Context

High precision and reliable wind speed forecasting is a challenge for meteorologists. Severe wind due to convective storms, causes considerable damages (large scale forest damage, outage, buildings/houses damage, etc.). Convective events such as thunderstorms, tornadoes as well as large hail, strong winds, are natural hazards that have the potential to disrupt daily life, especially over complex terrain favoring the initiation of convection. Even ordinary convective events produce severe winds which causes fatal and costly damages. Therefore, wind speed prediction is an important task to get advanced severe weather warning. This dataset contains the responses of a weather sensor that collected different weather variables such as temperatures and precipitation.

Content

The dataset contains 6574 instances of daily averaged responses from an array of 5 weather variables sensors embedded in a meteorological station. The device was located on the field in a significantly empty area, at 21M. Data were recorded from January 1961 to December 1978 (17 years). Ground Truth daily averaged precipitations, maximum and minimum temperatures, and grass minimum temperature were provided.

Attribute Information

1. DATE (YYYY-MM-DD)
2. WIND: Average wind speed [knots]
3. IND: First indicator value
4. RAIN: Precipitation Amount (mm)
5. IND.1: Second indicator value
6. T.MAX: Maximum Temperature (°C)
7. IND.2: Third indicator value
8. T.MIN: Minimum Temperature (°C)
9. T.MIN.G: 09utc Grass Minimum Temperature (°C)

Citation Request

If you want to cite this data:

fedesoriano. (April 2022). Wind Speed Prediction Dataset. Retrieved [Date Retrieved] from https://www.kaggle.com/datasets/fedesoriano/wind-speed-prediction-dataset

Air pollution management through wind speed forecasting: the time series exhibits a daily cyclical behavior and a long-term seasonality.

Note: Find data at source. ・ This map displays the wind forecast over the next 72 hours across the contiguous United States, in 3 hour increments, including wind direction, wind gust, and sustained wind speed.Zoom in on the Map to refine the detail for a desired area. The Wind Gust is the maximum 3-second wind speed (in mph) forecast to occur within a 2-minute interval within a 3 hour period at a height of 10 meters Above Ground Level (AGL). The Wind Speed is the expected sustained wind speed (in mph) for the indicated 3 hour period at a height of 10 meters AGL. Data are updated hourly from the National Digital Forecast Database produced by the National Weather Service.Where is the data coming from?The National Digital Forecast Database (NDFD) was designed to provide access to weather forecasts in digital form from a central location. The NDFD produces gridded forecasts of sensible weather elements. NDFD contains a seamless mosaic of digital forecasts from National Weather Service (NWS) field offices working in collaboration with the National Centers for Environmental Prediction (NCEP). All of these organizations are under the administration of the National Oceanic and Atmospheric Administration (NOAA).Wind Speed Source: https://tgftp.nws.noaa.gov/SL.us008001/ST.opnl/DF.gr2/DC.ndfd/AR.conus/VP.001-003/ds.wspd.binWind Gust Source: https://tgftp.nws.noaa.gov/SL.us008001/ST.opnl/DF.gr2/DC.ndfd/AR.conus/VP.001-003/ds.wgust.binWind Direction Source: https://tgftp.nws.noaa.gov/SL.us008001/ST.opnl/DF.gr2/DC.ndfd/AR.conus/VP.001-003/ds.wdir.binWhere can I find other NDFD data?The Source data is downloaded and parsed using the Aggregated Live Feeds methodology to return information that can be served through ArcGIS Server as a map service or used to update Hosted Feature Services in Online or Enterprise.What can you do with this layer?This map service is suitable for data discovery and visualization. Identify features by clicking on the map to reveal the pre-configured pop-ups. View the time-enabled data using the time slider by Enabling Time Animation.Alternate SymbologyFeature Layer item that uses Vector Marker Symbols to render point arrows, easily altered by user. The color palette uses the Beaufort Scale for Wind Speed. https://www.arcgis.com/home/item.html?id=45cd2d4f5b9a4f299182c518ffa15977 This map is provided for informational purposes and is not monitored 24/7 for accuracy and currency.If you would like to be alerted to potential issues or simply see when this Service will update next, please visit our Live Feed Status Page!

