Hybrid methods for land use and land cover classification using remote sensing and combined spectral feature extraction: A case study of Najran City, KSA

The European Commission launch of the twin Sentinel-2 satellites provides new opportunities for land use and land cover (LULC) classification because of the ready availability of their data and their enhanced spatial, temporal and spectral resolutions. The rapid development of machine learning over the past decade led to data-driven models being at the forefront of high accuracy predictions of the physical world. However, the contribution of the driving variables behind these predictions cannot be explained beyond generalized metrics of overall performance. Here, we compared the performance of three shallow learners (support vector machines, random forest, and extreme gradient boosting) as well as two deep learners (a convolutional neural network and a residual network with 50 layers) in and around the city of Malmö in southern Sweden. Our complete analysis suite involved 141 input features, 85 scenarios, and 8 LULC classes. We explored the interpretability of the five learners using Shapley additive explanations to better understand feature importance at the level of individual LULC classes. The purpose of class-level feature importance was to identify the most parsimonious combination of features that could reasonably map a particular class and enhance overall map accuracy. We showed that not only do overall accuracies increase from shallow (mean = 84.64%) to deep learners (mean = 92.63%) but that the number of explanatory variables required to obtain maximum accuracy decreases along the same gradient. Furthermore, we demonstrated that class-level importance metrics can be successfully identified using Shapley additive explanations in both shallow and deep learners, which allows for a more detailed understanding of variable importance. We show that for certain LULC classes there is a convergence of variable importance across all the algorithms, which helps explain model predictions and aid the selection of more parsimonious models. The use of class-level feature importance metrics is still new in LULC classification, and this study provides important insight into the potential of more nuanced importance metrics.

Landsat-like moderate resolution remote sensing images are widely used in land use and land cover (LULC) classification. Limited by coarser resolutions, most of the traditional LULC classifications that are based on moderate resolution remote sensing images focus on the spectral features of a single pixel. Inspired by the spatial evaluation methods in landscape ecology, this study proposed a new method to extract neighborhood characteristics around a pixel for moderate resolution images. 3 landscape-metric-like indexes, i.e., mean index, standard deviation index, and distance weighted value index, were defined as adjacent region features to include the surrounding environmental characteristics. The effects of the adjacent region features and the different feature set configurations on improving the LULC classification were evaluated by a series of well-controlled LULC classification experiments using K nearest neighbor (KNN) and support vector machine (SVM) classifiers on a Landsat 8 Operational Land Imager (OLI) image. When the adjacent region features were added, the overall accuracies of both the classifiers were higher than when only spectral features were used. For the KNN and SVM classifiers that used only spectral features, the overall accuracies of the LULC classification were 85.45% and 88.87%, respectively, and the accuracies were improved to 94.52% and 96.97%. The classification accuracies of all the LULC types improved. Highly heterogeneous LULC types that are easily misclassified achieved greater improvements. As comparisons, the grey-level co-occurrence matrix (GLCM) and convolutional neural network (CNN) approaches were also implemented on the same dataset. The results revealed that the new method outperformed GLCM and CNN approaches and can significantly improve the classification performance that is based on moderate resolution data.

Land use and land cover (LULC) analysis is crucial for understanding societal development and assessing changes during the Anthropocene era. Conventional LULC mapping faces challenges in capturing changes under cloud cover and limited ground truth data. To enhance the accuracy and comprehensiveness of the descriptions of LULC changes, this investigation employed a combination of advanced techniques. Specifically, multitemporal 30 m resolution Landsat-8 satellite imagery was utilized, in addition to the cloud computing capabilities of the Google Earth Engine (GEE) platform. Additionally, the study incorporated the random forest (RF) algorithm. This study aimed to generate continuous LULC maps for 2014 and 2020 for the Shrirampur area of Maharashtra, India. A novel multiple composite RF approach based on LULC classification was utilized to generate the final LULC classification maps utilizing the RF-50 and RF-100 tree models. Both RF models utilized seven input bands (B1 to B7) as the dataset for LULC classification. By incorporating these bands, the models were able to influence the spectral information captured by each band to classify the LULC categories accurately. The inclusion of multiple bands enhanced the discrimination capabilities of the classifiers, increasing the comprehensiveness of the assessment of the LULC classes. The analysis indicated that RF-100 exhibited higher training and validation/testing accuracy for 2014 and 2020 (0.99 and 0.79/0.80, respectively). The study further revealed that agricultural land, built-up land, and water bodies have changed adequately and have undergone substantial variation among the LULC classes in the study area. Overall, this research provides novel insights into the application of machine learning (ML) models for LULC mapping and emphasizes the importance of selecting the optimal tree combination for enhancing the accuracy and reliability of LULC maps based on the GEE and different RF tree models. The present investigation further enabled the interpretation of pixel-level LULC interactions while improving image classification accuracy and suggested the best models for the classification of LULC maps through the identification of changes in LULC classes.

