Supervised Classification Techniques Research Articles

Assessment of Soil Moisture Status Using Mid and Thermal Infrared Bands Case Study: Wadi Hassib, Khartoum State, Sudan

Soil moisture is the key factor that controls plant biological processes and indicates the environmental status. Recently, the application of remote sensing techniques in soil moisture monitoring has been widely used. In this study soil moisture was monitored during pre-autumn in March, autumn in September and post-autumn in December (2002), in order to identify the signature of different types of moist soils, which can be useful to interpret images. Supervised classification technique was adopted to determine the dominant land use/land cover classes in the area so that they can be vital indicators for the area and its suitability for many life styles. Monitoring moisture statuses can be used for general evaluation of land suitability for agriculture. The assessment of moisture statuses was performed in landsat ETM+ images using band 5 (MIR) as it is known as a sensitive band for moisture status and band 6 (Thermal) as a sensitive band to temperature variation as indicator of moisture status. The study revealed that band 5 and band 6 can be used to monitor soil moisture status during the different seasons in semi-arid areas, however, band 6 is less sensitive to variations in moisture. Therefore, this study recommends the use of Band 5 for monitoring soil moisture in semi-arid regions, and does not recommend the use of band 6 alone but with some supporting bands.

Improving geological mapping of the Farasan Islands using remote sensing and ground-truth data

ABSTRACTWe integrated satellite imagery (Landsat-8) with ground-truth data to produce a detailed and complete geological map of the Farasan Islands, off the Red Sea coast of Saudi Arabia at a scale of 1:100,000. This new map improves upon past efforts by expanding the mapped lithologies on the islands into four categories. We used different techniques to enhance this lithological differentiation, including band combination with ratio stretching and supervised classification techniques based on direct field validation. The former was used to distinguish differences in reflectance values across sets of bands to create a classification image from typical reflectance patterns. The geological feature boundaries were constrained by open-source high-resolution satellite imagery (WorldView-2) as well as field observations. The resulting map clearly distinguishes between different geomorphic and geologic features, including lineaments and lithologies. As the Farasan Islands are relatively remote and not easily accessible, with an area of 739 km2, these imagery-analysis techniques were an effective tool for using remote sensing data to produce new and better mapping products of this important area.

IMPACT OF FLOODING ON LAND USE/ LAND COVER TRANSFORMATION IN WULAR LAKE AND ITS ENVIRONS, KASHMIR VALLEY, INDIA USING GEOINFORMATICS

Abstract. Wular lake, located at an elevation of 1520 m above sea level in Kashmir valley, India. In the present study, the immediate and long term impact of flood (2014) over the Wular lake environs was analyzed by using satellite images and employing supervised classification technique in GIS environment. The LULC classification was performed on the images of 25th August 2014 (pre flood) and 13th September 2015 (post flood) and was compared, which indicated marked decrease in terrestrial vegetation (23.7 %), agriculture (43.7 %) and water bodies (39.9 %). Overlaying analysis was performed with pre and post flood classified images with reference to the satellite image of 10th September 2014(during flood) which indicated total area inundated during flood was 88.77 km2. With the pre-flood situation, the aquatic vegetation of 34.06 km2, 13.89 km2 of agriculture land and terrestrial vegetation of 3.13 km2 was inundated. In the post flood situation, it was also came into focus that more than the half of the area under water bodies was converted into sand deposits (22.76 km2) due to anomalous increase in siltation. The overlay analysis on post flood classified image indicated that aquatic vegetation followed by agriculture and sand deposits lie within the flood inundated area. Further spatial analysis was performed within the flood inundated area (88.77 km2) with pre and post classified image to understand the situation before and after the flood and to calculate the changes. These land use-land cover transformations signifies the ill effect of flooding on the biodiversity of Wular Lake.

