Geographic Information System Research Articles

Land-cover-based indoor gamma-ray dose after a nuclear accident: location factor mapping via Monte Carlo simulation, GIS, and remote sensing.

The importance of Remote Sensing (RS) and Geographic Information Systems (GIS) comes from the fact that they are means that have been proven effective in supporting and developing the decision-making process in the field of urban control. The city of Mosul in Iraq has been subjected to a tremendous change in the dynamics of land use due to the wars. This study aims to use RS techniques and Artificial Intelligence Geographic Information Systems (AI GIS), as the study relies on Sentinel-2 images and online data sources to evaluate the changes that occurred in the natural environment by comparing the years during and after the destruction. Four classification methods were used in this study; Support Vector Machine (SVM) learning, Scene Classification technique (SC), Normalized Difference Vegetation Index (NDVI), and Normalized Difference Water Index (NDWI). High classifications accuracies were obtained ranging between (92%–97%). The residential area had decreased, followed by vegetation, which was converted to bare land by 64% in the year 2017 due to the war effect. In 2023 some recovery of settlement and increasing in other sectors was observed. The approach highlights the capability of spatial technologies and the role of RS and GIS in sustainable development.

Caves are recognized as biodiversity hotspots for groundwater fauna, including obligate groundwater-dwelling copepods (Crustacea: Copepoda), exhibiting high species richness, endemism, and phylogenetic rarity. However, the extent to which caves alone provide a representative estimate of copepod species richness in karst areas remains uncertain. Taking advantage of the recently published EGCop dataset, the first expert-validated, Europe-wide occurrence dataset for obligate groundwater-dwelling copepods (hereinafter, GW copepods), this study investigates the distribution of GW copepods into karst areas, comparing species richness in caves versus other karst groundwater habitats ( e.g. , springs, karst streams, artificial wells), within and among the European karst units. The main aims are: (i) identifying karst areas which represent hotpots of GW copepod species richness; (ii) assessing to which extent caves, as open windows to the subterranean environments, contribute to define hotspots of GW copepods’ species richness into karst areas across Europe. EGCop comprises 6,986 records from 588 copepod species/subspecies distributed among four orders: Cyclopoida (3,664 records, 184 species), Harpacticoida (3,288 records, 395 species), Calanoida (32 records, seven species), and Gelyelloida (two records, two species). To perform geospatial analyses, we filtered the dataset by: (i) selecting only the records with spatial uncertainty in the associated coordinates lower than 10 km; (ii) searching for those records falling within, or very close to, the polygons representing European karst areas. Species richness hotspots were then estimated through geospatial analyses in geographic information system (GIS) environment. Within the selected records, those specifically referring to karst habitats (2,526 records, 369 species) are primarily represented by Harpacticoida (1,199 records, 228 species) and Cyclopoida (1,293 records, 132 species). Among species collected from karst habitats, records from caves (1,867, 73.9%) belong to 318 species (Harpacticoida = 189, Cyclopoida = 122, Calanoida = 7), representing 86.1% of the total species richness of karst habitats. Geospatial analyses reveal that the European hotspots of GW copepods’ species richness recorded exclusively in caves reflect the spatial arrangement of postglacial refugia in southern karst regions, though representing a subset of the broader diversity found across all karst groundwater habitats. Our findings highlight that the contribution of cave systems in groundwater biodiversity assessments and related conservation planning may vary depending on the evolution and morphologies of the target karst regions—often pointing to a high representativeness of caves for subterranean biodiversity, sometimes revealing their lower explanatory power within the broader karst systems.

