Transfer-Ensemble Learning: A Novel Approach for Mapping Urban Land Use/Cover of the Indian Metropolitans

Accurate identification of urban land use and land cover (LULC) is important for successful urban planning and management. Although previous studies have explored the capabilities of machine learning (ML) algorithms for mapping urban LULC, identifying the best algorithm for extracting specific LULC classes in different time periods and locations remains a challenge. In this research, three machine learning algorithms were employed on a cloud-based system to categorize urban land use of Kabul city through satellite images from Landsat-8 and Sentinel-2 taken in 2023. The most advanced method of generating accurate and informative LULC maps from various satellite data and presenting accurate outcomes is the machine learning algorithm in Google Earth Engine (GEE). The objective of the research was to assess the precision and efficiency of various machine learning techniques, such as random forest (RF), support vector machine (SVM), and classification and regression tree (CART), in producing dependable LULC maps for urban regions by analyzing optical satellite images of sentinel and Landsat taken in 2023. The urban area was divided into five classes: built-up area, vegetation, bare-land, soil, and water bodies. The accuracy and validation of all three algorithms were evaluated. The RF classifier showed the highest overall accuracy of 93.99% and 94.42% for Landsat-8 and Sentinel-2, respectively, while SVM and CART had lower overall accuracies of 87.02%, 81.12%, and 91.52%, 87.77%, with Landsat-8 and Sentinel-2, respectively. The results of the present study revealed that in this classification and comparison, RF performed better than SVM and CART for classifying urban territory for Landsat-8 and Sentinel-2 using GEE. Furthermore, the study highlights the importance of comparing the performance of different algorithms before selecting one and suggests that using multiple methods simultaneously can lead to the most precise map.

A precise and up-to-date Land Use and Land Cover (LULC) valuation serves as the fundamental basis for efficient land management. Google Earth Engine (GEE), with its numerous machine learning algorithms, is now the most advanced open-source global platform for rapid and accurate LULC classification. Thus, this study explores the dynamics of the LULC changes between 1993 and 2023 using Landsat imagery and the machine learning algorithms in the Google Earth Engine (GEE) platform. Focus group discussion and key informant interviews were also used to get further data regarding LULC dynamics. Support Vector Machine (SVM), Random Forest (RF), and Classification and Regression Trees (CART) were demonstrated for LULC classification. Six LULC types (agricultural land, grazingland, shrubland, built-up area, forest and bareland) were identified and mapped for 1993, 2003, 2013, and 2023. The overall accuracy and kappa coefficient demonstrated that the RF using images comprising auxiliary variables (spectral indices and topographic data) performed better than SVM and CART. Despite being the most common type of LULC, agricultural land shows a trend of shrinking during the study period. The built-up area and bareland exhibits a trend of progressive expansion. The amount of forest and shrubland has decreased over the last 20 years, whereas grazinglands have exhibited expanding trends. Population growth, agricultural land expansion, fuelwood collection, charcoal production, built-up areas expansion, illegal settlement and intervention are among causes of LULC shifts. This study provides reliable information about the patterns of LULC in the Robit watershed, which can be used to develop frameworks for watershed management and sustainability.

Accurate spatial information on Land use and land cover (LULC) plays a crucial role in city planning. A widely used method of obtaining accurate LULC maps is a classification of the categories, which is one of the challenging problems. Attempts have been made considering spectral (Sp), statistical (St), and index-based (Ind) features in developing LULC maps for city planning. However, no work has been reported to automate LULC performance modeling for their robustness with machine learning (ML) algorithms. In this paper, we design seven schemes and automate the LULC performance modeling with six ML algorithms-Random Forest, Support Vector Machine with Linear kernel, Support Vector Machine with Radial basis function kernel, Artificial Neural Network, Naïve Bayes, and Generalised Linear Model for the city of Melbourne, Australia on Sentinel-2A images. Experimental results show that the Random Forest outperforms remaining ML algorithms in the classification accuracy (0.99) on all schemes. The robustness and statistical analysis of the ML algorithms (for example, Random Forest imparts over 0.99 F1-score for all five categories and p value le 0.05 from Wilcoxon ranked test over accuracy measures) against varying training splits demonstrate the effectiveness of the proposed schemes. Thus, providing a robust measure of LULC maps in city planning.

