Citizen security is essential for the well-being of citizens. In the current context, Ecuador is facing a growing crime wave that generates deep concern among citizens. This study focused on analyzing the spatial-temporal patterns of robberies to people in the area of Terminal Terrestre of Cuenca in the period 2020-2022, using spatial analysis methods (Nearest Neighbor Index, Kernel Density Estimation and Grid Cell Mapping) and temporal analysis, through Geographic Information Systems (GIS). The results of applying these techniques generated cartographic products in which it was possible to visualize and detect several concentrations of points (hot spots) in different sectors of the study area. Likewise, the temporal analysis supported by data clocks and the Grid Cell Mapping method showed that there is a higher incidence of crime at certain times of day and in specific zones of the study area.
Bioclimatic classification is essential for understanding and managing the territory in a more sustainable way, as well as in biodiversity conservation management and climate change assessment. The supervised Maximum Likelihood (ML) classification method is a powerful tool for bioclimatic classification. Therefore, the ML classifier was applied in the Caroni River basin, using data from global sources, from which averages of climatic variables were extracted. Geographic Weighted Regression (GWR) and the 90 m SRTM DEM were used to improve the scale. The Holdridge classification was applied, this presented an overall accuracy of 93 % the classes of premontane rainforest, very humid tropical forest and premontane rainforest denoted the worst performance, as there are transitive structures involved that the classification model could not capture.
Air pollution is mostly due to anthropogenic causes degrading the quality of breathable air. The larger dimensions of gaseous pollutants are still challenging to inspect. Satellite data can quantify the concentrations of atmospheric pollutants that are specifically beneficial in understanding air pollution. This paper attempts to understand the air pollutants in the Kathmandu district (Nepal) retrieved from the Sentinel-5P satellite data from 2019 to 2022: by correlating with the weather parameter and vegetation indices, observing the yearly concentrations of the gaseous pollutants over the days of the year and observing their spatial distribution. In the results, temperature showed a predominantly strong positive correlation with methane (CH4), carbon monoxide (CO) and ozone (O-3) and a negative correlation with nitrogen dioxide (NO2), formaldehyde (HCHO), sulphur dioxide (SO2) and aerosol. Precipitation was negatively correlated with all the pollutants except the O-3. Vegetation indices, Normalised Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI), were negatively correlated with most of the gaseous pollutants signifying the importance of the vegetation towards mitigating the gaseous pollutants. Moreover, yearly trends of the gaseous pollutants and the spatial distributions were unique for all the gaseous pollutants. Lowest mean concentrations of the aerosol index, HCHO, NO2 and O-3 in different days of 2020 were suggestive towards the impacts of COVID-19 lockdown. In the broader context, proper vegetation and the remedial ways to maintain Kathmandu's temperature, around the city areas, is likely to moderate the gaseous pollutants in the city. This paper clearly points to the approach in utilising the satellite based data in air pollution inspections.
Bioclimatic classification is essential for understanding and managing the territory in a more sustainable way, as well as in biodiversity conservation management and climate change assessment. The supervised Maximum Likelihood (ML) classification method is a powerful tool for bioclimatic classification. Therefore, the ML classifier was applied in the Caroni River basin, using data from global sources, from which averages of climatic variables were extracted. Geographic Weighted Regression (GWR) and the 90 m SRTM DEM were used to improve the scale. The Holdridge classification was applied, this presented an overall accuracy of 93 % the classes of premontane rainforest, very humid tropical forest and premontane rainforest denoted the worst performance, as there are transitive structures involved that the classification model could not capture.
Citizen security is essential for the well-being of citizens. In the current context, Ecuador is facing a growing crime wave that generates deep concern among citizens. This study focused on analyzing the spatial-temporal patterns of robberies to people in the area of Terminal Terrestre of Cuenca in the period 2020-2022, using spatial analysis methods (Nearest Neighbor Index, Kernel Density Estimation and Grid Cell Mapping) and temporal analysis, through Geographic Information Systems (GIS). The results of applying these techniques generated cartographic products in which it was possible to visualize and detect several concentrations of points (hot spots) in different sectors of the study area. Likewise, the temporal analysis supported by data clocks and the Grid Cell Mapping method showed that there is a higher incidence of crime at certain times of day and in specific zones of the study area.