Monitoring Land Use/Land Cover Dynamics in the Province of Constantine, Algeria Using Remote Sensing and GIS

Objectives: The present study aims to investigate and analyse the dynamics of land use/land change over time in the province of Constantine, Algeria, using multi-temporal Landsat imagery and ancillary data. Methods/Statistical Analysis: A supervised classification technique using Maximum Likelihood algorithm was used for land use/land cover classification, to generate thematic maps, with six major classes. The accuracy assessment was applied for each maps based on stratified random method. Furthermore, post-classification technique was achieved to provide a detailed matrix of “from-to” change between 1987 and 2015. Findings: The results showed that the landscape patterns in the province of Constantine, Algeria, have been changed. The built-up areas and agricultural lands have increased by 375%, and 13% respectively. However, significant spatial reduction in vegetation areas was observed. Both of grasslands and forestlands were decreased by 54% and 9.11%, respectively, especially in the eastern part of the province. Application/Improvements: The dramatic decline in vegetation covers in the most mountainous areas, indicating the necessity to create new policies based on protecting and enhancing the natural vegetation. Keywords: Constantine, Land Use, Monitoring, Remote Sensing, GIS

Identification of historic landscape features and settlement mounds in the Western Nile Delta by means of remote sensing time series analysis and the evaluation of vegetation characteristics

Remote sensing techniques gain increasing importance in landscape archaeological research. Traditional archaeological excavation techniques are slow and time in the Nile Delta is running out. The Nile Delta has been settled and used for agricultural cultivation since the Neolithic period and is shaped by the interplay of urbanization and agriculture. In particular, the study of ancient settlement mounds (tells) and landscape archaeological features such as former river channels requires urgent action. This study seeks to develop supervised classification techniques on the basis of multitemporal Landsat 8 images to easily monitor existing high tells in the Delta that have not been destroyed yet. In the 19th and early 20th centuries many tells were destroyed, because tell sediments (sebakh) were harvested on an industrial scale in order to be used as fertilizer. These activities continued on a smaller scale into the mid to later 20th century. Geochemical analysis of ancient settlement material (sebakh) has confirmed the high content of nutrients. In a second step which is based on these geochemical findings, we seek to identify the category of lost tells which had been transformed into agricultural areas. We suggest that the presence of ancient settlement material enhances the overall vegetation performance and indirectly allows identification of lost tells via describing the vegetation performance. In general, the vegetation performance is a new measure and invented within this study. It is calculated as the product of different measures describing the plant growth, namely the mean NDVI (Normalized Difference Vegetation Index), growth statistics and crop rotations derived from a large set of multitemporal NDVI images. Our results show that there exists a relationship between vegetation performance and the appearance of archaeological material in the topsoil and such information can be useful for planning of non-invasive archaeological surveys. Remarkably the vegetation performance corresponds with the location of former Nile branches that are currently investigated by the authors on the basis of TandemX elevation data and sedimentological investigations of the area. Several factors such as water availability and salinity also affect plant growth and mask this relationship. Additionally, our methods to describe the number of crop rotations or growth statistics from NDVI time series help to analyse the agricultural areas in the Nile Delta. Therefore, the methods used in this study may offer important insights on aspects of urban sprawl and agricultural areas in the Nile Delta and beyond.

Assessing and monitoring the human influence on water quality in response to land transformation within Wular environs of Kashmir Valley

Wular Lake is the largest freshwater lake of India located in north western Himalayas of Kashmir Valley which has got deteriorated over the period of time due to the enough human interference within its catchment areas. The purpose of the present research study is to identify the changes in land use and land cover in the Wular catchment as well as its transformation into other classes and its impact on the overall water quality of the lake. For the present study Landsat (TM) image of 1992 and Landsat-8 (OLI) of 2015 have been used for assessing the changes in land use/land cover. Supervised classification technique was used to generate LULC maps of different categories pertaining to study area for years 1992 and 2015. Regarding water quality, water samples were collected from five different spots of the lake in four different seasons of the year—from December 2014 to September 2015. The sites from which samples were collected are Vintage Park, Ashtungo, Watlab, Makhdomyari and Ningal as site 1, 2, 3, 4, and 5 respectively. Some parameters of water like temperature, transparency, depth, conductivity and pH were examined on the spot during the sample collection by their respective measuring instruments. The rest of the parameters were examined in hydrological laboratory within 24 h after collection following the standard methods of APHA (Standard methods for the examination of water and wastewater, 21st edn. American Public Health Association, Washington, DC, 2005). The relationship between the LULC classes and water quality parameters has been calculated with the help of SHDI which has shown both positive and as well as negative results.

