsustainable management. The poor condition of the lake has also affected the surrounding wetlands. This study analyzes the land cover change of one of the wetlands in the southern part of Lake Urmia, known as Ghara-Gheshlagh wetland, in the period 1989–2015 using post-classification change detection and machine learning image classification. For this analysis, three Landsat images, acquired in 1989 (TM), 2001 (TM), and 2015 (Landsat-8), were used for the classification and change detection. Support vector machine learning algorithm, a supervised learning method, is employed, and images are classified into four main land cover classes namely “water,” ”barren,” “salty land,” and “agriculture and grassland.” Change detection was carried out for pairs of years 1989 to 2001 and 2001 until 2015. The results of this classification show that there is a sharp increase in the area of salt-saturated land as well as a decrease in the area of water resources. Overall classification accuracy obtained were high for the individual years: 1989 (91.48%), 2001 (90.63%), and 2015 (88.6%). Also, the Kappa coefficients for individual maps were high: 1989 (0.89), 2001 (0.8742), and 2015 (0.84). After that, the land cover change map of the study area is obtained between 1989 to 2001 and then 2001 to 2015. The results of this analysis suggest that more efforts should be taken to effectively manage water resources in the region and point to potential locations for focused management actions within the wetland area.

Modeling the Spatio-temporal dynamics and evolution of land use and land cover (1984–2015) using remote sensing and GIS in Raya, Northern Ethiopia

This study models the spatio-temporal dynamics, patterns, and evolution of land use and land cover (LULC) (1984–2015) using remote sensing and GIS supported by in-suit measurements in Raya, Northern Ethiopia. Landsat thematic mapper (TM), and operational land imager (OLI) path 168/169 and row 051/52 were acquired from the United States Geological Survey Landsat archive. All necessary image pre-processing techniques were applied to remove the distortions due to sensors. Eight major LULC types based on a supervised image classification and maximum likelihood decision rule were identified. Post-classification change detection method was also applied to detect the dynamics in LULC. Significant change in forestland, shrub/bush land, built-up area, grassland, cropland, barren land, and floodplain areas were observed over the period 1984–2015. Considerable losses were observed in grasslands (36.9%), water body (8.7%), and floodplain areas (74.4%), while other LULC types increased. This explains why the study area is frequently affected by drought and other related disasters. An overall accuracy of 88.5, 86.5 and 90.5% were observed for the 1984, 1995 and 2015 LULC, respectively. The overall Kappa coefficient of 0.87, 0.85, and 0.90 were also observed for the same periods. Besides, the Pearson pairwise correlation matrix among the 1984–1995, 1995–2015 and 1984–2015 LULC shows positive and strong correlation (r = 0.916, r = 0.908, r = 0.914) at p < 0.005 significance level. Therefore, there is no much difference in identifying LULC types using TM and OLI products. This study is crucial to implement scientific land use policies and strategies in the study area.

A post-classification change detection method based on iterative slow feature analysis and Bayesian soft fusion

Post-classification with multi-temporal remote sensing images is one of the most popular change detection methods, providing the detailed “from-to” change information in real applications. However, due to the fact that it neglects the temporal correlation between corresponding pixels in multi-temporal images, the post-classification approach usually suffers from an accumulation of misclassification errors. In order to solve this problem, previous studies have separated the change and non-change candidates with change vector analysis, and they have only updated the classes of the changed pixels with the post-classification; however, this approach with thresholding loses the continuous change intensity information, where larger values indicate higher probability to be changed. Therefore, in this paper, a new post-classification method with iterative slow feature analysis (ISFA) and Bayesian soft fusion is proposed to obtain reliable and accurate change detection maps. The proposed method consists of three main steps: 1) independent classification is implemented to obtain the class probability for each image; 2) the ISFA algorithm is used to obtain the continuous change probability map of multi-temporal images, where the value of each pixel indicates the probability to be changed; and 3) based on Bayesian theory, the a posteriori probabilities for the class combinations of coupled pixels are calculated to integrate the class probability with the change probability, which is named as Bayesian soft fusion. The class combination with the maximum a posteriori probability is then determined as the change detection result. In addition, a class probability filter is proposed to avoid the false alarms caused by the spectral variation within the same class. Two experiments with multi-temporal Landsat Thematic Mapper (TM) images indicated that the proposed method achieves a clearly higher change detection accuracy than the current state-of-the-art methods. The proposed method based on Bayesian theory and ISFA was also verified to have the ability to improve the change detection rate and reduce the false alarms at the same time. Given its effectiveness and flexibility, the proposed method could be widely applied in land-use/land-cover change detection and monitoring at a large scale.

