Land Use Classification Research Articles

The impact of landscape structure on pesticide exposure to honey bees

Pesticides may have serious negative impacts on bee populations. The pesticide exposure of bees could depend on the surrounding landscapes in which they forage. In this study, we assess pesticide exposure across various land-use categories, while targeting the Japanese honey bee, Apis cerana japonica, a native subspecies of the eastern honey bee. In a project involving public participation, we measured the concentrations of major pesticides in honey and beeswax collected from 175 Japanese honey bee colonies across Japan and quantitatively analyzed the relationships between pesticide presence/absence or pesticide concentration and land-use categories around the colonies. Our findings revealed that the surrounding environment in which bees live strongly influences pesticide residues in beehive materials, whether the pesticides are systemic or not, with a clear trend for each land-use category. Agricultural lands, particularly paddy fields and orchards, and urban areas resulted in higher pesticide exposure, whereas forests presented a lower risk of exposure. To effectively control pesticide exposure levels in bees, it is essential to understand pesticide usage patterns and to develop appropriate regulatory systems in non-agricultural lands, similar to those in agricultural lands.

Operational Google-Earth-Engine Workflow to Monitor Irrigated Areas in a Semi-Arid Climate

Abstract. Sustainable water resources management relies on advanced hydrological models calibrated from long-term satellite observations of water cycles. Monitoring water resources from Earth-observing satellites is enabled by cloud computing environments like Google Earth Engine (GEE) that support easy processing and analysis of archived data. While there are different satellite-based indicators of water resources availability, this paper focuses on mapping irrigated areas for each summer harvest season. The paper presents an automated workflow to extract yearly irrigated areas from imagery made public by Landsat and Sentinel-2. This method uses a normalised difference vegetation index (NDVI) to identify fields that exhibit higher vegetation greenness than their surroundings and are potentially being irrigated. As a first step, Google Earth Engine was used to create a seasonal maximum NDVI composite on which a grid-based thresholding algorithm was applied to identify irrigated areas in different parts of a catchment. The irrigated areas were then refined using morphological image processing and a quality-control step was conducted with ancillary datasets such as the most recent landuse classification, evapotranspiration data and crop phenology information. Finally, real-world use cases are presented to demonstrate the ability of satellite remote sensing to provide critical information on irrigation practices over the last 4 decades at the catchment scale.

Analysis of the Biennial Productivity of Arabica Coffee with Google Earth Engine in the Northeast Region of São Paulo, Brazil

Numerous challenges are associated with the classification of satellite images of coffee plantations. The spectral similarity with other types of land use, variations in altitude, topography, production system (shaded and sun), and the change in spectral signature throughout the phenological cycle are examples that affect the process. This research investigates the influence of biennial Arabica coffee productivity on the accuracy of Landsat-8 image classification. The Google Earth Engine (GEE) platform and the Random Forest algorithm were used to process the annual and biennial mosaics of the Média Mogiana Region, São Paulo (Brazil), from 2017 to 2023. The parameters evaluated were the general hits of the seven classes of land use and coffee errors of commission and omission. It was found that the seasonality of the plant and its development phases were fundamental in the quality of coffee classification. The use of biennial mosaics, with Landsat-8 images, Brightness, Greenness, Wetness, SRTM data (elevation, aspect, slope), and LST data (Land Surface Temperature) also contributed to improving the process, generating a classification accuracy of 88.8% and reducing coffee omission errors to 22%.

Toxic metal accumulation, health risk, and distribution in road dust from the urban traffic-intensive environment.

Owing to increasing levels of potentially toxic metals in road dust, air pollutants suspended in the air, pose significant health risks due to rapid, unplanned urbanization and industrialization. This study investigated the pollution status and health risks of trace metals (i.e., Cr, Cd, Ni, Cu, and Pb) in road dust collected from 16 locations across six land-use categories in Eskişehir, Türkiye, including residential, roadside, traffic, tram stations, and car industrial areas. The analysis of trace metals revealed distinct types of urban pollution based on these functional areas. In areas with heavy traffic, high concentrations of the elements, especially Zn, Cr, and Ni, would indicate significant toxic metal pollution. The overall contamination was evaluated using three indices: enrichment factor (EF 0.45-65.75), geo-accumulation index (Igeo - 2.50-4.18), and pollution index (PI 0.27-27.22). Human health risks of potentially toxic trace metals in urban road dust were evaluated for children and adult groups based on hazardous index (HI) and total cancer risk (TCR). The health risk assessments revealed that children (mean HIchildren 8.62E - 01; TCRchildren 6.99E + 04) are more vulnerable to toxic metal exposure than adults (mean HIadults 1.01E - 01; TCRadults 3.01E + 04), with ingestion being the primary exposure route over dermal contact and inhalation. In conclusion, we have captured the interaction between road dust and health risks, especially for children.

