Remote spectral imaging of coastal areas can provide valuable information for their sustainable management and conservation of their biodiversity. Unfortunately, such areas are very sensitive to changes due to human activity, natural phenomenon, introduction of non-native species, and climate change. Thus, the main objective of this research is the implementation of a robust image processing methodology to produce accurate bathymetry maps in shallow coastal waters using high-resolution multispectral WorldView-2/3 satellite imagery for the monitoring at the maximum spatial and spectral resolutions. Two different island ecosystems have been selected for the assessment, since they stand out for their richness in endemic species and they are more vulnerable to climate change: Cabrera National Park and Maspalomas Natural Protected area, located in the Balearic and Canary Islands, Spain, respectively. In addition, a third example to show the applicability of the mapping methodology to monitor the construction of a new port in Granadilla (Canary Islands) is presented. Contributions of this work focus on improving the preprocessing methodology and, mainly, on the proposal and assessment of new satellite-derived regression and machine learning bathymetric models, which have been validated and compared with respect to measured reference bathymetry. After a thorough analysis of nine techniques, using visual and quantitative statistical parameters, ensemble learning approaches have demonstrated excellent performance, even in challenging scenarios up to 35-m depth, with mean RMSE values around 2 m.

Visible light communications (VLC) technology is emerging as a candidate to meet the demand for interconnected devices’ communications. However, the costs of incorporating specific hardware into end-user devices slow down its market entry. Optical camera communication (OCC) technology paves the way by reusing cameras as receivers. These systems have generally been evaluated under static conditions, in which transmitting sources are recognized using computationally expensive discovery algorithms. In vehicle-to-vehicle networks and wearable devices, tracking algorithms, as proposed in this work, allow one to reduce the time required to locate a moving source and hence the latency of these systems, increasing the data rate by up to 2100%. The proposed receiver architecture combines discovery and tracking algorithms that analyze spatial features of a custom RGB LED transmitter matrix, highlighted in the scene by varying the cameras’ exposure time. By using an anchor LED and changing the intensity of the green LED, the receiver can track the light source with a slow temporal deterioration. Moreover, data bits sent over the red and blue channels do not significantly affect detection, hence transmission occurs uninterrupted. Finally, a novel experimental methodology to evaluate the evolution of the detection’s performance is proposed. With the analysis of the mean and standard deviation of novel K parameters, it is possible to evaluate the detected region-of-interest scale and centrality against the transmitter source’s ideal location.

Benthic communities, such as seagrass meadows, play a crucial environmental role in marine ecosystems and provide socio-economic benefits. Satellite remote sensing is currently used for their monitoring, and Deep Learning (DL) techniques offer improvements in mapping quality compared to traditional Machine Learning (ML). This study compares conventional ML and convolutional DL models for mapping Cymodocea nodosa meadows in El Río, Canary Islands, using WorldView-2 satellite imagery. An in-situ measurement campaign was conducted to generate an open dataset for segmentation. Evaluated models include Decision Trees, Gaussian Naïve Bayes, Support Vector Machines, K-Nearest Neighbors, Subspace KNN, Feedforward Neural Networks, U-Net, Attention U-Net, and Pix2Pix models. Results show that DL models significantly outperform conventional ML models in detecting Cymodocea nodosa. The best model (U-net) achieved an Intersection over Union (IoU) of 83% overall and 74% for Cymodocea nodosa, while the best ML model (FNN) only reached 62% and 23%, respectively. IoU was highlighted for its sensitivity to minor mapping changes. Additionally, a temporal analysis revealed a dramatic 96% reduction in Cymodocea nodosa coverage over 21 years, from 245.32 ha in 2001 to 9.31 ha in 2022. This study not only compares conventional ML and convolutional DL techniques for benthic habitat mapping but also provides a valuable methodology and dataset for future marine ecosystem monitoring research.

