HF-EOLUS. Task 5. Wind Resource Estimation Results

Offshore Wind Resource Estimation via HF-Radar ANN Inversion -- Vilano (Spain) Case Study Context and Motivation Offshore wind resource assessment is critical for wind energy development, but direct long-term measurements are often sparse. High-frequency (HF) coastal radars offer a potential alternative by indirectly sensing sea-surface winds through their backscatter signals. In the Vilano case study (Galician coast, NW Spain), we leverage an artificial neural network (ANN) that inverts HF radar observations into near-surface wind estimates. This approach (developed under the HF-EOLUS project, Zenodo DOI: 10.5281/zenodo.17464519) enables retrieval of 10 m wind fields over the coastal ocean by combining HF radar data with limited satellite and buoy observations. The motivation of this case study is to evaluate how well HF-radar--derived winds can characterize the offshore wind resource at a site of interest (the Vilano-Sisargas buoy location) and to demonstrate a workflow for deriving wind resource metrics from remote sensing data. Data Inputs The analysis uses three primary datasets (packaged as STAC-compliant GeoParquet files for reproducibility): HF-Radar ANN Wind Inversion Dataset -- Hourly 10 m wind vector estimates (speed and direction) derived from HF radar measurements via ANN inference. These data cover a grid of 56 offshore points (mesh nodes) around the study site and constitute the core input for wind resource computations (Zenodo DOI: 10.5281/zenodo.17464583). Vilano Offshore Buoy Measurements -- In-situ wind observations from the Puertos del Estado Vilano buoy (Sisargas buoy), which is a moored oceanographic buoy near Cape Vilán, Spain. The buoy provides hourly wind data (at 3 m anemometer height, extrapolated to 10 m) used as an independent reference for validation (Zenodo DOI: 10.5281/zenodo.17098037). MeteoGalicia Interpolated Winds (subset) -- Hourly 10 m wind components interpolated from the MeteoGalicia WRF 4 km domain over the Vilano area, treated as uncensored buoy-like series for an independent benchmark (Zenodo DOI: 10.5281/zenodo.17490873). The subset is published under use_case/catalogs/vilano_node_subset. Each dataset above is publicly available and includes spatiotemporal metadata in a STAC catalog. The ANN dataset represents a hindcast of wind conditions obtained by applying the trained ANN model to historical HF radar records, while the buoy dataset represents the ground-truth wind climate at the site. The MeteoGalicia subset supplies an additional mesoscale-based reference for paired comparisons. By comparing these, we ensure the ANN-derived winds are physically consistent and quantify any biases. The derived wind resource indicators (power density, capacity factor, Weibull diagnostics, and bootstrap summaries) together with their STAC packaging are openly released as HF-EOLUS. Task 5. Wind Resource Estimation Results (Zenodo DOI: 10.5281/zenodo.17594220). Please cite this record whenever you reuse the Vilano case study outputs. Reproducibility notes for the ANN/buoy and MeteoGalicia/buoy pipelines are documented in use_case/docs/vilano_comparison.md. Methodology We applied the HF-EOLUS Wind Resource Toolkit (Zenodo DOI: 10.5281/zenodo.17591545) to compute standard wind resource metrics from the ANN wind dataset, with optional validation against the buoy record. The ANN model was trained exclusively on HF-radar observations paired with Sentinel-1 SAR references (no buoy data in training), and its 10 m outputs were first adjusted to a representative wind turbine hub height (110 m) using a neutral logarithmic wind profile (open-sea roughness length 0.2 mm). At each analysis grid point, the toolkit then evaluated long-term wind statistics including mean wind speed, percentile speeds (e.g. P90, the 90th percentile), and the wind speed frequency distribution. A Weibull distribution was fitted to the wind speed data, with appropriate treatment of left-censoring beyond the radar's reliable speed range (~5.7--17.8 m/s) to account for the ANN's classification limits. From the wind speed distribution, we computed the wind power density (the mean available wind energy per unit area, W/m²) and estimated a capacity factor by applying a standard 6 MW offshore turbine power curve to the wind data. All calculations include quality-control filters: for example, data segments with low radar coverage or any bias flags were noted (though included in aggregate metrics) and "out-of-range" wind estimates (beyond the ANN's training range) were handled via a capped distribution approach. We also conducted a block-bootstrap analysis (500 resamples for the full dataset) to quantify statistical uncertainty in key metrics (e.g. confidence intervals for mean wind speed and power density). Finally, for validation, the toolkit synchronised the ANN predictions at the buoy's location with the buoy's observed time series, enabling a direct hour-by-hour comparison of wind speed and direction. Note: The methodology strictly avoids site-specific tuning beyond the ANN model itself -- all parameters (e.g. vertical extrapolation, censoring thresholds) follow