Land Cover Classification Accuracy Research Articles

Automated Cloud Shadow Detection from Satellite Orthoimages with Uncorrected Cloud Relief Displacements

Clouds and their shadows significantly affect satellite imagery, resulting in a loss of radiometric information in the shadowed areas. This loss reduces the accuracy of land cover classification and object detection. Among various cloud shadow detection methods, the geometric-based method relies on the geometry of the sun and sensor to provide consistent results across diverse environments, ensuring better interpretability and reliability. It is well known that the direction of shadows in raw satellite images depends on the sun’s illumination and sensor viewing direction. Orthoimages are typically corrected for relief displacements caused by oblique sensor viewing, aligning the shadow direction with the sun. However, previous studies lacked an explicit experimental verification of this alignment, particularly for cloud shadows. We observed that this implication may not be realized for cloud shadows, primarily due to the unknown height of clouds. To verify this, we used Rapideye orthoimages acquired in various viewing azimuth and zenith angles and conducted experiments under two different cases: the first where the cloud shadow direction was estimated based only on the sun’s illumination, and the second where both the sun’s illumination and the sensor’s viewing direction were considered. Building on this, we propose an automated approach for cloud shadow detection. Our experiments demonstrated that the second case, which incorporates the sensor’s geometry, calculates a more accurate cloud shadow direction compared to the true angle. Although the angles in nadir images were similar, the second case in high-oblique images showed a difference of less than 4.0° from the true angle, whereas the first case exhibited a much larger difference, up to 21.3°. The accuracy results revealed that shadow detection using the angle from the second case improved the average F1 score by 0.17 and increased the average detection rate by 7.7% compared to the first case. This result confirms that, even if the relief displacement of clouds is not corrected in the orthoimages, the proposed method allows for more accurate cloud shadow detection. Our main contributions are in providing quantitative evidence through experiments for the application of sensor geometry and establishing a solid foundation for handling complex scenarios. This approach has the potential to extend to the detection of shadows in high-resolution satellite imagery or UAV images, as well as objects like high-rise buildings. Future research will focus on this.

A “Region-Specific Model Adaptation (RSMA)”-Based Training Data Method for Large-Scale Land Cover Mapping

An accurate and historical land cover monitoring dataset for Alaska could provide fundamental information for a range of studies, such as conservation habitats, biogeochemical cycles, and climate systems, in this distinctive region. This research addresses challenges associated with the extraction of training data for timely and accurate land cover classifications in Alaska over longer time periods (e.g., greater than 10 years). Specifically, we designed the “Region-Specific Model Adaptation (RSMA)” method for training data. The method integrates land cover information from the National Land Cover Database (NLCD), LANDFIRE’s Existing Vegetation Type (EVT), and the National Wetlands Inventory (NWI) and machine learning techniques to generate robust training samples based on the Anderson Level II classification legend. The assumption of the method is that spectral signatures vary across regions because of diverse land surface compositions; however, despite these variations, there are consistent, collective land cover characteristics that span the entire region. Building upon this assumption, this research utilized the classification power of deep learning algorithms and the generalization ability of RSMA to construct a model for the RSMA method. Additionally, we interpreted existing vegetation plot information for land cover labels as validation data to reduce inconsistency in the human interpretation. Our validation results indicate that the RSMA method improved the quality of the training data derived solely from the NLCD by approximately 30% for the overall accuracy. The validation assessment also demonstrates that the RSMA method can generate reliable training data on large scales in regions that lack sufficient reliable data.

Estimating the distribution of reedbed in Britain demonstrates challenges of remotely sensing rare land cover types at large spatial scales

Common Reed Phragmites australis, globally one of the mostly widely distributed wetland plants, is important for biodiversity and for humans. However, like most wetland plant communities, reedbed has rarely been mapped at large geographical scales, restricting the information available to study reed’s range dynamics or inform its management. Using Sentinel-2 data and machine learning, we aimed to produce the first published remotely-sensed reedbed map of Britain; however, accuracy as assessed by field validation was relatively low (AUC = 0.671), with many false positives (commission error of 93.4%). A similar workflow carried out in Google Earth Engine, using nearly an order of magnitude more images, gave a lower commission error but a disproportionately higher omission error. Using the known commission and omission error, we estimate that in 2015–2017 ~ 7800 ha of Britain was reedbed. Our study highlights the enduring barriers to accurate land cover classification at large spatial scales. Even with a ‘big data’ approach, reflectance error and ecological factors such as confusion land cover types and geographical variation in temporal reflectance function will probably continue to limit the size of area for which land cover can be classified accurately, therefore limiting the utility of remote sensing for ecologists.