researchers

This nowCOASTâ„¢ time-offsets map service provides maps depicting the NWS surface wind speed forecasts from the National Digital Forecast Database (NDFD) at 6-hr increments out to 3 days (NDFD has forecasts out to 7 days which are available via the nowCOASTâ„¢ time enabled map service for NDFD elements). Each forecast is valid for the specified forecast projection hour with respect to the latest update cycle time. The forecast is valid at 10 m (33 feet) above ground level. The wind speeds are in units of knots (1 knot = 1.15 miles per hour). The wind speed forecast is indicated on the map by different colors for 5-knot increments up to 60 knots (69 mph) and then at 10-knot increments up to 100 knots (115 mph). The forecasts are updated in the nowCOASTâ„¢ map service four times per day. For more detailed information about layer update frequency and timing, please reference the nowCOASTâ„¢ Dataset Update Schedule.

PaperThis dataset is associated with the paper published in Scientific Data, titled "SDWPF: A Dataset for Spatial Dynamic Wind Power Forecasting over a Large Turbine Array." You can access the paper: https://www.nature.com/articles/s41597-024-03427-5If you find this dataset useful, please consider citing our paper: Scientific Data Paper@article{zhou2024sdwpf, title={SDWPF: A Dataset for Spatial Dynamic Wind Power Forecasting over a Large Turbine Array}, author={Zhou, Jingbo and Lu, Xinjiang and Xiao, Yixiong and Tang, Jian and Su, Jiantao and Li, Yu, and Liu, Ji and Lyu, Junfu and Ma, Yanjun and Dou, Dejing},journal={Scientific Data},volume={11},number={1},pages={649},year={2024},url = {https://doi.org/10.1038/s41597-024-03427-5},publisher={Nature Publishing Group}}Baidu KDD Cup Paper@article{zhou2022sdwpf,title={SDWPF: A Dataset for Spatial Dynamic Wind Power Forecasting Challenge at KDD Cup 2022}, author={Zhou, Jingbo and Lu, Xinjiang and Xiao, Yixiong and Su, Jiantao and Lyu, Junfu and Ma, Yanjun and Dou, Dejing}, journal={arXiv preprint arXiv:2208.04360},url = {https://arxiv.org/abs/2208.04360}, year={2022}}BackgroundThe SDWPF dataset, collected over two years from a wind farm with 134 turbines, details the spatial layout of the turbines and dynamic context factors for each. This dataset was utilized to launch the ACM KDD Cup 2022, attracting registrations from over 2,400 teams worldwide. To facilitate its use, we have released the dataset in two parts: sdwpf_kddcup and sdwpf_full. The sdwpf_kddcup is the original dataset used for the Baidu KDD Cup 2022, comprising both training and test datasets. The sdwpf_full offers a more comprehensive collection, including additional data not available during the KDD Cup, such as weather conditions, dates, and elevation.sdwpf_kddcupThe sdwpf_kddcup dataset is the original dataset used for Baidu KDD Cup 2022 Challenge. The folder structure of sdwpf_kddcup is:sdwpf_kddcup --- sdwpf_245days_v1.csv --- sdwpf_baidukddcup2022_turb_location.csv --- final_phase_test --- infile --- 0001in.csv --- 0002in.csv --- ... --- outfile --- 0001out.csv --- 0002out.csv --- ...The descriptions of each sub-folder in the sdwpf_kddcup dataset are as follows:sdwpf_245days_v1.csv: This dataset, released for the KDD Cup 2022 challenge, includes data spanning 245 days.sdwpf_baidukddcup2022_turb_location.csv: This file provides the relative positions of all wind turbines within the dataset.final_phase_test: This dataset serves as the test data for the final phase of the Baidu KDD Cup. It allows for a comparison of methodologies against those of the award-winning teams from KDD Cup 2022. It includes an 'infile' folder containing input data for the model, and an 'outfile' folder which holds the ground truth for the corresponding output. In other words, for a model function y = f(x), x represents the files in the 'infile' folder, and the ground truth of y corresponds to files in the 'outfile' folder, such as {001out} = f({001in}).More information about the sdwpf_kddcup used for Baidu KDD Cup 2022 can be found in Baidu KDD Cup Paper: SDWPF: A Dataset for Spatial Dynamic Wind Power Forecasting Challenge at KDD Cup 2022sdwpf_fullThe sdwpf_full dataset offers more information than what was released for the KDD Cup 2022. It includes not only SCADA data but also weather data such as relative humidity, wind speed, and wind direction, sourced from the Fifth Generation of the European Centre for Medium-Range Weather Forecasts (ECMWF) atmospheric reanalyses of the global climate (ERA5). The dataset encompasses data collected over two years from a wind farm with 134 wind turbines, covering the period from January 2020 to December 2021. The folder structure of sdwpf_full is:sdwpf_full--- sdwpf_turb_location_elevation.csv--- sdwpf_2001_2112_full.csv--- sdwpf_2001_2112_full.parquetThe descriptions of each sub-folder in the sdwpf_full dataset are as follows:sdwpf_turb_location_elevation.csv: This file details the relative positions and elevations of all wind turbines within the dataset.sdwpf_2001_2112_full.csv: This dataset includes data collected two years from a wind farm containing 134 wind turbines, spanning from Jan. 2020 to Dec. 2021. It offers comprehensive enhancements over the sdwpf_kddcup/sdwpf_245days_v1.csv, including:Extended time span: It spans two years, from January 2020 to December 2021, whereas sdwpf_245days_v1.csv covers only 245 days.Enriched weather information: This includes additional data such as relative humidity, wind speed, and wind direction, sourced from the Fifth generation of the European Centre for Medium-Range Weather Forecasts (ECMWF) atmospheric reanalyses of the global climate (ERA5).Expanded temporal details: Unlike during the KDD Cup Challenge where timestamp information was withheld to prevent data linkage, this version includes specific timestamps for each data point.sdwpf_2001_2112_full.parquet: This dataset is identical to sdwpf_2001_2112_full.csv, but in a different data format.

