Geospatial foundation models generate high-dimensional embeddings that achieve strong predictive performance, yet their internal organization remains obscure, limiting their scientific use. Recent interpretability studies relate Google AlphaEarth Foundations (GAEF) embeddings to continuous environmental variables, but it is still unclear whether the embedding space exhibits a functional or hierarchical organization, in which some dimensions act as specialized representations while others encode shared or broader geospatial structure. In this work, we propose a functional interpretability framework that reverse-engineers the role of embedding dimensions by characterizing their contribution to land cover structure from observed classification behavior. The approach combines large-scale experimentation with a structural analysis of embedding-class relationships based on feature importance patterns and progressive ablation. Our results show that embedding dimensions exhibit consistent and non-uniform functional behavior, allowing them to be categorized along a hierarchical functional spectrum: specialist dimensions associated with specific land cover classes, low- and mid-generalist dimensions capturing shared characteristics between classes, and highgeneralist dimensions reflecting broader environmental gradients. Critically, we find that accurate land cover classification (98
Este ensayo examina críticamente el concepto filosófico de reconocimiento para argumentar que su densidad analítica puede ampliarse mediante una territorialización transdisciplinaria. A partir del entrecruce entre filosofía, geografía crítica, epistemología y antropología, se sostiene que el reconocimiento no puede permanecer abstraído de las condiciones materiales, simbólicas y afectivas donde ocurre. Territorializarlo implica inscribirlo en un entramado sociohistórico donde las subjetividades se constituyen también desde la relación con los espacios habitados. El artículo distingue entre conceptos y nociones, y explora cómo la aplicabilidad empírica de una categoría como la de reconocimiento depende de su inscripción en experiencias vividas. Se analizan casos concretos —como procesos de reparación en territorios campesinos e indígenas— para ilustrar cómo el reconocimiento se encarna en prácticas espaciales, afectivas y políticas, influyendo en dinámicas de justicia cognitiva, justicia espacial y configuración institucional. A partir de un enfoque situado, se argumenta que las luchas no se reducen a demandas de inclusión cultural y acarrean el potencial de afirmar formas de existencia ligadas a mundos relacionales, sensibilidades territoriales y agencias no humanas. En este sentido, se propone una relectura del reconocimiento que integra la dimensión espacial como componente constitutivo. Las conclusiones apuntan a que territorializar el reconocimiento es condición necesaria para su mediación epistémica y transformadora, en tanto lo vuelve sensible a los modos en que lo social se encarna, se habita y se disputa.
This article presents the Intelligent Monitoring System (IMS), an AI-assisted, low-latency surveillance platform designed for defense environments. The study addresses the need for real-time autonomous situational awareness by integrating high-speed video transmission with advanced computer vision analytics in constrained network settings. The IMS employs a hybrid transmission architecture based on RTSP for ingestion and WHEP/WebRTC for distribution, orchestrated via MediaMTX, with the objective of achieving end-to-end latencies below one second. The methodology includes a comparative evaluation of video streaming protocols (JPEG-over-WebSocket, HLS, WebRTC, etc.) and AI frameworks, alongside the modular architectural design and prolonged experimental validation. The detection module integrates YOLOv11 models fine-tuned on the VisDrone dataset to optimize performance for small objects, aerial views, and dense scenes. Experimental results, obtained through over 300 h of operational tests using IP cameras and aerial platforms, confirmed the stability and performance of the chosen architecture, maintaining latencies close to 500 ms. The YOLOv11 family was adopted as the primary detection framework, providing an effective trade-off between accuracy and inference performance in real-time scenarios. The YOLOv11n model was trained and validated on a Tesla T4 GPU, and YOLOv11m will be validated on the target platform in subsequent experiments. The findings demonstrate the technical viability and operational relevance of the IMS as a core component for autonomous surveillance systems in defense, satisfying strict requirements for speed, stability, and robust detection of vehicles and pedestrians.
Background: Exercise adaptation is increasingly recognized as an immunometabolic process driven by coordinated interactions among inflammatory signaling, mitochondrial regulation, metabolic homeostasis, and recovery-associated physiology. Within this framework, NLRP3 inflammasome activation and PPARD-mediated metabolic signaling have emerged as biologically relevant pathways potentially involved in exercise-induced physiological adaptation. However, the contribution of regulatory genetic variations linking these pathways remains poorly characterized. Objective: To synthesize current evidence regarding the integration of NLRP3- and PPARD-related pathways in exercise immunometabolism and adaptive physiological responses to exercise, with particular emphasis on the regulatory variants NLRP3 rs10754558 and PPARD rs2267668 as potential contributors to interindividual variability in exercise adaptation. Methods: A structured narrative review complemented by exploratory systems-level in silico analyses was conducted using the PubMed, Scopus, and Web of Science databases until March 2026. Evidence related to exercise physiology, inflammatory regulation, metabolic adaptation, and exercise-associated phenotypes involving the NLRP3 and PPARD pathways was evaluated. Complementary analyses included functional annotation, protein–protein interaction network analysis, and pathway enrichment using STRING, Reactome, KEGG, Gene Ontology, and other publicly available genomic databases. Particular attention was given to the functional and regulatory context of rs10754558 and rs2267668 within the interconnected inflammatory and metabolic pathways relevant to exercise adaptation. Results: The reviewed evidence identified recurrent interactions among the inflammatory and metabolic pathways involved in exercise adaptation and recovery. NLRP3 rs10754558 and PPARD rs2267668 were identified as candidate regulatory variants potentially positioned at the interface between inflammatory responsiveness and metabolic flexibility, providing a biologically plausible framework for understanding the interindividual variability in exercise adaptation. Exploratory system-level analyses identified recurrent associations among inflammatory signaling, mitochondrial function, energy-sensing pathways, and metabolic regulation. These findings primarily reflect the functional annotations and system-level pathway associations identified through exploratory analyses. Conclusions: Current evidence supports a systems-level physiological framework in which inflammatory and metabolic pathways interact dynamically during exercise adaptation and recovery. NLRP3- and PPARD-related pathways, including the candidate regulatory variants rs10754558 and rs2267668, may contribute to interindividual variability in exercise-associated physiological responses and represent promising targets for future hypothesis-driven investigations in exercise immunometabolism, exercise genomics and precision exercise medicine.
Wetlands play a key role in hydrological regulation and flood risk reduction; however, their attenuation capacity depends not only on biophysical characteristics but also on sociocultural dynamics influencing their use and management. This study proposes and applies the Integrated Wetland Flood Risk Attenuation Index (IARH) to assess the flood risk attenuation capacity of wetlands from a socio-ecological perspective. The methodological framework was developed through a multicriteria approach integrating biophysical and sociocultural parameters operationalized through quantifiable indicators. Parameter weights were estimated using the Analytic Hierarchy Process (AHP), while indicators were normalized and aggregated into biophysical and sociocultural components. An exploratory pilot application was conducted in the Zapatosa Wetland Complex (Colombia) using secondary environmental and territorial information. Results indicate that storage volume, hydrological connectivity, and functional wetland area are the main biophysical determinants of flood regulation, whereas land occupation and socioeconomic dependence on wetland ecosystem services are the most influential sociocultural factors. The pilot application yielded an intermediate-high attenuation capacity (IARH = 0.661), with moderate stability under alternative weighting scenarios. The proposed IARH provides a replicable socio-ecological assessment framework that may support ecosystem-based risk management, wetland conservation, and territorial planning processes. Nevertheless, further empirical validation and field-based calibration are recommended to strengthen its applicability across different wetland contexts.