Identification of Residential and Commercial Area using Convolutional Neural Network

Abstract— Image classification of land use using aerial scene classification has become increasingly common around the world. Utilizing the power of Convolutional Neural Networks (CNNs), identification of various city township areas using satellite imagery has become more efficient compared to the previous manual labeling. The objective of this research is to build a convolutional neural network model for residential and commercial area identification. In the research, we also adopted Inception V3 and VGG16 to develop two transfer learning models for the identification system. The Inception V3-based model achieved the highest overall accuracy value of 100%, showing its effectiveness in accurate residential and commercial area identification. The proposed CNN model achieved an accuracy of 99%, while the VGG-16 model with all configurations being frozen achieved 99% accuracy.

Study on Urban Land Simulation under the Perspective of Local Climate Zoning—A Case Study of Guiyang City

The examination of land-use change simulations across a range of scenarios represents a pivotal research avenue for the advancement of sustainable development analysis. Nevertheless, the extant research merely categorises all building land in a land-use classification into a single category, which is unable to provide a detailed analysis of the dynamic internal spatial form of the city. This paper analyses 17 LCZ land-use types in Guiyang City in 2013 and 2022, and reclassifies them into 7 RLCZ land-use types based on the height of urban building sites. It also proposes three possible scenarios of BAU, WLC, and SPC in 2040 and simulates their land-use changes using the PLUS model. The results demonstrate that (1) the size of low-rise buildings in Guiyang has declined significantly over the past decade; (2) built-up land within cities is significantly affected by drivers such as night-time lighting, topography, elevation, and roads; (3) the SPC scenario emphasises a development pattern of land intensification and a focus on high density in urban built space. It also protects the stability of the ecosystem. The scenario can provide informative suggestions for spatial pattern changes in rapidly developing cities such as Guiyang.

Information-Theoretic Modeling of Categorical Spatiotemporal GIS Data.

An information-theoretic data mining method is employed to analyze categorical spatiotemporal Geographic Information System land use data. Reconstructability Analysis (RA) is a maximum-entropy-based data modeling methodology that works exclusively with discrete data such as those in the National Land Cover Database (NLCD). The NLCD is organized into a spatial (raster) grid and data are available in a consistent format for every five years from 2001 to 2021. An NLCD tool reports how much change occurred for each category of land use; for the study area examined, the most dynamic class is Evergreen Forest (EFO), so the presence or absence of EFO in 2021 was chosen as the dependent variable that our data modeling attempts to predict. RA predicts the outcome with approximately 80% accuracy using a sparse set of cells from a spacetime data cube consisting of neighboring lagged-time cells. When the predicting cells are all Shrubs and Grasses, there is a high probability for a 2021 state of EFO, while when the predicting cells are all EFO, there is a high probability that the 2021 state will not be EFO. These findings are interpreted as detecting forest clear-cut cycles that show up in the data and explain why this class is so dynamic. This study introduces a new approach to analyzing GIS categorical data and expands the range of applications that this entropy-based methodology can successfully model.

Quantitative prediction of water quality in Dongjiang Lake watershed based on LUCC

