Currently there is a huge amount of freely available hydrographic data, and it is increasingly important to have easy access to it and to be provided with as much information as possible. Argo is a global collection of around 4000 active autonomous hydrographic profilers. Argo data go through two quality processes, real time and delayed mode. This work shows a methodology to filter profiles within a given polygon using the odd–even algorithm; this allows analysis of a study area, regardless of size, shape or location. The aim is to offer two filtering methods and to discard only the real-time quality control data that present salinity drifts. This takes advantage of the largest possible amount of valid data within a given polygon. In the study area selected as an example, it was possible to recover around 80 % in the case of the first filter that uses cluster analysis and 30 % in the case of the second, which discards profilers with salinity drifts, of the total real-time quality control data that are usually discarded by the users due to problems such as salinity drifts. This allows users to use any of the filters or a combination of both to have a greater amount of data within the study area of their interest in a matter of minutes, rather than waiting for the delayed-mode quality control that takes up to 12 months to be completed. This methodology has been tested for its replicability in five selected areas around the world and has obtained good results.

La conservación de ecosistemas en zonas costeras debe contemplarse dentro de un marco sustentable con las actividades antropogénicas. Es relevante cuantificar el impacto que generan agentes externos, por lo que el objetivo de este trabajo es implementar un método para el monitoreo de la degradación en superficie de playa y vegetación litoral adyacente. Fueron recabadas capturas de imágenes aéreas de zonas costeras protegidas, obtenidas periódicamente mediante un vehículo drone. Se integró un dataset que contempla todas las fases estacionales y distingue 5 clases para su monitoreo: Mangle, vegetación rastrera, arena, mar y cerro-planicie. Para la segmentación semántica se implementaron y compararon distintas arquitecturas de redes neuronales convolucionales (CNN) empleando aprendizaje transferido. Los resultados han sido robustos en la clasificación, alcanzando una precisión global del 93.9% y entre 89.9-95.8% en las clases individuales. En la métrica Intersección sobre Unión, IoU, el rango fue entre 86.6-92.7%. En la detección de cambio son utilizadas series temporales para el monitoreo de clases. Este método ha sido aplicado al caso de estudio de la playa Ensenada Grande en el Parque Nacional Archipiélago Espíritu Santo.

Fuzzy systems are widely used in most fields of science and engineering, mainly because the models they produce are robust, accurate, easy to evaluate and capture real-world uncertainty better than do the classical alternatives. We propose a new methodology for structure and parameter tuning of Takagi–Sugeno–Kang fuzzy models using several optimization techniques. The output parameters are determined analytically, by finding the minimum of the root-mean-square error (RMSE) for a properly defined error function. The membership functions are simplified by considering symmetry and equispacing, to reduce the optimization problem of finding their parameters, and allow it to be carried out using the numerical method of gradient descent. Both algorithms are fast enough to finally implement a strategy based on the hill climbing approach to finding the optimal structure (number and type of membership functions) of the fuzzy system. The effectiveness of the proposed strategy is shown by comparing its performance, using four case studies found in current relevant works, to the popular adaptive network-based fuzzy inference system (ANFIS), and to other recently published strategies based on evolutionary fuzzy models. In terms of the RMSE, performance was at least 28% better in all case studies.

El fitoplancton es un microorganismo marino que aporta mas del 50 % del oxígeno del planeta y constituye el eslabón primario en las cadenas tróficas marinas. Sin embargo, la actividad antropogénica ha generado el vertido de grandes volúmenes de contaminantes en los océanos, alterando la abundancia y distribución de estos organismos, en un contexto donde aún se desconoce la magnitud de su relación con el cambio climático. Con el objetivo de aportar herramientas para abordar esta problemática, en este trabajo se desarrollo un modelo computacional basado en redes neuronales artificiales para predecir la concentración de biomasa fitoplanctónica (clorofila-a) a partir de variables fisicoquímicas y físicas. El modelo fue entrenado con datos de la plataformaCopernicus Marine Service, correspondientes al Pacifico Tropical Oriental frente a Perú. Los resultados muestran un excelente desempeño, con una precisión del 98.5 %, un coeficiente de determinación (R2) de 0.9994, un error cuadrático medio de 0.0005 µmol/m2 y un error absoluto medio de 0.0100 µmol/m2. Estos resultados confirman la efectividad del modelo propuesto, cumpliendo con el objetivo planteado y ofreciendo una herramienta útil para el monitoreo ambiental marino.

This paper presents an application of the Multi-Objective Genetic Algorithm (MOGA) for PID tuning capable of achieving good performance in the joint position regulation of a pendulum coupled to a servo-motor, and without exceed the motor nominal voltage. The performance is calculated using optimization indices as integral square error and integral time square error. Since the motor nominal voltage plays a key role in the performance of the controller, as well as the overshoot response of the joint position, the novelty of our proposal is that we have added the voltage magnitude and the overshoot response as additional performance indices. Experimental results on a commercial pendular device are presented to validate the proposed scheme, and a comparison is carried out with two other PID tuning methods to test its superiority.