Developing a Semi-Supervised Strategy in Time Series Mapping of Wetland Covers: A Case Study of Zrebar Wetland, Iran

Wetlands, essential for Earth’s health, ecological balance, and local economies, require accurate monitoring and assessment for effective conservation. Data-driven models based on remote sensing are highly capable of monitoring the status and classification of wetlands. This study developed a semi-supervised framework for mapping wetland covers in Zrebar, Iran, using Landsat time series data from 1984 to 2022. A pixel purification technique was applied to the temporal candidate images to refine the initial training data (conventional scenario) and generate purified training data (proposed scenario). The Support Vector Machine (SVM) algorithm was utilized to classify the land cover within the wetland, and the accuracy of the two scenarios was evaluated and compared. Over the study period, the analysis of land cover changes within Zrebar Wetland revealed significant spatial and temporal changes in soil and farmland, reed, and water from 1984 to 2022. The omission error rates for the classes soil and farmland, reed, and water were decreased from 0.14, 0.14, and 0.12 for scenario 1 to 0.03, 0.05, and 0.05 for scenario 2, respectively. In addition, the commission error for these classes decreased from 0.13, 0.18, and 0.09 for scenario 1 to 0.04, 0.06, and 0.04 after applying the filtered training data in the scenario 2. Finally, the overall accuracy of the initial training data (scenario 1) and the filtered training data (scenario 2) were 0.86 and 0.94, respectively. These results underscore the effectiveness of the proposed strategy in enhancing the accuracy of land cover classification within the wetland over time, highlighting its potential for future wetland conservation efforts.

Hyperspectral Tensor Completion Using Low-Rank Modeling and Convex Functional Analysis.

Hyperspectral tensor completion (HTC) for remote sensing, critical for advancing space exploration and other satellite imaging technologies, has drawn considerable attention from recent machine learning community. Hyperspectral image (HSI) contains a wide range of narrowly spaced spectral bands hence forming unique electrical magnetic signatures for distinct materials, and thus plays an irreplaceable role in remote material identification. Nevertheless, remotely acquired HSIs are of low data purity and quite often incompletely observed or corrupted during transmission. Therefore, completing the 3-D hyperspectral tensor, involving two spatial dimensions and one spectral dimension, is a crucial signal processing task for facilitating the subsequent applications. Benchmark HTC methods rely on either supervised learning or nonconvex optimization. As reported in recent machine learning literature, John ellipsoid (JE) in functional analysis is a fundamental topology for effective hyperspectral analysis. We therefore attempt to adopt this key topology in this work, but this induces a dilemma that the computation of JE requires the complete information of the entire HSI tensor that is, however, unavailable under the HTC problem setting. We resolve the dilemma, decouple HTC into convex subproblems ensuring computational efficiency, and show state-of-the-art HTC performances of our algorithm. We also demonstrate that our method has improved the subsequent land cover classification accuracy on the recovered hyperspectral tensor.

Exploring Distributed Scatterers Interferometric Synthetic Aperture Radar Attributes for Synthetic Aperture Radar Image Classification

Land cover classification of Synthetic Aperture Radar (SAR) imagery is a significant research direction in SAR image interpretation. However, due to the unique imaging methodology of SAR, interpreting SAR images presents numerous challenges, and land cover classification using SAR imagery often lacks innovative features. Distributed scatterers interferometric synthetic aperture radar (DS-InSAR), a common technique for deformation extraction, generates several intermediate parameters during its processing, which have a close relationship with land features. Therefore, this paper utilizes the coherence matrix, the number of statistically homogeneous pixels (SHPs), and ensemble coherence, which are involved in DS-InSAR as classification features, combined with the backscatter intensity of multi-temporal SAR imagery, to explore the impact of these features on the discernibility of land objects in SAR images. The results indicate that the adopted features improve the accuracy of land cover classification. SHPs and ensemble coherence demonstrate significant importance in distinguishing land features, proving that these proposed features can serve as new attributes for land cover classification in SAR imagery.