This data set contains NOAA/NCEP GFS deep layer mean wind forecast imagery over the Western Pacific Ocean. Products include deep layer mean and ensemble variance winds. Products are available every 12 hours out to 120 hours. These images were developed by NOAA/NCEP and are in gif format.

which corresponding to an hours

Dataset

1. observation data over 14 weather stations

Variables: hourly near-surface 2-min average wind speed, wind direction

2. ECMWF-IFS forecast data over 14 weather stations

Variables: hourly predictors at surface level and upper level in next 48 hours (shown in Table 1. and Table 2.)

Table 1. ECMWF-IFS forecast data at surface level

Table 2. ECMWF-IFS forecast data at upper level

3. key variables constructed by feature engineering

(1) sort-term statistics, including maximum, minimum, mean and variance of key variables (2t, 10u, 10v and 10ws) from ECMWF-IFS model during the next 48 hours,

(2) long-term statistics, including mean and deviation of key variables (2t, 10u, 10v and 10ws) from ECMWF-IFS model during history 3-yr period (January 2020–December 2022),

(3) thermodynamic factors, including the low-level wind shear between 10ws and 100ws, vertical wind shear between 200 hPa and 850 hPa, the differences between sst and 2t.

Scripts

1. Random Forest model training code

2. LightGBM model training code

3. XGBoost model training code

4. TabNet-MTL model training code

Map InformationThis nowCOAST time-enabled map service provides maps depicting NWS gridded forecasts of the following selected sensible surface weather variables or elements: air temperature (including daily maximum and minimum), apparent air temperature, dew point temperature, relative humidity, wind velocity, wind speed, wind gust, total sky cover, and significant wave height for the next 6-7 days. Additional forecast maps are available for 6-hr quantitative precipitation (QPF), 6-hr quantitative snowfall, and 12-hr probability of precipitation. These NWS forecasts are from the National Digital Forecast Database (NDFD) at a 2.5 km horizontal spatial resolution. Surface is defined as 10 m (33 feet) above ground level (AGL) for wind variables and 2 m (5.5 ft) AGL for air temperature, dew point temperature, and relative humidity variables. The forecasts extend out to 7 days from 0000 UTC on Day 1 (current day). The forecasts are updated in the nowCOAST map service four times per day. For more detailed information about the update schedule, please see: https://new.nowcoast.noaa.gov/help/#section=updatescheduleThe forecast projection availability times listed below are generally accurate, however forecast interval and forecast horizon vary by region and variable. For the most up-to-date information, please see https://graphical.weather.gov/docs/datamanagement.php.The forecasts of the air, apparent, and dew point temperatures are displayed using different colors at 2 degree Fahrenheit increments from -30 to 130 degrees F in order to use the same color legend throughout the year for the United States. This is the same color scale used for displaying the NDFD maximum and minimum air temperature forecasts. Air and dew point temperature forecasts are available every hour out to +36 hours from forecast issuance time, at 3-hour intervals from +36 to +72 hours, and at 6-hour intervals from +72 to +168 hours (7 days). Maximum and minimum air temperature forecasts are each available every 24 hours out to +168 hours (7 days) from 0000 UTC on Day 1 (current day).The relative humidity (RH) forecasts are depicted using different colors for every 5-percent interval. The increment and color scale used to display the RH forecasts were developed to highlight NWS local fire weather watch/red flag warning RH criteria at the low end (e.g. 15, 25, & 35% thresholds) and important high end RH thresholds for other users (e.g. agricultural producers) such as 95%. The RH forecasts are available every hour out to +36 hours from 0000 UTC on Day 1 (current day), at 3-hour intervals from +36 to +72 hours, and at 6-hour intervals from +72 to +168 hours (7 days).The 6-hr total precipitation amount forecasts or QPFs are symbolized using different colors at 0.01, 0.10, 0.25 inch intervals, at 1/4 inch intervals up to 4.0 (e.g. 0.50, 0.75, 1.00, 1.25, etc.), at 1-inch intervals from 4 to 10 inches and then at 2-inch intervals up to 14 inches. The increments from 0.01 to 1.00 or 2.00 inches are similar to what are used on NCEP/Weather Prediction Center's QPF products and the NWS River Forecast Center (RFC) daily precipitation analysis. Precipitation forecasts are available for each 6-hour period out to +72 hours (3 days) from 0000 UTC on Day 1 (current day).The 6-hr total snowfall amount forecasts are depicted using different colors at 1-inch intervals for snowfall greater than 0.01 inches. Snowfall forecasts are available for each 6-hour period out to +48 hours (2 days) from 0000 UTC on Day 1 (current day).The 12-hr probability of precipitation (PoP) forecasts are displayed for probabilities over 10 percent using different colors at 10, 20, 30, 60, and 85+ percent. The probability of precipitation forecasts are available for each 12-hour period out to +72 hours (3 days) from 0000 UTC on Day 1 (current day).The wind speed and wind gust forecasts are depicted using different colors at 5 knots increment up to 115 knots. The legend includes tick marks for both knots and miles per hour. The same color scale is used for displaying the RTMA surface wind speed forecasts. The wind velocity is depicted by curved wind barbs along streamlines. The direction of the wind is indicated with an arrowhead on the wind barb. The flags on the wind barb are the standard