Volunteered Geographic Information (VGI) has redefined the practices of geospatial data collection and utilization, by promoting collaboration and democratizing access to geographic information. However, existing tools present notable limitations regarding accessibility, adaptability, and cost, restricting their use in communities and research projects with limited resources. This article presents NexusMap, an open-source tool designed for the collection, visualization, and management of collaborative geographic information. Its development has addressed key technical and methodological challenges, such as the creation of modular and scalable architecture, accessible interfaces for users without technical training, and essential functionalities such as data validation and interoperability through open geospatial standards. NexusMap is easily adaptable to different types of projects, fostering inclusive and flexible participation. The plugin was evaluated through tests conducted with undergraduate and postgraduate students, including participants with and without prior GIS experience. The results indicate a high level of acceptance: students without technical training gave an average score of 4.49 out of 5 across all items, while advanced users rated the plugin with an average of 4.25. However, feedback from advanced users highlights priority areas for improvement in future versions. These insights suggest that future updates should prioritize these aspects to enhance the tool's suitability for more demanding professional environments. The source code is available at the NexusMap GitHub repository: https://github.com/EscalaDigital/nexusmap.
Landslides are among the phenomena that have caused significant material and human losses worldwide, largely due to the reduction of vegetation and changes in land use driven by human activities. The frequency of hurricanes in Mexico further accelerates these events by increasing precipitation accumulation. This study examines the impact of land use and vegetation changes on the susceptibility to hillside processes in the Zoque region of Chiapas, following the major landslides caused by Hurricane Eta in 2020. Changes in land use and vegetation between 1986 and 2020 were analyzed, and the region's susceptibility was subsequently modeled based on conditioning factors such as lithology, land use and vegetation, slope, and drainage density. The spatial analysis revealed that areas with the steepest slopes, where the most significant land use and vegetation changes had occurred, were the most susceptible to landslides. Deforested regions used for agriculture and livestock farming showed medium, high, and very high susceptibility, which were widespread throughout the area. This study is one of the few to identify landslide susceptibility in the region, and the results aim to support planning efforts for risk prevention and mitigation.
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.
Identifying and delineating urban centralities is fundamental to understanding the dynamics and inequalities of Latin American metropolises, a challenge that has historically been significant in urban studies. This article leverages the tools of the computational shift in the social sciences to address this problem in the region, formulating a mixed methodological strategy that prioritizes cost, parsimony, and reproducibility. Big data from Open Street Maps, the DBSCAN clustering technique, Python programming, fieldwork, and photographic documentation were used for the challenging case of Buenos Aires. As a result, the city's centralities were identified, illustrating the diversity of centers across different types and hierarchies. Finally, the article reflects on the lessons learned from the case study to replicate this experience in other cities in the region.
Synthetic Aperture Radar (SAR) polarimetry is a remote sensing technique known for being applied to monitoring and surface and deforestation. Polarimetry aims to characterise land surface by analyzing the properties of the signal that is scattered when using different combinations of polarization of the transmitting and receiving antennas, defined as polarimetric channels. The use of vertical/vertical polarization proved to be efficient for estimating the extent of deforested areas and musaceous monocrops discrimination in northern Costa Rica. To that end, Sentinel-1 images from the European Space Agency have been used, with a calibration/workflow process and a subsequent rescaling that allowed to draw a clear distinction between forested areas and monocrops more effectively than radar vegetation index based on cross-polarization.
Remote sensing data has been successfullyused to enhance sugarcanemonitoring and management, in topicssuch as yield estimation, health anomaly detection, orvariety classification. Specifically, variety classification is an essential objectivefor optimizing crop management, as it can guidestrategies such as plant renovation, pest control, or yield estimation. A literature review allowed identifyingthat the integration of diversesatellite platforms to enhance time series for sugarcane variety classification has not been explored.This strategy can improve the temporal density of available imagery in our study area, Costa Rica, with frequent cloud cover. Therefore, ourresearchproposedto classify six sugarcane varietiesusing anadditive approach (aggregating them in four variety groups)andemploying parametric and non-parametric algorithms on harmonized data from Sentinel-2 and Landsat-8/9. Validation was done at both pixel and plot scales. Thebest classifications were achieved using green and near infrared bands, along with the Enhanced Bloom Indexand Normalized Difference Infrared Indexvegetation indices. Regarding temporal dynamics, the most relevant months were September, November, and December, corresponding to advanced growth cycle stages.Support Vector Machine and Random Forest provided the best classification accuracies. At the pixel scale, the overall accuracy of all groups exceeded 0.86, with a slight decrease as the number of varieties increased. When validation was done at plot scale, the overall accuracyremained above 0.89 in all the groups. These achievementsweresuitableand valuableforsugarcane sustainable planning anddecision-making.
