Introducción: Los arroyos asociados a bofedales se hallan en ambientes donde las condiciones son extremas con temperaturas muy variables, baja presión atmosférica e intensa radiación solar. Sin embargo, existen ensamblajes de macroinvertebrados asociados a estos ambientes, cuya información es escasa. A escala global y regional, las características de los macroinvertebrados cambian con el aumento de la latitud y altitud (disminución de la riqueza y variación de la composición). A nivel local, también se puede agregar el efecto de las aguas ácidas y de elevada conductividad proveniente de manantiales que se unen a los arroyos, que generan heterogeneidad en la calidad de agua y consecuentemente en las características de los macroinvertebrados. Objetivo: Comparar la diversidad, composición y abundancia de macroinvertebrados y las características fisicoquímicas del agua de arroyos asociados a dos bofedales altoandinos, ubicados en el departamento de Ayacucho, Perú. Metodología: Se estudiaron once estaciones ubicados en arroyos de dos bofedales: 7 en Guitarrachayocc (G) de 43 ha (n = 28) y 4 en Pichccahuasi (P) de 28 ha (n = 8). Se empleó una red de Surber (0.3 mm de malla, área de muestreo de 1 200 cm2), para realizar muestreos mensuales de octubre de 2016 a abril de 2017. Análisis de componentes principales (PCA) y análisis de varianza multivariante no paramétrico (NP-MANOVA) se aplicaron para comparar las características del agua. Además, se utilizó un análisis de coordenadas principales (PCoA) y NP-MANOVA para comparar el ensamblaje. La prueba no paramétrica de Kruskal-Wallis (α = 0.05) se utilizó para comparar las abundancias absolutas de los taxa principales. Resultados: Las características del agua fueron heterogéneas, con pH de 3.2 (± 0.4) a 7.6 (± 0.1), conductividad de 168.9 (± 91) µS/cm a 1 117 (± 159.3) µS/cm; diferencias que fueron significativas (p < 0.05) al comparar las estaciones de muestreo, donde el agua de G6 presenta los mínimos valores de pH y los máximos de conductividad, al igual que cloruros. Se recolectaron un total de 8 126 individuos, distribuidos en 26 taxa de 20 familias, 11 órdenes y cinco clases. Los insectos fueron el grupo más diverso y abundante. A pesar a la cercanía de los arroyos de los bofedales, presentaron diferencias: en G, se registró 25 taxa, con dominancia de Macrelmis sp., Dicrotendipes sp., Claudioperla sp., Meridialaris sp. y en P, 9, con dominancia de Pedrowygomya sp., Hyalella sp. y Dicrotendipes sp. La densidad fue de 475 ind./m2 y de 31 ind./m2 para el bofedal G y P respectivamente, estos valores fueron estadísticamente diferentes (p < 0.05). El PCoA y el PCA confirmados por NP-MANOVA mostraron que G6 es diferente (p < 0.05) dentro de G porque recibe el aporte de agua de un manantial. Conclusiones: La riqueza, composición y densidad de los macroinvertebrados son diferentes en los arroyos según el bofedal al cual se halla asociado. La contribución de los manantiales a los arroyos genera cambios drásticos en la calidad del agua y los macroinvertebrados, determinando la formación de ensamblajes con diferente riqueza y estructura.

