Improvement of Moderate Resolution Land Use and Land Cover Classification by Introducing Adjacent Region Features

A multifeature soft-probability cascading scheme to solve the problem of land use and land cover (LULC) classification using high-spatial-resolution images to map rural residential areas in China is proposed. The proposed method is used to build midlevel LULC features. Local features are frequently considered as low-level feature descriptors in a midlevel feature learning method. However, spectral and textural features, which are very effective low-level features, are neglected. The acquisition of the dictionary of sparse coding is unsupervised, and this phenomenon reduces the discriminative power of the midlevel feature. Thus, we propose to learn supervised features based on sparse coding, a support vector machine (SVM) classifier, and a conditional random field (CRF) model to utilize the different effective low-level features and improve the discriminability of midlevel feature descriptors. First, three kinds of typical low-level features, namely, dense scale-invariant feature transform, gray-level co-occurrence matrix, and spectral features, are extracted separately. Second, combined with sparse coding and the SVM classifier, the probabilities of the different LULC classes are inferred to build supervised feature descriptors. Finally, the CRF model, which consists of two parts: unary potential and pairwise potential, is employed to construct an LULC classification map. Experimental results show that the proposed classification scheme can achieve impressive performance when the total accuracy reached about 87%.

Land use and land cover (LULC) are diverse and complex in urban areas. Remotely sensed images are commonly used for land cover classification but hardly identifies urban land use and functional areas because of the semantic gap (i.e., different definitions of similar or identical buildings). Social media data, “marks” left by people using mobile phones, have great potential to overcome this semantic gap. Multisource remote sensing data are also expected to be useful in distinguishing different LULC types. This study examined the capability of combined multisource remote sensing images and social media data in urban LULC classification. Multisource remote sensing images included a Chinese ZiYuan-3 (ZY-3) high-resolution image, a Landsat 8 Operational Land Imager (OLI) multispectral image, and a Sentinel-1A synthetic aperture radar (SAR) image. Social media data consisted of the hourly spatial distribution of WeChat users, which is a ubiquitous messaging and payment platform in China. LULC was classified into 10 types, namely, vegetation, bare land, road, water, urban village, greenhouses, residential, commercial, industrial, and educational buildings. A method that integrates object-based image analysis, decision trees, and random forests was used for LULC classification. The overall accuracy and kappa value attained by the combination of multisource remote sensing images and WeChat data were 87.55% and 0.84, respectively. They further improved to 91.55% and 0.89, respectively, by integrating the textural and spatial features extracted from the ZY-3 image. The ZY-3 high-resolution image was essential for urban LULC classification because it is necessary for the accurate delineation of land parcels. The addition of Landsat 8 OLI, Sentinel-1A SAR, or WeChat data also made an irreplaceable contribution to the classification of different LULC types. The Landsat 8 OLI image helped distinguish between the urban village, residential buildings, commercial buildings, and roads, while the Sentinel-1A SAR data reduced the confusion between commercial buildings, greenhouses, and water. Rendering the spatial and temporal dynamics of population density, the WeChat data improved the classification accuracies of an urban village, greenhouses, and commercial buildings.

This work aims to develop a new method to map Land Use and Land Cover (LULC) classes in the São Paulo State, Brazil, using Landsat-8 Operational Land Imager (OLI) data. The novelty of the proposed method consists of selecting the images based on the spectral and temporal characteristics of the LULC classes. First, we defined the six classes to be mapped in the year 2020 as forest, forest plantation, water bodies, urban areas, agriculture, and pasture. Second, we visually analyzed their variability spectral characteristics over the year. Then, we pre-processed these images to highlight each LULC class. For the classification, the Random Forest algorithm available on the Google Earth Engine (GEE) platform was utilized individually for each LULC class. Afterward, we integrated the classified maps to create the final LULC map. The results revealed that forest areas are primarily concentrated in the eastern region of São Paulo, predominantly on steeper slopes, accounting for 19% of the study area. On the other hand, pasture and agriculture dominated 73% of all São Paulo’s landscape, reaching 39% and 34%, respectively. The overall accuracy of the classification achieved 89.10%, while producer and user accuracies were greater than 84.20% and 76.62%, respectively. To validate the results, we compared our findings with the MapBiomas Project classification, obtaining an overall accuracy of 85.47%. Therefore, our method demonstrates its potential to minimize classification errors and offers the advantage of facilitating post-classification editing for individual mapped classes.

