Monitoring vegetation-index dynamics in tropical regions remains challenging due to persistent cloud contamination, landscape heterogeneity, and the lack of standardised and reproducible analytical workflows. This paper presents an open-source, fully reproducible end-to-end methodology for multitemporal vegetation monitoring using Sentinel-2 Level-2A (L2A) Bottom-of-Atmosphere (BOA) reflectance imagery. The methodology was applied to Military Grid Reference System (MGRS) tile T18NVL in the Colombian Eje Cafetero region (4.43°N–5.43°N, 74.91°W–75.90°W) for the 2017–2025 period. The proposed workflow integrates storage-efficient direct extraction of spectral reflectance from compressed Standard Archive Format for Europe (SAFE) archives using the Geospatial Data Abstraction Library (GDAL) /vsizip/ interface, per-pixel cloud and shadow masking based on the Sentinel-2 Scene Classification Layer (SCL), computation of Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Soil-Adjusted Vegetation Index (SAVI), and Normalized Difference Moisture Index (NDMI) spectral indices, a diagnostic Random Forest experiment based on threshold-labelled spectral classes, non-parametric Mann–Kendall trend analysis with Sen’s slope estimation, and external agreement assessment against European Space Agency (ESA) WorldCover 10 m 2020 and Google Earth Pro reference data. The methodology reduced per-scene I/O time by approximately 98% without additional disk overhead while retaining a median of 57.9% valid pixels under a mean scene cloud fraction of 35.4%. Mann–Kendall analysis detected no statistically significant long-term trend in any of the four vegetation indices. Seasonal NDVI peaks during September–November were consistent with the bimodal regional precipitation regime, supporting temporal coherence in the satellite-derived vegetation-index response. External agreement was low, with an Overall Accuracy (OA) of 20.2% against ESA WorldCover and 19.9% against Google Earth Pro, indicating systematic over-prediction of woody and mixed-canopy vegetation classes. These results show that single-date optical spectral indices are insufficient for reliable thematic separation of shade-grown coffee, secondary forest, and dense forest within heterogeneous tropical landscapes. The complete version-controlled codebase is publicly available to support methodological reproducibility and adaptation across data-scarce tropical regions.

This work presents a real-time, explainable Eye-to-Hand visual-feedback architecture for trajectory control of a planar 2RRR parallel manipulator. A fine-tuned YOLOv8n detector locates an end-effector marker, a calibrated homography converts image coordinates into Cartesian position, and the resulting visual error feeds a Cartesian PID correction before inverse kinematics generates the actuator commands. A previously validated ROS/Gazebo digital twin supplies reference trajectories, while the Dynamixel MX-64 encoders are retained only as an independent measurement source for training, calibration, and experimental validation. On 3,142 test images, the observer achieved a position RMSE of 3.455 mm (MAE = 2.804 mm). Wilcoxon tests detected no significant median offset on either Cartesian axis, although confidence intervals for the arithmetic mean differences excluded zero and indicate small mean offsets. The camera-in-the-loop controller was evaluated in 12 physical runs covering four trajectories; whole-trajectory errors ranged from 1.48 to 2.57 mm RMSE, with a pooled RMSE of 1.78 mm and a maximum error of 4.52 mm. Grad-CAM, LIME, and SHAP concentrated their attribution on the end-effector marker during successful detections and lost spatial agreement under synthetic occlusion. The framework combines real-time visual correction, independent encoder-based validation, digital-twin-assisted experimentation, and explainable perception. Physical validation was performed on the Dynamixel-equipped prototype; operation with actuators lacking joint-state telemetry remains to be investigated.

En Colombia, el sector transporte es responsable del 49% de las emisiones de CO₂ y del 43% del consumo total final de energía. Con el objetivo de mitigar estos impactos y avanzar hacia una transición energética más limpia, se ha impulsado la incorporación de flotas vehiculares eléctricas. En los últimos años, la venta de estos vehículos ha mostrado un crecimiento significativo, alcanzando 6 000 unidades en 2023. Este avance ha sido dado en parte por iniciativas gubernamentales orientadas a fomentar su adopción mediante planes y políticas públicas. No obstante, persiste la incertidumbre sobre si la tendencia actual del mercado será suficiente para alcanzar las metas nacionales, como la incorporación de 600 000 vehículos eléctricos para el año 2030. En este contexto, se destaca la importancia de analizar las tendencias del mercado de vehículos eléctricos. Este estudio propone el uso de un modelo de Máquina de Vectores de Soporte (SVM, por sus siglas en inglés) para proyectar la cantidad de vehículos livianos, y posteriormente, estimar el porcentaje de participación de los vehículos eléctricos en la flota vehicular durante el periodo 2030-2035. Para ello, se emplean datos históricos y variables exógenas como el Producto Interno Bruto (PIB), la población y el precio de la gasolina. Las proyecciones generadas a partir de este enfoque contribuyen a la planificación de infraestructura, la anticipación de necesidades de movilidad y el abordaje de desafíos relacionados con la sostenibilidad energética y la reducción de emisiones. Asimismo, facilitan la identificación de áreas de mejora y el diseño de estrategias alineadas con los compromisos climáticos internacionales.