Land Use Map Research Articles (Page 1)

Rapid urbanization in Southeast Asia has been posing huge impacts on local food systems, altering spatial-temporal patterns of urban agriculture, ecosystems and social life. Understanding these changes is crucial for cities planning their land use and infrastructure development to achieve a balance between urban growth, agricultural sustainability, and food security. This study mapped the changes between 2013 and 2020 of five agricultural types within (peri)urban areas in Huế, a province’s capital in Vietnam. High-resolution SPOT satellite images (1.5m) and a deep learning model based on the U-net architecture were used to map land use and agriculture types. This approach addresses challenges in generating extensive labelled datasets in urban settings characterized by fragmented farmland and dense development. The optimized U-net model achieved high classification performance (for 2013: IoU = 0.86 and Kappa = 0.93, for 2020: IoU = 0.87 and Kappa = 0.92) even when operated on regular CPU computers, demonstrating its practical applicability for countries with limited technical infrastructure. This is also the first study in Southeast Asia to accurately map (overall accuracy 85% for 2013 and 87% for 2020) multiple types of urban agriculture at 1.5 m resolution, enabling detailed spatial-temporal changes analysis. These results can inform decision-makers in elaborating effective land use strategies and food security plans, and offer researchers a scalable deep learning framework for urban agriculture mapping in rapidly urbanizing regions.

This study proposes and validates an innovative solution for cadastral mapping, focusing on the Rural Environmental Registry (CAR). It begins with an analysis of current legislation, exploring geotechnologies and innovations applied to mapping. The methodology uses a Remotely Piloted Aircraft (RPA) equipped with GNSS and satellite internet, eliminating the need for ground support points and standing out for its precision and accuracy in generating orthophotomosaics. The study area was the Professor Hélio Barbosa Experimental Farm of the UFMG School of Veterinary Medicine, located in the municipality of Igarapé, Minas Gerais. The generated products include high-resolution orthophotomosaics, thematic maps of land use and land cover, area delimitation (APP, legal reserve, consolidated use), and a digital surface model. These maps demonstrated high positional precision and accuracy, in accordance with Brazilian and American technical standards. Compared to traditional methods, the approach resulted in faster processing and a significant reduction in operating costs. The proposal proves viable for replication in rural cooperatives and associations, contributing to the improvement of the CAR and the territorial management of rural properties.

Landscape fragmentation, driven by diverse agricultural practices, represents one of the significant challenges for biodiversity conservation. Although some sub-regions in Bahia are considered better preserved due to their traditional land-use patterns, comparative assessments with less preserved areas remain scarce. This study aimed to evaluate the landscape structure in two rural communities in Bahia, Brazil: Rio do Engenho (Ilhéus) and Riacho da Guia (Alagoinhas), characterized respectively by agroforestry systems (cabruca) and monocultures (citrus and eucalyptus). The methodology was based on the analysis of CBERS-04A satellite images (2024) with an 8-meter spatial resolution, processed using QGIS 3.34. Land-use and land-cover mapping was conducted through manual visual interpretation, identifying up to nine thematic classes. To assess landscape structure, nine ecological metrics were calculated using the LecoS plugin, encompassing composition, shape, connectivity, and diversity. The results indicated that Rio do Engenho has a larger proportion of native vegetation, greater cohesion, and lower edge density, revealing a configuration more favorable to biodiversity conservation. In contrast, Riacho da Guia exhibited higher fragmentation, a predominance of agricultural land uses, and reduced connectivity among forest remnants. Therefore, the findings demonstrate that adopting agroforestry systems enhances biodiversity maintenance and ecosystem resilience, whereas monoculture practices accelerate environmental degradation.