Wet-ConViT: A Hybrid Convolutional–Transformer Model for Efficient Wetland Classification Using Satellite Data

Accurate and efficient classification of wetlands, as one of the most valuable ecological resources, using satellite remote sensing data is essential for effective environmental monitoring and sustainable land management. Deep learning models have recently shown significant promise for identifying wetland land cover; however, they are mostly constrained in practical issues regarding efficiency while gaining high accuracy with limited training ground truth samples. To address these limitations, in this study, a novel deep learning model, namely Wet-ConViT, is designed for the precise mapping of wetlands using multi-source satellite data, combining the strengths of multispectral Sentinel-2 and SAR Sentinel-1 datasets. Both capturing local information of convolution and the long-range feature extraction capabilities of transformers are considered within the proposed architecture. Specifically, the key to Wet-ConViT’s foundation is the multi-head convolutional attention (MHCA) module that integrates convolutional operations into a transformer attention mechanism. By leveraging convolutions, MHCA optimizes the efficiency of the original transformer self-attention mechanism. This resulted in high-precision land cover classification accuracy with a minimal computational complexity compared with other state-of-the-art models, including two convolutional neural networks (CNNs), two transformers, and two hybrid CNN–transformer models. In particular, Wet-ConViT demonstrated superior performance for classifying land cover with approximately 95% overall accuracy metrics, excelling the next best model, hybrid CoAtNet, by about 2%. The results highlighted the proposed architecture’s high precision and efficiency in terms of parameters, memory usage, and processing time. Wet-ConViT could be useful for practical wetland mapping tasks, where precision and computational efficiency are paramount.

Assessing Land Cover Classification Accuracy: Variations in Dataset Combinations and Deep Learning Models

Assessing Land Cover Classification Accuracy: Variations in Dataset Combinations and Deep Learning Models

Machine learning based urban land cover classification using PolInSAR data: a study with ALOS-2 and RADARSAT-2 datasets

A substantial variation in the land cover dynamics has been observed as a consequence of increasing urban expansion. Polarimetric synthetic aperture radar (PolSAR) data is widely being used for land cover studies in urban areas due to its all-weather, day-and-night imaging capabilities. However, in densely built-up areas, challenge arises with buildings having large Azimuth Orientation Angles (AOAs). These buildings are often misclassified as vegetation due to the depolarization of radar signal causing volumetric scattering response from the structures. This study addresses this issue by proposing an approach that integrates polarimetric information with interferometric SAR (InSAR) coherence to improve the differentiation between urban structures and vegetated areas, enhancing the accuracy of urban land-cover classification. Vegetated areas exhibit lower temporal coherence due to changes in the orientation of its leaves and branches caused by wind, seasonal variations, growth phenology, and other factors. In contrast, urban structures, being relatively stable targets, maintain high temporal coherence values. In present research various decomposition and scattering parameters were evaluated, along with PolInSAR coherence derived from L-band (ALOS-2) and C-band (RADARSAT-2), using two machine learning algorithms namely, Random Forest (RF) and Convolutional Neural Network (CNN). The C-band RADARSAT-2 data, particularly with six-component decomposition parameters, performed better, achieving an overall accuracy as 85.85% using RF algorithm. To further improve classification results, optical datasets from Landsat constellation were fused with SAR parameters using Gram-Schmidt fusion technique. This fusion led to significant improvements, achieving an overall accuracy of 94.50% and kappa statistics of 0.92, when CNN algorithm was applied to the fused optical and C-band RADARSAT-2 dataset. These results demonstrate the effectiveness of combining PolInSAR and optical data for more accurate urban land-cover classification, particularly in complex urban environments.

Implementation of Deep Learning Technique for Accurate Land Cover Classification

Detecting and modelling Land Cover are crucial for managing natural resources, assessing environmental impacts, and preserving ecological connectivity. Convolutional Neural Networks (CNNs) have become pivotal in advancing remote sensing applications, particularly in land cover classification. Therefore, this study introduces a CNN classifier for the prediction land cover efficiently. The pre processing is carried out based on Principle Component Analysis (PCA), which reduces the dimensionality of the input data while retaining essential information. This step aims to enhance computational efficiency and improve the CNN’s ability to extract relevant features during training. Following pre processing, a comprehensive training phase involves optimizing the CNN architecture using a labelled dataset. This process allows the network to learn intricate spatial patterns and spectral characteristics crucial for accurate land cover classification. Evaluation of the trained model occurs in the testing phase, where performance metrics such as accuracy, precision, recall, and F1 score are computed using an independent validation dataset. Results obtained from the python software demonstrate that the CNN PCA framework’s capability to achieve high classification accuracy across diverse land cover types.

