Table 1 - available via license: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Content may be subject to copyright.
Source publication
Land cover changes considered as one of the important global phenomena exerting perhaps one of the most significant effects on the environment than any other factor. It is, therefore, vital that accurate data on land cover changes are made available to facilitate the understanding of the link between land cover changes and environmental changes to...
Context in source publication
Context 1
... applying the cross tabulation technique on classified images of the years 2000 and 2004, statistical results were obtained showing the land cover changes that occurred within the per- iod from 2000 to 2004 (Table 1). To visualize the changes that occurred in that period, a simple technique (El-Hattab, 2015a) was used to create a final change image for each land cover class, representing the areas of change, either positive or neg- ative, in addition to the areas that showed no change. ...
Citations
... Ground truthing and accuracy assessment were done for the most current satellite image (Landsat 8 OLI, 2020) and inferences were made to the other two images (1986 and 2007). LULC change was accomplished using post-classification comparison (El-Hattab, 2016). The ground truthing involved going out into the field with printed classified images, a digital camera, and a handheld Global Positioning System (GPS) device -specifically the Garmin GPSMAP 64csx. ...
This paper examined land use and land cover (LULC) dynamics over 34 years in the Bosomtwe biosphere vis-à-vis population trends within a buffer of 5km using an integrated remote sensing and geographic information systems (GIS) approach to assess the changes in the land use and land cover. Supervised classification and post-classification change detection technique in GIS was applied to three multi-temporal Landsat images (1986, 2007, and 2020). The date selection was informed by the availability of Landsat imagery with limited cloud cover. The analysis showed that the built-up category recorded the highest percentage change (260.2%) with an annual rate of 7.7%. Forest cover recorded a loss of 66.3% of area coverage with an increase in farmland from 50.8% in 1986 to 68.5% in 2020. Besides, Lake Bosomtwe was contracted by 0.76 km2 over the period under review. There was a strong positive correlation between population density and both cropland (r = 0.89) and built-up areas (r = 0.70). It is recommended that intensification of monitoring activities by the district assembly would help to reduce the anthropogenic activities being conducted in the area.
... Finally, Otsu's thresholding [22] was applied to the magnitudes of the C2VA to generate binary change maps from the inputs. To evaluate the change detection results, we have generated reliable ground-truth maps utilizing post-classification change detection techniques [24], followed by manual rectification to assign classes as changed or unchanged. In this experiment, the raw subject and reference images were regarded as the uncalibrated cases, whereas the normalized subject image and reference image were treated as the calibrated cases for the purposes of clarity and ease of explanation. ...
These authors contributed equally to this work. Abstract: Relative radiometric normalization (RRN) is a critical pre-processing step that enables accurate comparisons of multitemporal remote-sensing (RS) images through unsupervised change detection. Although existing RRN methods generally have promising results in most cases, their effectiveness depends on specific conditions, especially in scenarios with land cover/land use (LULC) in image pairs in different locations. These methods often overlook these complexities, potentially introducing biases to RRN results, mainly because of the use of spatially aligned pseudo-invariant features (PIFs) for modeling. To address this, we introduce a location-independent RRN (LIRRN) method in this study that can automatically identify non-spatially matched PIFs based on brightness characteristics. Additionally, as a fast and coregistration-free model, LIRRN complements keypoint-based RRN for more accurate results in applications where coregistration is crucial. The LIRRN process starts with segmenting reference and subject images into dark, gray, and bright zones using the multi-Otsu threshold technique. PIFs are then efficiently extracted from each zone using nearest-distance-based image content matching without any spatial constraints. These PIFs construct a linear model during subject-image calibration on a band-by-band basis. The performance evaluation involved tests on five registered/unregistered bitemporal satellite images, comparing results from three conventional methods: histogram matching (HM), blockwise KAZE, and keypoint-based RRN algorithms. Experimental results consistently demonstrated LIRRN's superior performance, particularly in handling unregistered datasets. LIRRN also exhibited faster execution times than blockwise KAZE and keypoint-based approaches while yielding results comparable to those of HM in estimating normalization coefficients. Combining LIRRN and keypoint-based RRN models resulted in even more accurate and reliable results, albeit with a slight lengthening of the computational time. To investigate and further develop LIRRN, its code, and some sample datasets are available at link in Data Availability Statement.