Analyzing spatiotemporal land use/cover dynamic using remote sensing imagery and GIS techniques case: Kan basin of Iran

Land use/land cover (LU/LC) that are significant elements for the interconnection of human activities and environment monitoring can be useful to find out the deviations of saving a maintainable environment. Remote sensing is a very useful tool for the affair of land use or land cover monitoring, which can be helpful to decide the allocation of land use and land cover. Supervised classification-maximum likelihood algorithm in GIS was applied in this study to detect land use/land cover changes observed in Kan basin using multispectral satellite data obtained from Landsat 5 (TM) and 8 (OLI) for the years 2000 and 2016, respectively. The main aim of this study was to gain a quantitative understanding of land use and land cover changes in Kan basin of Tehran over the period 2000–2016. For this purpose, firstly supervised classification technique was applied to Landsat images acquired in 2000 and 2016. The Kan basin was classified into five major LU/LC classes including: Built up areas, garden, pasture, water and bare-land. Change detection analysis was performed to compare the quantities of land cover class conversions between time intervals. The results revealed both increase and decrease of the different LU/LC classes from 2000 to 2016. The results indicate that during the study period, built-up land, and pastures have increased by 0.2% (76.4 km2) and 0.3% (86.03 km2) while water, garden and bare land have decreased by 0, 0.01% (3.62 km2) and 0.4% (117.168 km2), respectively. Information obtained from change detection of LU/LC can aid in providing optimal solutions for the selection, planning, implementation and monitoring of development schemes to meet the increasing demands of human needs in land management.

A scheme for high level data classification using random walk and network measures

Supervised classification techniques are known to exploit physical information of the analysed data, such as similarity, distribution and other low level features. Despite the relevance of such features, recent works have showed that a higher variety of patterns can be detected by combining low level and high level features. In this paper, it is proposed a supervised classification technique which applies limiting probabilities of the random walk theory over underlying networks constructed from input labeled data. The appealing feature of the proposed approach is that the adjacency matrix which carries both physical and structural information about the data. Structural information are given by features extracted from network connections. The class of a given unlabeled sample is estimated by a heuristic called ease of access, which is measured by the random walk process over the adjacency matrix. Such approach makes the technique quite general as one can put distinct data measures of interest in the connection matrix of the underlying data network to guide the random walker. Specifically, we show examples of combining low and high level features in the proposed classification scheme. Simulation results using artificial and real data sets suggest that the proposed technique is not only competitive with current and established classification techniques, but it also can reveal intrinsic structural patterns formed by the input data.

Using Landsat images to monitor changes in the snow-covered area of selected glaciers in northern Pakistan