In recent years, Geographical Information Systems (GIS) and their associated databases have become essential tools in the management of water supply infrastructure. Their application in water utilities extends beyond public health protection and now plays a pivotal role in network operation, maintenance planning, and risk analysis. This study focuses on the integration of GIS tools, operational data, and failure records in the risk - based management of water distribution systems, with particular attention to minimizing disruptions in water supply to consumers. A fundamental requirement for reliable operation of a water supply system is detailed knowledge of its network structure, operating conditions, technical status, and historical data on system failures. Modern GIS platforms, especially when integrated with other digital tools such as SCADA systems, hydraulic models, and monitoring software, provide a robust framework for this. One of the most valuable GIS functionalities for both water suppliers and consumers is the systematic registration of failures in the water distribution network. Failure logs, compiled over several years, offer critical insights into the causes, frequency, and seasonality of breakdowns. These dataset s serve as the foundation for assessing infrastructure reliability and planning targeted maintenance interventions. This study presents an example of failure analysis conducted on a selected water supply network in Poland. The analysis highlights dominant failure causes and their temporal distribution. Using GIS - based numerical maps and failure databases, spatial distribution and intensity of pipe damage were evaluated. This facilitated the identification of high - risk areas and pipelines with elevated failure rates, which pose the greatest threat to continuous water supply. Risk mapping based on failure frequen cy and infrastructure condition supports decision - making in the allocation of repair resources and scheduling of rehabilitation works. This approach not only improves the effectiveness of maintenance teams but also reduces the risk of service interruptions. Moreover, the methodology is aligned with broader European policies such as the INSPIRE Directive, which promotes harmonized spatial data infrastructures as a basis for environmental and risk assessments. In an era where informatization drives operational efficiency, GIS and related information systems offer unmatched potential in the risk assessment and management of water distribution infrastructure. Their ability to process and visualize complex datasets transforms raw operational data into actionable intelligence. The outcome is a proactive maintenance strategy that enhances the resilience and security of water supply systems, ultimately ensuring uninterrupted service delivery to consumers.

Blast furnace slag is a byproduct of metallurgy, generated during the production of crude iron in blast furnaces. This materi al is often deposited in stockpiles, where it is essential to monitor its volume and weight for efficient utilization and environme ntal management. Accurate determination of the volume and tonnage of slag stockpiles enables optimized handling of this secondary material while minimizing environmental impacts. Modern methods of spatial data collection and analysis, such as GNSS (Global Navigation Satellite System) and GIS (Geographic Information Systems), provide effective tools for this purpose. This study focuses on evaluating the volumes and weight of two blast furnace slag stockpiles in PC Ladce, a.s. using GNSS measurements a nd GIS applications, specifically ArcMap and ArcScene. The measurements were conducted using the direct method of a GNSS point network with the S999 device. The collected data were subsequently processed into a triangulated and raster - based terrain model. Based on these models, the stockpile volumes and total slag weight were calculated using a bulk density of 1.14 t/m³. The res ults of this analysis highlight the significance of utilizing modern geodetic technologies for industrial management. GIS and GNSS methods enable more accurate quantification of stored materials and provide reliable data for industrial managers and environmental agencies. In addition to quantifying the volume and weight of the stockpiles, this study also generated visuali zation models and contour maps, aiding in better result interpretation and more efficient planning for future slag management. The findings of this study demonstrate that the use of GNSS and GIS is a reliable approach for accurately determining the volume and weight of blast furnace slag stockpiles, allowing for improved control over this material and its further processing.