... Land-use/land cover change detection Classification comparisons of land cover statistics were utilized according to El-Hattab (2016). Four change maps for 1990-2000, 2000-2010, 2010-2020, and 1990-2020 were prepared by post-classification comparison method using ENVI (5.3) by running two classification images for the same scene at a different date. ...
A key source of information for many decision support systems is identifying land use and land cover (LULC) based on remote sensing data. Land conservation, sustainable development, and water resource management all benefit from the knowledge obtained from detecting changes in land use and land cover. The present study aims to investigate the multi-decadal coastal change detection for Ras El-Hekma and El-Dabaa area along the Mediterranean coast of Egypt, a multi-sectoral development area. Besides, the superiority of the area is highly dependent on its proximity to three development projects: the tourism and urban growth pole at Ras El-Hekma, the beachfront Alamain New Mega City, and the Nuclear Power Plant at El Dabaa. This study utilized multi-spectral Landsat satellite images covering 1990, 2010, and 2020 to perceive the post-classification change detection analysis of the land use and land cover changes (LULCC) over 30 years. The results of the supervised classification from 1990 to 2020 showed a 47.33 km² (4.13%) expansion of the agricultural land area, whereas the bare soil land area shrunk to 73.13 km² (6.24%). On the other hand, the built-up activities in the area launched in 2010 and escalated to 20.51 km²(1.77%) in 2020. The change in land use reveals the shift in the economic growth pattern in the last decade toward tourism and urban development. Meanwhile, it indicates that no conflict has yet arisen regarding the land use between the expanded socioeconomic main sectors (i.e., agriculture, and tourism). Therefore, the best practices of land use management and active participation of the stakeholders and the local community should be enhanced to achieve sustainability and avoid future conflicts. An area-specific plan including resource conservation measures and the provision of livelihood alternatives should be formulated within the National Integrated Coastal Zone Management (ICZM) plan with the participation of the main stakeholders and beneficiaries. The findings of the present work may be considered useful for sustainable management and supportive to the decision-making process for the sustainable development of this area.
... Dale, 1997;Dias et al., 2023;Dolman & Verhagen, 2003;El-Hattab, 2016). Globally, cumulative landuse changes accelerate land cover transformation (Lambin, 1997). ...
Technology-driven population expansion is closely linked to land use change. Unregulated mining, urbanization, industrialization, and forest clearing threaten land use and cover. This study used GIS and statistical methods to examine land use and cover changes in eastern India’s Asansol-Durgapur Development Authority (ADDA). The Kappa coefficient was used to validate each year’s LULC map accuracy. This region is changing rapidly due to industrial and urban development, which might cause environmental issues. Thus, this area is ideal for a scientific land-use change study. The central hypothesis of this study is that the LULC of an industrial area is spatially heterogeneous and that the number of hotspots is gradually increasing in response to the dynamicity of land use change over time and space. Three years (1992, 2007, and 2022) were used to determine the estimated transition rate. Hotspots of land use change were identified using autocorrelation statistics for LULC clustering using Moron’s I and Gi Z statistics. The proportion of land encompassed by natural vegetation experienced a decline from 12% in 1992 to 4% in 2022. Similarly, the extent of land occupied by agricultural activities decreased from 47 to 38% during the period spanning from 1992 to 2022. The industrial and coal mining sectors experienced a modest growth rate of 1% during the period spanning from 1992 to 2022. If the current rate of land use change persists, it will gradually and consistently alter the existing landscape. This study’s findings can potentially inform strategies to mitigate the adverse impacts of industrialization and urbanization on the region's natural resources.
... The application of change detection has proven beneficial in monitoring environmental conditions and aiding in the identification of potential problems, which in turn can inform effective development strategies concerning LULC changes [72]. The accuracy of LULC change detection relies on precise classification mapping [73,74], enabling the tracking and quantification of such changes. RS data serve as a valuable resource for determining the magnitude of change, as is evident from the discernible differences between two images captured at distinct points in time [75]. ...
... Detecting changes across multi-temporal images over time requires a post-classification process that allows for pixel-based comparisons. Classified maps must be categorized appropriately [70,73]. Table 5 and Fig. 7 present the results obtained from the RF algorithm within the selected time frame from 1991 to 2021. ...
The identification of land use/land cover (LULC) changes is important for monitoring, evaluating, and preserving natural resources. In the Kurdistan region, the utilization of remotely sensed data to assess the effectiveness of machine learning algorithms (MLAs) for LULC classification and change detection analysis has been limited. This study monitors and analyzes LULC changes in the study area from 1991 to 2021 using a quantitative approach with multi-temporal Landsat imagery. Five MLAs were applied: Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN), K-Nearest Neighbor (KNN), and Extreme Gradient Boosting (XGBoost).