Land Use and Land Cover (LULC) classification using remote sensing data is a challenging problem that has evolved with the update and launch of new satellites in orbit. As new satellites are launched with higher spatial and spectral resolution and shorter revisit times, LULC classification has evolved to take advantage of these improvements. However, these advancements also bring new challenges, such as the need for more sophisticated algorithms to process the increased volume and complexity of data. In recent years, deep learning techniques, such as convolutional neural networks (CNNs), have shown promising results in this area. Training deep learning models with complex architectures require cutting-edge hardware, which can be expensive and not accessible to everyone. In this study, a simple CNN based on the LeNet architecture is proposed to perform LULC classification over Sentinel-2 images. Simple CNNs such as LeNet require less computational resources compared to more-complex architectures. A total of 11 LULC classes were used for training and validating the model, which were then used for classifying the sub-basins. The analysis showed that the proposed CNN achieved an Overall Accuracy of 96.51% with a kappa coefficient of 0.962 in the validation data, outperforming traditional machine learning methods such as Random Forest, Support Vector Machine and Artificial Neural Networks, as well as state-of-the-art complex deep learning methods such as ResNet, DenseNet and EfficientNet. Moreover, despite being trained in over seven million images, it took five h to train, demonstrating that our simple CNN architecture is only effective but is also efficient.

Analyzing land use and land cover (LULC) is crucial for understanding community development and evaluating changes in the Anthropocene era. Traditional LULC mapping struggles with challenges like capturing changes under cloud cover and limited ground truth data. To enhance the accuracy and comprehensiveness of LULC change descriptions, this study applies a blend of advanced techniques. Specifically, it utilizes Landsat-8 satellite imagery with a 30- meter multitemporal resolution, alongside the cloud computing capabilities of the Google Earth Engine (GEE) platform. Additionally, a random forest (RF) algorithm is integrated into the study. This research aims to generate sustainable LULC maps for the Samin Watershed for the years 2014 and 2023. A novel dual composite RF approach based on LULC classification is used to create the final LULC classification map, leveraging the RF-50 and RF-100 tree models. Both RF models use seven input bands (B1 to B7) as datasets for LULC classification.

Understanding changes in Land Use and Land Cover (LULC) is critical to good environmental management and urban planning.This study uses Landsat 8 Collection 2 imagery to investigate LULC variations in Bantwal Taluk, Dakshina Kannada, between 2013 and 2024.Maximum Likelihood Classification (MLC), Support Vector Machine (SVM), and Random Forest (RF) were used to identify and classify six LULC classes: dense vegetation, vegetation, waterbodies, built-up areas, barren land, and floodplains.Accuracy points created in ArcMap were confirmed against Google Earth Pro ground truth data.RF had the highest accuracy, with 88.33% in 2013, 90% in 2018, and 86.67% in 2024, surpassing MLC and SVM.The findings revealed major LULC transitions, such as urban expansion by 10.43% and agricultural land reduction by 22,42% between 2013 and 2024.This study provides critical information for environmental planning, disaster management, and sustainable land use in Bantwal Taluk by doing extensive LULC mapping and change analysis.