Landsat satellite images were used to map and monitor the snow-covered areas of four glaciers with different aspects (Passu: 36.473°N, 74.766°E; Momhil: 36.394°N, 75.085°E; Trivor: 36.249°N, 74.968°E; and Kunyang: 36.083°N, 75.288°E) in the upper Indus basin, northern Pakistan, from 1990-2014. The snow-covered areas of the selected glaciers were identified and classified using supervised and rule-based image analysis techniques in three different seasons. Accuracy assessment of the classified images indicated that the supervised classification technique performed slightly better than the rule-based technique. Snow-covered areas on the selected glaciers were generally reduced during the study period but at different rates. Glaciers reached maximum areal snow coverage in winter and pre-monsoon seasons and minimum areal snow coverage in monsoon seasons, with the lowest snow-covered area occurring in August and September. The snow-covered area on Passu glacier decreased by 24.50%, 3.15% and 11.25% in the pre-monsoon, monsoon and post-monsoon seasons, respectively. Similarly, the other three glaciers showed notable decreases in snow-covered area during the pre- and post-monsoon seasons; however, no clear changes were observed during monsoon seasons. During pre-monsoon seasons, the eastward-facing glacier lost comparatively more snow-covered area than the westward-facing glacier. The average seasonal glacier surface temperature calculated from the Landsat thermal band showed negative correlations of -0.67, -0.89, -0.75 and -0.77 with the average seasonal snow-covered areas of the Passu, Momhil, Trivor and Kunyang glaciers, respectively, during pre-monsoon seasons. Similarly, the air temperature collected from a nearby meteorological station showed an increasing trend, indicating that the snow-covered area reduction in the region was largely due to climate warming.

Driving forces behind land transformations in the Tamiraparani sub-basin, South India

The present study emphasizes the long-term (1992–2012) land alteration and its driving factors in the Tamiraparani sub-basin, south India. The multi-temporal landuse/land cover features were extracted from the Landsat images (TM and ETM+, 30m resolution) using a supervised classification technique with maximum likelihood classifier. The extracted features were classified into various landuse/ land cover categories with level I classification scheme of NRSC, India. Six major landuse classes such as forest, settlement, barren land, water bodies, agricultural land and fallow land were recognized. The overall accuracy for the year 1992, 2002, and 2012 shows 85.55%, 82.81% and 83.59% respectively. The overall Kappa coefficients for the datasets are near to 0.8, which indicates acceptable accuracy for landuse/ land cover classification. The results reveals that the spatial extent of forest, settlement and barren land has evolved in the past 20 years but, the water bodies, agricultural land and fallow land has reduced significantly. The reduction in agricultural land in the study area for the past 20 years is due to the combination of natural environment and socio-economic factors such as low rainfall in the plains, increased surface temperature, reduced soil moisture condition, high rate of evapo-transpiration, reduced water storage level in the reservoirs and ponds, and reduced vegetation cover. These factors are linked with climate change, it alters the socio-economic condition of the area, and such situation will affect the overall ecosystem in the Tamiraparani sub-basin in the near future.

Shoreline change assessment using multi-temporal satellite images: a case study of Lake Sapanca, NW Turkey.

The research summarized here determines historical shoreline changes along Lake Sapanca by using Remote Sensing (RS) and Geographical Information Systems (GIS). Six multi-temporal satellite images of Landsat Multispectral Scanner (L1-5 MMS), Enhanced Thematic Mapper Plus (L7 ETM+), and Operational Land Imager Sensors (L8 OLI), covering the period between 17 June 1975 and 15 July 2016, were used to monitor shoreline positions and estimate change rates along the coastal zone. After pre-possessing routines, the Normalized Difference Water Index (NDWI), Modified Normalized Difference Water Index (MNDWI), and supervised classification techniques were utilized to extract six different shorelines. Digital Shoreline Analysis System (DSAS), a toolbox that enables transect-based computations of shoreline displacement, was used to compute historical shoreline change rates. The average rate of shoreline change for the entire cost was 2.7m/year of progradation with an uncertainty of 0.2m/year. While the great part of the lake shoreline remained stable, the study concluded that the easterly and westerly coasts and deltaic coasts are more vulnerable to shoreline displacements over the last four decades. The study also reveals that anthropogenic activities, more specifically over extraction of freshwater from the lake, cyclic variation in rainfall, and deposition of sediment transported by the surrounding creeks dominantly control spatiotemporal shoreline changes in the region. Monitoring shoreline changes using multi-temporal satellite images is a significant component for the coastal decision-making and management.