Dynamic Monitoring of Typical Geographic Mining Conditions of Yanzhou Coal Field Based on High-resolution Remote Sensing Images

In order to monitor geographic mining conditions timely and dynamically with high accuracy, this paper took relocation of villages with underground coal resources and farmland with seeper and subsidence as typical geographic mining conditions of Yanzhou coal field in China, extracted monitoring information and made corresponding statistical analysis based on the aerial image in 2009 and GF-2 satellite image in 2015, using object-oriented post-classification change detection method on ENVI software. The results show that from the year 2009 to 2015, Yanzhou Coal field totally moved 11 villages, with a total area of 2.53km2, and the average plaque area was 0.23 km2. The villages with deeper subsidence and perennial seeper had been reclaimed to pond and the area was approximately 0.09km2, while those with shallow subsidence had been reclaimed to farmland and the area was approximately 1.81km2. The total area of farmland with seeper and subsidence was basically unchanged and the area that hadn’t been reclaimed decreased 2.744km2. On the whole, the effects of the reclamation of Yanzhou coal field is remarkable, but there are still 0.63 km2 village and 3.47km2 farmland not yet reclaimed in Xinglongzhuang, Dongtan, Baodian coal mine. Local governments should develop appropriate reclamation plans to improve the efficiency of land use.

Urban new construction land parcel detection with normalized difference vegetation index and PanTex information

An urban new construction land parcel detection method based on normalized difference vegetation index (NDVI) and built-up area presence index is proposed for high-resolution remote sensing images. The method consists of three main steps: construction land detection using NDVI and PanTex, false change removal, and new construction land parcel extraction. More specifically, a change proportion index is raised to convert the pixel-based change detection map to parcels in combination with a segmentation process. From experimental results validated using two cases of high-resolution optical satellite images, the proposed method is demonstrated to be efficient and achieves a per-object overall accuracy rate beyond 95%, significantly superior to the traditional postclassification change detection method. Furthermore, the proposed method avoids errors resulting from classification in the method of postclassification comparison.

Multi-Level Land Cover Change Analysis in the Forest-Savannah Transition Zone of the Kintampo Municipality, Ghana

This study presents a multi-level analysis of land cover change in the Kintampo Municipality of Ghana using Landsat TM, ETM + and Landsat 8 images from 1986, 2001 and 2014, respectively. The expected and observed annual rates of land cover change for the periods 1986 to 2001 and 2001 to 2014 were analyzed at temporal and intra and inter-land cover levels using post-classification change detection. The results reveal that the expected annual rate of land cover change for the time intervals is 2.55 %. The observed annual rate of change from 2001 to 2014 is 2.63 %, which is greater than the expected value. This shows that land cover changed faster than expected in this period. The observed intra-land cover gains and losses for woodland is 2.49 % which is less than expected for the change periods. This suggests that the observed gain and loss in woodlands are attributable to random changes. The inter-land cover level changes for both periods reveal that when woodland gained or lost, it did not target shrub/grassland. This shows that the process of gain or loss in woodland in both periods was random. This is an indication that woodland cover is sustained by a slow, natural regeneration process and not by anthropogenic activities. The findings highlight the relevance of multilevel land cover analysis in land cover assessment. The temporal level highlights the need to relate changes in land cover to anthropogenic activities for a better understanding of the changes. The study also revealed that multi-level land cover analysis can facilitate management decisions on whether to reduce loss in woodland or increase gain in woodland cover from shrub land.

EVALUATE THE CAPABILITY OF LANDSAT8 OPERATIONAL LAND IMAGER FOR SHORELINE CHANGE DETECTION/INLAND WATER STUDIES

Abstract. This paper explored the capability of Landsat-8 Operational Land Imager (OLI) for post classification change detection analysis and mapping application because of its enhanced features from previous Landsat series. The OLI support vector machine (SVM) classified data was successfully classified with regard to all six test classes (i.e., open land, residential land, forest, scrub land, reservoir water and waterway). The OLI SVM-classified data for the four seasons (i.e. winter, spring, summer and autumn seasons) were used for change detection analysis of six situations; situation1: winter to spring seasonal change detection resulted reduction in reservoir water mapping and increases of scrub land; situation 2: winter to summer seasonal change detection resulted increase in dam water mapping and increase of scrub land. winter to summer which resulted reduction in dam water mapping and increase of vegetation; situation 3: winter to summer seasonal change detection resulted increase in increase in open land mapping; situation 4: spring to summer seasonal change detection resulted reduction of vegetation and shallow water and increase of open land and reservoir water; situation; 5: spring to autumn seasonal change detection resulted increase of reservoir water and open land; and Situation 6: summer to autumn seasonal change detection resulted increase of open land. OLI SVM classified data found suitable for post classification change detection analysis due to its resulted higher overall accuracy and kappa coefficient.