Land Use/ Cover Change (LUCC) plays a crucial role in influencing hydrological processes, nutrient cycling, and sediment transport in watersheds, ultimately impacting water quality on both spatial and temporal scales. Accurately predicting changes in watershed water quality is beneficial for the sustainable management of water resources. Current models often lack the ability to effectively predict water quality changes in a dynamic spatio-temporal context, particularly in complex watershed environments. The overall purpose of the study is to establish a comprehensive and dynamic modeling framework that links LUCC with water quality, allowing for accurate predictions of future water quality under varying land use scenarios. The model, which uses water quality as the dependent variable and LUCC as the independent variable, was developed to quantitatively predict changes in watershed water quality. To achieve this, annual multi-period remote sensing images from Landsat-5, Landsat-8 or Sentinel-2 satellites spanning from 1992 to 2022 were analyzed. Random Forest (achieving a Kappa coefficient of 0.9468) were employed to classify land use within the watershed. Based on classification results, a Cellular Automata-Markov chain model (CA-Markov) was constructed to simulate and predict the spatio-temporal patterns of land use, incorporating driving factors such as proximity to water systems, roads, elevation, and slope. Validation of the model using LUCC data from 2020 yielded a high prediction accuracy with a Kappa coefficient of 0.9505. The CA-Markov model was further utilized to project LUCC under three different scenarios—natural development, ecological protection, and arable land protection—between 2023 and 2033. Based on these projections, the coupled water quality and LUCC model was employed to predict water quality changes in the watershed over the same period. Key findings indicate that water quality is likely to improve under ecological protection scenario, while deterioration is expected under natural development scenario and cropland protection scenario due to urban expansion, agricultural practices, and water diversion for irrigation. This study provides a robust framework for watershed management, offering scientific guidance for source management and water purification efforts, thereby contributing significantly to the sustainable development of water resources.

Predicting pavement surface conditions through artificial neural networks

In this study, six distinct types of pavement distress were evaluated using the pavement condition index (PCI) rating: ravelling, rutting, cracking (including alligator, transverse and longitudinal cracks), shoving, patching and potholes. The severity levels of these distress types are utilised for classification, and these levels are subsequently converted into PCI values. The proposed methodology incorporates a thorough analysis, considering various variables such as average daily traffic, land-use classification, number of lanes, road width and length, pavement age, road alignment, vehicle type and weather conditions in Berzhite, Tirana, Albania. To predict PCI values, an artificial neural network model was employed due to its versatility in handling diverse inputs. Key performance metrics, including R2, mean squared error and mean absolute error, are used for model assessment. Notably, model 2, featuring two hidden layers, exhibits superior performance over model 1. However, due to size constraints in testing and validation datasets in this study, the accuracy of the model is somewhat limited. Future directions for research involve expanding the dataset to enhance model accuracy and incorporating advanced features to capture a more complex comprehension of pavement conditions.

Python-Based Urban Land Suitability Evaluation for Effective Urban Planning

Abstract: One of the global environmental problems is that the population is growing rapidly around the world. unfortunately, land is a limited resource. Land suitability analysis merges as the most efficient and commonly used method that represents an effective informative tool to support policymakers and planners in developing optimal master plans, maintaining sustainability, and ensuring social equity among residents. Python's free and open-source ecosystem of geospatial libraries like Geo Pandas makes it a cost-effective alternative to proprietary GIS software for this purpose. Furthermore, Python excels at automation, allowing you to write scripts that save time and ensure consistency for repetitive tasks in land suitability analysis. At first, users can choose the project type based on the classification of land use and input raster and vector data. After that, each layer is reclassified, and a weighted overlay is applied at the end. A raster would be the final land suitability output file. Urban planning benefits greatly from Python's capabilities. Land suitability models can assess the viability of development projects by considering factors like flood risk, slope stability, and proximity to infrastructure. The applications extend far beyond these initial examples. Python's land suitability models are instrumental in environmental management as well. Habitat suitability modeling, for instance, considers factors like vegetation cover, water availability, and connectivity to existing habitats to identify areas suitable for specific wildlife species. This information is crucial for conservation planning and restoration efforts. This paper is designed to explain the beneficial aspects of a Python-based approach to land suitability modelling and how it operates.

Effects of Peromyscus spp. (Rodentia: Cricetidae) presence, land use, and ecotone on Ixodes scapularis (Acari: Ixodidae) ecology in an emergent area for tick-borne disease.

As the range of Ixodes scapularis Say expands, host abundance and land use can play important roles in regions where ticks and their associated pathogens are emerging. Small mammal hosts serve as reservoirs of tick-borne pathogens, with Peromyscus leucopus Rafinesque often considered a primary reservoir. A sympatric species Peromyscus maniculatus Wagner is also a competent reservoir and is notoriously difficult to differentiate from P. leucopus. Anthropogenic land use can alter host and habitat availability, potentially changing tick exposure risk. We tested the hypotheses that tick infestation and pathogen prevalence differ between the two Peromyscus spp. and that host-seeking I. scapularis density and pathogen prevalence differ across land use and ecotone gradients. We live trapped small mammals and collected ticks across 3 land-use classifications and ecotones in Maine, an emergent area for tick-borne disease. We tested each small mammal and tick sample for Borrelia burgdorferi, Anaplasma phagocytophilum, and Babesia microti. While both Peromyscus spp. serve as hosts for immature ticks, P. leucopus exhibited a higher tick infestation frequency and intensity. We did not detect any significant difference in pathogen infection prevalence between the two species. The density of I. scapularis nymphs and the density of infected nymphs did not differ significantly between land-use types, though did differ across ecotones. We also noted a significant north/south gradient, with higher tick densities and pathogen prevalence at the southern end of the study area. Our study highlights the potential variability in tick density and pathogen prevalence across fine spatial scales within an emerging region for tick-borne disease.