Location-allocation models are algorithms for finding the optimal location for services and facilities. Traditionally, these models were performed statically, without considering changes in network and service demand throughout the day. We evaluated the impact of incorporating the dynamic characteristics of public transport service networks and daily traffic behavior on covered demand. For this purpose, big data sources were used, drawing from Madrid’s public transport data and TomTom’s traffic history. Dynamic location-allocation models were developed using both data sources to incorporate the temporal and spatial details of public transportation frequencies and vehicular congestion. We found that daily variation in public transportation service and congestion affects the number of people who can visit a shopping center within a specified time frame. This research incorporates variables from new data sources, thereby enabling the development of dynamic models. This approach is helpful for decision-making related to the localization of services within cities.
Synthetic Aperture Radar (SAR) polarimetry is a remote sensing technique known for being applied to monitoring and surface and deforestation. Polarimetry aims to characteriseland surfaceby analyzing the properties of the signal that is scattered when using different combinations of polarization of the transmitting and receiving antennas, defined as polarimetric channels. The use of vertical/vertical polarization proved to be efficient for estimating the extent of deforested areas and musaceous monocrops discrimination in northern Costa Rica. To that end, Sentinel-1 images from the European Space Agency havebeen used, with a calibration/workflow process and a subsequent rescaling that allowed to draw a clear distinction between forested areas and monocrops more effectively than radar vegetation index based on cross-polarization.
Water resource management and sanitation are global priorities, as established in the Sustainable Development Goals, as well as for the United States and its territories, including Puerto Rico, located in the Caribbean. A study was conducted using the Communities Without Sanitary Sewer Model, which was developed in a Geographic Information System, to identify creeks of higher risk areas in watershed in Puerto Rico Island. Surface water samples were taken to analyse the presence of faecal Enterococcus. Out of the results obtained, 8 out of 10 were positive and exceeded the regulatory values, that confirm the contamination of surface waters with pathogens associated with lack of sanitary infrastructure to collect wastewater, the presence of septic tanks, either through filtration, overflow, or direct discharge of wastewater from non-point sources from communities surrounding rivers. Continuous contamination downstream was found in areas where sanitary services are already provided, confirming that contaminants are transported through water flow. This study concludes that the quality of surface waters in these areas is poor and poses a risk to public health, as well as the aquatic life of river ecosystems.
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.
Identifying and delineating urban centralities is fundamental to understanding the dynamics and inequalities of Latin American metropolises, a challenge that has historically been significant in urban studies. This article leverages the tools of the computational shift in the social sciences to address this problem in the region, formulating a mixed methodological strategy that prioritizes cost, parsimony, and reproducibility. Big data from Open Street Maps, the DBSCAN clustering technique, Python programming, fieldwork, and photographic documentation were used for the challenging case of Buenos Aires. As a result, the city's centralities were identified, illustrating the diversity of centers across different types and hierarchies. Finally, the article reflects on the lessons learned from the case study to replicate this experience in other cities in the region.
Landslides are among the phenomena that have caused significant material and human losses worldwide, largely due to the reduction of vegetation andchanges in land use driven by human activities. The frequency of hurricanes in Mexico further accelerates these events by increasing precipitation accumulation. This study examines the impact of land use and vegetation changes on the susceptibility to hillside processes in the Zoque region of Chiapas, following the major landslides caused by Hurricane Eta in 2020. Changes in land use and vegetation between 1986 and 2020 were analyzed, and the region's susceptibility was subsequently modeled based on conditioning factors such as lithology, land use and vegetation, slope, and drainage density. The spatial analysis revealed that areas with the steepest slopes, where the most significant land use and vegetation changes had occurred, were the most susceptible to landslides. Deforested regions used for agriculture and livestock farming showed medium, high, and very high susceptibility, which were widespread throughout the area. This study is one of the few to identify landslide susceptibility in the region, and the results aim to support planning efforts for risk prevention and mitigation.
