https://ijg.journals.publicknowledgeproject.org/index.php/journal/issue/feed International Journal of Geoinformatics 2026-10-31T04:48:00+00:00 Prof. Nitin Kumar Tripathi editor@e-geoinfo.com Open Journal Systems <p><strong>Aim &amp; Scope</strong></p> <p>ISSN 2673-0014 (Online) | ISSN 1686-6576 (Printed)</p> <p><strong>International Journal of Geoinformatics</strong> aims at publishing scientific and technical developments in the diverse field of Geoinformatics encompassing Remote Sensing, Photogrammetry, Geographic Information Systems, and Global Positioning Systems. Papers dealing with innovations in theoretical, experimental, and system design aspects are welcome. Routine applications without significant findings will not be considered.</p> <p>The International Journal of Geoinformatics is an <strong>open-access</strong> publication that offers free and unrestricted access to its content, enabling anyone to read, download, copy, and distribute the published research articles under the Creative Commons Attribution License (CC-BY).</p> <p>Under the <strong>CC-BY license</strong>, users are permitted to copy, adapt, and redistribute the work, as long as they provide appropriate attribution to the original author or source.</p> <p><strong><em>International Journal of Geoinformatics </em></strong>is a peer reviewed journal in the field of Remote Sensing, Geographic Information Systems (GIS), Photogrammetry, and Global Positioning Systems (GPS). It publishes papers in the application of RS/GIS/GPS in various fields: environment, health, disaster, agriculture, planning, development, business etc. It has an International Editorial Board and a panel of Peer Reviewers to ensure the quality of research papers. This will enhance citations and H-Index. International Journal of Geoinformatics is indexed by prestigious indexing services such as <strong>SCOPUS, EBSCO, British Library, Google Scholar, Geoscience Australia, etc</strong>. We are trying for more indexing services to include IJG.</p> <p><strong>International Journal of Geoinformatics</strong> has been published in two formats, as printed version ISSN 1686-6576 and electronic version ISSN 2673-0014. The first printed edition has been published in 2005 and now year 12 and also electronic version has been published in Vol. 1, No. 1, March 2005. In 2014, IJG published both 4 issues (March, June, September, and December) in <strong>hardcopy and online</strong>. The online version is enhancing the citations and is also found easy to access by the reader.</p> <p>Since 2021, IJG published only online version but the number of issue are increased to 6 issues (February, April, June, August, October, and December).</p> <p>Since 2023, the <strong>monthly issues</strong> of the online version of IJG have been published.</p> <p>Open Access old issues (2005 - 2012) can be viewed here: <a href="https://creativecity.gscc.osaka-cu.ac.jp/IJG/issue/archive">https://creativecity.gscc.osaka-cu.ac.jp/IJG/issue/archive</a></p> <p> </p> <p> </p> https://ijg.journals.publicknowledgeproject.org/index.php/journal/article/view/5233 GIS-AHP-Based Landslide Susceptibility Assessment of the Bradost Anticline, Northern Iraq 2026-10-30T23:59:16+00:00 O.A. Ismaeel rayan.ghazi@uomosul.edu.iq A.S. Al-Jawadi rayan.ghazi@uomosul.edu.iq H. Gh. M. Adeeb rayan.ghazi@uomosul.edu.iq R. Gh Thannoun rayan.ghazi@uomosul.edu.iq <p><em>The use of landslide susceptibility assessment is a vital step for sustainable land-use planning and risk mitigation, especially in mountainous areas and in complex tectonic and geomorphological environments. The present study aims to assess the landslide susceptibility in the Bradost Anticline through an integrated Geographic Information System (GIS) and Analytic Hierarchy Process (AHP) approach. The following 10 conditioning factors were considered: geology, lineament density, slope, elevation, stream density, gully density, slope curvature, topographic wetness index, normalized difference vegetation index, land use/land cover. All the factors were treated, standardized and visualised as thematic GIS layers. The AHP was then applied to normalize the weights and weighted layers were combined to create a landslide susceptibility map. Very high, high and moderate stability zones cover 11.36%, 25.05% and 29.87% of the area, respectively. The low and very-low-stability areas constitute 23.05% and 10.67%, respectively, showing high or very high landslide susceptibility (33.72%) in the study area. The highest weights were recalculated for geology, lineament density, and slope (0.190, 0.188, and 0.179, respectively). An overall accuracy of 83.06%, a kappa coefficient of 0.787, and an area under the ROC curve of 0.894 were used to validate the model. These outcomes show high level of agreement with the observations in the field and high level of discriminatory performance. The framework can be used as a regional screening basis for landslide mitigation, land-use planning and infrastructure protection in vulnerable mountainous terrain.