Fully invertible hyperbolic neural networks for segmenting large-scale surface and sub-surface data

The large spatial/temporal/frequency scale of geoscience and remote-sensing datasets causes memory issues when using convolutional neural networks for (sub-) surface data segmentation. Recently developed fully reversible or fully invertible networks can mostly avoid memory limitations by recomputing the states during the backward pass through the network. This results in a low and fixed memory requirement for storing network states, as opposed to the typical linear memory growth with network depth. This work focuses on a fully invertible network based on the telegraph equation. While reversibility saves the major amount of memory used in deep networks by the data, the convolutional kernels can take up most memory if fully invertible networks contain multiple invertible pooling/coarsening layers. We address the explosion of the number of convolutional kernels by combining fully invertible networks with layers that contain the convolutional kernels in a compressed form directly. A second challenge is that invertible networks output a tensor the same size as its input. This property prevents the straightforward application of invertible networks to applications that map between different input–output dimensions, need to map to outputs with more channels than present in the input data, or desire outputs that decrease/increase the resolution compared to the input data. However, we show that by employing invertible networks in a non-standard fashion, we can still use them for these tasks. Examples in hyperspectral land-use classification, airborne geophysical surveying, and seismic imaging illustrate that we can input large data volumes in one chunk and do not need to work on small patches, use dimensionality reduction, or employ methods that classify a patch to a single central pixel.

Shallow soils in dryland ecosystems: Drivers of C accumulation and land management implications

Shallow soils (i.e., Lithic Entisols) cover about 20% of Brazilian drylands. Inherent soil characteristics (i.e., shallow depths) and water scarcity restrict plant growth and carbon (C) inputs in these soils. In such a sensitive ecosystem, sustainable land management options are key to promoting socio-economic development and ensuring food security. Here, we use a dataset of 50 Lithic Entisol profiles distributed within the Brazilian drylands (northeastern region) to: (i) investigate the effects of land-use (cropland, grassland, and native forest), climate (semi-arid and dry sub-humid), and slope classes (0–3%, 3–8%, 8–20% and 20–45%) on soil C accumulation; and (ii) evaluate how understanding multiple drivers C accumulation can support the identification of sustainable land management options. The results suggested that land use does not affect C stock and C/N ratio, nevertheless, they were affected by climate. Under dry sub-humid climate conditions, C stocks were 41.7 Mg ha−1, 44% higher than under semi-arid climate (28.9 Mg ha−1), a result that reflects the effect of higher biomass production in wetter environments. Under slopes of 20–45%, C stocks were 54.3 Mg ha−1, 172% higher than under slopes of 0–3% (19.9 Mg ha−1), because of the higher altitudes and wetter conditions under steeper slopes. Our results showed that areas under lower slopes have lower C stocks and lower aridity index. These drier conditions reduce the productive potential of annual crops and grasslands but enable the cultivation of high-yielding Crassulacean Acid Metabolism (CAM) crops, such as Agave spp, which have a high potential for biofuel production. Furthermore, the possibility of reintroducing organic residues from ethanol production can promote an increase in C stocks, contributing to climate change mitigation. Ultimately, our study provides insights from a holistic view of SOC accumulation drivers, supporting land use planning of highly sensitive environments in tropical drylands around the world.

DCAI-CLUD: a data-centric framework for the construction of land-use datasets

A high-quality land-use dataset is crucial for constructing a high-performance land-use classification model. Due to the complexity and spatial heterogeneity of land-use, the dataset construction process is inefficient and costly. This challenge affects the quality of datasets, consequently impacting the model’s performance. The emerging field of Data-Centric Artificial Intelligence (DCAI) is expected to deliver techniques for dataset optimization, offering a promising solution to the problem. Therefore, this study proposes a data-centric framework named DCAI-CLUD for the construction of land-use datasets. Based on this framework, the accuracy and rate of data labeling are improved by 5.93 and 28.97%. The Gini index of the dataset and the proportion of samples with non-mixed land-use categories are enhanced by 3.27 and 8.52%. The overall accuracy (OA) and Kappa of the land-use classification model improved significantly by 27.87 and 58.08%. This study is the first to introduce DCAI into the field of geographic information and remote sensing and verify its effectiveness. The proposed framework can effectively improve the construction efficiency and quality of the dataset and synchronously optimize the model performance. Based on the proposed framework, we constructed a multi-source land-use dataset of major cities in China named CN-MSLU-100K.