meteorological convention in units of knots. The wind speed and wind velocity forecasts are available hourly out to +36 hours from 00:00 UTC on Day 1 (current day), at 3-hour intervals out to +72 hours, and at 6-hour intervals from +72 to +168 hours (7 days). The wind gust forecasts are available hourly out to +36 hours from 0000 UTC on Day 1 (current day) and at 3-hour intervals out to +72 hours (3 days).The total sky cover forecasts are displayed using progressively darker shades of gray for 10, 30, 60, and 80+ percentage values. Sky cover values under 10 percent are shown as transparent. The sky cover forecasts are available for each hour out to +36 hours from 0000 UTC on Day 1 (current day), every 3 hours from +36 to +72 hours, and every 6 hours from +72 to +168 hours (7 days).The significant wave height forecasts are symbolized with different colors at 1-foot intervals up to 20 feet and at 5-foot intervals from 20 feet to 35+ feet. The significant wave height forecasts are available for each hour out to +36 hours from 0000 UTC on Day 1 (current day), every 3 hours from +36 to +72 hours, and every 6 hours from +72 to +144 hours (6 days).Background InformationThe NDFD is a seamless composite or mosaic of gridded forecasts from individual NWS Weather Forecast Offices (WFOs) from around the U.S. as well as the NCEP/Ocean Prediction Center and National Hurricane Center/TAFB. NDFD has a spatial resolution of 2.5 km. The 2.5km resolution NDFD forecasts are presently experimental, but are scheduled to become operational in May/June 2014. The time resolution of forecast projections varies by variable (element) based on user needs, forecast skill, and forecaster workload. Each WFO prepares gridded NDFD forecasts for their specific geographic area of responsibility. When these locally generated forecasts are merged into a national mosaic, occasionally areas of discontinuity will be evident. Staff at NWS forecast offices attempt to resolve discontinuities along the boundaries of the forecasts by coordinating with forecasters at surrounding WFOs and using workstation forecast tools that identify and resolve some of these differences. The NWS is making progress in this area, and recognizes that this is a significant issue in which improvements are still needed. The NDFD was developed by NWS Meteorological Development Laboratory.As mentioned above, a curved wind barb with an arrow head is used to display the wind velocity forecasts instead of the traditional wind barb. The curved wind barb was developed and evaluated at the Data Visualization Laboratory of the NOAA-UNH Joint Hydrographic Center/Center for Coastal and Ocean Mapping (Ware et al., 2014). The curved wind barb combines the best features of the wind barb, that it displays speed in a readable form, with the best features of the streamlines which shows wind patterns. The arrow head helps to convey the flow direction.Time InformationThis map is time-enabled, meaning that each individual layer contains time-varying data and can be utilized by clients capable of making map requests that include a time component.This particular service can be queried with or without the use of a time component. If the time parameter is specified in a request, the data or imagery most relevant to the provided time value, if any, will be returned. If the time parameter is not specified in a request, the latest data or imagery valid for the present system time will be returned to the client. If the time parameter is not specified and no data or imagery is available for the present time, no data will be returned.In addition to ArcGIS Server REST access, time-enabled OGC WMS 1.3.0 access is also provided by this service.Due to software limitations, the time extent of the service and map layers displayed below does not provide the most up-to-date start and end times of available data. Instead, users have three options for determining the latest time information about the service:Issue a returnUpdates=true request for an individual layer or for the service itself, which will return the current start and end times of available data, in epoch time format (milliseconds since 00:00 January 1, 1970). To see an example, click on the "Return Updates" link at the bottom of this page under "Supported Operations". Refer to the ArcGIS REST API Map Service Documentation for more information.Issue an Identify (ArcGIS REST) or GetFeatureInfo (WMS) request against the proper layer corresponding with the target dataset. For raster data, this would be the "Image Footprints with Time Attributes" layer in the same group as the target "Image" layer being displayed. For vector (point, line, or polygon) data, the target layer can be queried directly. In either case, the attributes returned for the matching raster(s) or vector feature(s) will include the following:validtime: Valid timestamp.starttime: Display start time.endtime: Display end time.reftime: Reference time (sometimes reffered to as issuance time, cycle time, or initialization time).projmins: Number of minutes from reference time to valid time.desigreftime: Designated reference time; used as a common reference time for all items when individual reference times do not match.desigprojmins: Number of minutes from designated reference time to valid time.Query the nowCOAST LayerInfo web service, which has been created to provide additional information about each data layer in a service, including a list of all available "time stops" (i.e. "valid times"), individual timestamps, or the valid time of a layer's latest available data (i.e. "Product Time"). For more information about the LayerInfo web service, including examples of various types of