Declared protected areas have ecologically important landscapes that must be conserved and protected. Status of protected areas could be monitored through land use and land cover (LULC) assessments. LULC offers baseline data for integrated land use planning and improvement of existing policies are therefore necessary to be conducted. This study was conducted to monitor the existing LULC of six islands within the Batanes Protected Landscapes and Seascapes (BPLS) through a machine learning (ML)-based random forest (RF) classifier using multi-sourced data such as Landsat imageries’ surface reflectance (SR), Landsat-derived land surface temperature (LST), and global ecosystem dynamic investigation (GEDI)-derived height (Ht) metrics and to determine the effects of the LST and Ht metrics to LULC classification. Four layer stacked images with different features were analyzed – including SR, SR-LST, SR-Ht, and SR-LST-Ht. The result of the LULC classification showed an accuracy based on Macro F1-score and Kappa (K) of 0.81 and 0.83, 0.83and 0.86, 0.86 and 0.89, and 0.93 and 0.94, for SR, SR-LST, SR-Ht, and SR-LST-Ht, respectively. When compared to the existing global-scale LULC, this study has higher accuracy than the GLAD and ESRI products, which have Macro F1-scores and K-values of 0.73 and 0.71, and 0.59 and 0.64, respectively. To conclude, the inclusion of LST and Ht information in addition to SR data in LULC classification can improve the accuracy by up to 12% and 11% based on Macro F1-score and K,respectively. The result of this study can serve as a reference for achieving improved and reliable LULC information that is necessary for monitoring fluctuations of the global earth’s resources and comprehensive LULC planning. In addition, the technique used in this study can serve as a reference in generating reliable LULC information that can aid in the sustainable implementation of policies, rules, and regulations intended for declared protected areas like BPLS.

Analyzing land use and land cover (LULC) using remote sensing (RS) imagery is essential for many environmental and social applications. The increase in availability of RS data has led to the development of new techniques for digital pattern classification. Very recently, deep learning (DL) models have emerged as a powerful solution to approach many machine learning (ML) problems. In particular, convolutional neural networks (CNNs) are currently the state of the art for many image classification tasks. While there exist several promising proposals on the application of CNNs to LULC classification, the validation framework proposed for the comparison of different methods could be improved with the use of a standard validation procedure for ML based on cross-validation and its subsequent statistical analysis. In this paper, we propose a general CNN, with a fixed architecture and parametrization, to achieve high accuracy on LULC classification over RS data from different sources such as radar and hyperspectral. We also present a methodology to perform a rigorous experimental comparison between our proposed DL method and other ML algorithms such as support vector machines, random forests, and k-nearest-neighbors. The analysis carried out demonstrates that the CNN outperforms the rest of techniques, achieving a high level of performance for all the datasets studied, regardless of their different characteristics.

Utilizing multitemporal indices and spectral bands of Sentinel-2 to enhance land use and land cover classification with random forest and support vector machine