Placed in a landscape of great beauty, Terra Nostra Garden has more than two centuries of history, a unique landscape architecture, a dense canopy, several botanical collections, and thermal waters. The garden is located at Furnas village, an active volcanic area of the Azorean Island of São Miguel. The increased number of visitors associated with the Terra Nostra Garden Hotel and the garden natural SPA, triggered the need of a Geographic Information System (GIS) to improve both park management and contents communication. This work aimed to add scientific and economical value to the historical Terra Nostra Garden through the implementation of a GIS. With this purpose we established the following specific objectives: describe the origin and evolution of Terra Nostra Garden, supported on published work, unpublished notes, and age determination in georeferenced tree specimens; implement a GIS linked to walking trails covering the maximum points of interest regarding: special specimens, botanical collections, historical constructions, and points of view; and select 121 plant specimens of interest to obtain the following information: height, diameter at breast heigh, canopy area, and phenology. The heart of Terra Nostra Garden has its origins in the 1786 summer house of Thomas Hickling. Trees’ age estimation enabled to link the sampled trees to different garden historical periods supporting an apparent pattern of plantation from West to East and from North to South explained by the land acquisitions made sequentially by the Viscount and his son the Marquis. The oral tradition referring the Quercus robur as the oldest tree, already present in Thomas Hickling Garden, was confirmed (255 years) by the Viscount Duarte Borges da Câmara Medeiros, as well the plantation of at least one Araucaria near the tank (Araucaria bidwillii). Besides Quercus robur, we linked two more specimens to the Thomas Hickling period. Araucaria heterophylla, a species introduced to Kew Gardens in 1793 by Joseph Banks, was planted in the early 1800s at Terra Nostra Garden by Thomas Hickling. Although the Ginkgo Lane has been designed between 1936/37 by Vasco Bensaude; an older specimen planted by the Marquises’ heirs already existed. This study allowed also to identify the tallest Araucaria heterophylla in Europe (world fourth place).

Abstract. Globalisation has accelerated the spread of invasive agricultural pests, including Popillia japonica Newman, introduced to Italy in 2014. This species has caused severe damage to vineyards, highlighting the need for efficient detection methods. Manual identification, though accurate, is time-consuming and labour-intensive. This study explores a computer vision (CV)-based approach using Near-Infrared (NIR) imagery captured by Uncrewed Aerial Systems (UAS) to detect adult Popillia specimens. Conducted in two vineyards in northern Italy, the project aims to develop a standardised and replicable monitoring protocol. CV-based detections are validated by entomologists and integrated into a Geographic Information System (GIS) to generate prescription maps for targeted drone-based pesticide application. However, traditional feature extraction and matching (FEM) algorithms, such as SIFT, SURF, and ORB, struggle in vineyard environments due to repetitive structures (seriality of fixed components, such as poles, supports, etc) and limited NIR texture. These limitations hinder image alignment, especially in the absence of geodetic-grade GNSS and high-precision IMU data. To address this, the study replaces FEM methods with deep image matching (DIM) techniques like SuperPoint and DISK for feature extraction, paired with SuperGlue for graph-based matching. Applied within a visual SLAM (vSLAM) framework, these deep learning models significantly improve image connectivity and alignment. Experimental results, supported by a fine-tuned SuperPoint model trained on vineyard datasets from the DANTE2 project, demonstrate up to 90% alignment improvement over conventional methods. This work presents a robust, scalable solution for accurate pest mapping in viticulture, contributing a fine-tuned PyTorch model to the scientific community.

Reducing social exclusion through technology is a key challenge for sustainable development, particularly within the context of accessible tourism. This study, as part of the “MOUNTAINS WITHOUT BARRIERS” project, addresses this issue by aiming to identify optimal locations for specialized all-terrain wheelchair rental stations in mountainous regions. The primary purpose is to ensure these locations are seamlessly integrated with existing local transport systems, fostering genuine accessibility. A dedicated methodology was developed to analyze the spatial integration of the accessible trail network with the transport system in the Beskid Agglomeration. The analysis, conducted using Geographic Information System (GIS) tools, considers access via both individual transport and public transport, with a clear emphasis on prioritizing the latter to promote sustainable mobility patterns. Applying this approach, the study identified potential station locations that are not only conveniently situated at trailheads but are also highly accessible via public transport. The main finding indicates that strategic placement can significantly minimize the necessity for private car usage. Integrating tourism infrastructure with public transport is crucial for increasing the real-world accessibility of mountain areas for people with disabilities. Furthermore, the results and methodology provide valuable recommendations that can serve as a practical input for Sustainable Urban Mobility Plans (SUMP).