</em></p> 2026-10-31T00:00:00+00:00 Copyright (c) 2026 https://ijg.journals.publicknowledgeproject.org/index.php/journal/article/view/5244 Historical Analysis and Future Projections of Meteorological Drought in Northeast Thailand Using Statistically Downscaled Climate Models 2026-10-31T04:48:00+00:00 Z.N. Qaisrani engr.zbaloch@gmail.com J. Som-ard jaturong.s@msu.ac.th S.R. Suwanlee savittri.s@msu.ac.th N. Nuthammachot narissara.n@psu.ac.th S. Ninsawat sarawutn@ait.ac.th k. Siripattanachotikul kritsada.c@msu.ac.th <p><em>Drought is a reoccurring meteorological hazard that seriously affects agricultural production, water resources and the livelihoods of rural people. The current study investigates the past, observed drought conditions as well as future climate change scenario in Northeast Thailand by combining historical meteorological observations, satellite-derived precipitation datasets, and statistically downscaled Global Climate Model (GCM) outputs. The SPI based on fitting the Gamma-distribution and through probability-of-normal transformation was employed in 12-month periods to describe drought severity and duration from 1994 to 2023. Future scenarios were projected using CanESM2 (CMIP5) and CanESM5 (CMIP6) under RCP4.5 and RCP8.5 emission pathways for mid-century (2041–2070) and late-century (2071–2100) periods. The accuracy of the climate projections was improved through bias correction via Quantile Mapping (QM) and empirical downscaling with Multiple Linear Regression (MLR), with calibration and validation of the models undertaken through a split sampling approach (70% calibration and 30% validation) over the baseline period (1994-2023). Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS) rainfall datasets were incorporated primarily to fill gaps and extend the temporal continuity of station records. However, CHIRPS-based spatial maps were not produced, as the study focused on temporal drought patterns. The performance evaluation showed notable improvements, with R² values over 0.70 for precipitation and over 0.85 for temperature, along with RMSE reductions of 25 to 40% across representative stations. Historical analysis revealed an increase in the occurrence and intensity of events droughts at representative stations like Nongkai, Khon Kaen, and Ubon Ratchathani. In addition, RCP8.5 projections have depicted a growth in the number of extreme events where SPI values have fallen below -1.5 and their frequency is foreseen to double by 2100. The results demonstrate that satellite-derived precipitation datasets combined with statistically downscaled climate models can support regional drought assessment based on representative stations. Moreover, the results reflect a pressing need for water management, early warning systems, and climate-resilient crops. This work supports the National Adaptation Plan of Thailand and regional drought mitigation strategies with respect to evolving climatic conditions.</em></p> 2026-10-31T00:00:00+00:00 Copyright (c) 2026 https://ijg.journals.publicknowledgeproject.org/index.php/journal/article/view/5234 A Deep Learning Framework for Personalized Land Parcel Recommendation: Integrating TF-IDF User Profiling with Spatial Analytics 2026-10-31T00:07:22+00:00 U. W. Deviantari udianadeviantari@its.ac.id T. Aditya triasaditya@ugm.ac.id P. N. Djojomartono prinug@ugm.ac.id <p><em>Selecting land parcels for purchase or development requires the evaluation of multiple spatial, economic, and user-specific factors. Existing recommender systems in property and spatial decision-support domains commonly rely on collaborative filtering or conventional content-based approaches. However, these methods are often limited in land administration contexts, where transaction records are sparse, parcel characteristics are heterogeneous, and user preferences are context-dependent. To address this limitation, this study proposes an AI-driven land parcel recommendation framework based on a Feature-based Multi-Criteria Recommendation System (FMCRS), integrating user-profile information with spatial and economic land attributes. User identity and professional affiliation were transformed into numerical features using Term Frequency–Inverse Document Frequency (TF-IDF), while land attributes included road width, zoning classification, distance to the central business district (CBD), and predicted land value. The framework was evaluated using data from land valuation professionals in Surabaya City by comparing Ordinary Least Squares (OLS) and Deep Neural Network (DNN) models. The DNN model achieved better predictive performance than OLS, with an R² of 0.92 and a MAPE of 4% on the training dataset, as well as slightly higher testing performance. These results indicate that the proposed framework can better capture non-linear relationships between user profiles and spatial land attributes. Overall, this approach is relevant for supporting personalized, spatially informed, and data-driven land parcel recommendation in complex urban environments with limited historical interaction data.