Seagrass and seaweed meadows hold a very important role in coastal and marine ecosystems. However, anthropogenic impacts pose risks to these delicate habitats. This paper analyses the multitemporal impact of the construction of the largest industrial port in the Canary Islands, near the Special Area of Conservation Natura 2000, on Cymodocea nodosa seagrass meadows (sebadales) of the South of Tenerife, in the locality of Granadilla (Canary Islands, Spain). Very-high-resolution WorldView-2 multispectral satellite data were used for the analysis. Specifically, three images were selected before, during, and after the construction of the port (2011, 2014, and 2022, correspondingly). Initially, advanced pre-processing of the images was performed, and then seabed maps were obtained using the machine learning K-Nearest Neighbors (KNN) supervised classification model, discriminating 12 different bottom types in Case-2 complex waters. The maps achieved high-quality metrics with Precision values of 85%, 81%, and 80%, recall of 76%, 77%, and 77%, and F₁ scores of 80%, 79%, and 77% for 2011, 2014, and 2022, respectively. The results mainly show that the construction directly affected the seagrass and seaweed habitats. In particular, the impact of the port on the meadows of Cymodocea nodosa, Caulerpa prolifera, and maërl was assessed. The total maërl population was reduced by 1.9 km² throughout the study area. However, the Cymodocea nodosa population was maintained at the cost of colonizing maërl areas. Furthermore, the port sedimented a total of 0.98 km² of seabed, especially Cymodocea nodosa and maërl. In addition, it was observed that Caulerpa prolifera was established as a meadow at the entrance of the port, replacing part of the Cymodocea nodosa and maërl areas. As additional results, bathymetric maps were generated from satellite imagery with the Sigmoid model, and the presence of a submarine outfall was, as well, presented.

Patrones claros y consistentes de vigor del cultivo, fenología y estado hídrico en viñedos y olivares pueden obtenerse cuando la información procedente de múltiples plataformas de teledetección se analiza de forma conjunta. En este estudio, el uso combinado de imágenes multiespectrales y térmicas de Sentinel-2, WorldView y UAV permitió la caracterización de las condiciones del cultivo desde escalas regionales hasta intra-parcela. Las series temporales de Sentinel-2 (2020–2025) capturaron, a 10 y 20 m de resolución, la variabilidad interanual y el desarrollo estacional, identificando periodos recurrentes sensibles al estrés. Los datos WorldView, con una resolución espacial de 50 cm, revelaron fuertes contrastes espaciales en densidad y vigor del dosel en grandes zonas de producción, mientras que las observaciones UAV, a 10 cm, mostraron la heterogeneidad a escala fina asociada al estrés hídrico y a la variabilidad estructural. Un subconjunto de índices de vegetación, seleccionado a partir de un conjunto inicial de 27, mostró una correlación robusta con mediciones de campo de potencial hídrico foliar, contenido de clorofila y estado fenológico. En comparación con análisis de una única plataforma, el enfoque integrado produjo una discriminación marcadamente mejorada de niveles de estrés y clases de vigor. Estos resultados demuestran que la fusión de datos multiplataforma proporciona una base fiable y operativa para la gestión de precisión de cultivos perennes, apoyando intervenciones dirigidas en sistemas de vid y olivo.

La identificación y mapeo de los viñedos en islas volcánicas presenta una elevada complejidad debido a la fuerte variabilidad topográfica, la fragmentación de las parcelas y la coexistencia de múltiples sistemas de cultivo tradicionales. En este contexto, la teledetección y las técnicas de Deep Learning constituyen herramientas prometedoras para mejorar la monitorización agrícola. El presente estudio evalúa el rendimiento del modelo U‑Net para la segmentación de viñedos utilizando datos del Plan Nacional de Ortofotografía Aérea (PNOA) de 2021, combinando información espectral (RGB y NIR) y datos derivados de LiDAR (DEM y CHM). Se entrenaron cuatro configuraciones del modelo U‑Net con distintas combinaciones de datos de entrada con el fin de analizar el impacto de cada fuente de información. Los resultados muestran que todas las configuraciones alcanzan métricas bastante robustas (F1‑Score >71%, IoU >55%). Sin embargo, la integración de datos multimodales mejora sistemáticamente la segmentación. La mejor combinación (RGB + NIR + DEM + CHM) obtuvo un F1‑Score del 75.32% y una IoU del 60.41%, evidenciando el impacto de incorporar información topográfica y de estructura de la vegetación. Este trabajo demuestra el potencial de la fusión de datos espectrales y LiDAR junto con modelos U‑Net para la detección y monitorización precisa de viñedos en entornos agrícolas heterogéneos.