Monitoring the dynamics of land use and land cover (LULC) is imperative in the changing climate and evolving urbanization patterns worldwide. The shifts in land use have a significant impact on the hydrological response of watersheds across the globe. Several studies have applied machine learning (ML) algorithms using historical LULC maps along with elevation data and slope for predicting future LULC projections. However, the influence of other driving factors such as socio-economic and climatological factors has not been thoroughly explored. In the present study, a sensitivity analysis approach was adopted to understand the effect of both physical (elevation, slope, aspect, etc.) and socio-economic factors such as population density, distance to built-up, and distance to road and rail, as well as climatic factors (mean precipitation) on the accuracy of LULC prediction in the Brahmani and Baitarni (BB) basin of Eastern India. Additionally, in the absence of the recent LULC maps of the basin, three ML algorithms, i.e., random forest (RF), classified and regression trees (CART), and support vector machine (SVM) were utilized for LULC classification for the years 2007, 2014, and 2021 on Google earth engine (GEE) cloud computing platform. Among the three algorithms, RF performed best for classifying built-up areas along with all the other classes as compared to CART and SVM. The prediction results revealed that the proximity to built-up and population growth dominates in modeling LULC over physical factors such as elevation and slope. The analysis of historical data revealed an increase of 351% in built-up areas over the past years (2007-2021), with a corresponding decline in forest and water areas by 12% and 36% respectively. While the future predictions highlighted an increase in built-up class ranging from 11 to 38% during the years 2028-2070, the forested areas are anticipated to decline by 4 to 16%. The overall findings of the present study suggested that the BB basin, despite being primarily agricultural with a significant forest cover, is undergoing rapid expansion of built-up areas through the encroachment of agricultural and forested lands, which could have far-reaching implications for the region's ecosystem services and sustainability.

Land Use and Land Cover (LULC) classification is essential for monitoring environmental changes, managing resources, and planning sustainable development. However, accurate classification remains challenging because of the diversity of landscapes and the computational demands of processing large datasets. Among various machine learning (ML) algorithms, such as Convolutional Neural Networks (CNN), Support Vector Machines (SVM), Random Forest (RF), and Classification and Regression Trees (CART), RF and CART were chosen for this study because of their robustness, simplicity, and efficiency in handling complex LULC classification tasks. This study focuses on the Brahmani-Baitarani River Basin, a region known for its environmental significance and susceptibility to land-use changes. Using remote sensing data from Landsat 8, Landsat 9, and Sentinel-2 satellites, a comparative analysis of RF and CART was conducted to evaluate their LULC mapping performance. The datasets were processed and analyzed on the Google Earth Engine (GEE) platform using multi-temporal image data and advanced filtering techniques. The results revealed that RF consistently delivered higher classification accuracy than CART, making it a reliable choice for LULC studies in dynamic and heterogeneous landscapes. By integrating high-resolution satellite imagery with ML algorithms, this study provided detailed insights into the spatial distribution of land use across the Brahmani-Baitarani Basin. These findings have practical applications in urban planning, natural resource management, and environmental conservation, and offer valuable information for decision-makers and researchers working to address global environmental challenges.

Comparison of accuracy and reliability of random forest, support vector machine, artificial neural network and maximum likelihood method in land use/cover classification of urban setting

The growing human population accelerates alterations in land use and land cover (LULC) over time, putting tremendous strain on natural resources. Monitoring and assessing LULC change over large areas is critical in a variety of fields, including natural resource management and climate change research. LULC change has emerged as a critical concern for policymakers and environmentalists. As the need for the reliable estimation of LULC maps from remote sensing data grows, it is critical to comprehend how different machine learning classifiers perform. The primary goal of the present study was to classify LULC on the Google Earth Engine platform using three different machine learning algorithms—namely, support vector machine (SVM), random forest (RF), and classification and regression trees (CART)—and to compare their performance using accuracy assessments. The LULC of the study area was classified via supervised classification. For improved classification accuracy, NDVI (normalized difference vegetation index) and NDWI (normalized difference water index) indices were also derived and included. For the years 2016, 2018, and 2020, multitemporal Sentinel-2 and Landsat-8 data with spatial resolutions of 10 m and 30 m were used for the LULC classification. ‘Water bodies’, ‘forest’, ‘barren land’, ‘vegetation’, and ‘built-up’ were the major land use classes. The average overall accuracy of SVM, RF, and CART classifiers for Landsat-8 images was 90.88%, 94.85%, and 82.88%, respectively, and 93.8%, 95.8%, and 86.4% for Sentinel-2 images. These results indicate that RF classifiers outperform both SVM and CART classifiers in terms of accuracy.