Characterization and evaluation of environmental units as a management and conservation strategy of the Palmira Desert (Ecuador)

Globally, deserts are considered as fragile and unique biomes. They have the capacity to provide various ecosystem services, and possess great tourism potential and scientific value, but are also susceptible to modifications or alterations in their geomorphology. Despite the strategic importance of these ecosystems at a global level, there is limited specialized research directed towards the study of deserts in Ecuador. The purpose of this research is to determine the susceptibility to degradation and carrying capacity of environmental units to support tourist and recreational activities, thereby offering the community a sustainable resource over time. The delimitation of environmental units was carried out based on the identification of land use and land cover through the supervised classification method. Multicriteria analysis was used to obtain the areas susceptible to degradation, where the environmental units were evaluated through expert evaluation. Once the results of the previous methodologies were obtained, areas with environmental and tourist potential were identified using the hosting capacity matrix, which is based on anthropic activities developed in the area. Subsequently, a proposal for conservation strategies and activities at the national and local levels was formulated. Five categories of land use and land cover were identified, resulting in 11 environmental units represented in spatial data. It was determined that approximately 31% of the territory is more susceptible to degradation, while the remaining 69% is less susceptible. Based on the susceptibility of these areas, 7 activities and 2 tourist routes were designated to help reduce anthropogenic pressure. Additionally, the community was provided with 5 proposals for conservation strategies at the national level, 4 at the local level, and 4 activities to be developed based on the findings identified during the investigation. This highlights the significant potential that the Palmira Desert has to become a conservation area.

Comparative analysis of RUSLE and SWPT for sub-watershed conservation prioritization in the Ayu watershed, Abay basin, Ethiopia

Ethiopia is currently facing a major environmental problem caused by soil erosion. In order to tackle this problem, it is essential to implement a comprehensive watershed management approach and give priority to conservation efforts depending on the level of severity. Therefore, the objective of this research is to evaluate the mean annual soil erosion and rank the sub-watersheds for conservations in the Ayu watershed, utilizing the Revised Universal Soil Loss Equation (RUSLE) model and the Sub-Watershed Prioritization Tool (SWPT). RUSLE was utilized to predict the annual average soil erosion rate, while SWPT was applied to conduct Weighted Sum Analysis (WSA) for ranking sub-watersheds. Support Vector Machine (SVM) was employed for classifying land use and land cover. The Relative importance of morphometric and topo-hydrologic features in the SWPT was analyzed using a Random Forest model. The Bland-Altman plot and Wilcoxon Signed Rank Test were employed to assess the agreement in prioritizing watersheds between RUSLE results and the SWPT. Furthermore, field observations were conducted to validate the land use classification by collecting ground data. In addition, the study was enhanced with local viewpoints by conducting focus group discussions with agricultural experts and farmers to obtain qualitative insights and validation of resuts. The findings showed that soil loss varied from 0 to 110 t/ha/yr, with an average of 8.95 t/ha/yr, resulting in a total loss of 384365.3 tons annually. The comparison of RUSLE and SWPT showed a moderate positive relationship (r = 0.59). The results of the Bland-Altman plot indicate a consistent agreement between the two methods. However, there is inconsistency among the five sub watersheds. This study enhances the knowledge of soil erosion patterns and offers useful guidance for watershed conservation techniques. It can be also used as a beneficial framework for managing watersheds, with possible uses outside of the Ayu watershed.