Land use and land cover (LULC) change information is essential in urban planning and management. With the rapid urbanization in China, many illegal land developments have emerged in some rapidly developing regions and have caused irreversible environmental problems, posing a threat to sustainable urban development. Short-interval monitoring of LULC change therefore is necessary in these regions to control and prevent illegal land developments at an early stage.
\nConventional optical remote sensing is limited by weather conditions and has difficulties collecting timely data in tropical regions characterized by frequent cloud cover. Radar remote sensing, not affected by clouds, is therefore a potential tool for collecting timely LULC information in these regions. Polarimetric SAR (PolSAR) is more suitable than single-polarization SAR for monitoring LULC change because it can discriminate different types of scattering mechanisms. The overall objective of this study is to conduct short-interval monitoring of LULC change using RADARSAT-2 PolSAR images.
\n
\nClassification methods that achieve high accuracy for PolSAR images are essential in monitoring LULC change. In this study, a new method, based on the integration of polarimetric decomposition, PolSAR interferometry, object-oriented image analysis, and decision tree algorithms, is proposed for LULC classification using RADARSAT-2 PolSAR data. A comparison between the proposed classification method and Wishart supervised classification which is commonly used for the classification of PolSAR data showed that the proposed method can significantly improve LULC classification accuracy. Polarimetric decomposition, PolSAR interferometry, object-oriented image analysis, and decision tree algorithms have been determined to contribute to the improvement achieved by the proposed classification method.
\n
\nSelection of appropriate incidence angle is important in LULC classification using PolSAR images because incidence angle influences the intensity and patterns of radar return. Based on the proposed classification method, the present study further investigates the influence of incidence angle on LULC classification using RADARSAT-2 PolSAR images. LULC classifications using incidence angles of 31.50 and 37.56° were conducted separately. The influence of incidence angle on the classification was investigated by comparing the results of the two independent classifications. The comparison showed that large incidence angle performs much better than small incidence angle in the classification of different vegetation types, whereas small incidence angle outperforms large incidence angle in reducing the confusion between urban/built-up areas and vegetation, that between vegetable and barren land, and that among barren land, water, and lawn. Considering that the detection of urban/built-up areas and barren land is important in monitoring illegal land developments, small incidence angle is more suitable than large incidence angle in monitoring illegal land developments.
\n
\nChange detection methods that achieve high accuracy for PolSAR data are also essential in monitoring LULC change. The current study proposes a new method for LULC change detection using RADARSAT-2 PolSAR images. The proposed change detection method combines change vector analysis (CVA) and post-classification comparison (PCC) to detect LULC changes using object-oriented image analysis. The classification of PolSAR images is based on the proposed classification method. Compared with the PCC based on Wishart supervised classification, the proposed change detection method can achieve much higher accuracy for LULC change detection. Further investigation indicated that CVA, PCC, and object-oriented image analysis all contribute to the higher accuracy achieved by the proposed change detection method.
\n
\nShort-interval monitoring of LULC change was carried out using a time series of RADARSAT-2 PolSAR images. The monitoring was based on monthly LULC change detection using the proposed change detection method and appropriate incidence angle. The influence of environmental factors on short-interval monitoring of LULC change was investigated by analyzing the monthly change detection results. Paddy harvesting and planting, seasonal crop growth, and change in soil moisture and surface roughness were found to exert significant influence on the short-interval monitoring of LULC change. High accuracy can be achieved for short-interval monitoring of construction sites and bulldozed land using RADARSAT-2 PolSAR images. However, paddy harvesting and growth still cause false alarms on the monitoring of these two LULC classes.
\n
\nThe study indicated that conducting short-interval monitoring of LULC change using RADARSAT-2 PolSAR images is effective. High accuracy can be achieved for short-interval monitoring of construction sites and bulldozed land using the proposed change detection and classification methods, which can provide important information for the control and prevention of illegal land developments at an early stage.

One of the materials essential for human life that must manage properly is the land. Land use and land cover (LULC) classification can help us how to manage land. The satellite can record images that can use as the data for LULC classification. This research aims to perform LULC classification using Convolutional Neural Network (CNN) on EuroSAT remote sensing image dataset taken from the Sentinel-2 satellite. CNN has become a well-known method to deal with image feature extraction. We used several CNN for feature extraction, such as VGG19, ResNet50, and InceptionV3. Then, we recalibrated the feature of CNN using Channel Squeeze & Spatial Excitation (sSE) block. We also used Support Vector Machine (SVM) and Twin SVM (TWSVM) as the classifier. VGG19 with sSE block and TWSVM achieved the highest experimental results with 94.57% accuracy, 94.40% precision, 94.40% recall, and 94.39% F1-score.

The classification of land use and land cover (LULC) is a well-studied task within the domain of remote sensing and geographic information science. It traditionally relies on remotely sensed imagery and therefore models land cover classes with respect to their electromagnetic reflectances, aggregated in pixels. This paper introduces a methodology which enables the inclusion of geographical object semantics (from vector data) into the LULC classification procedure. As such, information on the types of geographic objects (e.g., Shop, Church, Peak, etc.) can improve LULC classification accuracy. In this paper, we demonstrate how semantics can be fused with imagery to classify LULC. Three experiments were performed to explore and highlight the impact and potential of semantics for this task. In each experiment CORINE LULC data was used as a ground truth and predicted using imagery from Sentinel-2 and semantics from LinkedGeoData using deep learning. Our results reveal that LULC can be classified from semantics only and that fusing semantics with imagery—Semantic Boosting—improved the classification with significantly higher LULC accuracies. The results show that some LULC classes are better predicted using only semantics, others with just imagery, and importantly much of the improvement was due to the ability to separate similar land use classes. A number of key considerations are discussed.