In the Peruvian Amazon, there are few ecological studies on the diversity patterns of aquatic macroinvertebrates, essential for the management of these fluvial ecosystems. In such context, our objective was to determine the taxonomic composition and its relationship with environmental variables along an altitude gradient of the Alto Madre de Dios River, a basin with the potential to register new species. We established 22 stations in an altitudinal range from 398 to 2411 masl and evaluated the water physicochemical characteristics and the fluvial habitat: pH, water temperature (T, ° C), electrical conductivity (CE, μS.cm-1), river width (A, m), depth (P, cm), shadow, current flow speed (m · s-1), and depth. We took macroinvertebrate samples with a 200-μm-mesh-size kick net and identified 56 taxa distributed in the orders Acari, Ephemeroptera, Coleoptera, Diptera, Hemiptera, Megaloptera, Odonata, Plecoptera, Trichoptera, and Decapoda. In the multivariate classification and grouping analysis, four groups of statistically differentiated stations (p <0,05) were classified, mainly by speed and the type of dominant substrate, which explains the abundance and wide distribution of Chironomidae, Baetodes, Traulodes, and Anacroneuria. Macroinvertebrate taxa changed notably along the gradient reporting a greater diversity in areas with middle altitudes and a relationship with environmental variables. Hay pocos estudios ecológicos sobre los patrones de diversidad de los macroinvertebrados acuáticos en la Amazonía peruana, a pesar de ser esenciales para la gestión y manejo de estos ecosistemas fluviales. En este contexto, el objetivo del presente estudio fue determinar su composición taxonómica y su relación con las variables ambientales a lo largo de un gradiente altitudinal del río Alto Madre de Dios, cuenca en donde podrían registrarse nuevas especies. Se establecieron 22 estaciones en un rango altitudinal de 398 a 2.411 m s.n.m., cuantificando las características fisicoquímicas del agua y del hábitat fluvial: pH, temperatura del agua (T, °C), conductividad eléctrica (CE, μS.cm-1), ancho del río (A, m), profundidad (P, cm), sombra y velocidad del flujo de la corriente (m·s-1). Para los muestreos de macroinvertebrados se utilizó una red “de patada” de 200 μm de tamaño de malla. Se identificaron 56 taxones distribuidos en los órdenes Acari, Ephemeroptera, Coleoptera, Diptera, Hemiptera, Megaloptera, Odonata, Plecoptera, Trichoptera y Decapoda. Los análisis multivariados de clasificación y agrupamiento permitieron establecer cuatro grupos de estaciones estadísticamente diferenciadas (p<0,05), principalmente por la velocidad y el tipo de sustrato dominante, lo que explica la abundancia y amplia distribución de Chironomidae, Baetodes, Thraulodes y Anacroneuria. Los taxones de macroinvertebrados cambiaron notablemente a lo largo del gradiente, reportándose una mayor diversidad en zonas con altitudes medias y una relación con las variables ambientales.

Vulnerable road users in informal urban environments confront a distinct set of hazards that standard computer vision datasets are ill-equipped to represent: artisanal speed bumps constructed without regulatory compliance, deteriorated road markings, and the mototaxi—a three-wheeled motorized vehicle that constitutes the primary informal transport mode in intermediate Andean cities yet is absent from all major international repositories. This paper presents QHAWAY—from Quechua qhaway, a transitive verb meaning “to look; to observe”—an Advanced Driver Assistance System (ADAS) predicated on instance segmentation, monocular distance estimation via the pinhole camera model, and Time-to-Collision (TTC) computation, developed for the road environment of Ayacucho, Peru (2761 m a.s.l.), a city recognised by UNESCO as a Creative City of Crafts and Folk Art since 2019. A hybrid dataset comprising 25,602 images with 127,525 annotated instances across 12 classes was assembled by combining an original local collection of 4598 images (10,701 instances) captured through four complementary acquisition methods across the five urban districts of the Huamanga province with three established international datasets (BDD100K, BSTLD, RLMD; 21,004 images, 116,824 instances). A three-phase progressive training strategy with monotonically increasing resolution (640, 800, and 1024 pixels) was evaluated as an ablation study. A multi-architecture comparison spanning YOLOv8L-seg and the YOLO26 family (nano, small, large) identified YOLO26L-seg as the best-performing model, attaining mAP50 Box of 0.829 and mAP50 Mask of 0.788 at epoch 179. The integration of ByteTrack multi-object tracking with the pinhole equation $D=(H_{\mathrm{real}}\times f)/h_{\mathrm{px}}$ delineates operational risk zones aligned with the NHTSA forward collision warning standard (danger: <3 m; caution: 3–7 m; TTC threshold ≤ 2.4 s). The system sustains processing rates of 19.2–25.4 FPS on an NVIDIA RTX 5080 GPU. A systematic field survey established that 96% of the audited speed bumps fail to comply with MTC Directive No. 01-2011-MTC/14, constituting the first quantitative record of informal road infrastructure non-compliance in the Andean region. Validation was conducted under naturalistic driving conditions without staged scenarios. Grad-CAM explainability analysis, encompassing three complementary visualisation algorithms (Grad-CAM, Grad-CAM++, and EigenCAM), confirmed that model attention concentrates consistently on safety-critical objects.