This map displays the forecasted wind speeds over the next 72 hours across the contiguous United States. Wind Speed is the expected 10-meter Above Ground Level (AGL) sustained wind speed (in knots) for the indicated hour. Wind speed forecasts are valid at the top of the indicated hour. Data are updated hourly from the National Digital Forecast Database produced by the National Weather Service.Where is the data coming from?The National Digital Forecast Database (NDFD) was designed to provide access to weather forecasts in digital form from a central location. The NDFD produces forecast data of sensible weather elements. NDFD contains a seamless mosaic of digital forecasts from National Weather Service (NWS) field offices working in collaboration with the National Centers for Environmental Prediction (NCEP). All of these organizations are under the administration of the National Oceanic and Atmospheric Administration (NOAA).Source: https://tgftp.nws.noaa.gov/SL.us008001/ST.opnl/DF.gr2/DC.ndfd/AR.conus/VP.001-003/ds.wspd.binWhere can I find other NDFD data?The Source data is downloaded and parsed using the Aggregated Live Feeds methodology to return information that can be served through ArcGIS Server as a map service or used to update Hosted Feature Services in Online or Enterprise.What can you do with this layer?This map service is suitable for data discovery and visualization. Identify features by clicking on the map to reveal the pre-configured pop-ups. View the time-enabled data using the time slider by Enabling Time Animation.This map is provided for informational purposes and is not monitored 24/7 for accuracy and currency.If you would like to be alerted to potential issues or simply see when this Service will update next, please visit our Live Feed Status Page!