</em></p> 2026-10-31T00:00:00+00:00 Copyright (c) 2026 https://ijg.journals.publicknowledgeproject.org/index.php/journal/article/view/5235 Systematic Review of Sentinel-5P Nitrogen Dioxide (NO₂) Validation and Surface Estimation Methods (2018–2025): Implications and Perspectives for Indonesia 2026-10-31T00:13:20+00:00 A.O. Setiowati ana.setiowati@bmkg.go.id S. Pok psophak@rua.edu.kh L.M. Jaelani lmjaelani@its.ac.id <p><em>This review examines validation and conversion of Sentinel-5P TROPOMI column data to near-surface concentrations, focusing on NO₂ and contextualizing CO, SO₂, O₃, and HCHO from 2018–2025. Following PRISMA guidelines, a three-stage Scopus search identified 1,022 studies, narrowed to 150 validation-focused studies. Studies were included if they (i) converted TROPOMI vertical column density to surface concentration and (ii) reported at least one quantitative metric (R², RMSE, MAE, or correlation) against ground observations. After full-text assessment, 15 met both criteria. A single reviewer conducted screening and extraction, a limitation. Extracted fields included conversion method, algorithm, reference type, region, and performance metrics. Bibliometric mapping showed a shift toward machine learning in 2023–2024, alongside a Global North–Global South disparity and limited research in maritime continental regions. In this predominantly mid-latitude corpus, Random Forest, XGBoost, neural networks, and deep learning were most common and generally agreed more strongly with ground observations than direct column–surface correlations or chemical-transport-model scaling. However, no head-to-head comparisons on identical datasets existed, so this advantage is context-dependent. On held-out data, deep learning achieved validation R² of 0.914–0.919 across three annual UK test sets; Random Forest achieved R² = 0.875 (training R² = 0.949) in China’s Fenwei Plain; and XGBoost achieved pan-European test-set MAE of 7.77 µg/m³. Metrics represent validation/test performance unless noted otherwise. NO₂ dominates global validation, while evidence for CO, SO₂, and O₃ remains limited, particularly in tropical, cloudy regions with sparse monitoring. None of the 15 studies addressed the tropics or provides direct evidence for the Maritime Continent. In Indonesia, the critical bottleneck is the absence of Pandora or MAX-DOAS reference spectrometers. Installation in Jakarta and Surabaya should be prioritized, followed by staged NO₂, CO, and volcanic SO₂ estimation workflows adapted to tropical monsoon conditions.</em></p> 2026-10-31T00:00:00+00:00 Copyright (c) 2026 https://ijg.journals.publicknowledgeproject.org/index.php/journal/article/view/5236 Geospatially Grounded Satellite Image Captioning with Improved Factual Consistency using Directional Scene Graphs and Large Language Models: An Automated Pipeline for Semantic Summarization of Satellite Images 2026-10-31T00:16:57+00:00 S. Patil suchitrapatil@somaiya.edu N. More neelkamalsurve@somaiya.edu N. Mohite nikhil.mohitel@somaiya.edu <p><em>Remote sensing image captioning has recently attracted significant attention for automated interpretation of satellite imagery; however, existing approaches often rely primarily on visual features and insufficiently model explicit geospatial relationships, resulting in factually inconsistent descriptions and limited spatial reasoning. To address this limitation, this paper proposes an automated end-to-end framework for geospatially grounded semantic summarization of remote sensing images by integrating object detection, geographic coordinate transformation, directional spatial reasoning, and large language models (LLMs). The proposed framework uses the YOLOv11 object detector on the DIOR dataset to identify objects and then the affine transformation is applied to convert pixel-level bounding boxes into WGS-84 geographic coordinates. A novel Directional Spatial Relationship Graph (DSRG) is then constructed to model adjacency, density-based clustering, transportation proximity, and object importance, thereby capturing both geometric and functional relationships among detected objects. The extracted spatial knowledge is organized using a