Hybrid WideResNet-Dual Spatial Embedding Vision Transformer with SE blocks: a high-accuracy model for Land Use and Land Cover classification in remote sensing

Accurate Land Use and Land Cover (LU/LC) classification is essential for sustainable resource management, urban development, and environmental conservation. The integration of remote sensing data with supervised machine learning algorithms has significantly enhanced classification accuracy and efficiency. This study evaluates the performance of five widely used supervised learning algorithms namely 1) Classification and Regression Tree (CART), 2) Gradient Boost Tree (GB), 3) K-Nearest Neighbours (KNN), 4) Support Vector Machine (SVM) and 5) Random Forest (RF) for LU/LC mapping in study area of East Godavari District, Andhra Pradesh, India over a time period of 2 years between 2023 and 2025. High-resolution Landsat-8 imagery is processed and classified using above algorithms, with model performance assessed based on overall accuracy, Kappa coefficient, precision and F1-score. The findings indicated that Gradient Tree Boost demonstrated superior performance compared to the other classifiers, attaining the highest accuracy of 98.26% along with a Kappa coefficient of 0.9761. Random Forest closely followed, achieving an accuracy of 97.39% and a Kappa value of 0.9642. Additionally, both SVM and KNN exhibited strong classification capabilities, with respective accuracies of 96.52% and Kappa values of 0.9522, highlighting their effectiveness in land cover classification applications. The study also examines the computational efficiency and reliability of each classifier, offering insights into their suitability for LU/LC analysis in diverse landscapes. The findings contribute to the optimization of machine learning techniques for remote sensing applications, aiding in data-driven decision-making for land management. Future research can explore deep learning-based classification models and multi-temporal analysis to further enhance LU/LC mapping accuracy.

Efficiently implementing remote sensing image classification with high spatial resolution imagery can provide significant value in land use and land cover (LULC) classification. The new advances in remote sensing and deep learning technologies have facilitated the extraction of spatiotemporal information for LULC classification. Moreover, diverse disciplines of science, including remote sensing, have utilised tremendous improvements in image classification involving convolutional neural networks (CNNs) with transfer learning. In this study, instead of training CNNs from scratch, the transfer learning was applied to fine-tune pre-trained networks Visual Geometry Group (VGG16) and Wide Residual Networks (WRNs), by replacing the final layers with additional layers, for LULC classification using the red–green–blue version of the EuroSAT dataset. Moreover, the performance and computational time are compared and optimised with techniques such as early stopping, gradient clipping, adaptive learning rates, and data augmentation. The proposed approaches have addressed the limited-data problem, and very good accuracies were achieved. The results show that the proposed method based on WRNs outperformed the previous best results in terms of computational efficiency and accuracy, by achieving 99.17%.

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.

In the last decades, Adama city has experienced drastic changes in its shape, not just in its vast geographical expansion, but also by internal transformations. Subsequently, understanding and evaluating the spatiotemporal variability of urban land use and land cover (LULC) shifts, and it is important to bring forth the right strategies and processes to track population development in decision-making. The goal of this analysis was therefore to examine LULC changes that have taken place over 37 years, forecast the long-term urban development in Adama City using geospatial techniques. To attain this, satellite data of Landsat 1973, 2000 and 2010 was downloaded from USGS Earth Explorer and processed using Arc GIS 10.5, Erdas 9.2, and Idrisi 32. A supervised classification technique has been used to prepare the base maps with six land cover classes that are accustomed to generate LULC maps. The maps are cross-tabulated to measure LULC changes, to look at land-use transfers between the land cover classes, to spot increases and declines in built-up areas in comparison to other land cover classes, and to determine the spatial changes in built-up areas. Finally, Markov Chain and CA-Markov techniques were used to model the LULC changes in the Adama district and to forecast possible changes in urban land use. The model was verified by the Kappa statistics and also by the application of other validation techniques. The growth of built-up areas in the last 37 years has risen from 2% in 1973, 10% in 2000 and 23% in 2010 and estimated about 60% over the next 30 years (2040).