Overview

The purpose of this work is to assess the sensitivity of the forecast for turbine height wind speed to initial condition (IC) uncertainties over the Columbia River Gorge and Columbia River Basin for two typical weather phenomena: a local thermal gradient induced by a marine air intrusion and passage of a cold front. The Weather Research and Forecasting (WRF) model data assimilation system (WRFDA) was used to generate ensemble ICs from the North American Regional Analysis (NARR) for the WRF model initialization. The simulated turbine-height wind speeds were categorized into four types using the self-organizing map (SOM) technique. This work advances understanding of IC uncertainties impacts on wind speed forecasts and locates the high-impact regions.

Data Details

This dataset contains 100 ensemble simulation outputs over the WFIP2 study region (outer domain, d01) for the sea-breeze case. Variables include surface pressure (PSFC), geopotential height (PH), pressure (P), 2-m temperature (T2), and wind speed (U & V) are compressed in a single zip file for each case. The files are named in the format of [var].[timestamp].nc, which contain 100 ensembles in one file. WRF namelists are also included. The sea-breeze case is for the time period 2016-08-16 to 2016-08-17.

Accurate short-term forecasts of wind conditions and power generation are critical for the cost-effective and reliable integration of offshore wind farms along the U.S. East Coast. These forecasts, spanning operational horizons from few minutes to several days ahead, are essential inputs to grid- and farm-level operational decision-making.

Yet, long-term records of hub-height wind measurements in U.S. offshore regions are scarce, fragmented, or difficult to access. This lack of publicly available, high-quality data presents a significant barrier to the development, benchmarking, and deployment of advanced forecasting models—unlike other regions with significant offshore wind potential (e.g., the North Sea), where well-curated datasets have fueled progress and accelerated the progress in data-driven forecasting.

In response, and as part of a NOWRDC-supported project, Rutgers University developed one of the first data-driven offshore wind forecasting models specifically tailored to the U.S. East Coast. This repository contains important datasets related to this project:

• A year-long record of raw and processed hub-height wind speeds at key offshore wind energy locations in the NY/NJ Bight.

• Day-ahead forecasts of key meteorological variables from an in-house numerical weather prediction (NWP) model developed by Rutgers University, called RU-WRF.

• Machine learning–based hub-height wind speed forecasts from AIRU-WRF - Rutgers' newly developed offshore wind forecasting model, trained on both historical measurements and RU-WRF outputs.

By making the datasets and forecasts publicly available, we aim to catalyze further research, model development, and benchmarking studies in offshore wind for U.S. coastal regions.


Related publications and patents:

[1] Ye, Feng, Joseph Brodie, Travis Miles, and Ahmed Aziz Ezzat. “AIRU-WRF: A physics-guided spatio-temporal wind forecasting model and its application to the US Mid Atlantic offshore wind energy areas.” Renewable Energy 223 (2024): 119934 (*An earlier version of AIRU-WRF that primarily focused on six-hour ahead forecast horizons, i.e., <= 6 hours*)

[2] Ye, Feng, Travis Miles, and Ahmed Aziz Ezzat. “Improved spatio-temporal offshore wind forecasting with coastal upwelling information.” Applied Energy 380 (2025): 125010 (**An update to AIRU-WRF to model coastal upwelling effects**)

[3] Ye, Feng, Travis Miles, and Ahmed Aziz Ezzat. “Offshore Wind Energy Prediction Using Machine Learning with Multi-Resolution Inputs.” In Multimodal and Tensor Data Analytics for Industrial Systems Improvement, pp. 167-183. Cham: Springer International Publishing, 2024 (**A variant of AIRU-WRF that leverages multi-resolution WRF inputs**).