Improved credit card churn prediction based on rough clustering and supervised learning techniques

Every process is digitized in the current society. Transfer of money from one account holder to another has become possible in seconds because of advanced technologies in information processing. Not only this in all sectors like railways, insurance, health sector, fashion technology, education sector, sales and business sectors, and advertisement sectors every firm digitized its operations. One such sector is banking where every individual based on his or her financial status will be considered for crediting loan, and credit card etc. If the credit score of the loan availing person is high banks will be ready to provide him with the loan but the availing person can opt for any one of the banks on his or her own willing. Such scenario happens in credit card churn prediction also. Hence the banks should take healthy measures to retain the existing credit card holders without any churn. Withholding existing customers of a firm plays an important role to increase the overall revenue of the firm and retains the good name of the firm in competitive market. Hence every organization takes key measures to withhold existing customers using customer management models. Because customer retention is a crucial task as it reduces the time, money and workforce needed for adding new customers to the firm. Customers retention technique in credit card churn prediction (C3P) was done using only supervised classification techniques. But it could not end with better results. So, through many proven hybrid classification techniques we can bring better accuracy in C3P. Also C3P lags in highly efficient techniques like rough set theory. Hence in this work initially we perform data processing techniques and in second stage we propose modified rough K-means algorithm used for clustering credit card holders and in next stage hold-out method divides the cluster data into testing and training clusters. At last classification is performed using various algorithms like support vector machine, random forest, decision tree, K-nearest neighbor, and Naive Bayes. Finally we evaluate the work using precision, recall (sensitivity), specification, accuracy, and misclassification error.

Survey of supervised classification techniques for hyperspectral images

PurposeThis paper aims to provide a framework of the supervised hyperspectral classification, to study the traditional flowchart of hyperspectral image (HIS) analysis and processing. HSI technology has been proposed for many years, and the applications of this technology were promoted by technical advancements.Design/methodology/approachFirst, the properties and current situation of hyperspectral technology are summarized. Then, this paper introduces a series of common classification approaches. In addition, a comparison of different classification approaches on real hyperspectral data is conducted. Finally, this survey presents a discussion on the classification results and points out the classification development tendency.FindingsThe core of this survey is to review of the state of the art of the classification for hyperspectral images, to study the performance and efficiency of certain implementation measures and to point out the challenges still exist.Originality valueThe study categorized the supervised classification for hyperspectral images, demonstrated the comparisons among these methods and pointed out the challenges that still exist.

Unsupervised PolSAR Image Classification Using Discriminative Clustering

This paper presents a novel unsupervised image classification method for polarimetric synthetic aperture radar (PolSAR) data. The proposed method is based on a discriminative clustering framework that explicitly relies on a discriminative supervised classification technique to perform unsupervised clustering. To implement this idea, we design an energy function for unsupervised PolSAR image classification by combining a supervised softmax regression model with a Markov random field smoothness constraint. In this model, both the pixelwise class labels and classifiers are taken as unknown variables to be optimized. Starting from the initialized class labels generated by Cloude–Pottier decomposition and $K$ -Wishart distribution hypothesis, we iteratively optimize the classifiers and class labels by alternately minimizing the energy function with respect to them. Finally, the optimized class labels are taken as the classification result, and the classifiers for different classes are also derived as a side effect. We apply this approach to real PolSAR benchmark data. Extensive experiments justify that our approach can effectively classify the PolSAR image in an unsupervised way and produce higher accuracies than the compared state-of-the-art methods.

Posture Detection Based on Smart Cushion for Wheelchair Users.