This paper presents a land use and land cover (LULC) classification approach that accounts landscape heterogeneity. We addressed this challenge by subdividing the study area into more homogeneous segments using several biophysical and socio-economic factors as well as spectral information. This was followed by unsupervised clustering within each homogeneous segment and supervised class assignment. Two classification schemes differing in their level of detail were successfully applied to four landscape types of distinct LULC composition. The resulting LULC map fulfills two major requirements: (1) differentiation and identification of several LULC classes that are of interest at the local, regional, and national scales, and (2) high accuracy of classification. The approach overcomes commonly encountered difficulties of classifying second-level classes in large and heterogeneous landscapes. The output of the study responds to the need for comprehensive LULC data to support ecosystem assessment, policy formulation, and decision-making towards sustainable land resources management.

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.

Brazil, with more than 8 million km², presents six different biomes, ranging from natural grasslands (Pampa biome) to tropical rainfall forests (Amazo&#x0302;nia biome), with different land-use types (mostly pasturelands and croplands) and pressures (mainly in the Cerrado biome). The objective of this article is to present a new method to discriminate the most representative land use and land cover (LULC) classes of Brazil, based on the PROBA-V images. The images were converted into vegetation, soil, and shade fraction images by applying the linear spectral mixing model. Then, the pixel-based, highest proportion, annual mosaics of the fraction images, and their corresponding standard deviation images were derived and classified using the random forest algorithm. The following LULC classes were considered: forestlands, shrublands, grasslands, croplands, pasturelands, water bodies, and others. An agreement analysis was conducted with two available LULC maps derived from the Landsat satellite, the MapBiomas, and the Finer Resolution Observation and Monitoring-Global Land Cover (FROM-GLC) projects. Forestlands (412 million ha) and pasturelands (242 million ha) were the two most representative LULC classes; and croplands accounted for 30 million ha. The results presented an overall agreement of 69% and 58% with the MapBiomas and FROM-GLC projects, respectively. The proposed method is a good alternative to support operational projects of LULC map production that are important for planning biodiversity conservation or environmentally sustainable land occupation.

The change detection and land use and land cover (LULC) maps are more important powerful forces behind numerous ecological systems and fallow land. The current research focuses on demarcating the spatiotemporal LULC changes, NDVI and change detections maps. These effects directly affect the ecosystem, land resources, cropping pattern and agriculture. LULC assessment and surveillance are essential for long-term planning and sustainable use of natural resources. However, we have developed the soft computing machine learning algorithm for mapping land use and land cover based on the Google earth engine (GEE) platform and change detection mapping done by SAGA GIS software. It is significantly used for ecological safety and planning under various climate variations. To accurately describe the land use and land cover classes with changes are identified in the area. This area exclusively uses the multitemporal Landsat-5 (30 m) and Sentinel-2 (10 m) imageries in LULC mapping. The GEE is a cloud-computing platform with the prevailing classification ability of random forest (RF) models to make five-year interval LULC maps for 2010, 2015 and 2020. To unique multiple RF models established as a classifier in the algorithm created by JavaScript and GEE. SAGA GIS has provided the best platform for detecting changes in land use and land cover classes. NDVI maps are created based on the cloud-based platform. These maps value ranges between −0.68 to −0.15, 0.76 to −0.29 and 0.66 to −0.11 in 2010, 2015 and 2020. Experimental outcomes indicate five classes such as water bodies, built up, barren, cropland and fallow land during 2010, 2015 and 2020. The overall accuracy of User and Producer for 2010, 2015 and 2019 years in between 86.23%, 88.34%, 85.53% and 92.51%, 94.34% and 91.54%, respectively. We have observed that (2010, 2015 − 2020) agriculture and built-up land increased by 1040.76 ha, 1246.32 ha, 1500.93 ha and 34.96 ha, 37.08 ha, 42.58 ha, respectively. Other side degraded land, fallow land, waterbodies areas (953.19 ha, 679.23 ha, 937.24 ha and 1385.73 ha, 1513.53 ha, 991.08 ha and 32.85 ha, 21.33 ha, 25.66 ha) are increased during the year of 2010, 2015 and 2020, respectively. While results have been done by GEE cloud platform and remote sensing data, this developed algorithm easily classified the land use maps from Landsat-5 and Sentinel-2 TM imagery in the machine learning approach. The determined 30-m and 10-m three-year LULC maps are made-up to deliver vital data on the changes, monitoring and understanding of which types of LULC classes and changes have occupied a place in the Rahuri area.