Diagnosis of the accuracy of land cover classification using bootstrap resampling

ABSTRACT Since the 1970s, there has been a long history of assessing the accuracy of remotely sensed land cover types. Various accuracy assessment methods have been proposed, including the method of bootstrap resampling. However, the potential of the bootstrap resampling method to diagnose the accuracy of remote sensing monitoring of land cover has not been fully explored. Here, we used the land cover map classified in the Gannan Tibetan Autonomous Region as an example and investigated the impact of two parameters in the bootstrap resampling method on the assessment of land cover classification accuracy: the number of validation points and the number of bootstrap resampling times. Varying these two parameters can help diagnose the accuracy of remote sensing classifications of land cover. The main conclusions are as follows. First, the number of validation points required to achieve a stabilized accuracy estimate varies among land cover types. It indicates not only the level of homogeneity of the land cover type but also the level of difficulty associated with classifying it. Second, it is not necessary to have a very large number of bootstrap resampling times to estimate the classification accuracy – 50 was sufficient. In summary, we recommend that various numbers of validation points be employed in bootstrap to objectively and comprehensively assess the overall, producer’s, and user’s accuracies of remote sensing classifications of land cover.

Improvement of land cover classification accuracy by training sample clustering

The subject of this article is land cover classification based on geospatial data. The supervised classification methods are appropriate for most of the thematic tasks of remote sensing because they provide the opportunity to set the characteristics of the initial classes in the form of a training sample set, in contrast to unsupervised methods. There are many approaches to processing such a set; however, their common disadvantage is that they do not consider the factor of training sample separability. This characteristic indicates the extent to which signatures representing different classes do not overlap. A low degree of separability is inherent in high-level training sample mixing. Thus, separability affects classification accuracy. One possible ways to increase separability is training sample clustering. Considering the above, the goal of this study is to develop a training sample clustering technique to improve land cover classification accuracy by increasing the separability of training samples. The tasks of this work are as follows: 1) develop a method for training sample separability assessment; 2) develop a training sample clustering technique based on training sample separability; 3) test the effectiveness of the developed technique by applying it to experimental land cover classification. In the experiments, two land cover classifications were obtained for each of the two selected study areas (i.e., one before and another after training sample clustering. Six land cover classes were defined for each experiment. The training samples were selected for each class. Conclusions. After the application of the developed technique, an increase in the separability of the training samples was evidenced by the developed separability index. In turn, this approach led to an improvement in land cover classification. For the first experiment, this was evidenced by an increase in the overall accuracy and kappa coefficient by 20% (from 63 to 83%) and 21% (from 60% to 81%), respectively. In the second experiment, the increase was 4% (from 77% to 81%) and 5% (from 66% to 71%), respectively.

Application of Sentinel-2A Images for Land Cover Classification Using NDVI in Jember Regency

The advancement of remote sensing technology has led to the development of sophisticated image processing methods that yield highly accurate land cover classification information, minimizing misinterpretations. The Normalized Difference Vegetation Index (NDVI) is a widely utilized method in remote sensing for measuring green vegetation. A significant portion of the Jember Regency area is covered by vegetation. This study aimed to identify various land cover types in the Jember Regency area, quantify the area for each classification, and establish the NDVI value ranges for each type of cover. Sentinel-2 was employed as the primary data source, and the NDVI method was utilized for land cover classification in the Jember Regency. The region exhibited diverse land cover types. Data from Sentinel-2A captured in June and October 2019 were chosen due to their accessibility, open-source nature, and adequate spectral, spatial, and temporal resolution. The classification in this study encompassed five classes: water bodies, settlements, dry fields, irrigated paddy fields, and forests. Error analysis was conducted using a confusion matrix with the Overall and Kappa algorithms. The accuracy results for June indicated a Kappa Accuracy of 37.7% and Overall Accuracy of 54.5%. In October, the Kappa Accuracy increased to 39.9%, and the Overall Accuracy reached 56.5%. In conclusion, the NDVI method did not meet the criteria for accurately interpreting land cover classification.