The dynamics of urban expansion and land use/land cover changes using remote sensing and spatial metrics: the case of Mekelle City of northern Ethiopia

ABSTRACTInformation on the rate and pattern of urban expansion is required by urban planners to devise proper urban planning and management policy directions. This study evaluated the dynamics and spatial pattern of Mekelle City’s expansion in the past three decades (1984–2014). Multi-temporal Landsat images and Maximum Likelihood Classifier were used to produce decadal land use/land cover (LULC) maps. Changes in LULC and spatial pattern of urban expansion were analysed by post-classification change detection and spatial metrics, respectively. The results showed that in the periods 1984–1994, 1994–2004, and 2004–2014, the built-up area increased annually by 10%, 9%, and 8%, respectively; with an average annual increment of 19% (100 ha year−1), from 531 ha in 1984 to 3524 ha in 2014. Between 1984 and 2014, about 88% of the gain in built-up area was from conversion of agricultural lands, which decreased by 39%. Extension of existing urban areas was the dominant growth type, which accounted for 54%, 75%, and 81% of the total new development during 1984–1994, 1994–2004, and 2004–2014, respectively. The spatial metrics analyses revealed urban sprawl, with increased heterogeneity and gradual dispersion in the outskirts of the city. The per capita land consumption rate (ha per person) increased from 0.009 in 1984 to 0.014 in 2014, indicating low density urban growth. Based on the prediction result, the current (2014) built-up area will double by 2035, and this is likely to have multiple socioeconomic and environmental consequences unless sustainable urban planning and development policies are devised.

Land-cover classification and analysis of change using machine-learning classifiers and multi-temporal remote sensing imagery

Frequent human activity and rapid urbanization have led to an assortment of environmental issues. Monitoring land-cover change is critical to efficient environmental management and urban planning. The current study had two objectives. The first was to compare pixel-based random forest (RF) and decision tree (DT) classifier methods and a support vector machine (SVM) algorithm both in pixel-based and object-based approaches for classification of land-cover in a heterogeneous landscape for 2010. The second was to examine spatio-temporal land-cover change over the last two decades (1990–2010) using Landsat data. This study found that the object-based SVM classifier is the most accurate with an overall classification accuracy of 93.54% and a kappa value of 0.88. A post-classification change detection algorithm was used to determine the trend of change between land-cover classes. The most significant change from 1990 to 2010 was caused by the expansion of built-up areas. In addition to the net changes, the rate of annual change for each phenomenon was calculated to obtain a better understanding of the process of change. Between 1990 and 2010, an average of 4.53% of lands turned to the built-up annually and there was an annual decrease of about 0.81% in natural land. If the current trend of change continues, regardless of the actions of sustainable development, drastic declines in natural areas will ensue. The results of this study can be a valuable baseline for land-cover managers in the region to better understand the current situation and adopt appropriate strategies for management of land-cover.

Analysis of urban growth and sprawl from remote sensing data: Case of Fez, Morocco

Abstract Fez is the most ancient of the imperial cities of Morocco. In Fez the rate of population growth has been spectacular in recent times (484,300 inhabitants in 1982 and 1,129,768 in 2014). The accelerated rate of population growth has generated a large urban sprawl in all its forms and serious environmental problems. In this research, we have analyzed the relationship between urbanization and land use changes and their impact on cityscape in Fez and the importance of the increase in impervious surface areas. Satellite imageries and census data have been used to identify different patterns of land use change and growth of the city for the period 1984–2013. Classification and analysis of the satellite imageries were performed using Erdas imagine and ArcGIS Software. Urban sprawl in Fez was assessed over 29 years (1984–2013). The overall accuracy of land cover change maps, generated from post-classification change detection methods and evaluated using several approaches, ranged from 78% to 87%. The maps showed that between 1984 and 2013 the amount of urban or developed land increased by about 121%, while rural cover by agriculture and forest decreased respectively by 11% and 3%.