Geographical information systems and Remote Sensing has become efficient tool for land use and land cover classification. This study was conducted in Shirur Kasar Tehsil, in the Beed district of Maharashtra, India. Multispectral images of the Landsat 8 satellite were downloaded from USGS, and a resolution of 30 m was used for this study. The processing of images was done in Arc GIS, which provides various tools and functions for image classification. The maximum likelihood supervised classification technique was used for land use land cover classification. Land use and land cover (LULC) classification was conducted for the years 2014, 2019, and 2024, spanning a decade. During the period from 2014 to 2019, agricultural land and vegetation declined by 9% and 12%, respectively, while barren land, settlement, and water bodies increased by 1%, 31%, and 81%, respectively. From 2019 to 2024, barren land and water bodies decreased by 13% and 58%, respectively, whereas agricultural land, settlement, and vegetation increased by 9%, 5%, and 19%, respectively. Significant changes were observed over the entire study period (2014–2024), particularly in settlement areas, whichexhibited a continuous increase. Conversely, barren land demonstrated a notable decrease. These findings highlight the dynamic shifts in LULC classes over the decade. The study reveals substantial land use change in the study area, which was in settlement. It was increased by 38% due to increased population, migration from rural to urban areas, and demand for settlements. Accuracy assessment was done using the Kappa Coefficient method; according to the Kappa Coefficient, overall accuracy for the years 2014, 2019, and 2024 was found to be 90%, 90%, and 95%, respectively, with Kappa Coefficients 0.9, 0.9, and 0.95. Based on these results, theaccuracy and kappa coefficient values have good criteria and can be used for further analysis.

Land use and land cover (LULC) change analyses are critical for the sustainable planning and management of natural resources in the face of rapid population growth across the globe. It is believed that LULC changes cause severe environmental challenges such as climate change, biodiversity loss, pollution, alteration to the physical and chemical properties of the soil as well as the destruction of the ozone layer. The main objective of the study was to assess the LULC changes at Hova Farm from 1992 to 2011 using geospatial technologies. Three Landsat images for 1992, 2001, and EMT+ for 2011 were used. The Landsat images had a resolution of 30m by 30m. Five LULC classes of woodland, wooded grassland, cultivated land, bushland and water body were created using the supervised classification maximum likelihood in ENVI 5.0. Field observation and measurements were also used to validate remotely sensed data. The accuracy assessment for the classified maps for 1992, 2001 and 2011 was 88.74%, 86, 67% and 87% respectively. The results indicated that the greatest LULC changes occurred between 1992 and 2001 and was attributed to the fast-track land reform programme and illegal mining activities on the farm. The study recommends the creation of a LULC database for the periodic monitoring and sustainable management of natural resources at both local and national levels in Zimbabwean.