The postures of wheelchair users can reveal their sitting habit, mood, and even predict health risks such as pressure ulcers or lower back pain. Mining the hidden information of the postures can reveal their wellness and general health conditions. In this paper, a cushion-based posture recognition system is used to process pressure sensor signals for the detection of user’s posture in the wheelchair. The proposed posture detection method is composed of three main steps: data level classification for posture detection, backward selection of sensor configuration, and recognition results compared with previous literature. Five supervised classification techniques—Decision Tree (J48), Support Vector Machines (SVM), Multilayer Perceptron (MLP), Naive Bayes, and k-Nearest Neighbor (k-NN)—are compared in terms of classification accuracy, precision, recall, and F-measure. Results indicate that the J48 classifier provides the highest accuracy compared to other techniques. The backward selection method was used to determine the best sensor deployment configuration of the wheelchair. Several kinds of pressure sensor deployments are compared and our new method of deployment is shown to better detect postures of the wheelchair users. Performance analysis also took into account the Body Mass Index (BMI), useful for evaluating the robustness of the method across individual physical differences. Results show that our proposed sensor deployment is effective, achieving 99.47% posture recognition accuracy. Our proposed method is very competitive for posture recognition and robust in comparison with other former research. Accurate posture detection represents a fundamental basic block to develop several applications, including fatigue estimation and activity level assessment.

Using UAS Hyperspatial RGB Imagery for Identifying Beach Zones along the South Texas Coast

Shoreline information is fundamental for understanding coastal dynamics and for implementing environmental policy. The analysis of shoreline variability usually uses a group of shoreline indicators visibly discernible in coastal imagery, such as the seaward vegetation line, wet beach/dry beach line, and instantaneous water line. These indicators partition a beach into four zones: vegetated land, dry sand or debris, wet sand, and water. Unmanned aircraft system (UAS) remote sensing that can acquire imagery with sub-decimeter pixel size provides opportunities to map these four beach zones. This paper attempts to delineate four beach zones based on UAS hyperspatial RGB (Red, Green, and Blue) imagery, namely imagery of sub-decimeter pixel size, and feature textures. Besides the RGB images, this paper also uses USGS (the United States Geological Survey) Munsell HSV (Hue, Saturation, and Value) and CIELUV (the CIE 1976 (L*, u*, v*) color space) images transformed from an RGB image. The four beach zones are identified based on the Gray Level Co-Occurrence Matrix (GLCM) and Local Binary Pattern (LBP) textures. Experiments were conducted with South Padre Island photos acquired by a Nikon D80 camera mounted on the US-16 UAS during March 2014. The results show that USGS Munsell hue can separate land and water reliably. GLCM and LBP textures can slightly improve classification accuracies by both unsupervised and supervised classification techniques. The experiments also indicate that we could reach acceptable results on different photos while using training data from another photo for site-specific UAS remote sensing. The findings imply that parallel processing of classification is feasible.

Improved prediction of missing protein interactome links via anomaly detection

Interactomes such as Protein interaction networks have many undiscovered links between entities. Experimental verification of every link in these networks is prohibitively expensive, and therefore computational methods to direct the search for possible links are of great value. The problem of finding undiscovered links in a network is also referred to as the link prediction problem. A popular approach for link prediction has been to formulate it as a binary classification problem in which class labels indicate the existence or absence of a link (we refer to these as positive links or negative links respectively) between a pair of nodes in the network. Researchers have successfully applied such supervised classification techniques to determine the presence of links in protein interaction networks. However, it is quite common for protein-protein interaction (PPI) networks to have a large proportion of undiscovered links. Thus, a link prediction approach could incorrectly treat undiscovered positive links as negative links, thereby introducing a bias in the learning. In this paper, we propose to denoise the class of negative links in the training data via a Gaussian process anomaly detector. We show that this significantly reduces the noise due to mislabelled negative links and improves the resulting link prediction accuracy. We evaluate the approach by introducing synthetic noise into the PPI networks and measuring how accurately we can reconstruct the original PPI networks using classifiers trained on both noisy and denoised data. Experiments were performed with five different PPI network datasets and the results indicate a significant reduction in bias due to label noise, and more importantly, a significant improvement in the accuracy of detecting missing links via classification.