The results showed that the RF algorithm produced the most accurate maps of the three-decade study period, accompanied by a high kappa coefficient (0.93–0.97) compared with the SVM
(0.91–0.95), ANN (0.91–0.96), KNN (0.92–0.96), and XGBoost (0.92–0.95) algorithms. Consequently, the RF classifier was implemented to categorize all obtainable satellite images. Socioeconomic changes throughout these transition periods were revealed by the change detection results. Rangeland and barren land areas decreased by 11.33 % (− 402.03 km2) and 6.68 % (− 236.8 km2), respectively. The transmission increases of 13.54 % (480.18 km2), 3.43 % (151.74 km2), and 0.71 % (25.22 km2) occurred in agricultural land, forest, and built-up areas, respectively. The outcomes of this study contribute significantly to LULC monitoring in developing regions, guiding stakeholders to identify vulnerable areas for better land use planning and sustainable environmental protection.
... 36 The causes of changes to the earth's surface might be either natural or manmade. 37 One of the most crucial tasks is detecting post-classification changes to determine their type, tempo, and intensity. However, variations in land cover within and between periods cannot be effectively accounted by a simple examination of change or the degree of change. ...
Rapid population growth, human migration, and commercial activities are changing land use and Land cover at a faster rate. The human being's need and greed to sustain themselves alter the earth's natural environment, and that change affected us. However, poor and unmanageable land conversion led to severe environmental effects. For planning and management purposes, precise information regarding land use and its characteristics is required to ensure the sustainability of the area. The current study uses multi-temporal satellite images to analyze the decadal change from 1991 to 2021. Supervised image classification is performed using the Maximum likelihood classifier. The main goal of this study is to compare post-classification results using change vector analysis and analyze human impact on the environment using FRAGSTAT. Fragstat is a widely used software program designed for analyzing spatial patterns in categorical maps. It is commonly employed in landscape ecology, conservation biology, and land management studies. The primary purpose of Fragstats is to quantify and assess the composition and configuration of patches or landscape elements within a given area. The built-up area increased from 2.57% to 8.41% over the past 30 years, while the agricultural land decreased from 83.51% to 70.05%. It was observed that the density of patches and percentage of landscape reduction over time, the rise in the number of patches for agricultural class from 3570 in 1991 to 10173 in 2021 indicates that spatial diversity is increasing in the class with higher levels of anthropogenic disturbances. Moreover, in landscape-level indices, the number of patch and landscape shape index increases, and a fall in the largest patch index indicate that the landscape is becoming more complicated and fragmented. To achieve the sustainable land-use planning and safeguard natural ecosystems and biodiversity from anthropogenic activities, land-use change maps are utilized as an early warning system.
... The theoretical basis and physical fundaments of the employed SD (separated/fused) and the appropriateness of the classification algorithms would be other sources of the differences. Other researchers have obtained good accuracies in post-classification CD through the combination of simple classification methods, as reported by El-Hattab (2016). However, the impact of the classification algorithm on change detection results has also been highlighted in previous studies (Serra et al. 2003) such as the findings observed in the present study. ...
Several methods have been developed to detect differences between temporal satellite images for change detection. Image differencing, which is easy to compute and implement, does not require ground-based data. In this study, the performance of 11 other spectral distances was explored in addition to simple differencing for change detection. Moreover, the fusion of these distances was evaluated using various methods, including linear combination, classification, and majority voting. Comparing the results in different study areas showed that Pearson-Correlation and Spearman-Correlation were the most accurate distances. Additionally, the evaluation of the results indicated that the unsupervised fusion of different distances could increase the final accuracy by an average of 10%. Furthermore, the classification of distance images, which had slightly lower accuracy than the post-classification comparison of original images, was more accurate than the fusion of distances using these methods or thresholding the individual distances.
... Different methods have been developed in order to improve accuracy, such as using textural information, spectral indices, ancillary data, visual interpretation, smoothing or post-classification (e.g., Bhosale et al., 2014;El-Hattab, 2016;Lik o et al., 2022;Manandhar et al., 2009;Thakkar et al., 2017), but there is no standard methodology to choose one. The selection or development of the most effective procedure is highly dependent on multiple factors i.e., the target object (plant), the initial dataset and the obtained results before performing the postclassification procedure. ...