ABSTRACT New approach for interpreting Interferometric Synthetic Aperture Radar (InSAR) results with unsupervised machine learning on variables and time series. The study compares Persistent Scatterer Interferometry (PSI) results from X-band (PAZ-X) and C-band (Sentinel-1) satellite images over a Portuguese region. Validation with GNSS data demonstrates high precision, with average Euclidean Distances (ED) of 2.8 mm (X-band) and 3.6 mm (C-band). Despite having fewer images (25 vs. 30), X-band achieves higher scatter density (1,126 scatterers/km²) compared to C-band (678 scatterers/km²). InSAR reduced dimensionality and independent variables are clustered using K-means, DBSCAN, and OPTICS algorithms. Time-series are clustered using partitioning and hierarchical methods based on ED and Dynamic Time Warping (DTW) measures. The clusters obtained were interpreted and a refinement mode is implemented based on inter-algorithm consistency to enhance cluster reliability. For evaluation and application results are compared with land-use maps. The findings indicate that Sentinel-1 exhibits higher complexity (15% lower consistency with land-use map) compared to PAZ-X. Moreover, the refinement mode improves target identification for both datasets, increasing classification accuracy by 5% and 7% for PAZ-X and Sentinel-1, respectively. The methodology enhances geohazard monitoring generating alert index maps for specific elements with applicability in urban planning, infrastructure stability and natural hazard mitigation.

This study was conducted to determine the groundwater potential zone by using the Geographical Information System (GIS) method in Sungai Seguntor, Sandakan, Sabah, Malaysia, and its surroundings. The study area consists of the Sandakan Formation, the Volcanic Breccia and the Quaternary Alluvium. The ArcGIS 10.5 and Global Mapper software were used in this study. Eight thematic maps have been produced: lithological map, rainfall map, drainage density map, lineament density map, soil type map, landuse map, elevation map and slope steepness map. GIS methods were used during the spatial analysis stage. All the thematic maps are weighted based on their emphasis on the existence of groundwater. During the map integration stage, the Raster Calculator is used based on the Eigen Vector of each parameter. The final map produced shows that almost 30% of the study area has high groundwater potential, most of which is in lowland alluvium areas with relatively high drainage density. This final map also shows significant results with tube well data obtained from the Department of Minerals and Geosciences, Sabah, Malaysia.

Soil compaction is one of the problems faced due to land conversion in agriculture, directly impacting land productivity. This study aimed to identify the distribution of soil density with the Dynamic Penetration Index (DPI) method, the influence of land use, and the determinants of soil compaction, and provide recommendations to control soil density on agricultural land around the sub-watershed area. This research used an exploratory descriptive method, and sample points were determined by purposive sampling. There are 45 sample points determined based on the overlay map of soil type, land use, slope, and rainfall. The low DPI class has an area of 8,227 ha (34.34%), and the very low DPI class has an area of 15,729 ha (65.65%). The highest DPI value was in the plantation land use, and the lowest was in the rice field land use. Plantations experienced soil compaction due to intensive land use without soil quality restoration. The determining factors that affect soil compaction were porosity and bulk density. High porosity means low DPI values and, therefore, low compaction. High bulk density means high DPI value and therefore high compaction. Recommendations for land management include adding organic matter and tillage using a hoe or tractor to optimize soil compaction.

Multi-temporal high-resolution urban land-use mapping and change analysis based on a deep geospatial-temporal adaptation network

Mountain settlements represent culturally rich but environmentally fragile landscapes, shaped by enduring processes of ecological adaptation and human resilience. In western Sichuan, Jiarong Tibetan villages, with their distinctive integration of defensive stone towers and settlements, embody this coupling of culture and the environment. We hypothesize that settlement cores in these villages were shaped by natural environmental factors, with subsequent expansion reinforced by the cultural significance of towers. To test this, we applied a micro-scale spatial–environmental framework to four sample villages in Suopo Township, Danba County. High-resolution World Imagery (Esri, 0.5–1 m, 2022–2023) was classified via a Random Forest algorithm to generate detailed land-use maps, and a 100 × 100 m fishnet grid extracted topographic metrics (elevation, slope, aspect) and accessibility measures (distances to streams, roads, towers). Geographically weighted regression (GWR) was then used to examine how slope, elevation, aspect, proximity to water and roads, and tower distribution affect settlement patterns. The results show built-up density peaks on southeast-facing slopes of 15–30°, at altitudes of 2600–2800 m, and within 50–500 m of streams, co-locating with historic watchtower sites. Based on these findings, we propose four zoning strategies—a Core Protected Zone, a Construction And Development Zone, an Ecological Conservation Zone, and an Industry Development Zone—to balance preservation with growth. The resulting policy recommendations offer actionable guidance for sustaining traditional settlements in complex mountain environments.