Improving land cover classification accuracy of Sentinel-2 images: a systematic review of articles between 2015 and 2021

Improving land cover classification accuracy of Sentinel-2 images: a systematic review of articles between 2015 and 2021

Multi-Scale Feature Fusion Network with Symmetric Attention for Land Cover Classification Using SAR and Optical Images

The complementary characteristics of SAR and optical images are beneficial in improving the accuracy of land cover classification. Deep learning-based models have achieved some notable results. However, how to effectively extract and fuse the unique features of multi-modal images for pixel-level classification remains challenging. In this article, a two-branch supervised semantic segmentation framework without any pretrained backbone is proposed. Specifically, a novel symmetric attention module is designed with improved strip pooling. The multiple long receptive fields can better perceive irregular objects and obtain more anisotropic contextual information. Meanwhile, to solve the semantic absence and inconsistency of different modalities, we construct a multi-scale fusion module, which is composed of atrous spatial pyramid pooling, varisized convolutions and skip connections. A joint loss function is introduced to constrain the backpropagation and reduce the impact of class imbalance. Validation experiments were implemented on the DFC2020 and WHU-OPT-SAR datasets. The proposed model achieved the best quantitative values on the metrics of OA, Kappa and mIoU, and its class accuracy was also excellent. It is worth mentioning that the number of parameters and the computational complexity of the method are relatively low. The adaptability of the model was verified on RGB–thermal segmentation task.

Fine-resolution land cover mapping over large and mountainous areas for Lāna‘i, Hawaii using posterior probabilities, and expert knowledge

ABSTRACT The task of accurately mapping species-specific vegetation cover in remote and topographically complex regions like those found in Hawaiʻi presents unique challenges. This study leverages a machine learning approach to accurately classify vegetation into fine species-specific classes across the island of Lāna‘i, Hawaii, offering a novel methodology for tackling such challenges. Utilizing high-resolution WordView-2 satellite imagery, a neural network classifier and a custom lidar-based geometric correction, we introduced two new approaches to refine our high-resolution land cover classifications. This included the implementation of prior-based adjustments to class posterior probabilities to enhance land cover classification accuracy. Moreover, we developed mixed hierarchical classification maps that use class posterior probabilities to identify, at the pixel level, the finest land cover class that meets a user-defined confidence threshold. The resulting high-resolution land cover map for Lāna‘i captures the rich diversity and distribution of native and invasive plant species with high overall accuracy, generally exceeding 95%, based on independent ground control data. The capacity to produce wall-to-wall species-level vegetation maps provides a new window into monitoring vegetation dynamics on Lāna‘i and similarly remote and topographically complex regions, and contributes to our broader understanding of ecosystem responses to invasive species, climatic changes, and land management practices such as erosion and sediment control planning. Our approach offers a blueprint for similar efforts in other complex and remote ecosystems.

Spatio-temporal analysis of urban expansion using remote sensing data and GIS for the sustainable management of urban land: the case of Burayu, Ethiopia

PurposeThe purpose of this study is to analyze the horizontal expansion of Burayu Town between 1990 and 2020. The study typically acts as a baseline for integrated spatial planning in small- and medium-sized towns, which will help to plan sustainable utilization of land.Design/methodology/approachLandsat5-TM, Landsat7 ETM+, Landsat5 TM and Landsat8 OLI were used in the study, along with other auxiliary data. The LULC map classifications were generated using the Random Forest Package from the Comprehensive R Archive Network. Post-classification, spatial metrics, and per capita land consumption rate were used to understand the manner and rate of expansion of Burayu Town. Focus group discussions and key informant interviews were also used to validate land use classes through triangulation.FindingsThe study found that the built-up area was the most dynamic LULC category (85.1%) as it increased by over 4,000 ha between 1990 and 2020. Furthermore, population increase did not result in density increase as per capita land consumption increased from 0.024 to 0.040 during the same period.Research limitations/implicationsAs a result of financial limitations, there were no high-resolution satellite images available, making it challenging to pinpoint the truth as it is on the ground. Including senior citizens in the study region allowed this study to overcome these restrictions and detect every type of land use and cover.Practical implicationsData on urban growth are useful for planning land uses, estimating growth rates and advising the government on how best to use land. This can be achieved by monitoring and reviewing development plans using satellite imaging data and GIS tools.Originality/valueThe use of Random Forest for image classification and the employment of local knowledge to validate the accuracy of land cover classification is a novel approach to properly customize remote sensing applications.