Objective: Pediatric cancer, though less prevalent than adult malignancies, constitutes a significant public health concern due to its long-term effects on survival, development, and quality of life. This study aimed to investigate spatial patterns and temporal trends of pediatric cancer in Romania over a ten-year period (2008–2017), identifying persistent and emerging geographic hotspots using Geographic Information Systems (GIS)–based modelling and spatial statistics. Methods: A national pediatric cancer registry provided by the Ministry of Health was analyzed for cases among individuals aged 0–18 years, categorized by administrative-territorial units (ATUs), ICD-10 codes, sex, and year. Spatial indicators of persistence (recurrent prevalence across multiple years) and continuity (uninterrupted recurrence) were computed. Hotspot analysis was conducted using Local Moran’s I, and trend patterns were assessed through temporal modeling. Additionally, fractal and complexity metrics were applied to characterize the spatial structure and heterogeneity of cancer persistence and continuity across regions. Results: Although national pediatric cancer prevalence exhibited a modest decline from 3.57‰ in 2008 to 3.44‰ in 2017, GIS-based spatial modeling revealed stable high-risk clusters in Central and South-Eastern Romania, particularly in historically industrialized counties such as Hunedoara, Prahova, and Galați. These correspond to regions with past heavy industry and chemical pollution. Male children presented a higher frequency of malignant tumors (48,502 cases in males vs. 36,034 in females), while benign and uncertain-behavior neoplasms increased more prominently among females (from 3847 to 4116 cases, compared with 3141 to 3199 in males). Several rural localities showed unexpected prevalence spikes, potentially associated with socioeconomic deprivation, limited health literacy, and reduced access to pediatric oncology services. Regional disparities in diagnostic and reporting capacities were also evident. Conclusion: GIS-based spatial epidemiology proved effective in revealing localized, sex-specific, and persistent disparities in pediatric cancer across Romania. The integration of spatial indicators and complexity metrics into national cancer control programs could strengthen early detection, optimize resource allocation, and reduce health inequities. These findings highlight the value of combining geospatial analysis and fractal modeling to guide evidence-based public health strategies for pediatric oncology.

Abstract. Simultaneous Localization and Mapping (SLAM) has become a fundamental technology in various applications, including robotics, autonomous navigation, geographic information systems (GIS), and infrastructure inspection. This paper presents a new version of GuPho, a low-cost, lightweight, and portable visual SLAM-based system equipped with AI-driven capabilities for real-time mapping, object detection, and defect analysis. The system integrates stereo vision and deep learning (DL) methods to enhance spatial understanding and enable accurate real-time scene interpretation. In particular, we explore DL-based semantic segmentation, monocular depth estimation (MDE), and stereo depth estimation to improve 3D reconstruction and size measurement of cracks for infrastructure monitoring. We implement state-of-the-art neural networks, including RF-DETR and YOLO for real-time crack and windows segmentation and Depth Anything V2, Depth Pro, and Unimatch for depth estimation. Our results demonstrate the potential of GuPho as an affordable and efficient system for real-time mobile mapping and defect assessment. The real-time and AI capabilities of our in-house solution are showcased here: https://youtu.be/ATIwn4zOSFw

Abstract. The True Digital Orthophoto Map (TDOM) possesses both map geometric accuracy and image characteristics, serving as an essential product for digital twins and Geographic Information Systems (GIS). Traditional TDOM generation methods typically involve a series of intricate geometric processing steps, which often result in computational inefficiency, high costs, and error accumulation. More recently, 3DGS-based methods were developed to generate TDOM in more efficient manner, yet they show some degenerated rendering performance on sparse view scenarios, which is naturally common when dealing with boundary area of photogrammetric UAV images. To address the above issues, we introduce a hybrid method that integrates 3DGS with Few-Shot Gaussian Splatting (FSGS, Zhu et al. (2024)). Specifically, our method first partitions the UAV images into dense and sparse view scenarios based on image overlapping degree. Then, two specific 3DGS training solutions are employed: in dense-view scenarios, the standard 3DGS optimization is applied, in sparse-view scenarios, the FSGS framework is adopted, which incorporates a proximity-guided Gaussian unpooling strategy and monocular depth supervision, thereby enhancing adaptive density control and geometric guidance through improved constraints on Gaussians. Third, two trained Gaussians are merged. Finally, by substituting the perspective projection with the orthogonal projection, our method directly generates TDOM while eliminating the requirement for explicit Digital Surface Model (DSM) and occlusion detection. Extensive experimental results demonstrate that our method outperforms existing commercial software in several aspects while achieving superior orthophoto quality compared to 3DGS in sparse-view scenarios. Project Web: https://walterwang2024.github.io/HyGS-TDOM/