It has been proven that in modern conditions, the use of geographic information systems is of particular importance for ensuring geospatial monitoring of land use for residential and public development in regions. Trends have been identified and transformations in land use and development have been highlighted. As a result of systematising existing scientific research, directions have been identified and GIS tools for monitoring procedures in the field of land use have been characterised. Unresolved issues in the development and implementation of geospatial monitoring of land use for residential and public development at the regional level have been identified, taking into account the capabilities, methods and models of GIS. The article achieves the research objective of developing directions and identifying the specifics of GIS application in the system of geospatial monitoring of land use for residential and public development in regions. To achieve this goal, the following tasks were solved: determining the directions for the application of geographic information systems to ensure geospatial monitoring of land use for residential and public buildings at the regional level; forming a geodata base; building geoinformation monitoring maps of residential and public land use at the regional level; identifying the characteristics of geospatial monitoring, taking into account the consequences of the Russian Federation's aggression. The directions for the application of geoinformation systems to ensure geospatial monitoring of residential and public land use at the regional level have been determined. Proposed areas for the development of a geodata base for the creation and implementation of geospatial monitoring of land use for residential and public development. GIS monitoring maps have been constructed showing the level of geoinformation provision for land for residential and public development and the impact of factors characterizing the consequences of Russian aggression.

Land Use and Land Cover (LULC) changes play a significant role in shaping urban landscapes and environmental sustainability. This study analyzes LULC transformations in Ayodhya City between 2014 and 2024 using Remote Sensing and GIS techniques. Utilizing Landsat 8 satellite imagery and the Semi-Automatic Classification Plugin (SCP) in QGIS, the study classifies land into five major categories: Waterbodies, Forest, Agricultural Land, Bare Land, and Built-Up Areas. The findings indicate a significant increase in built-up areas, rising from 49.12% in 2014 to 56.23% in 2024, primarily driven by Ayodhya’s growing religious and tourism-related importance and government-led infrastructural developments. Concurrently, agricultural land declined from 28.59% to 24.97%, and forest cover reduced from 2.71% to 2.37%, reflecting urban expansion and land conversion. Additionally, bare land decreased from 10.75% to 9.39%, while waterbodies exhibited a slight increase from 1.73% to 1.75%, possibly due to conservation efforts and water management strategies. The study underscores the utility of Remote Sensing and GIS in monitoring urban growth, assessing environmental changes, and aiding sustainable urban planning. The findings emphasize the need for balanced land-use policies to mitigate environmental degradation and ensure sustainable development in Ayodhya City.

Wetland dynamics in the Indus River Delta: A Sentinel-2 and machine learning approach.

The study examines the impact of floods on crop production in the Nabogo River basin, identifying flood risk and area affected. The flood extent in the research region was determined using Sentinel 1 images, global surface water, and a digital elevation model between July and October 2023. Flood analysis was carried out using Sentinel-2A and MODIS images, with cloud processing avoided and cloud and shadow masking techniques utilised. High-resolution data were used to map land use land cover (LULC) for affected and non-affected crops in the Nabogo River basin. The analyses were processed using Google Earth Engine. Heavy rainfall in the region, particularly upstream of the Nabogo River in northern of Ghana and Burkina Faso, causes severe flood damage every year, affecting farmers’ crop production and social economics through surface runoff and riverine damage. The flood extent inundates a minimum of 50 ha in July, extending to 34,090 ha in August. The flood extent reached its peak of 60,900 ha in September during discharge of water at the Burkina Faso’s Bagri Dam spillway through the White Volta in Ghana. Between July and October 2023, 24,223 ha of farm land were flooded, affecting 5,928 ha of crops. The impacted cropland experienced a 28-day flood with an average height of 1–3 m. Nevertheless, many farmers are forced to produce along the riverbank anyway due to land ownership and soil fertility benefits. To prevent ongoing losses, early-maturing crops are recommended.