Grounded Prompt Framework (GPF), which constrains LLMs to generate geographically grounded summaries based exclusively on detected objects and their spatial context. The framework is evaluated using object detection metrics (Precision, Recall, mAP), Geographic Intersection-over-Union (Geo-IoU), graph statistics, grounding score, hallucination rate, ROUGE, and BERTScore. Experimental results demonstrate that the proposed YOLOv11 model achieves a Precision of 0.893, Recall of 0.784, mAP@0.5 of 0.854, and mean Geo-IoU of 0.8685. The comparative analysis of different evaluated language models showed that the structured prompting strategy substantially improves factual consistency, with Gemini 2.5 Flash achieving a hallucination rate of 1.6% at the same time maintaining competitive grounding performance. A DIOR dataset does not provide real georeferenced object annotations; geospatial consistency is evaluated using synthetic reference polygons. It represented a current limitation of the study. Overall, the proposed DSRG–GPF framework provides an effective approach for generating geospatially grounded and factually consistent semantic summaries of remote sensing imagery, supporting applications in geospatial intelligence, infrastructure monitoring, and GIS-based decision-making.</em></p> 2026-10-31T00:00:00+00:00 Copyright (c) 2026 https://ijg.journals.publicknowledgeproject.org/index.php/journal/article/view/5237 Accuracy and Uncertainty Assessment of Spatial Interpolation Methods for Reservoir Bathymetric Modelling 2026-10-31T00:24:45+00:00 K. Khasanov kh.khasanov@outlook.com M. Bakiev kh.khasanov@outlook.com S. Djabbarova kh.khasanov@outlook.com D. Norboeva kh.khasanov@outlook.com O. Vafoeva kh.khasanov@outlook.com K. Rakhmatilloyeva kh.khasanov@outlook.com G. Mulladjanova kh.khasanov@outlook.com <p><em>Accurate estimates of reservoir storage and long-term capacity loss are essential for reliable operation, sediment-management planning, and risk-informed decision making. However, bathymetric point surveys are irregularly distributed, and the reconstruction of the submerged surface introduces interpolation uncertainty that propagates into stage–storage curves and capacity-loss estimates. This study investigates the influence of spatial interpolation uncertainty on reservoir capacity-loss estimates and evaluates long-term sedimentation by comparing reservoir-bed conditions in 1987 and 2023 using Kamashi Reservoir (Uzbekistan) as a case study. Historical reservoir-bed conditions were reconstructed from digitized and georeferenced engineering topographic maps prepared in 1987, while the 2023 reservoir bed was modelled using bathymetric survey data. Five surface modelling approaches Inverse Distance Weighting (IDW), Radial Basis Functions (RBF), Ordinary Kriging (OK), Universal Kriging (UK), and Empirical Bayesian Kriging (EBK) were calibrated under a unified grid, extent, and neighbourhood design and assessed using leave-one-out cross-validation (LOOCV). Uncertainty was propagated via residual-bootstrap Monte Carlo simulation (10,000 realizations per method), and differences among methods were tested using ANOVA and Tukey’s HSD (p &lt; 0.001). EBK provided the most robust performance (RMSE = 0.569 m; R<sup>2</sup> = 0.9806), while OK minimized MAE (0.32 m); both showed near-zero bias. Comparison of the reconstructed reservoir-bed surfaces from 1987 and 2023 revealed substantial sediment accumulation and morphological changes within the reservoir basin. Updated elevation–volume relationships derived from the reliability-ranked EBK model indicate a total capacity loss of approximately 7.7 Mm³ (30.8%) since 1987 and near-complete infilling of dead storage (~97.5%). DEM-of-Difference (DoD) analysis revealed spatially heterogeneous sedimentation, with deposition reaching +8.26 m and localized erosion of up to −1.20 m. The proposed workflow provides practical quality control for bathymetric modelling and supports reliable assessment of reservoir sedimentation and capacity loss. The results can assist operational reservoir management and provide a scientific basis for planning sediment-removal and dredging activities.</em></p> 2026-10-31T00:00:00+00:00 Copyright (c) 2026 https://ijg.journals.publicknowledgeproject.org/index.php/journal/article/view/5238 Satellite and Reanalysis-Based Estimation of Surface PM2.5 Concentrations Using Bayesian Averaging and Random Forest Models 2026-10-31T00:29:27+00:00 T. A. Tran antt@tdmu.edu.vn T. K. Le antt@tdmu.edu.vn T. L. Nguyen antt@tdmu.edu.vn H. A. C. Thai antt@tdmu.edu.vn <p><em>Air pollution characterized by elevated fine particulate matter (PM₂.