ContextChanges in landscape patterns, which refer to the composition and spatial configuration of land use and land cover (LULC) classes in a landscape, can have negative impacts on biodiversity and environmental processes such as carbon cycles. Such impacts are both dependent on the spatial extent of changes and which LULC classes are affected, but previous global-scale landscape pattern assessments have focused on single LULC classes or landscape-level measurements only. A comprehensive, multiscale analysis across multiple LULC types is therefore key for understanding the full impact of landscape pattern change on the environment.ObjectivesWe assessed global-scale change in landscape patterns for six LULC classes from the HILDA+ dataset (urban, cropland, pasture/rangeland, forest, unmanaged grass/shrubland, and sparse/no vegetation) between 1992 and 2020.MethodsSix class-level landscape metrics with predictable scaling behaviour across landscape extents were calculated at global scale for each LULC class and year. Landscape metrics were quantified for five landscape extents (100, 400, 1600, 6400 and 25,600 km2). Trends in landscape metrics were evaluated and linked to changes in LULC composition (area) and configuration over time.ResultsUnmanaged grass/shrubland LULC expanded in area and showed increased number of patches, edge length, and complexity in shapes, while pasture/rangeland and forest LULC tended to decline in area, number of patches, and edge length. Even though there was high spatial heterogeneity in landscape pattern change for all LULC classes, neighbouring 100 km2 landscapes often showed the same directional change in area and fragmentation.ConclusionsGlobal landscape pattern change was highly variable for all LULC classes between 1992 and 2020, suggesting that drivers of LULC change act on local to regional scales. We expect that the multiscale global dataset of landscape metrics generated here will have future applications in understanding the drivers of landscape pattern change and its environmental impacts.Supplementary InformationThe online version contains supplementary material available at 10.1007/s10980-025-02210-0.

One of the most significant applications of remote sensing data is to prepare land use and land cover (LULC) maps. LULC maps are always affected by seasonality and a single LULC map of a particular month is prepared to represent a year in most of the research, especially in change detection research. This does not represent the real view of the landscape because the seasonal variation of different LULC types is always overlooked. Considering the issue, the current method aims to solve the problem by incorporating seasonal LULC using the raster overlay method to remove the seasonality effect on LULC classification. To apply this method, a minimum of two seasonal LULC maps is required for a single study year. The map needs to overlay and then reclassify according to the stable and rotational LULC pattern of the study area. This method will replicate the actual LULC pattern of a study area from satellite images. Summary of the method is as follows:•LULC of each season was classified using image classification technique.•LULC of each seasons are coded and combined using overlay technique.•Combined map is reclassified to prepare the actual LULC map.

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 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.

Geospatial vector data with semantic annotations are a promising but complex data source for spatial prediction tasks such as land use and land cover (LULC) classification. These data describe the geometries and the types (i.e., semantics) of geo-objects, such as a Shop or an Amenity. Unlike raster data, which are commonly used for such prediction tasks, geospatial vector data are irregular and heterogenous, making it challenging for deep neural networks to learn based on them. This work tackles this problem by introducing novel encodings which quantify the geospatial vector data allowing deep neural networks to learn based on them, and to spatially predict. These encodings were evaluated in this work based on a specific use case, namely LULC classification. We therefore classified LULC based on the different encodings as input and an attention-based deep neural network (called Perceiver). Based on the accuracy assessments, the potential of these encodings is compared. Furthermore, the influence of the object semantics on the classification performance is analyzed. This is performed by pruning the ontology, describing the semantics and repeating the LULC classification. The results of this work suggest that the encoding of the geography and the semantic granularity of geospatial vector data influences the classification performance overall and on a LULC class level. Nevertheless, the proposed encodings are not restricted to LULC classification but can be applied to other spatial prediction tasks too. In general, this work highlights that geospatial vector data with semantic annotations is a rich data source unlocking new potential for spatial predictions. However, we also show that this potential depends on how much is known about the semantics, and how the geography is presented to the deep neural network.

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.

In this paper, we demonstrated the possibility of performing land use and land cover (LULC) classification over a wide area by an L-band polarimetric synthetic aperture radar (SAR). In previous studies, there has been scant LULC classification by polarimetric SAR data over a wide area. We used satellite-based SAR data with an area of ca. 320 000 km <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> obtained by the Phased Array type L-band SAR (PALSAR)-2 phase array. We performed the LULC classification using full polarimetry (FP), compact polarimetry (CP), and dual polarimetry (DP) data by PALSAR-2 and compared their classification accuracy. Our results show FP to be the most accurate. The CP and the DP have the advantages of large-scale coverage and compact data volume but is slightly less accurate than the FP. To further improve accuracy of the classification process, texture analysis, observation date information, and feature elimination are effective. We determined the classification accuracy for seven classes to be 73.4% (the kappa coefficient is 0.668). We found the rice paddy, forest, grass, and urban areas to be sufficiently accurate (84.5%) for practical application. We compared the obtained classification map with an existing LULC map to grasp the LULC changes induced by a recent disaster and successfully detected the damage areas of the disaster. These results indicate the possibility of large-scale LULC monitoring by an L-band polarimetric SAR, which can acquire images rapidly without being affected by weather.