Fire occurs naturally and anthropogenically in the Cerrado biome, influenced by hydrology, climate, topography, and land use. Mapping burned areas is essential for understanding the causes of fire and improving prevention and regulation. However, fire scars are often confused with bare soil in agricultural regions. This study presents a method for mapping burned areas using spectral indices and artificial neural networks (ANN). We evaluated the accuracy of these techniques and identified the best input variables for scar detection. Using Sentinel-2 images from 2018 to 2021 during dry periods, we applied NDVI, SAVI, NBR, and CSI indices. The study included two stages: first, finding optimal classification configurations for fire scars, and second, mapping land use and cover with fire scars and crops. Results showed that using all Sentinel-2 bands and the four indices post-fire achieved over 93.7% accuracy and a kappa index of 0.92. Fire scars were mainly located in areas with temporary crops like soybean, sugarcane, rice, and cotton. This low-cost method allows for effective monitoring of fire scars, underscoring the need to regulate agricultural practices in the Cerrado, where burning poses environmental and health risks.

Sustainable settlement design necessitates the incorporation of environmental carrying capacity determined by ecosystem services. In border areas like the Sota Border Area (KPN) in Papua, ecological pressures intensify as a result of population expansion and economic endeavours. This study assesses the environmental carrying capacity and resilience of settlements through an ecosystem services framework, comparing conditions in 2019 and 2024 to evaluate the impact of development plans. The analysis focuses on five key ecosystem services: food provision, clean water supply, water flow regulation and flood control, disaster protection, and air quality maintenance. Data collection involved field surveys, remote sensing, and GIS-based spatial overlay analysis to map land use changes and ecosystem service values. Results in 2019 showed residential development concentrated in zones with high ecosystem service values, such as food provision (771.7 ha in SUB BWP 2) and clean water supply (742.98 ha in SUB BWP 3). Development in low-lying areas prioritized flood regulation (460.1 ha in SUB BWP 1) and disaster protection (560.7 ha in SUB BWP 1). By 2024, developed land in the very high clean water supply zone of SUB BWP 1 increased sharply from 0.10 ha to 28.86 ha. This research highlights the critical need to incorporate ecosystem service data into settlement planning to sustain environmental capacity and enhance border region sustainability

Salt-affected soils critically affecting irrigation practices and crop production, and also improper irrigation practices aggravated soil salinity problems in Asaita District. This study was conducted to assess the magnitude and spatial variability of salt-affected soils in the irrigated areas of Asaita District, Afar Region, Northeastern Ethiopia using GIS and remote sensing techniques. To undertake this study, base map of land use/ land cover were created based on desk review of existing document, initial data using ARC GIS 10.3 software and Google earth imagery. Soil samples were collected and analyzed for its selected physichochemical properties. A total of 100 surface soil samples (0-30 and 30-60cm depth) were collected randomly from each stratum, with locations recorded using GPS. Additionally, 104 samples were collected from six soil profiles.The findings revealed that soil salinity is a critical issue, affecting 100% of the study area, with 69.85% classified as saline and 30.15% as saline-sodic soils. The spatial analysis indicated that soil salinity (ECe) exhibited strong spatial dependence, whereas sodicity (ESP) showed weak spatial dependency, and soil pH had moderate spatial dependence. The primary drivers of soiol salinity were found to be excessive irrigation, poor drainage systems, and low-quality irrigation water, leading to salt accumulation in the soil profile. Improved irrigation practices and drainage interventions reduced surface salinity by 25-30%, potentially reclaiming over 3,500ha of marginal land. These results highlight the urgent need for sustainable soil and water management practices to prevent further land degradation and ensure long-term agricultural productivity.

Land use and land cover mapping is a key tool for understanding how territorial configuration influences biotic, abiotic, and anthropic components. In this regard, Geo Big Data technologies enable the agile and accurate generation of cartographic products. This study proposes two solutions for mapping land use and land cover in Uruguay for the 2021–2022 agricultural year. The inputs include Sentinel-1 and Sentinel-2 imagery, Google Earth Engine, GEEMAP, Scikit-learn, and the Random Forest and Support Vector Machines algorithms. The methodology highlights the creation of a multitemporal dataset, hyperparameters tuning, and supervised classification. As a result, two maps were generated: S1S2RF_uy and S1S2SVM_uy. Both products exhibited elevated levels of accuracy, although S1S2RF_uy performed slightly better, with an overall accuracy of 83 % and a kappa coefficient of 0.81, compared to 81 % and 0.78 for S1S2SVM_uy. At the class level, Random Forest showed a greater ability to classify agricultural covers, while Support Vector Machines were more effective in identifying artificial surfaces such as urban fabric. The findings confirm that hyperparameter tuning is essential for optimal classifier performance. Based on the reported accuracy statistics, it is also demonstrated that freely accessible Geo Big Data resources are well-suited for the efficient production of national-scale cartography at medium-to-high spatial resolution. Future research should prioritise regional focus and extend timeframes beyond the traditional agricultural year.