The urban heat island (UHI) effect in Andean cities is a critical yet understudied phenomenon, where complex topography and rapid urbanization uniquely alter local climates. This research analyzes the spatiotemporal evolution of the surface UHI and its linkage to urban morphology in Ayacucho, Peru, through a 40-year multi-temporal analysis (1986–2016) using Landsat images. We developed a synthetic Urban Heat Island Index (UHII) through Principal Component Analysis (PCA), integrating land surface temperature (LST), spectral indices, and urban morphological parameters. Our results identify a critical transition in 2006, with the emergence of persistent heat spots driven by unplanned expansion. The surface UHI intensity reached urban-rural differences of 4.31 °C (day) and 5.82 °C (night), showing a positive trend. Urban morphology was a key determinant, with high-density blocks exhibiting a minimum nocturnal LST 3.53 °C higher than low-density areas. Statistical trend tests confirmed a significant intensification, while a strong negative correlation with vegetation indices (R² = 0.97) underscored the vital mitigation role of green infrastructure. This study provides academics with a robust methodological framework for UHI analysis in complex terrains. For public and private urban managers, it offers spatially explicit evidence to prioritize actionable strategies, such as integrating green infrastructure and regulating urban form, to enhance climate resilience in Andean cities.

This paper presents a distributed edge computing system for real-time urban traffic monitoring that integrates vehicle speed estimation and automatic license plate recognition (ALPR) on NVIDIA Jetson Orin NX devices. The system addresses the need for low-cost, automated traffic enforcement in developing urban environments where certified radar-based speed measurement infrastructure is not available. The proposed architecture consists of two independent processing nodes. The first node performs speed estimation using an IMOU aerial camera, YOLO26n-based vehicle detection, ByteTrack multi-object tracking, perspective homography transformation, and Kalman filtering for instantaneous speed computation. The second node performs license plate recognition employing a frontal camera, YOLO26n detection, and a Compact Convolutional Transformer (CCT) OCR model for real-time plate reading. Both subsystems are deployed on Jetson Orin NX modules with TensorRT FP16-optimized models, sustaining 20.0–22.3 FPS for speed estimation and 29–36 FPS for license plate recognition. The system incorporates the Peruvian traffic regulation (DS 025-2021-MTC) for automated violation classification, including speeding offenses (code M20) with the 5 km/h camera tolerance threshold introduced by DS 011-2026-MTC. Field validation was conducted at Jr. Carlos F. Vivanco, Ayacucho, Peru (2719–2725 m a.s.l.). Speed estimation was validated in a 40-pass nocturnal campaign against 1 Hz GNSS Doppler velocity spanning 16.9–48.8 km/h, a range that covers both the 30 km/h statutory limit and the 35 km/h enforcement tolerance. The configuration deployed during the campaign, which smooths the metric foot-point with a constant-velocity Kalman filter, attained a mean absolute error of 3.19 km/h at the enforcement line. The residual was identified as the steady-state lag of that motion model under vehicle acceleration, with which it correlates at r = −0.727; replacing it with a constant-acceleration model reduces the error to 1.32 km/h under leave-one-pass-out cross-validation and removes the dependence on acceleration entirely (r = +0.003). The improvement was verified to transfer to the Jetson deployment node. Two earlier campaigns are retained for completeness because they identified deployment failure modes—an RTSP stream resolution renegotiation and a speed-display defect affecting vehicles stopped beyond the measurement zone—that are reported as engineering contributions in their own right. A comprehensive model development study, comprising six training experiments (M1–M6) across three architectures (YOLOv8m-seg, YOLO11m-seg, YOLO26-seg/det), documents the methodological transition from instance segmentation to bounding-box detection driven by edge computing latency constraints. The results demonstrate the feasibility of deploying a traffic enforcement prototype using commercial edge devices and IP camera infrastructure, offering a scalable and cost-effective solution for smart city applications in developing regions.