Land Use and Land Cover (LULC) classification plays a crucial role in understanding and monitoring changes to Earth's landscapes, which are essential for urban planning, environmental management, agriculture, and biodiversity conservation. As human activities such as urbanization and deforestation continue to transform land cover, accurate and timely LULC classification becomes increasingly important. In recent years, optical Earth observation (EO) data from satellite missions like Landsat and Sentinel - 2 have provided high - resolution imagery that captures the dynamic changes in land surfaces. However, traditional methods for LULC classification, such as decision trees or support vector machines (SVMs), require extensive manual feature extraction and tend to struggle with large datasets and complex landscapes. This has led to the adoption of deep learning (DL) approaches, which are more effective at handling the complexities of EO data. Deep learning models, particularly convolutional neural networks (CNNs), have gained prominence in LULC classification because of their ability to automatically learn hierarchical spatial features directly from raw image data. CNNs excel at capturing intricate spatial patterns, allowing them to outperform traditional methods in terms of accuracy and automation. Additionally, other DL architectures, such as recurrent neural networks (RNNs) and hybrid models, have further improved classification performance, particularly for multi - temporal data, which is common in EO datasets. This review examines the current state of DL techniques for LULC classification, focusing on key algorithms, such as CNNs and RNNs, frequently used EO datasets, and the challenges researchers face, such as imbalanced data, high computational costs, and model interpretability. Finally, it highlights future research directions, including unsupervised learning, improving class imbalance, and enhancing the interpretability of DL models, which will further advance the field of LULC classification.

Land Use and Land Cover (LULC) classification is vital for environmental and ecological applications. Sentinel-2 is a new generation land monitoring satellite with the advantages of novel spectral capabilities, wide coverage and fine spatial and temporal resolutions. The effects of different spatial resolution unification schemes and methods on LULC classification have been scarcely investigated for Sentinel-2. This paper bridged this gap by comparing the differences between upscaling and downscaling as well as different downscaling algorithms from the point of view of LULC classification accuracy. The studied downscaling algorithms include nearest neighbor resampling and five popular pansharpening methods, namely, Gram-Schmidt (GS), nearest neighbor diffusion (NNDiffusion), PANSHARP algorithm proposed by Y. Zhang, wavelet transformation fusion (WTF) and high-pass filter fusion (HPF). Two spatial features, textural metrics derived from Grey-Level-Co-occurrence Matrix (GLCM) and extended attribute profiles (EAPs), are investigated to make up for the shortcoming of pixel-based spectral classification. Random forest (RF) is adopted as the classifier. The experiment was conducted in Xitiaoxi watershed, China. The results demonstrated that downscaling obviously outperforms upscaling in terms of classification accuracy. For downscaling, image sharpening has no obvious advantages than spatial interpolation. Different image sharpening algorithms have distinct effects. Two multiresolution analysis (MRA)-based methods, i.e., WTF and HFP, achieve the best performance. GS achieved a similar accuracy with NNDiffusion and PANSHARP. Compared to image sharpening, the introduction of spatial features, both GLCM and EAPs can greatly improve the classification accuracy for Sentinel-2 imagery. Their effects on overall accuracy are similar but differ significantly to specific classes. In general, using the spectral bands downscaled by nearest neighbor interpolation can meet the requirements of regional LULC applications, and the GLCM and EAPs spatial features can be used to obtain more precise classification maps.

As one of the important components of Earth observation technology, land use and land cover (LULC) image classification plays an essential role. It uses remote sensing techniques to classify specific categories of ground cover as a means of analyzing and understanding the natural attributes of the Earth's surface and the state of land use. It provides important information for applications in environmental protection, urban planning, and land resource management. However, remote sensing images are usually high-dimensional data and have limited available labeled samples, so performing the LULC classification task faces great challenges. In recent years, due to the emergence of deep learning technology, remote sensing data processing methods based on deep learning have achieved remarkable results, bringing new possibilities for the research and development of LULC classification. In this paper, we present a systematic review of deep-learning-based LULC classification, mainly covering the following five aspects: (1) introduction of the main components of five typical deep learning networks, how they work, and their unique benefits; (2) summary of two baseline datasets for LULC classification (pixel-level, patch-level) and performance metrics for evaluating different models (OA, AA, F1, and MIOU); (3) review of deep learning strategies in LULC classification studies, including convolutional neural networks (CNNs), autoencoders (AEs), generative adversarial networks (GANs), and recurrent neural networks (RNNs); (4) challenges faced by LULC classification and processing schemes under limited training samples; (5) outlooks on the future development of deep-learning-based LULC classification.