[4] Ye, Feng, Joseph Brodie, Travis Miles, and Ahmed Aziz Ezzat. “Ultra-short-term probabilistic wind forecasting: Can numerical weather predictions help?.” In 2023 IEEE Power & Energy Society General Meeting (PESGM), pp. 1-5. IEEE, 2023 (**A method to leverage WRF wind velocity predictions for very-short-term wind forecasting**).

[5] Ji, Jiaxiang, Ye, Feng, Travis Miles, and Ahmed Aziz Ezzat. “A Multivariate, Time-Dependent Ensemble Method for Space-Time Wind Energy Forecasting,” Under Review (2025) (**Most recent version of AIRU-WRF -as of June 2025- that primarily focused on day-ahead forecasting, i.e., <= 24 hours**)

[6] Walid, K.B., Ye, F., Ji, J., Miles, T., Aziz Ezzat, A., and Jiang, Y., “Economic and Reliability Value of Improved Offshore Wind Forecasting in Bulk Power Grid Operation,” Working paper (2025). (**An economic validation study that quantifies the projected grid benefits of AIRU-WRF**)

[7] “Techniques To Provide Improved Wind Input for Operating Offshore Wind Turbines,” U.S. Application 19/111. Inventors: Ahmed Aziz Ezzat, Feng Ye, Travis Miles, Joseph Brodie (**Patent for AIRU-WRF supported by the Rutgers Office of Innovation Ventures**)

The maximum wind speed during the forecast period km/hr (mdws). Week 1 and week 2 forecasted index is available daily from September 1 to August 31. Week 3 and week 4 forecasted index is available weekly (Thursday) from September 1 to August 31. Winds can significantly influence crop growth and yield mainly due to mechanical damage of plant vegetative and reproductive organs, an imbalance of plant-soil-atmosphere water relationships, and pest and disease distributions in agricultural fields. The maximum wind speed and the number of strong wind days over the forecast period represent short term and extended strong wind events respectively. Agriculture and Agri-Food Canada (AAFC) and Environment and Climate Change Canada (ECCC) have together developed a suite of extreme agrometeorological indices based on four main categories of weather factors: temperature, precipitation, heat, and wind. The extreme weather indices are intended as short-term prediction tools and generated using ECCC’s medium range forecasts to create a weekly index product on a daily and weekly basis.

This dataset contains Weather Research and Forecasting 12KM wind imagery generated in real-time during the ICE-L project. Horizontal winds are modeled at the following hPa levels: 250, 300, 500, 700, 850, and 925. The imagery is in PNG format and covers the time span from 2007-11-19 00:00:00 to 2007-12-21 23:59:59.

This nowCOAST time-enabled map service provides maps depicting the forecasts of the sensible weather and marine weather elements for wind velocity, wind speed, and wind gusts. Generated by the weather forecasters at regional NWS Weather Forecast Offices (WFOs) and the National Centers for Environmental Prediction (NCEP). The NDFD is a seamless composite or mosaic of gridded forecasts from individual NWS Weather Forecast Offices (WFOs) from around the U.S. as well as the NCEP Ocean Prediction Center and National Hurricane Center/TAFB. The time resolution of forecast projections varies by variable (element) based on user needs, forecast skill, and forecaster workload. Each WFO prepares gridded NDFD forecasts for their specific geographic area of responsibility. When these locally generated forecasts are merged into a national mosaic, occasionally areas of discontinuity will be evident. Staff at NWS forecast offices attempt to resolve discontinuities along the boundaries of the forecasts by coordinating with forecasters at surrounding WFOs and using workstation forecast tools that identify and resolve some of these differences. The NWS is making progress in this area, and recognizes that this is a significant issue in which improvements are still needed. The NDFD was developed by NWS Meteorological Development Laboratory. The spatial resolution is about 2.5 km (1.6 mi) for CONUS, HI, and Guam, 1.25 km (0.8) for PR and 3km (1.9 mi) for Alaska. The latest wind speed and wind velocity forecasts are available hourly out to +36 hours from 00:00 UTC on Day 1 (current day), at 3-hour intervals out to +72 hours, and at 6-hour intervals from +72 to +168 hours (7 days). The wind gust forecasts are available hourly out to +36 hours from 0000 UTC on Day 1 (current day) and at 3-hour intervals out to +72 hours (3 days). Day 1-3 forecasts are updated hourly from 00Z to 23Z and Day 4-7 forecasts are updated at 00, 06, 12, 18, and 22Z.