Monitoring greenhouse gas emissions, such as methane (CH₄), carbon dioxide (CO₂) or nitrous oxide (N₂O), is an important element of climate policy and environmental engineering. This paper presents the concept and initial validation of a mobile measurement system based on an unmanned aerial vehicle (UAV) equipped with a FLIR GF77 or Gx620 thermal imaging camera. The system enables remote, non - contact detection and quantitative analysis of gas emissions in agricultural and urbanized environments. The aim of the study was to assess the possibility of using infrared imaging methods to visualize and analyze greenhouse gas emissions in real time. The methodology includes recording video recordings in the thermal range from the UAV, and then analyzing the recorded data in the MATLAB environment. Techniques such as thermal image segmentation, optical flow analysis to determine the direction and speed of gas cloud movement, and data conversion into volumetric units were used. The UAV system additionally integrates GP S modules and laser rangefinders, which allows for precise spatial mapping of emissions. Thermal imaging data is saved locally on SD cards. The obtained results confirm the possibility of effective detection of gas emissions with high spatial resolution. T he recorded data enables integration with geographic information systems (GIS), which allows for the creation of dynamic emission maps.

Landslides have become increasingly frequent and destructive in Uttarakhand, leading to substantial loss of life and significant damage to infrastructure. This research focuses on generating a detailed landslide susceptibility map for a selected area in Chamoli district, Uttarakhand, by integrating remote sensing and geographical information system (GIS) techniques. Twelve critical factors influencing landslide occurrence, such as slope, aspect, vegetation cover, proximity to geological structures, distance from roads, elevation, curvature, topographic wetness index (TWI), stream power index (SPI), drainage proximity, and lithology, were considered. The Statistical Information Value Model (SIVM) was used to assess the contribution (weight) of each factor class toward landslide occurrence. These derived weights were then integrated using a weighted overlay method to produce the final landslide susceptibility map. The predictive accuracy of the model was validated through receiver operating characteristic (ROC) analysis, achieving an area under the curve (AUC) value of 0.72. The results demonstrate that the SIVM-based weighted overlay approach provides a reliable tool for identifying landslide-prone zones, offering valuable insights for land use planning and disaster mitigation.

Zacatecas is a Mexican state from where there are few studies about biodiversity, venomous ophidians and people's experience of snakebites. In the state, there are 12 species of venomous snakes distributed in three genera: Crotalus, Micruroides and Micrurus, which could represent some risk for the locals. The objective of this study was to make use of Geographic Information Systems (GIS) and programming to determine the relationship between population variables and the number of snakebites registered by the Zacatecas Health Services (SSZ) from 2007 to 2017 at the municipal level. Climatic, social and biological variables were used to gain a better understanding of the situation. It was found that men working in livestock breeding, agriculture, subsistence hunting or mining are more vulnerable, especially if older than 65. The municipalities of Concepción del Oro, Villa de Cos, El Plateado de Joaquín Amaro, Loreto and Ojocaliente exhibit the highest risk, while special monitoring must be conducted in Guadalupe, Fresnillo and Zacatecas due to their high population density, as well as in Valparaíso on account of its rich venomous ophidian fauna. Additionally, it is suggested to carry out preventive actions and detailed data gathering about snakebites to guarantee information quality. This study constitutes the first formal, detailed work about the epidemiological panorama of envenoming caused by the bite of a snake (ophidiotoxicosis) in Zacatecas from which further investigation and modelling may derive.