₅) is a critical environmental and public health challenge in rapidly industrializing regions where ground-based monitoring networks remain sparse. This study evaluates and compares two predictive models - a probabilistic linear ensemble via Bayesian Model Averaging (BMA) and a non-parametric machine learning algorithm using Random Forest (RF) - to estimate surface PM₂.₅ concentrations across Binh Duong province, located in the North of Ho Chi Minh City, Vietnam during the dry seasons of 2024 - 2025. The models integrate multi-source satellite observations, including MODIS Aerosol Optical Depth (AOD), Sentinel-5P TROPOMI tropospheric pollutants (NO₂, SO₂, and CO), and ERA5 meteorological reanalysis variables. Model parameters and predictive robustness were optimized and evaluated using repeated 5-fold cross-validation. The cross-validation results revealed that the Random Forest model outperformed the BMA model, achieving an R² of 0.703, MAE of 4.594 ± 0.48 µg/m³, RMSE of 5.608 ± 0.62 µg/m³, and MAPE of 39.621%. In comparison, the BMA model yielded a validation R² of 0.626, MAE of 4.839 µg/m³, RMSE of 5.992 µg/m³, and MAPE of 40.852%. The moderate MAPE values (~40%) indicate that while the framework is not suitable for strict regulatory compliance enforcement, it serves as an effective screening and spatial assessment tool. Satellite-derived surface maps successfully reproduced regional spatial gradients, highlighting pronounced PM₂.₅ concentrations in southern industrial corridors (Di An, Thuan An, and Thu Dau Mot) contrasting with lower levels in northern rural districts. These findings demonstrate the practical utility of integrating satellite remote sensing with machine learning for dry-season air quality screening and environmental management in data-limited developing regions.</em></p> 2026-10-31T00:00:00+00:00 Copyright (c) 2026 https://ijg.journals.publicknowledgeproject.org/index.php/journal/article/view/5239 Evaluating Shoreline Prediction Models Using Satellite Imagery and Open-Source Tools 2026-10-31T00:32:49+00:00 J. Thomas sw23079s@st.omu.ac.jp⃰ T. Nemoto sw23079s@st.omu.ac.jp⃰ S. Dhar sw23079s@st.omu.ac.jp⃰ V. Raghavan sw23079s@st.omu.ac.jp⃰ <p>This study integrates open-source satellite-based shoreline extraction and statistical shoreline-change analysis to evaluate tidal correction and prediction ability in two contrasting coastal settings. Shoreline change is assessed using CoastSat-derived shorelines and AMBUR (Analyzing Moving Boundary Using R)-based rate modeling at Texas, United States of America and Ishikawa, Japan. Publicly available Sentinel‑2, Landsat, and high-resolution elevation datasets (NOAA (National Oceanic and Atmospheric Administration) lidar, GSI (Geospatial Information Authority of Japan) DEM, and SDB (Satellite Derived Bathymetry)) are combined with hourly or model tide records to extract, tidally correct, and analyze multi-decadal shoreline positions. Validation at San Jose Island compares tidally corrected Sentinel‑2 shorelines with 1 m NOAA lidar shorelines in terms of baseline distance, beach slope, and shoreline elevation. The CoastSat shoreline reproduces the lidar-derived planform with a distance RMSE of 14.26 m and 80% of transects within the low‑error band; slope and elevation comparisons yield RMSE values of 3.83° and 1.05 meters, with over 78% and 85% of transects, respectively, falling within corresponding low‑error thresholds. For Wajima, three different geostatistical methods were used to analyze historical Landsat shorelines from 1987 to 2014. Using 28 years of shoreline data, the 2023 pre-earthquake shoreline was extrapolated with an average error of 8.19 to 10.73 meters. The 2024 post-earthquake shoreline prediction showed errors exceeding 50 meters in MAE. Thus, when sudden shifts reshape coastlines, these trend methods fall short. Still, comparing the predicted 2023 shoreline with the observed 2024 shoreline, researchers found a coastline advance of roughly 150 to 200 meters, matching separate radar-based estimates along the Noto Peninsula. This study shows the combined CoastSat–AMBUR workflow to provides a framework for shoreline extraction, tidal correction validation, and future shoreline extrapolation and the application of CoastSat and AMBUR for before and after an earthquake.