Satellite Long-Term Monitoring of Wetland Ecosystem Functioning in Ramsar Sites for Their Sustainable Management

The long-term monitoring of wetland ecosystem functioning is critical because wetlands, which provide multiple services, can be affected by human activities and climate change. The aim of this study was to monitor wetland ecosystem functioning in the long term using the Landsat archive. Four contrasting, Ramsar wetlands were selected in boreal, temperate, arid, and tropical areas. First, the annual sum of the normalized difference vegetation index (NDVI-I) was calculated as an indicator of annual net primary productivity for the period 1984–2021 using the continuous change detection and classification (CCDC) algorithm. Next, the influence of the number of Landsat images and class of land use and land cover (LULC) on the accuracy of the CCDC was investigated. Finally, correlations between annual NDVI-I and climate were analyzed. The results revealed that NDVI-I accuracy was influenced mainly by the LULC class and to a lesser extent by the number of cloud-free Landsat observations. Infra- and inter-site variations in NDVI-I were high and showed an overall increasing trend. NDVI-I was positively correlated with the mean temperature. This study shows that this approach applied in contrasting sites is robust for the long-term monitoring of wetland ecosystem functioning and can be used to improve the implementation of international biodiversity conservation policies.

Adapting LoRa Ground Stations for Low-latency Imaging and Inference from LoRa-enabled CubeSats

Recent years have seen the rapid deployment of low-cost CubeSats in low-Earth orbit, many of which experience significant latency (several hours) from the time information is gathered to the time it is communicated to the ground. This is primarily due to the limited availability of ground infrastructure that is bulky to deploy and expensive to rent. This article explores the opportunity in leveraging the extensive terrestrial LoRa infrastructure as a solution. However, the limited bandwidth and large amount of Doppler on CubeSats precludes these LoRa links to communicate rich satellite Earth images—instead, the CubeSats can at best send short messages. This article details our experience in designing LoRa-based satellite ground infrastructure that requires software-only modifications to receive packets from LoRa-enabled CubeSats recently launched by our team. We present Vista, a communication system that adapts encoding onboard the CubeSat and decoding configuration on commercial LoRa ground stations to allow images to be communicated. We perform a detailed evaluation of Vista by leveraging wireless channel measurements from a recent CubeSat (2021), and show that Vista can achieve 55.55% lower latency in retrieving data with 12.02 dB improvement in packet retrieval in the presence of terrestrial interference. We then evaluate Vista on a case study on land-use classification over images transmitted over the CubeSat link to further demonstrate a 4.56 dB improvement in image PSNR and 1.38× increase in classification accuracy over baseline approaches.

A Spatio-Temporal Analysis of the Frequency of Droughts in Mexico’s Forest Ecosystems

Droughts can affect forest ecosystems and lead to soil degradation, biodiversity loss, and desertification. Not all regions of Mexico are affected in the same way, as some areas are naturally more prone to drought due to their geographical location. Therefore, the objective of this work was to carry out a spatio-temporal analysis of the occurrence of droughts (severe and extreme) in Mexican forest systems, covering the period 2000–2021, and to study the area covered by these events in Mexican forest systems. This analysis was divided into three stages: the classification of land use and vegetation, spatial mapping and the classification of drought intensity, and an analysis of drought frequency and probability in forest systems. The results show that more than 46% of Mexico’s forest area experienced severe and extreme droughts during the 21-year period studied. Broadleaved forests were most affected by severe and extreme droughts, with a frequency of 6 years. The increasing frequency of droughts poses a major challenge to the resilience of forest ecosystems in Mexico, highlighting the need to implement climate change adaptation and forest management measures to protect the country’s biodiversity and natural resources.

Comparative analysis of different supervised methods for satellite-based land-use classification: a case study of Reyhanlı

Satellite-based land-use classification plays a crucial role in various Earth observation applications, ranging from environmental monitoring to disaster management. This study presents a comparative analysis of machine learning techniques applied to land cover classification using Landsat-9 and Sentinel-2 satellite imagery in the Reyhanlı district in southern Türkiye. Three different classification algorithms, Random Forest (RF), Support Vector Machine (SVM), and Maximum Likelihood Classification (MLC), were evaluated for their ability to distinguish different land cover classes. High resolution multispectral satellite imagery processed under the same conditions using Geographic Information System (GIS) software was utilized in this study. Visual inspection and statistical evaluation, including overall accuracy and kappa coefficient, were employed to assess classification performance. The classification of Sentinel-2 and Landsat-9 satellite imagery using different machine learning algorithms resulted in the highest overall accuracy (OA = 0.911, Kappa = 0.879) for Sentinel 2 imagery with the RF algorithm. These findings highlight the importance of satellite image selection and algorithm optimization for accurate land cover mapping. This study provides valuable insights for local planners and authorities and underscores the potential of Sentinel-2 imagery combined with machine learning techniques for effective land-use classification and monitoring.