Mean wind speed at a height of 10 metres above the surface over the period 00h-24h local time. Unit: m s-1. The Wind Speed variable is part of the Agrometeorological indicators dataset produced by the European Centre for Medium-Range Weather Forecasts (ECMWF) through the Copernicus Climate Change Service (C3S). The Agrometeorological indicators dataset provides daily surface meteorological data for the period from 1979 to present as input for agriculture and agro-ecological studies. This dataset is based on the hourly ECMWF ERA5 data at surface level and is referred to as AgERA5. References: https://doi.org/10.24381/cds.6c68c9bb

The Copernicus Climate Change Service (C3S) aims to combine observations of the climate system with the latest science to develop authoritative, quality-assured information about the past, current and future states of the climate in Europe and worldwide. ECMWF operates the Copernicus Climate Change Service on behalf of the European Union and will bring together expertise from across Europe to deliver the service.

Data publication: 2021-01-30

Data revision: 2021-10-05

Contact points:

Metadata Contact: ECMWF - European Centre for Medium-Range Weather Forecasts

Resource Contact: ECMWF Support Portal

Data lineage:

Agrometeorological data were aggregated to daily time steps at the local time zone and corrected towards a finer topography at a 0.1° spatial resolution. The correction to the 0.1° grid was realized by applying grid and variable-specific regression equations to the ERA5 dataset interpolated at 0.1° grid. The equations were trained on ECMWF's operational high-resolution atmospheric model (HRES) at a 0.1° resolution. This way the data is tuned to the finer topography, finer land use pattern and finer land-sea delineation of the ECMWF HRES model.

Resource constraints:

License Permission

This License is free of charge, worldwide, non-exclusive, royalty free and perpetual. Access to Copernicus Products is given for any purpose in so far as it is lawful, whereas use may include, but is not limited to: reproduction; distribution; communication to the public; adaptation, modification and combination with other data and information; or any combination of the foregoing.

Where the Licensee communicates or distributes Copernicus Products to the public, the Licensee shall inform the recipients of the source by using the following or any similar notice:

• Generated using Copernicus Climate Change Service information [Year]

and/or

• Generated using Copernicus Atmosphere Monitoring Service information [Year]

More information on Copernicus License in PDF version at: https://cds.climate.copernicus.eu/api/v2/terms/static/licence-to-use-copernicus-products.pdf

Online resources:

Data download from original source

The global wind speed monitoring market size was valued at USD 1.5 billion in 2025 and is projected to reach USD 4.5 billion by 2033, exhibiting a CAGR of 12.4% during the forecast period. The market growth is primarily driven by the rising demand for renewable energy sources, such as wind power, and the need for accurate wind speed data for efficient and safe operation of wind turbines. Moreover, the increasing adoption of wind speed monitoring systems in agriculture, aviation, and other sectors is further contributing to market growth. Key market trends include the growing adoption of IoT and AI technologies, which enable remote monitoring and data analysis, and the emergence of highly accurate and affordable wind speed sensors. The market is expected to witness significant growth in emerging economies, such as China and India, where there is a substantial investment in renewable energy projects. Additionally, the rising awareness about environmental sustainability and the need for accurate wind speed data for weather forecasting and disaster management are expected to drive market growth in the coming years. Wind speed monitoring is critical for various industries, including agriculture, aviation, energy, and others. It provides valuable insights into wind patterns, which can help optimize operations, improve safety, and mitigate risks.

This dataset contains gridded spatial fields of daily 10-meter wind speed U-component (m/s) ensemble forecasts with a 48-hour lead time. The forecast data are from the European Centre for Medium-Range Weather Forecasts' (ECMWF) 50-member ensemble, and the time range of forecast days is 10 years from 2007-01-03 to 2017-01-02. The forecast is on a 0.5° × 0.5° grid, covering the region from -10° E to 30° E and from 30° N to 70° N, resulting in 81 × 81 grid points roughly covering Europe.