standard or documented values to ensure the results are generalisable. No explicit wave or stability corrections were applied (neutral atmosphere assumed), and the capacity factor estimation is theoretical (no wind farm losses or wake effects included), consistent with a resource assessment scenario. Results Wind Resource Characteristics: The ANN-based wind climatology indicates a strong offshore wind resource in the Vilano region. Table 1 summarizes the key wind resource metrics at 110 m height, aggregated over the 56 analysis nodes. The median hub-height wind speed is about 9.4 m/s, and even the lower-ranked sites exhibit mean speeds on the order of 9 m/s. The upper end (90th percentile among sites) of mean wind speeds is about 10.0 m/s, reflecting consistently high winds across the area. These winds translate to a high available energy density: the median wind power density is roughly 785 W/m², with the windiest locations reaching ~1000 W/m². Such conditions would correspond to a substantial energy yield -- for a generic 6 MW offshore turbine, the median capacity factor is estimated around 0.58 (i.e. 58% of maximum output on average), with the best sites approaching 0.69. These figures underscore the excellent wind potential of this coastal area. Metric (at 110 m height) Median P90 (High) Mean wind speed 9.37 m/s 9.96 m/s Wind power density 785 W/m² 1003 W/m² Capacity factor (6 MW turbine) 0.58 0.69 Table 1: Long-term wind resource metrics derived from the HF-radar ANN dataset for the Vilano study area. Median values (typical site) and P90 values (top-performing sites) are shown. Wind power density is the mean available power per unit area of wind, and capacity factor is the fraction of a 6 MW turbine's output that would be realized on average under these winds. The ANN-inferred wind regime is not only strong on average but also shows relatively robust high-wind occurrence (P90 levels are close to the medians, indicating a narrow spread of consistently high winds). This consistency is partially a result of the censoring -- extremely low or high winds fall outside the radar's optimal sensitivity, so the effective distribution is focused in the moderate-to-high range. Despite this, the bootstrap uncertainty analysis suggests that for sites meeting basic data-quality thresholds, the uncertainty in mean wind or power estimates is on the order of ±10--15% (95% confidence), which is acceptable for preliminary resource evaluation. Validation against Buoy Measurements: We compared the ANN-derived wind time series to the buoy's observed winds at the buoy location (after adjusting both to 110 m height). Over the period of overlapping data (11,412 hourly pairs), the ANN consistently predicts higher wind speeds than those recorded by the buoy. For example, the ANN-predicted mean wind speed at the buoy site is about 11.3 m/s, whereas the buoy's measured mean is 7.8 m/s over the same hours. Similarly, the ANN's 90th-percentile wind speed reaches 15.4 m/s compared to the buoy's 13.5 m/s. Despite this positive bias in wind speed, the wind power density estimates from ANN and buoy are more aligned -- 627 W/m² vs 607 W/m² at 110 m, respectively, for the matched period. Table 2 presents these comparisons, along with the buoy's long-term climatology for context. Notably, the buoy's full-record mean wind speed is 8.9 m/s (higher than the 7.8 m/s during matched hours), and its overall power density is ~850 W/m², indicating that some high-wind events recorded by the buoy were likely missing in the ANN dataset. Metric (110 m) ANN (paired hours) Buoy (paired hours) Buoy climatology Mean wind speed 11.27 m/s 7.77 m/s 8.88 m/s 90th percentile wind speed 15.36 m/s 13.53 m/s 15.13 m/s Wind power density 626.8 W/m² 607.1 W/m² ~850 W/m² Table 2: Wind climate comparison at the Vilano buoy location. "Paired hours" refers to the time span where both ANN and buoy data are available simultaneously. For reference, the buoy's full climatology (all available data over the deployment) is also summarized on the right. The ANN shows a high bias in wind speed relative to the buoy, but the computed power densities are within ~3% during matched periods. The buoy's full record includes some higher-wind periods that were not captured in the ANN input, hence its higher long-term power density. This validation highlights some important considerations. The ANN model tends to overestimate wind speeds at this specific location. Nevertheless, the fact that power density -- a function of the cube of wind speed -- is so close between ANN and buoy suggests that the overall energy content of the wind is being captured reasonably well by the ANN inversion. The buoy's higher long-term power density (850 W/m²) compared to the paired-sample value (607 W/m²) is mainly due to periods of very high winds that the radar missed. Additional benchmark against MeteoGalicia interpolation: We also synchronised the MeteoGalicia interpolated subset with the PdE Vilano buoy (uncensored, 110 m) over 37 541 matched hours (2018-05-01 to 2023-06-01) to quantify how a mesoscale surrogate compares against the in-situ record. As with the ANN validation, both series are height-aligned to 