Wind energy’s ability to liberate the world from conventional sources of energy relies on lowering the significant costs associated with the maintenance of wind turbines. Since icing events on turbine rotor blades are a leading cause of operational failures, identifying icing in advance is critical. Some recent studies have utilized deep learning (DL) techniques to predict icing events with high accuracy by leveraging rotor blade images, but these studies only focus on specific wind parks and fail to generalize to unseen scenarios (e.g., new rotor blade designs). In this paper, we aim to facilitate ice prediction on the face of lack of ice images in new wind parks. We propose the utilization of synthetic data augmentation via a generative artificial intelligence technique—the neural style transfer algorithm to improve the generalization of existing ice prediction models. We also compare the proposed technique with the CycleGAN as a baseline. We show that training standalone DL models with augmented data that captures domain-invariant icing characteristics can help improve predictive performance across multiple wind parks. Through efficient identification of icing, this study can support preventive maintenance of wind energy sources by making them more reliable toward tackling climate change.

Vertical-axis wind turbines are excellent candidates to diversify wind energy technology, but their aerodynamic complexity limits industrial deployment. To improve the efficiency and lifespan of vertical-axis wind turbines, we desire data-driven models and control strategies that take into account the timing and duration of subsequent events in the unsteady flow development. Here, we aim to characterise the chain of events that leads to dynamic stall on a vertical-axis wind turbine blade and to quantify the influence of the turbine operation conditions on the duration of the individual flow development stages. We present time-resolved flow and unsteady load measurements of a wind turbine model undergoing dynamic stall for a wide range of tip-speed ratios. Proper orthogonal decomposition is used to identify dominant flow structures and to distinguish six characteristic stall stages: the attached flow, shear-layer growth, vortex formation, upwind stall, downwind stall and flow reattachment stage. The timing and duration of the individual stages are best characterised by the non-dimensional convective time. Dynamic stall stages are also identified based on aerodynamic force measurements. Most of the aerodynamic work is done during the shear-layer growth and the vortex formation stage which underlines the importance of managing dynamic stall on vertical-axis wind turbines.

The placement of a scaled-down Savonius (drag) vertical-axis wind turbine on model buildings is analysed experimentally by the use of turbine performance and flow field measurements in a wind tunnel. The set-up consists of two surface mounted cubes aligned in the flow direction. The turbine is tested at six different streamwise positions – three on each cube. Velocity field measurements are performed with particle image velocimetry along the centreline of the cubes with and without the turbine. The performance at each position is evaluated based on measurements of the produced torque and the rotational speed of the turbine. It is demonstrated that the common practice of estimating wind resources based on the urban flow field without the turbine present is insufficient. The turbine has a substantial influence on the flow field and thus also on the available power. The performance is found to be optimal in the front and centre of the first building with a significant drop-off to the back. This trend is reversed for the downstream building. Holistically, for more generic geometries and varying wind directions, the results suggest the central position on a building is a good compromise.

This study uses an experiment where ferry passengers are sold hotel room “views” to evaluate the impact of wind turbines views on tourists’ vacation experience. Participants purchase a chance for a weekend hotel stay. Information about the hotel rooms was limited to the quality of the hotel and its distance from a large wind turbine, as well as whether or not a particular room would have a view of the turbine. While there was generally a negative effect of turbine views, this did not hold across all participants, and did not seem to be effected by distance or hotel quality.

The present study consists of a synthesis of the lithostratigraphy, geotechnical properties, geometry and distribution of Eocene and Quaternary deposits of the Belgian continental shelf. It is based on available large datasets (seismics, cores, cone penetration tests) and their interpretations synthesised from numerous studies from the last 20 years. A significant effort has been focused on data digitisation and integration into appropriate GIS software packages in order to compare the data in a much more dynamic and flexible way. New insights have been proposed on the lithostratigraphy and geotechnical properties of offshore and onland deposits.

An application is presented for the selection of wind farm implantation sites. Geological and geotechnical aspects of direct interest for wind farm implantation site selection have been focused on, such as the stability of the offshore wind turbine structures and the minimization of environmental impacts on the seabed. Sites suitable for wind turbines using monopile structures on the Belgian continental shelf are proposed.

A simple electromagnetic model of wind-turbine's main structural elements as the linear wired structures is developed to simulate the temporal patterns of observed radar return Doppler spectra (micro-Doppler). Using the model, the micro-Doppler for different combinations of the turbines rotation frequency, radar pulse repetition frequency, and duration of the Doppler measurement interval are analyzed. The model is validated using the PARSAX radar experimental data. The model ability to reproduce the observed Doppler spectra main features can be used for development of signal-processing algorithms to suppress the wind-turbines clutter in modern Doppler radars.

The Egyptian vulture Neophron percnopterus is categorized as Endangered on the IUCN Red List, as well as on the European and Spanish Red Lists. Spain is home to the most important breeding population of Egyptian vultures in Europe but this population has differing trends at a regional scale. We present data for the Egyptian vulture population in the Cantabrian Mountains, north-west Spain, during the last 3 decades and assess the main threats to the species there. The Egyptian vulture population in the Cantabrian Mountains was estimated to be 175 breeding pairs in 2008, which comprised 13–14% of the Spanish population. This population has been stable, or increasing slightly, since 2000. During 2000–2008 4.3% of the Cantabrian Egyptian vulture population was affected by the use of illegal poison. During the same period the number of sheep and goats reared (which contributes to the maintenance of Egyptian vulture territories) was reduced by 27.4%, which could lead to food shortages for the vultures in the near future. Currently 32 breeding pairs (18.3% of the population) have wind turbines within their foraging areas, with an average of 59 wind turbines per territory (range 1–176). During the next few years this number will increase to 110 turbines per territory within 69 vulture territories (39.4% of the population). Nearly a third (32.6%) of breeding territories are located outside protected areas. Better coordination between administrative areas is needed to guarantee the conservation of the Cantabrian Mountains population of Egyptian vultures through effective surveillance and protection in the numerous existing protected areas.