Agricultural productivity is influenced by soil fertility, which depends on the nutrient content of the soil as well as the land use and management practices applied. The objective of this study is to identify the chemical properties of the soil, determine its chemical fertility status, and analyzed limiting factors. The research was conducted from December 2024 to February 2025 using survey methods and laboratory analysis according to the criteria of the Soil Research Center (1995). Representative sample points were determined by purposive method on the overlay results of thematic maps (Land Use Maps, Slope Maps, Elevation Maps) and resulted in 12 Land Units. The analysis results showed that the Cation Exchange Capacity (CEC) values range from 2,2 - 7,55 cmol (+)/kg classified as very low to low, Base Saturation (BS) ranges from 56,24 - 99,99% categorized as high to very high, P2O5 was 59,66 - 88,37 mg/100g classified as high to very high, K2O was 2,09 - 15,51 mg/100g categorized as very low to low, C-organic was 0,46 – 2,38% classified as low to moderate, and pH H2O was 4,83 – 7,7 indicating acidic to slightly alkaline conditions therefore the status of soil chemical fertility obtained 2 status, very low covering an area of 373,19 ha (39,42%) and low covering 600,09 ha (60,58%). The low fertility status is mainly influenced by the low Cation Exchange Capacity, content of K2O, and Organic Carbon.

Despite the critical role of agriculture in Kenya’s economic development, conversion of prime agricultural land to concrete landscapes is increasing at a worrying trend, thus putting national food sovereignty and overall environmental quality at risk. This study investigated this dimension using Ruiru Sub-County as a case study. The aim was to trigger land use planning and policy changes towards a balanced approach between emerging real estate markets and saving agricultural land for posterity. Geographic Information System procedures were used to map land use and land cover changes from 1988 to 2024. Results showed that by 2024, land under agriculture had reduced by 45.62% while urban land use had increased by 509%. Similarly, bare and rocky area increased by 133%, which was indicative of increasing land loss to abandoned stone mining quarries. Decline in land sizes also means reduced area under industrial crops like coffee and tea, and hence the shift to leafy vegetables and annual crops demanded by the increasing urban market. Further, expected increase in intensive peri-urban farming systems, will likely be accompanied with heavy use of agro-chemicals. Therefore, there is need for policy interventions to save agricultural land from unregulated competing uses and also to integrate environmental management best practices in County land use master plans.

Land use changes reflect the dynamic growth of a region driven by continuously evolving human activities. Semarang Regency, located in Central Java Province, is currently experiencing significant land use changes due to suburbanization, population growth, and increasing population density each year. This study aims to predict land use changes in Semarang Regency as a basis for identifying potential non-compliance with the RTRW, referring to the renewal of the RTRW before the end of its validity period.To analyze these changes, a spatial approach using Geographic Information System (GIS) and Remote Sensing is essential to map land use in 2013, 2018, and 2024. This analysis is further integrated with Cellular Automata (CA) modelling and logistic regression to identify factors influencing land use changes and to predict land use patterns in Semarang Regency through 2034. The study predicts that by 2034, built-up land will expand by 9.315,83 hectares, while agricultural land will increase by 9.054,79 hectares. Conversely, forest and conservation land are projected to decrease by 18.433 hectares, and water bodies will shrink by approximately by 53,94 hectares. The results of this prediction can be used as a reference in preparing spatial planning policies that are more adaptive and in line with field conditions.

Mapping Land Use Change to Analyze Urbanization and its Impact on Urban Floods in Tebessa City, Algeria.