اهداف: پایش تغییرات کاربری‌ها و درک پویایی آن در یک حوضۀ آبخیز، از جایگاه خاصی در مدیریت پایدار آن حوضه برخوردار است. هدف تحقیق حاضر، استفاده از سنجش از دور و GIS جهت تهیۀ نقشۀ تغییرات و شناسایی انتقالات کاربری اراضی و پوشش زمین با به‌کارگیری ماتریس انتقال و تصاویر ماهوارۀ لندست در حوضۀ آبخیز دریاچۀ ارومیه می‌باشد. روش: جهت انجام تحقیق، از تصاویر ماهوارۀ لندست در دورۀ زمانی 2015 ـ 1988 استفاده گردید. بدین‌منظور پس از انجام پیش‌پردازش‌های موردنظر، جهت انجام طبقه‌بندی از روش‌های ماشین‌بردار پشتیبان و روشیءگرا استفاده و سپس اعتبارسنجی گردیدند. همچنین جهت برآورد میزان انتقالات و دیگر ویژگی‌های حوضۀ آبخیز دریاچۀ ارومیه، ابتدا ماتریس انتقالی استخراج شده و سپس طبقه‌بندی شئ‌گرا بین دوره‌های زمانی 2015ـ1988 ارائه شد. سپس با استفاده از فرمول‌های موردنظر، میزان پایداری، افزایش، کاهش، تغییرات کل، تغییرات خالص و مبادلۀ همزمان کاربری‌های اراضی و پوشش زمین مشخص گردید. یافته‌ها/ نتایج: پس از ارزیابی صحت، صحت کلی برای نقشه‌های حاصل از ماشین بردار پشتیبان و روش شئ‌گرا به‌ترتیب برابر با 94 و 92 درصد و مقدار کاپای آنها به‌ترتیب 92 و 89 برآورد شد که نشان‌دهندۀ برتری روش شئ‌گرا در مقایسه با روش ماشین بردار پشتیبان است. در کل، هر دو روش طبقه‌بندی توانستند صحت قابل‌قبولی برای نقشه‌های کاربری اراضی و پوشش زمین ارائه دهند. نتایج حاصل از انتقالات نشان داد به‌طور میانگین، 59 درصد از چهرۀ زمین در حوضۀ آبخیز دریاچۀ ارومیه در فاصلۀ زمانی 2015ـ 1988 پایداری پوشش داشته است، که بیشترین میزان این تداوم براساس مقدار این کاربری در فاصلۀ زمانی 2015ـ1988 مربوطه به مناطق مسکونی می-باشد. حدود 14 درصد از سطح حوزۀ آبخیز دریاچۀ ارومیه به‌صورت تبادل همزمان بوده است. همچنین سطوح آبی حوضۀ آبخیز دریاچۀ ارومیه در دورۀ زمانی فوق، بیشترین ازدست‌دادگی و کمترین تبادل همزمان را تجربه کرده است. نتیجه‌گیری: حوضۀ آبخیز دریاچۀ ارومیه در این فاصلۀ زمانی (2015ـ1988) تغییرات و انتقالات شدیدی را تجربه کرده است، تاجایی‌که تنها 59 درصد از چهرۀ زمین، ثابت مانده و قسمت‌های دیگر، انواعی از انتقال‌ها را تجربه کرده‌اند. همچنین سطوح آبی و سپس مراتع، بیشترین آسیب-پذیری را تجربه کرده‌اند که نشان از افزایش اراضی فاقد پوشش و اراضی زراعی (کشاورزی) می-باشد. این تجزیه‌وتحلیل ما را به سنجش و تجسم میزان انتقالات عمدۀ LULC درجهت برنامه‌ریزی آیندۀ حوضۀ آبخیز دریاچۀ ارومیه توصیه می‌کند.

Agricultural land use and land cover (LULC) classification using synthetic aperture radar (SAR) data is a fundamental application in remote sensing and precision agriculture. Leveraging the abilities of SAR, which can enter over cloud cover and deliver detailed data about surface features, allows a robust analysis of agricultural landscapes. By harnessing the control of SAR data and innovative deep learning (DL) methods, this technique provides a complete solution for effectual and automatic agricultural land classification, paving the method for informed decision-making in present farming systems. This study introduces a new gradient based optimizer with deep learning based agricultural land use and land cover classification (GBODL-ALULC) technique on SAR data. The GBODL-ALULC technique aims to detect and classify distinct types of land cover that exist in the SAR data. In the GBODL-ALULC technique, the feature extraction process takes place by a residual network with a convolutional block attention mechanism (ResNet-CBAM) model. At the same time, the GBO system has been executed for the best hyperparameter choice of the ResNet-CBAM model which helps to improve the overall LULC classification results. Finally, a regularized extreme learning machine (RELM) algorithm has been for the detection and classification of land covers. The performance study of the GBODL-ALULC method is carried out on the SAR dataset. The simulation outcome depicted that the GBODL-ALULC methodology reaches effectual LULC classification outcomes over compared methods.

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.

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.

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.