</p> 2026-10-31T00:00:00+00:00 Copyright (c) 2026 https://ijg.journals.publicknowledgeproject.org/index.php/journal/article/view/5240 An Object-Oriented Graphic Library for Independent Cadastral Mapping Software Development 2026-10-31T00:35:06+00:00 T. P. Huynh phamthehuynh@humg.edu.vn <p><em>Cadastral mapping applications in Vietnam have traditionally relied on commercial graphic platforms such as AutoCAD and MicroStation for core graphic processing and application development. While these platforms provide mature graphic and extension capabilities, there remains a need to investigate independent software architectures tailored to cadastral-specific graphic and topology requirements. This study aims to design and functionally validate an object-oriented graphic library as a core software component for specialized cadastral mapping application development. A design-and-development approach was adopted, comprising cadastral requirement analysis, review of selected CAD graphic platforms, design of a layered object-oriented architecture, integration of established geometric and topological processing techniques, and prototype implementation. The proposed library integrates fundamental graphic entities, including points, lines, polylines, circles, arcs, text, and blocks, with cadastral-specific classes such as parcels, parcel labels, and map frames. Functional validation of the prototype covered graphic-object management, DXF data exchange, topology processing, parcel-region generation, cadastral map-frame generation, and cadastral annotation. The results show that these components could be integrated and executed within the prototype and produced the intended functional outputs. These findings provide proof-of-concept evidence for the functional feasibility of organizing fundamental graphic processing, cadastral-specific objects, and topology-processing functions within an independent object-oriented core library. The contribution of the study is therefore primarily architectural and implementation-oriented rather than the development of new geometric algorithms or a new cadastral information model. Further evaluation using large-scale cadastral datasets, quantitative performance metrics, professional user assessment, and interoperability with contemporary land-administration and geospatial standards is required to establish the scalability and practical applicability of the proposed architecture</em></p> 2026-10-31T00:00:00+00:00 Copyright (c) 2026 https://ijg.journals.publicknowledgeproject.org/index.php/journal/article/view/5241 Machine Learning-Based Detection of Land Use and Land Cover Change in Phu Quoc Special Zone, An Giang Province, Vietnam, Using Google Earth Engine 2026-10-31T00:37:08+00:00 L.C. Mai mlcanh@tdu.edu.vn <p><em>Phu Quoc Special Zone is one of the most developed island destinations in Vietnam. The island has undergone significant land use and land cover (LULC) changes due to urbanization, infrastructure development, and tourism. The objective of this study is to analyze LULC changes from 1995 to 2025 in Phu Quoc usiing Landsat satellite imagery and machine learning (ML) algorithms on the Google Earth Engine (GEE) platform. Four ML algorithms, namely Random Forest, Classification and Regression Tree, Gradient Tree Boosting, and Support Vector Machine, were employed to identify distinct LULC classes, including forest, agricultural land, built-up area, bare land and water body. The classification results yielded an overall accuracy ranging from 85.24 ± 2.81% to 94.41 ± 1.59% and Kappa coefficients ranging from 0.80 ± 0.03 to 0.93 ± 0.02 across the analyzed years, indicating that RF outperformed the other algorithms. Although forest remained the most dominant LULC class, its area decreased by 11.56% over the study period. Conversely, built-up area expanded rapidly by 627.72%, primarily through conversion from forest, agricultural land, and bare land, highlighting the profound impacts of urbanization, infrastructure development, and tourism on LULC changes. The findings demonstrate the effectiveness of integrating ML algorithms within the GEE platform for long-term LULC monitoring. The identified LULC changes provide valuable spatial information to support land-use planning, management, and sustainable land use.</em></p> 2026-10-31T00:00:00+00:00 Copyright (c) 2026 https://ijg.journals.publicknowledgeproject.org/index.php/journal/article/view/5242 Spatiotemporal Land Use and Land Cover Change Analysis (2005–2025) and Future Projections to 2040 in Prayagraj, India, Using Machine Learning and Google Earth Engine 2026-10-31T00:38:55+00:00 P. Thammaboribal prapasgnss@gmail.com N. Agrawal prapasgnss@gmail.com A. Srivastava prapasgnss@gmail.com M. Maurya prapasgnss@gmail.com N. K. Tripathi prapasgnss@gmail.com <p><em>Rapid urbanization has significantly transformed land use and land cover (LULC) patterns in Indian cities, creating a need for reliable spatial information to support urban planning and sustainable land management. This study investigates LULC dynamics in Prayagraj, Uttar Pradesh, India, from 2005 to 2025 and projects potential changes for 2030, 2035, and 2040 using multi-temporal Landsat imagery and Google Earth Engine (GEE). Four LULC classes: water bodies, vegetation, built-up land, and barren land were mapped using three supervised