Urban green spaces (UGSs) provide essential environmental services for the well-being of ecosystems and society. Due to the constant environmental, social, and economic transformations of cities, UGSs pose new challenges for management, particularly in fast-growing metropolitan areas. With technological advancement and the evolution of deep learning, it is possible to optimize the acquisition of UGS inventories through the detection of geometric patterns present in satellite imagery. This research evaluates two deep learning model techniques for semantic segmentation of UGS polygons with the use of different convolutional neural network encoders on the U-Net architecture and very high resolution (VHR) imagery to obtain updated information on UGS polygons at the metropolitan area level. The best model yielded a Dice coefficient of 0.57, IoU of 0.75, recall of 0.80, and kappa coefficient of 0.94 with an overall accuracy of 0.97, which reflects a reliable performance of the network in detecting patterns that make up the varied geometry of UGSs. A complete database of UGS polygons was quantified and categorized by types with location and delimited by municipality, allowing for the standardization of the information at the metropolitan level, which will be useful for comparative analysis with a homogenized and updated database. This is of particular interest to urban planners and UGS decision-makers.

Insecticide resistance in Aedes aegypti (Linnaeus, 1762), the primary vector of several arboviruses, threatens vector control efficacy and motivates evaluation of current and candidate public health insecticides, such as imidacloprid and broflanilide, and their molecular impacts. Here, we used RNA sequencing (RNA-seq) to characterize the transcriptomic response to one-hour acute exposure to an operational partial-mortality concentration (<50%) of imidacloprid and broflanilide in two Ae. aegypti strains: a field-derived, pyrethroid-resistant population from San Nicolás and a susceptible laboratory strain (New Orleans). Adults were exposed for 1 h to partial-mortality concentration (<50%) doses of each insecticide or acetone control, and differential gene expression and Gene Ontology (GO) enrichment were assessed with DESeq2-based workflows. We detected pronounced baseline transcriptomic differences between strains and extensive activation of gene expression after insecticide exposure, with a strong bias toward up-regulation. A shared transcriptional core involving proteolysis, transmembrane transport, detoxification pathways, and structural remodeling of the cuticle and cytoskeleton was identified across contrasts. Despite these common elements, broflanilide elicited largely conserved early responses between strains, whereas imidacloprid amplified pre-existing divergence and produced marked population-specific transcriptional signatures. These findings suggest greater transcriptional changes in the field-derived strain, particularly in response to imidacloprid, and highlight the importance of integrating population-specific molecular information when designing insecticide rotation schemes and resistance management strategies targeting Ae. aegypti.

In Mexico, dam construction requires a thorough Environmental Impact Manifestation (Manifestación de Impacto Ambiental, or MIA), which is a comprehensive environmental assessment report submitted to the Secretariat of the Environment and Natural Resources (SEMARNAT) for review and authorization. The MIA, however, is a formal document that outlines the potential environmental impacts of a dam project, including construction and operation. These methodologies are obsolete compared to the currently available technologies. This study tests a new procedure of 3D tree surveying of a closed-canopy woodland of different types of forests on a dam in Linares, in eastern Mexico. A DJI drone—Matrice 350 assembly—was used to collect imagery in 16 missions during the summer of 2024. A canopy height model was built from the UAV-extracted point cloud and LiDAR bare earth surface. Treetops were delineated in a variable-sized local maxima filter, and tree crowns were outlined via inverted watershed segmentation. The outputs include a tree inventory that contains thousands of trees (location, tree height, crown polygon), varying among the different types of vegetation. These new datasets give a more comprehensive approach to establish further decision making.

Latin America is among the most urbanized regions in the world. SELPER, a Latin American non profit organization is interested in contributing to a better understanding of climate-related problems using Earth Observation and remote sensing data. This collaborative research by ISPRS and SELPER researchers responds not only to the intensification of the urban heat island (UHI) effect caused by the rapid development of cities in recent decades, but also recognizes the importance of preserving and restoring critical blue-green infrastructure to mitigate the effects of climate change. During a first stage, the study focused in 16 major Latin American megacities present at 6 countries, collectively home to approximately 73 million people: São Paolo (22.62), Mexico City (22.28), Buenos Aires (15.69), Río de Janeiro (13.73), Bogotá (11.51), Lima (11.2), Santiago (6.9), Belo Horizonte (6.25), Guadalajara (5.42), Monterrey (5.12), Brasilia (4.87), Recife (4.26), Porto Alegre (4.21), Medellin (4.1), Salvador (3.96) and Curitiba (3.81). Each city was mapped and analyzed using Google Earth Engine and remote sensing data. The analysis included Land Surface Temperatures (LST) and Local Climate Zones (LCZ) for the years 2003, 2008, 2018 and 2021. Preliminary results explored the UHI distributions and the impact of different levels of urban development by LCZ. First-stage acchievements indicate, that these megacities exhibit: (1) a diffuse urban model, (2) urban heat islands are spatially and temporally located, (3) compromised green-blue infrastructure during the last decades, and (4) differences in construction materials and morphological changes among surface structures. Collaboration is needed. For the second stage the researcher's group is developing green-blue infrastructure models for each city, such as the Urban Canopy Model (UCM), Riparian Infrastructure Model (RIM) and/or Urban Green Areas (UGA). These models will be based on a fusion of Earth Observation, remote sensing data and local knowledge. Moreover, important information will be retrieved, such as meteorological local station data and socioeconomic information. In summary, collaborative efforts could achieve potential results to create the basis for implementing preventive policies for sustainable planning, promoting climate justice, and adopting nature-based solutions in Latin American megacities.

Multiple factors influence the risk of heat stroke and that, collectively, define the vulnerability of the population. This vulnerability can be physiologically differentiated by older adults and children, by gender, or due to the level of exposure to sporting activities or labor, among others. During the last two decades, hot extreme events are drastically increasing related to climate change and other climate phenomena such as El Niño event. The World Health Organization estimates that more than 70,000 heat-related deaths occurred in Europe during the last two weeks of August 2003 and almost 62,000 deaths during summer 2022. In Mexico, the record of heat-related deaths was set during the summer of 2023 when the Health Secretariat reported 373 deaths due to extreme heat events. The five ranking states were Nuevo León (27% of the cases), Sonora (20%), Baja California (14%), Tamaulipas and Veracruz (8% respectively), and 80% of them are located between the 25 to 31°Latitude North. To understand which the most influential factors for heat-related deaths are, this study analyzes the interaction between land surface temperature, spatial population dynamics, and the exposure-response relationship to urban form and the concentration of air pollution in the Monterrey Metropolitan Area. The paper will present the operational structure of a smart information system based on RS and GIS for planning a better and safer city life in San Nicolás de los Garza, the municipality that ranked first on heat-related deaths. In summary, results indicate the next highlights: (1) extreme heat waves are increasing every year in the metropolitan area, (2) urban heat islands are spatially and temporally located, therefore, (3) risk reduction and civil protection actions must include a holistic approach including warning early systems, social, labor and health care actions, (4) preventive policies must be implemented such as sustainable urban planning for population climate justice, (5) and adopting nature-based solutions.