This study analyzes the available solar resource in the community of San Francisco de Paján, with the purpose of assessing its applicability in renewable energy projects, particularly community-based photovoltaic systems. For this purpose, historical data on solar irradiation, cloud cover, and temperature (2010–2024) were collected from the NASA POWER platform. The information was subjected to quality control and subsequently analyzed using statistical methods and time series models, complemented with geographic information system tools. The results show that the average daily global irradiation in the community ranges between 3.3 and 3.85 kWh/m²·day, with seasonal peaks in March and April exceeding 4.0 kWh/m²·day. The linear trend analysis indicates a progressive decrease of 0.01804 kWh/m²·day per year, implying a moderate reduction towards 2050, with projected values between 3.2 and 3.3 kWh/m²·day. Nevertheless, these levels remain technically viable for the implementation of small- and medium-scale photovoltaic systems.

The morphometric analysis of a river basin provides critical insights into its hydrological and geomorphological characteristics, essential for effective watershed management and planning. This study presents a detailed morphometric analysis of the Gostani River Basin using Remote Sensing (RS) and Geographic Information System (GIS) techniques. High-resolution satellite imagery and topographic data, including Digital Elevation Models (DEMs), were utilized to extract drainage networks and basin boundaries. Key linear, areal, and relief morphometric parameters such as stream order, bifurcation ratio, drainage density, stream frequency, elongation ratio, and relief ratio were computed using GIS tools. The results reveal that the Gostani River Basin exhibits dendritic drainage patterns, moderate drainage density, and a sub-mature stage of geomorphic development, indicating semi-permeable sub-surface material and moderate to low relief. The analysis highlights the usefulness of RS and GIS in deriving accurate and comprehensive morphometric parameters, facilitating better understanding of basin dynamics for sustainable water resource management and environmental planning.

Abstract. This research presents a scalable, cloud-based workflow integrating Machine Learning (ML) and 3D Geographic Information Systems (GIS) to support the automated detection of architectural elements and urban management. Via Unmanned Aerial Vehicle (UAV) georeferenced images, the system enables an automated and scheduled detection, geolocation, and import of architectural elements (e.g., domes, photovoltaics panels, tanks) data and metadata into a 3D GIS environment. A validated urban case study was conducted using UAV-acquired georeferenced images processed through a Structure-from-Motion (SfM) pipeline. Orthoimage chunks and dataset were uploaded to Google Cloud Storage, triggering an event-driven architecture built on a Cloud Computing Infrastructure. The pipeline leverages Vertex AI object detection via AutoML, the predictions of which are subsequently enriched with geospatial metadata. The output data is stored in BigQuery and Cloud Storage for urban GIS integration and analysis. Results confirm the viability of the pipeline for repeatable, and automated urban monitoring, reducing manual labour and improving safety for building maintenance workers. This approach is focused on the use of mobile mapping data processing, 3D reconstruction of urban areas, AI process for detection and urban maintenance and to develop smart city applications.

Abstract Three-dimensional modelling of buildings requires reliable data sources and sophisticated tools capable of delivering exhaustive models that can facilitate property management. The authors devised a methodology for 3D building modelling using only open-access geospatial databases like Light detection and ranging (LiDAR) scanning, map and photogrammetry resources, and the relevant publicly available land and topography databases. The models integrate building geometry and detailed object information, which makes them versatile tools for property valuation, management, and structural health monitoring. The study brings together Building Information Modeling (BIM) and Geographic Information Systems (GIS) tools that can integrate spatial data and build precise models with details of critical parts of buildings, such as roofs, walls, window and door openings, balconies, terraces, hard infrastructure, and other structural and fit-out components. The methodology’s performance and versatility were verified on single-family residential buildings in Kraków (Poland). The results have confirmed that the constructive collaboration of open-access geospatial data, GIS, and BIM yields high-grade 3D models for structural health monitoring, action planning, and building life cycle management. This approach leads to effective property (resources) management and streamlines planning and taking actions over the life cycle.