machine learning algorithms: Random Forest (RF), Support Vector Machine (SVM), and Classification and Regression Trees (CART). Classification performance was evaluated using overall accuracy (OA) and the Kappa coefficient. Among the three classifiers, SVM demonstrated the most consistent performance, achieving a mean OA of approximately 0.93 across the five reference years. The historical analysis revealed substantial landscape transformation, particularly the expansion of built-up areas and the overall decline in vegetation cover. The RF-based prediction model was evaluated by comparing a simulated LULC map for 2025 with the corresponding classified map derived from satellite imagery. Although the model reproduced several broad spatial patterns, it overestimated built-up and barren land in some areas, indicating uncertainty in the projected results. The future projections suggest increasing built-up land and declining vegetation between 2030 and 2040, while water bodies and barren land exhibit more variable patterns. These findings demonstrate the potential of integrating satellite remote sensing, machine learning, and cloud-based geospatial processing for long-term LULC assessment. However, the projected changes should be interpreted cautiously because of classification uncertainty, spatial-resolution constraints, and limitations in representing the complex processes governing urban expansion. Further validation and comparison with alternative spatial prediction models are necessary to improve the reliability of future LULC scenarios.</em></p> 2026-10-31T00:00:00+00:00 Copyright (c) 2026 https://ijg.journals.publicknowledgeproject.org/index.php/journal/article/view/5243 Geospatial Economic Evaluation of Integrated Community-Based Collaborative Care Models for Long-Term Care in Rural Thailand 2026-10-31T00:41:55+00:00 P.M.D. Scully nithikethkul2016@gmail.com L. Zheng nithikethkul2016@gmail.com W. Aneksak nithikethkul2016@gmail.com C. Meenongwar nithikethkul2016@gmail.com C. Nithikathkul nithikethkul2016@gmail.com <p><em>Thailand’s public health system is facing rising socioeconomic pressures, especially among its rapidly aging society and the fiscally constrained rural regions of this lower-to-middle income country (LMIC). Identifying cost-efficient Long-Term Care (LTC) public health designs is vital to addressing this challenge across rural geographical regions. Our research set out to find synergies between elderly mental health support and LTC public health protocols, through the design integrated community-based collaborative care (I-CBCC) intervention models. The geospatial decision support tool utilizes discrete event simulation models, measured by 3 quantitative metrics: their operational workload, service delivery quality and cost-efficiency metrics, and compares proposed designs to national protocol baseline designs. Experimental model designs build from the current national public health protocols; the proposed I-CBCC model adds four key interventions, which include home-based case initialization, long-term care giver integration and digital system integration. Ablation analysis studies each (intervention) design component. Parameter sensitivity analyses were conducted to verify robustness of each model. Large geospatial datasets over four rural provinces form the data sources of the evaluations, including epidemiology (106,068 elderly participants; collected 2020-2024) and public health facilities (1,032). A geospatial analysis layer (subdistrict choropleth mapping, spatial cluster statistics, and a multi-criteria priority ranking) localizes the simulated impacts for policy rollout planning. The proposed I-CBCC model significantly improves performance in the three metrics via the I-CBCC interventions model. Cost efficiency metric found 42% total cost savings per average-patient case, over the baseline. Service delivery quality metric retained and improved upon the level of the national protocol, with positive net effect: .31 Cohen's D. Operational workload metrics reduced in areas of screenings, follow-ups and travel, by up to 44%. Geospatial analysis of the per-patient outputs shows the benefits are region-wide (positive in all 366 analyzed subdistricts), while unmet need is significantly spatially clustered (Moran's I = 0.394, p = 0.001), yielding a district priority ranking for a staggered policy rollout. The intervention synergies of the I-CBCC specialized protocol are preferable to the national protocol in this setting. These findings serve as a scalable framework for improving the national public health protocol, with a geospatial multi-criteria prioritization index identifying the districts for phased policy rollout.</em></p> 2026-10-31T00:00:00+00:00 Copyright (c) 2026