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.

Land use and land cover (LULC) data are important to monitor and assess environmental change. LULC classification using satellite images is a method widely used on a global and local scale. Especially, urban areas that have various LULC types are important components of the urban landscape and ecosystem. This study aims to classify urban LULC using WorldView-3 (WV-3) very high-spatial resolution satellite imagery and the object-based image analysis method. A decision rules set was applied to classify the WV-3 images in Kathu subdistrict, Phuket province, Thailand. The main steps were as follows: (1) the image was ortho-rectified with ground control points and using the digital elevation model, (2) multiscale image segmentation was applied to divide the image pixel level into image object level, (3) development of the decision ruleset for LULC classification using spectral bands, spectral indices, spatial and contextual information, and (4) accuracy assessment was computed using testing data, which sampled by statistical random sampling. The results show that seven LULC classes (water, vegetation, open space, road, residential, building, and bare soil) were successfully classified with overall classification accuracy of 94.14% and a kappa coefficient of 92.91%.

The main objective of this research was to evaluate land use and land cover (LULC) change in Battambang province of Cambodia over the last two decades. The LULC maps for 1998, 2003, 2008, 2013 and 2018 were produced from Landsat satellite imagery using the supervised classification technique with the maximum likelihood algorithm. Each map consisted of seven LULC classes: built-up area, water feature, grassland, shrubland, agricultural land, barren land and forest cover. The overall accuracies of the LULC maps were 93%, 82%, 94%, 93% and 83% for 1998, 2003, 2008, 2013 and 2018, respectively. The LULC change results showed a significant increase in agricultural land, and a large decrease in forest cover. Most of the changes in both LULC types occurred during 2003–2008. Overall, agricultural land, shrubland, water features, built-up areas and barren land increased by 287,600 hectares, 58,600 hectares, 8300 hectares, 4600 hectares and 1300 hectares, respectively, while forest cover and grassland decreased by 284,500 hectares and 76,000 hectares respectively. The rate of LULC changes in the upland areas were higher than those in the lowland areas of the province. The main drivers of LULC change identified over the period of study were policy, legal framework and projects to improve economy, population growth, infrastructure development, economic growth, rising land prices, and climate and environmental change. Landmine clearance projects and land concessions resulted in a transition from forest cover and shrubland to agricultural land. Population and economic growth not only resulted in an increase of built-up area, but also led to increasing demand for agricultural land and rising land prices, which triggered the changes of other LULC types. This research provides a long-term and detailed analysis of LULC change together with its drivers, which is useful for decision-makers to make and implement better policies for sustainable land management.

Land Use and Land Cover (LULC) are key indicators of global environmental change. As a result, the extensive effort was dedicated to creating larger-scale products of LULC from Remote Sensing (RS) data, allowing the technical group to utilize these products for a wide array of downstream applications. This phenomenon causes widespread anxiety about natural resources. Therefore, observing LULC changes was significant for natural resource management and evaluating the effects of environmental change. Machine Learning (ML) has recently gained significance for fast and accurate LULC mapping using RS data, driven by the growing requirement for ecological, environmental, and resource management. It is crucial to compute the performance of diverse ML models for reliable LULC mapping. This study proposes a novel Remote Sensing-Based Land Use and Land Cover Classification Using Deep Learning with Tuna Swarm Optimisation (RSLULCC-DLTSO) methodology. The RSLULCC-DLTSO methodology aims to advance intelligent and automated LULC classification systems that assist in sustainable land management and environmental decision-making. In the pre-processing stage, the RSLULCC-DLTSO technique utilizes a Wiener Filtering (WF) model to eliminate noise and enhance the quality of satellite images. Furthermore, the DenseNet-121-based feature extraction captures hierarchical spatial patterns and textures from RSI. A Variational Autoencoder (VAE) model is also used for LULC classification. Finally, the Tuna Swarm Optimisation (TSO) model optimally adjusts the hyperparameter values of the VAE technique, resulting in improved classification performance. A wide range of simulation analyses of the RSLULCC-DLTSO approach is implemented under the EuroSat dataset. The comparative study of the RSLULCC-DLTSO approach illustrated a superior accuracy value of 98.57% compared to existing models.

Land use and land cover classification using phenological variability from MODIS vegetation in the Upper Pangani River Basin, Eastern Africa