Species composition of forests is a very important component from the point of view of nature conservation and forestry. We aimed to identify 10 tree species in a hilly forest stand using a hyperspectral aerial image with a particular focus on two invasive species, namely Ailanthus tree and black locust. Deep learning‐based training data augmentation (TDA) and post‐classification techniques were tested with Random Forest and Support Vector Machine (SVM) classifiers. SVM had better performance with 81.6% overall accuracy (OA). TDA increased the OA to 82.5% and post‐classification with segmentation improved the total accuracy to 86.2%. The class‐level performance was more convincing: the invasive Ailanthus trees were identified with 40% higher producer's and user's accuracies (PA and UA) to 70% related to the common technique (using a training dataset and classifying the trees). The PA and UA did not change in the case of the other invasive species, black locust. Accordingly, this new method identifies well Ailanthus, a sparsely distributed species in the area; while it was less efficient with black locust that dominates larger patches in the stand. The combination of the two ancillary steps of hyperspectral image classification proved to be reasonable and can support forest management planning and nature conservation in the future.
... The Iterative Self-Organizing Data Analysis Technique Algorithm (ISODATA) was applied in six papers (4%) (Rahman 2016;Sunwoo, Nguyen, and Choi 2018;Ma et al. 2019;El-Hattab 2016). This algorithm is one of the most popular variants of the K-means clustering algorithm. ...
In the current climate change context, detecting and monitoring relevant land use/land cover (LULC) changes in insular and coastal areas is critical as soon as they occur. This research consists of a systematic literature review of 167 open-access articles from January 2010 to June 2022, based on several parameters, namely year of publication, journals, geographic location of the study area, time range of the studies, data source, data type, sensors, remote sensing-based approach, data processing algorithms, accuracy assessment approach, and spatial resolution, using the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) declaration as a guideline. The results revealed that the years 2020 and 2021 showed the highest number of studies published, namely 33 for each year (20%). The continent with the most case studies was Asia (48%), with China being the most productive country in this field (23%). The most analyzed time range was superior to 20 years (37% of the studies). Satellite imagery was the most applied data source (77%), followed by relevant historical data (e.g., land cover maps). The multispectral data was used in 77% of the studies, and the Landsat Mission represents three of five of the most used sensors. Normalized Difference Vegetation Index was the most applied remote sensing-based approach (10%), and the Maximum Likelihood Classifier Algorithm was the most widely used data processing algorithm (10%). The Overall Accuracy is the most applied accuracy assessment approach used in 85 papers (51%). Many articles used a 30-meter spatial resolution (69%), and higher resolutions completed the top 5 approaches. This study contributes to perceiving the main current approaches for monitoring LULC changes in insular and coastal environments to identify research gaps for future developments.
... Do, 2015;El-Hattab, 2016;Neptune & Mothe, 2021). In this study, change detection analysis was performed through the post-classification comparison of land cover classes corresponding to the four processed Landsat images, based on the comparative analysis of individually produced classifications of different dates. ...
The Algerian Saharan rangelands are an arid ecosystem characterized by limited soil, water, and vegetation resources, which make it very susceptible to degradation. This research focuses on the diachronic assessment and multi-temporal mapping of the degradation of steppe vegetation in the south of Biskra during the period 1987-2019, using remote sensing data (MSAVI index), for extracting spatiotemporal data to monitor the rangeland vegetation dynamics. We examined demographic evolution, number of livestock, and land use from quantitative data. The results show that during this period, the landscape of the region changed considerably. The area of rangelands decreased from 19,939 ha (1987) to 3605 ha (2019), where 58% of the pre-existing vegetation was transformed into bare soil. This study confirmed that the rangeland vegetation health is closely related to climate, and its degradation is mainly due to the recurrence, duration, severity, and magnitude of drought events. Manmade activities were also a determinant factor of long-term degradation of the rangeland, such as the expansion of new land development areas that increased from 3754 ha (1987) to 24,410 ha (2019). This trend was found throughout the region, including predominantly pastoral regions such as Oumache and El Haouch, leading to overgrazing with a loss of about 2% of vegetation cover. All these factors have led to a severe and continuous degradation of pastoral resources in a vulnerable environment. The preservation of these limited resources requires appropriate management of the ecosystem and a rational exploitation of its vegetation, soil, and water resources.