Cross-border malaria control programs have become indispensable components of regional and global health strategies aimed at achieving malaria elimination. These initiatives emphasize cooperation among countries sharing porous borders where human mobility, environmental factors, and socioeconomic disparities facilitate sustained transmission. The Global Fund to Fight AIDS, Tuberculosis and Malaria, established in 2002, remains the principal funding mechanism supporting these efforts, having disbursed over US$21.7 billion to more than 150 countries. Recent innovations, particularly Geographic Information Systems (GIS), mobile health (m-health) applications, and decision-support systems are revolutionizing the detection, monitoring, and control of malaria in endemic regions. GIS technology facilitates spatial mapping, vector surveillance, and environmental modeling, allowing for evidence-based decision-making in malaria control programs across Africa, Asia, and Latin America. Likewise, m-health applications enable timely reporting, real-time case management, and improved coordination among health workers, particularly in remote and border communities. Community engagement and education remain central to malaria elimination success, fostering local ownership and compliance with preventive interventions such as indoor residual spraying (IRS), insecticide-treated nets (ITNs), and early diagnosis initiatives. Furthermore, monitoring and evaluation frameworks have evolved to capture dynamic indicators beyond morbidity and mortality, focusing instead on transmission foci, parasitological confirmation, and imported case tracking. However, challenges persist in sustaining funding, harmonizing policies, and ensuring cross-border coordination. The future of malaria control depends on integrating sustainable practices, strengthening research and development, and mobilizing domestic political will to complement international support. Effective cross-border malaria control will require adaptive policy mechanisms, regional data-sharing platforms, and sustained commitment to innovation, ultimately driving the global malaria eradication agenda toward 2030. KEYWORDS: Cross-Border Malaria Control, Geographic Information Systems (GIS), Global Fund, Mobile Health (m-Health) Innovations, and Regional Health Collaboration.

Soil erosion is a major environmental challenge in Mediterranean regions, where climatic variability, steep slopes, and human activities accelerate land degradation. In the north-central region of Algeria, the Mitidja Plain faces increasing erosion pressure, threatening biodiversity, agricultural productivity, and long-term soil sustainability. This study aims to assess soil erosion risk by integrating the Revised Universal Soil Loss Equation (RUSLE), the Analytical Hierarchy Process (AHP), and Geographic Information System (GIS) techniques within a Cloud-Based Geospatial (CBG) framework using the Google Earth Engine (GEE) platform. High-resolution datasets on rainfall, topography, soil properties, and land cover were processed in GEE to derive five RUSLE factors: rainfall runoff erosivity (RE), soil erodibility (KS), slope length steepness (LS), cropping management (CM), and management practices (PC). The analysis revealed that 41% of the Mitidja Plain is at severe erosion risk, with an average soil loss of 88.72 t ha⁻¹ yr⁻¹ and a maximum of 161.13 t ha⁻¹ yr⁻¹. Erosion hotspots correspond to areas where slopes exceed 22°, vegetation cover is sparse, and rainfall intensity is high. The AHP-weighted integration achieved strong predictive accuracy (AUC = 0.87), identifying slope characteristics as the most influential factor (weight = 0.292). Forested areas reduced erosion risk in 30% of the region, while unprotected mountainous zones covering 22% of the study area require urgent intervention. These findings demonstrate the effectiveness of CBG-enhanced modeling for mapping priority conservation areas. Recommendations include terracing, check dams, vegetation restoration, and adaptive agricultural practices to reduce soil loss, particularly in agricultural lands with moderate to high vulnerability (48% of the plain). The methodology provides a replicable framework for other Mediterranean regions facing similar erosion pressures, offering robust spatial data to guide soil management and conservation planning.