110 m and evaluated on the intersection of timestamps; the buoy climatology column gives the full buoy record for context. MeteoGalicia remains faster than the buoy across all metrics and overestimates power density, but the figures are consistent with offshore Iberian WRF-based assessments such as Salvação & Soares (2018). Metric (110 m) MeteoGalicia (paired) Buoy (paired) Buoy climatology Mean wind speed 9.59 m/s 8.68 m/s 8.88 m/s 90th percentile wind speed 16.06 m/s 15.13 m/s 15.13 m/s Wind power density 964.9 W/m² 809.0 W/m² 850.1 W/m² Table 3: MeteoGalicia–buoy comparison at 110 m. Paired columns use 37 541 matched hours (2018-05-01 to 2023-06-01) with the MeteoGalicia subset treated as uncensored; the climatology column reports the buoy’s full record (same height correction). Artefacts and pipeline are documented in use_case/docs/vilano_comparison.md (“MeteoGalicia validation pipeline”). Triple-matched comparison (ANN vs MeteoGalicia vs buoy): To control for sampling differences, we also evaluated the three sources on their common intersection (9 926 hours, 2018-05-24 to 2023-05-10) after height-aligning all series to 110 m. Even though all three time series capture the same events, the MeteoGalicia model reports substantially higher power than both the ANN and the buoy, highlighting its positive bias over this shared subset. Metric (110 m) ANN (paired) MeteoGalicia (paired) Buoy (paired) Mean wind speed 11.32 m/s 9.65 m/s 7.72 m/s 90th percentile wind speed 15.49 m/s 16.29 m/s 13.53 m/s Wind power density 647.2 W/m² 998.3 W/m² 601.3 W/m² Table 4: Triple-matched metrics at 110 m (deterministic estimators). All columns use the same 9 926-hour intersection; artefacts live under use_case/artifacts/triple_comparison/ann/resource/ and use_case/artifacts/triple_comparison/meteogalicia/resource/, and the commands are documented in use_case/docs/vilano_comparison.md. Conclusion The Vilano use case shows that HF-radar–derived winds, inverted via an ANN trained only with Sentinel-1 SAR references, can recover a strong offshore wind climate without relying on local masts or Lidar. Site-wide medians around 9–10 m/s at 110 m and power densities near 785 W/m² (CF ≈ 0.6) confirm the coastal potential. Validation against the PdE buoy reveals the main caveat: the ANN overestimates speed (and thus P90), though power density stays close to the buoy once censored and height-aligned. The triple-matched experiment reinforces the picture: with all sources on the same timestamps, ANN remains closer to the buoy in power (~647 vs 601 W/m²), while the uncensored MeteoGalicia surrogate stays clearly high-biased in both speed and energy (~998 W/m²). Future improvements should target bias reduction (speed and direction), better handling of out-of-range samples, and broader multi-sensor validation to tighten confidence intervals before downstream siting decisions. Acknowledgements This work has been funded by the HF-EOLUS project (TED2021-129551B-I00), financed by MICIU/AEI /10.13039/501100011033 and by the European Union NextGenerationEU/PRTR - BDNS 598843 - Component 17 - Investment I3. Members of the Marine Research Centre (CIM) of the University of Vigo have participated in the development of this repository. Disclaimer This software is provided "as is", without warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, and noninfringement. In no event shall the authors or copyright holders be liable for any claim, damages, or other liability, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the software or the use or other dealings in the software. References Salvação, N., & Soares, C. G. (2018). Wind resource assessment offshore the Atlantic Iberian coast with the WRF model. Energy, 145, 276–287. Herrera Cortijo, J. L., Fernández-Baladrón, A., Rosón, G., Gil Coto, M., Dubert, J., & Varela Benvenuto, R. (2025a). HF-EOLUS HF-Radar Wind Inversion Toolkit for Artificial Neural Networks Training and Inference (v0.1.1) (v0.1.1). Zenodo. https://doi.org/10.5281/zenodo.17464519 Herrera Cortijo, J. L., Fernández-Baladrón, A., Rosón, G., Gil Coto, M., Dubert, J., & Varela Benvenuto, R. (2025b). HF-EOLUS. Task 2. HF-Radar Wind Inversion Models and Results for VILA and PRIO Stations. Zenodo. https://doi.org/10.5281/zenodo.17464583 Herrera Cortijo, J. L., Fernández-Baladrón, A., Rosón, G., Gil Coto, M., Dubert, J., & Varela Benvenuto, R. (2025). Project HF‑EOLUS. Task 1. Puertos del Estado Vilano Buoy Data Bundle (GeoParquet + STAC) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.17098037 Herrera Cortijo, J. L., Fernández-Baladrón, A., Rosón, G., Gil Coto, M., Dubert, J., & Varela Benvenuto, R. (2025). HF EOLUS Wind Resource Toolkit (v0.1.0) (v0.1.0). Zenodo. https://doi.org/10.5281/zenodo.17591545 Herrera Cortijo, J. L., Fernández-Baladrón, A., Rosón, G., Gil Coto, M., Dubert, J., & Varela Benvenuto, R. (2025). HF-EOLUS. Task 5. Wind Resource Estimation Results. Zenodo. https://doi.org/10.5281/zenodo.17594220 Herrera Cortijo, J. L., Fernández-Baladrón, A., Rosón, G., Gil Coto, M., Dubert, J., & Varela Benvenuto, R. (2025). HF-EOLUS Task 3. MeteoGalicia Wind Interpolation Outputs. Zenodo. https://doi.org/10.5281/zenodo.17490873