Land use and land cover (LULC) classification maps help understand the state and trends of agricultural production and provide insights for applications in environmental monitoring. One of the major downfalls of the LULC technique is inherently linked to its need for ground truth data to cross-validate maps. This paper aimed at evaluating the efficiency of machine learning (ML) in limiting the use of ground truth data for LULC maps. This was accomplished by (1) extracting reliable LULC information from Sentinel-2 and Landsat-8 s images, (2) generating remote sensing indices used to train ML algorithms, and (3) comparing the results with ground truth data. The remote sensing indices that were tested include the difference vegetation index (DVI), the normalized difference vegetation index (NDVI), the normalized built-up index (NDBI), the urban index (UI), and the normalized bare land index (NBLI). Extracted vegetation indices were evaluated on three ML algorithms, namely, random forest (RF), k-nearest neighbour (K-NN), and k dimensional-tree (KD-Tree). The accuracy of these algorithms was assessed with standard statistical measures and ground truth data randomly collected in Prince Edward Island, Canada. Results showed that high kappa coefficient values were achieved by K-NN (82% and 74%), KD-Tree (80% and 78%), and RF (83% and 73%) for Sentinel-2A and Landsat-8 imagery, respectively. RF was a better classifier than K-NN and KD-Tree and had the highest overall accuracy with Sentinel-2A satellite images (92%). This approach provides the basis for limiting the collection of ground truth data and thus reduces the labour cost, time, and resources needed to collect ground truth data for LULC maps.

Socioeconomic activities and natural environmental changes are the main drivers of land use and land cover (LULC) changes worldwide and this directly affects the amount of soil organic carbon (SOC) stock. Though LULC affects the amount of SOC stocks and fluxes, the mid-lands of Tigray are less studied and represented. In this study, an attempt has been made to determine the effects of LULC change on SOC at watershed scale in the Central Tigray, Northern mid-lands of Ethiopia. Geographically the study area is found in Kola Tembien district, which is about 125 km away from Mekelle, the capital city of Tigray to the west. Five LULC types (cropland, grazing land, forest land, shrub/bush land and settlement) were identified. Nine composite and undisturbed soil samples at a depth of 20 cm and 10 cm respectively were collected randomly from each LULC type. Analysis of LULC change has been undertaken using satellite images of Landsat 5 TM, Landsat 7 ETM+ and Landsat 8 (OLI) with 30 m spatial resolution in ArcGIS10.3 and ERDAS Imagine14. One-way ANOVA was used for SOC analysis among LULC types. The analysis has showed that LULC change was undertaken in Jira watershed during the last 30 years (1987-2017). The highest SOC concentration was observed in forest land and the lowest was observed in cropland in all studied years. The amount of SOC concentration between each LULC types during all study years was significantly different at p < 0.05 except, cropland and grazing land in 1987 and grazing land and shrub/bush land in all study years. Change in LULC has affected the amount of SOC stock in the LULC types. For example, 18.7 t/ha of SOC was gained during the last 30 years due to the conversion of grazing land into forest land. During the thirty years interval (1987-2017) a total of 714.7 ton of SOC stock was gained due to the conversion of the land uses and management interventions. The highest SOC was gained due to the conversion of grazing land in to forest land (2007-2017) which has offered a total of 635.53 ton of SOC. A model was created to predict SOC of similar environments by using the observed SOC and NDVI values of the 2017 LULC types. Finally, the study concluded that the LULC change has affected the amount of SOC stock in the watershed and it is better to increase coverage of forest lands to store more organic carbon in the soil.

The study of Land Use and Land Cover (LULC) in Enugu, southeastern Nigeria, is crucial for understanding its effects on erosion and groundwater recharge. Different LULC types, coupled with varying slope gradients and soil types, create a complex interaction that influences soil stability and water infiltration in the region. This research aims to assess the distribution of LULC types, slope gradients, and soil types in Enugu, and to evaluate their impacts on erosion rates and groundwater recharge potential. Data for LULC, slope gradients, and soil types were collected and analyzed to determine their spatial distribution and characteristics. The study employed GIS techniques to map these variables and assess their interactions. Erosion potential and groundwater recharge capacity were evaluated based on the characteristics of the LULC types, slopes, and soils. The analysis revealed that trees cover the largest area (3709.74 km²), playing a significant role in stabilizing the soil and reducing erosion through their extensive root systems and canopy cover. Rangeland (2631.81 km²) also contributes to soil stability, although less effectively than forested areas. Crops (192.40 km²) have mixed impacts on erosion depending on agricultural practices. Built areas (1162.69 km²) present challenges due to impervious surfaces, which increase surface runoff and reduce groundwater recharge. Slope gradients were found to correlate with erosion processes and groundwater dynamics. Gentle slopes (0 - 1.81 degrees) cover 1870.15 km² and facilitate infiltration, enhancing groundwater recharge. Moderate slopes (1.81 - 4.06 degrees), covering 3275.46 km², are more prone to erosion, while steeper slopes (4.06 - 11.73 degrees) covering 2176.54 km² experience accelerated runoff and increased erosion rates. The steepest slopes (11.73 - 44.06 degrees) are the most erosion-prone areas, requiring significant intervention. The soil analysis showed that Dystric Nitosols (4052.80 km²) with the lowest K-factor (0.0178) are least prone to erosion and have high infiltration capacity, making them beneficial for groundwater recharge. Plinthic Acrisols (2732.53 km²) and Ferric Acrisols (102.36 km²) exhibit moderate erosion susceptibility. Dystric Fluvisols (793.92 km²) with the highest K-factor (0.0223) are highly erosion-prone. Gleysols (20.69 km²) have low to moderate erosion susceptibility. The interplay between LULC types, slope gradients, and soil types significantly influences erosion and groundwater recharge in Enugu. The study highlights the need for targeted land management practices, such as afforestation, contour farming, terracing, and the use of cover crops to mitigate erosion and enhance groundwater recharge. This research provides a comprehensive analysis of the relationships between LULC, slope gradients, and soil types in Enugu, offering valuable insights for developing effective land management strategies to address erosion and groundwater recharge challenges.