Impact of land use/land cover changes on evapotranspiration and model accuracy using Google Earth engine and classification and regression tree modeling

This research uses a Classification and Regression Tree (CART) model with Google Earth Engine (GEE) to assess the winter season’s land cover and change detection mapping impact on the evapotranspiration (crop water requirement) parameters. Winter seasons, crucial for agricultural planning, and irrigation water requirement challenges in accurately mapping land cover and detecting changes due to the dynamic nature of farming practices during this period. In this study, Landsat-8 OLI images have been combined to map Land use and Land cover (LULC) and other change detection mapping in Akola Block, Maharashtra, India, during the 2018–2022 winter season. As an discoverer researcher that found detailed information of LULC classes during last 2018 to 2022 winter seasons, the use of the CART model in combination with a cloud-computing GEE demonstrates to be a practical approach for accurate land cover classification and change detection maps to create a pixel-based winter seasons information of study area. The novelty of this study lies in its innovative use of GEE, a powerful platform for remote sensing and geospatial analysis, to create LULC maps with remarkable accuracy. Achieving a 100% training accuracy across the four years under consideration is an exceptional feat, highlighting the reliability and stability of the methodology. Furthermore, the validation accuracy values, ranging from 89 to 94% for the winter seasons of 2018 to 2022, underscore the robustness of this approach. Such consistently high accuracy in mapping LULC over time is a groundbreaking achievement and offers a new dimension to the field of hydrology. For the hydrological community, the implications of this study are profound. Accurate LULC mapping and change detection provide critical data for modeling and analyzing the effects of land use changes on water resources, watershed management, and water quality. The User, Kappa, and Producer accuracy metrics used in this research highlight the model’s performance and its suitability for hydrological applications. These accurate LULC maps can aid in the development of hydrological models, forecasting, and decision-making processes, ultimately contributing to more effective water resource management and environmental conservation. In summary, this study’s innovative use of GEE, its remarkable accuracy in LULC mapping, and its relevance to the hydrological community demonstrate the potential for advanced remote sensing and geospatial tools to significantly improve our understanding of land use changes and their implications for water resources and environmental management.

SEMANTIC KNOWLEDGE EMBEDDING DEEP LEARNING NETWORK FOR LAND COVER CLASSIFICATION

Abstract. Land cover classification is essential basic information and key parameters for environmental change research, geographical and national monitoring, and sustainable development planning. Deep learning can automatically and multi-level extract the features of complex features, which has been proven to be an effective method for information extraction. However, one of the major challenges of deep learning is its poor interpret-ability, which makes it difficult to understand and explain the reasoning behind its classification results. This paper proposes a deep cross-modal coupling model (CMCM) for integrating semantic features and visual features. The representation of knowledge map is indicatively introduced into remote sensing image classification. Compared to previous studies, the proposed method provides accurate descriptions of the complex semantic objects within a complex land cover environment. The results showed that the integration of semantic knowledge improved the accuracy and interpret-ability of land cover classification.

A SHALLOW NEURAL NETWORK MODEL FOR URBAN LAND COVER CLASSIFICATION USING VHR SATELLITE IMAGE FEATURES

Abstract. Recently, image classification techniques using neural networks have received considerable attention in sustainable urban development, since their applications have an extreme effect on building distribution, infrastructural networks, and water resource management. In this research, a back-propagation shallow neural network model is presented for very high resolution satellite image classification in urban environments. Workflow procedures consider selecting and collecting data, preparing required study areas, extracting distinctive features, and applying the classification process. Visual interpretation is performed to identify observed land cover classes and detect distinctive features in the urban environment. Pre-processing techniques are implemented to present the used images in a more suited form for the classification techniques. A shallow neural network model (supported by MathWorks MATLAB environment) is successfully applied and results are evaluated. The proposed model is tested for classifying both WorldView-2 and WorldView-3 multispectral images with different spatial and spectral characteristics to check the model’s applicability to various kinds of satellite imagery and different study areas. Model outcomes are compared to two well-known classification methods; the Nearest Neighbour object-based method and the Maximum Likelihood pixel-based classifier, to validate and check the model stability. The overall accuracy achieved by the proposed model is 86.25% and 83.25%, while the nearest neighbour approach has obtained 84.50% and 82.75%, and the maximum likelihood classifier has accomplished 82.50% and 80.25% for study area 1 and study area 2 respectively. Obtained results indicate that the developed shallow neural network model achieves a promising accuracy for urban land cover classification in comparison with the standard techniques.