Early identification of cotton fields using mosaicked aerial multispectral imagery

U.S. Department of Agriculture-Agricultural Research Service, Insect Control and CottonDisease Research Unit, 2771 F&B Road, College Station, Texas 77845, United StatesAbstract. Early identification of cotton fields is important for advancing boll weevil eradicationprogress and reducing the risk of reinfestation. Remote sensing has long been used for cropidentification, but limited work has been reported on early identification of cotton fields.Theobjectiveofthisstudyistoevaluateaerialimageryforidentifyingcottonfieldsbeforecottonplants start to bloom. A two-camera imaging system was used to acquire red-green-blue andnear-infrared images with 1-m pixel resolution along two flight lines over an 8km×12 kmcropping area. The images were mosaicked using two approaches: manual georeferencing fol-lowed by position-based mosaicking in Erdas Imagine and content-based automatic mosaickinginPix4DMapper.Themosaickedimageswerethenclassifiedintodifferentcropsandcovertypesusing supervised classification techniques. Results showed that both types of mosaics wereeffective for cotton identification and that maximum likelihood classification produced thebest overall accuracy of 90% for the position-based approach and 91% for the content-basedapproach. The methodologies presented in this study will be useful for boll weevil eradicationprogram managers to quickly and efficiently identify cotton fields at relatively early growthstages using mosaicked aerial imagery.

Land cover change detection using GIS and remote sensing techniques: A spatio-temporal study on Tanguar Haor, Sunamganj, Bangladesh

Tanguar Haor is one of the two listed Ramsar Site of this country which contains a rich amount of biodiversity as well as a highly productive ecosystem. But the valuable landscape undergoes a radical change in its form over the decades. This study uses past and recent satellite data to evaluate the typical landscape change over the decades. Both pre-classification and post classification change detection approach was used to assess the change result from 1980 to 2010. In pre-classification approach CVA, NDVI and NDWI analysis were implemented to assess the change scenario. Maximum likelihood supervised classification technique was performed to create the signature class of significant land cover category (deep water, shallow water, vegetation, and settlement). After ensuring satisfactory accuracy value for each classified image a detail post classification change detection analysis was executed. Image differencing, statistical change detection techniques (transition probability matrix), change dynamics analysis was also operated to evaluate the statistics of past change relative to present. This study illustrated that, about 40% land cover of the total study area has been converted over 30years period. Forested and high land vegetation’s are disappearing rapidly, deep water bodies consist of large lakes are becoming the rare feature of the study area. Widespread development of settlement and dominant shallow water feature are converting the natural wetland a permanent low lying agricultural land.

Sustainability of Water Bodies of Edku Lake, Northwest of Nile Delta, Egypt: RS/GIS Approach

In this paper, Edku Lake was selected as a case study to apply the RS/GIS techniques to investigate the water body sustainability. It is one of the northern coastal lakes in Egypt, located at the northwestern part of the Nile Delta. Edku Lake is an important fishing area in Egypt and receives its water from two sources. One of sources is the drainage water of Kom Belag and Bersik drains and second is the sea water. Remote sensing and GIS software are used in this study for processing of the images and managing the database of each image. The different techniques of classification were tested, the results showed that the maximum likelihood supervised classification technique was more accurate to monitor changes in the water bodies of the Lake. The technique was applied to subsets of the Landsat TM, ETM+ and OLI/TIRS images acquired on 1984, 1990, 1998, 2003 and 2015, respectively to monitor changes in the Lake. The results showed that the water bodies of the lake decreased during the period from 1984 to 2015. The extracted data from the images have been used to develop statistical models for the different classes to predict the future situation of each class. The results of prediction indicated that the water body of the lake will be more decrease in 2030. The results indicate that the water body of the lake is not sustainable. The results of this study will act as warning for the decision makers to take the necessary actions/policy to reduce the environmental risk and maintain the healthy environment of the lake.