This study investigated the dynamics of land use and land cover (LULC) modelling, mapping, and assessment in the Kegalle District ofSri Lanka, where policy decision-making is crucial in agricultural development where LULC temporal datasets are not readily available.Employing remotely sensed datasets and machine learning algorithms, the work presented here aims to compare the accuracy of three classification approaches in mapping LULC categories across the time in the study area primarily using the Google Earth Engine (GEE). Three classifiers namely random forest (RF), support vector machines (SVM), and classification and regression trees (CART) were used in LULC modelling, mapping, and change analysis. Different combinations of input features were investigated to improve classification performance. Developed models were optimised using the grid search cross-validation (CV) hyperparameter optimisation approach. It was revealed that the RF classifier constantly outstrips SVM and CART in terms of accuracy measures, highlighting its reliability in classifying the LULC. Land cover changes were examined for two periods, from 2001 to 2013 and 2013 to 2022, implying major alterations such as the conversion of rubber and coconut areas to built-up areas and barren lands. For suitable classification with higher accuracy, the study suggests utilising high spatial resolution satellite data, advanced feature selection approaches, and a combination of several spatial and spatial-temporal data sources. The study demonstrated practical applications of derived temporal LULC datasets for land management practices in agricultural development activities in developing nations.

Human population growth and land use and land cover (LULC) change have always developed side by side. Considering selection of a good Machine Learning (ML) classifier algorithm is needed considering the high estimation of LULC maps based on remote sensing. This study aims to produce a LULC classification of Landsat-8 and Sentinel-2 images by comparing the accuracy performance of three ML algorithms, namely: Classification and Regression Tree (CART), Random Forest (RF), and Support Vector Machine (SVM). Dataset comparison ratios were also explored to find the LULC classification results with the best accuracy. Sentinel-2 is better than Landsat-8 regarding Overall Accuracy (OA) and Coefficient Kappa. The comparison ratio of the training and testing datasets with a good level of accuracy is 70:30 on both images with the average OA Landsat-8 and Sentinel-2 being 92.09% and 94.21%, respectively. The RF algorithm outperforms CART and SVM in both types of satellite imagery. The mean OA of the CART, RF, and SVM classifiers was 92.03%, 94.74%, 83.54% on Landsat-8, 93.14%, 96.15%, and 93.34% on Sentinel-2, respectively.

Application of machine learning approaches for land cover monitoring in northern Cameroon

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.

Abstract. LULC, or Land Use and Land Cover, refers to the classification and description of different types of land and its usage patterns, including urban areas, forests, agricultural land, etc. In remote sensing, satellite imagery for LULC mapping is becoming more widespread. Numerous studies examine various approaches to improve mapping efficiency and accuracy, highlighting the significance of various data sources, machine learning algorithms, and categorization techniques. This study employs machine learning classifiers, namely Random Forest (RF), Support Vector Machine (SVM), Gradient Boosted Trees (GTB), Classification and Regression Trees (CART), and K-Nearest Neighbors (KNN) for land use and land cover (LULC) classification of Madurai district utilizing Google Earth Engine. The findings reveal the impressive performance of Random Forest, boasting an overall accuracy of 99.01 percent coupled with a commendable Kappa coefficient of 98.68. Conversely. However, amidst these commendable achievements, it’s noteworthy to highlight the nuanced variations observed between the accuracy of training and validation sets. This discrepancy is attributed to the intrinsic intricacies of the learning processes inherent within the algorithms, underscoring the nuanced nature of algorithmic methodologies and their implications on accuracy assessment within spatial analysis frameworks. The generated land use and land cover (LULC) map allows for a comparison between the ground truth data and the surveys conducted to assess issues such as water scarcity and the drying of natural and man-made water bodies.