Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
815
datasets available to search
ShareScore release 0.7.1
Dataset results
815 results for “Forecasting”
Probabilistic forecasts of the daily maximum of the Kp index produced by the SERENADE prototype model and three empirical models for the period 2010-2018
<p>This dataset contains the probabilistic outputs of SERENADE's first prototype model dedicated to the forecasting of the <span class="math-tex">\(\textit{Kp}_{\textrm{max, 24 h}}\)</span> index for forecasting horizons ranging between 2 and 7 days. The period covered is the one of the SDOML dataset, which is 2010-05 --- 2018-12. All data is contained in a single pickle file, that can be opened in Python, using the following code lines:</p> <p><span class="math-tex">\(\texttt{import pickle}\\ \texttt{with open(DATA_PATH+`/serenade_outputs.pkl', `rb') as f:}\\ ~~~~\texttt{dict_outputs = pickle.load(f)}\)</span></p> <p>The pickle file contains a dictionnary, which itself contains Pandas DataFrames. Each DataFrame corresponds to a forecasting horizon. The dictionnary's keys are the forecasting horizons stored as strings, that is:</p> <p><span class="math-tex">\(\texttt{dict_output.keys() = [`2',`3',`4',`5',`6',`7']}\)</span></p> <p>The DataFrames are indexed by datetime. They contain the observed (true) hourly values of the daily maximum of the Kp index, the forecasts provided by SERENADE and three baseline models (Climatology model, Persistence model and 27-day Recurrence model). The forecast values include the mean and the standard deviation of the forecast normal distributions. Missing moments are due to the absence of EUV images needed to provide the forecast at the given moment.</p> <p> </p>
WaterBench-Iowa: A Large-scale Benchmark Dataset for Data-Driven Streamflow Forecasting
<p>WaterBench-Iowa is a comprehensive benchmark dataset for streamflow forecasting. It follows FAIR data principles that are prepared with a focus on convenience for utilizing in data-driven and machine learning studies and provides benchmark performance for state-of-art deep learning architectures on the dataset for comparative analysis. By aggregating the datasets of streamflow, precipitation, watershed area, slope, soil types, and evapotranspiration from federal agencies and state organizations (i.e., NASA, NOAA, USGS, and Iowa Flood Center), we provided the WaterBench for hourly streamflow forecast studies. This dataset has a high temporal and spatial resolution with rich metadata and relational information, which can be used for varieties of deep learning and machine learning research. To some extent, WaterBench makes up for the lack of a unified benchmark in earth science research. We highly encourage researchers to use the WaterBench for deep learning research in hydrology.</p>
An analogue based forecasting system for Mediterranean marine litter concentration - Code and simulations dataset
<p>This dataset contains the files and codes required to perform the computations described in "An analogue based forecasting system for Mediterranean marine litter concentration" by Gabriel Jordà and Javier Soto-Navarro, to be published in Ocean Science 2022</p> <p><strong>Summary</strong></p> <p>This dataset comprises the files and code necessary to implement a statistical forecasting system for marine litter (ML) concentration in the Mediterranean Sea based on the analogues method. The system uses a historical database of ML concentration simulated by a high resolution realistic model and is trained to identify meteorological situations in the past that are similar to the forecasted ones. Then, the corresponding ML concentrations of the past analog days are used to construct the ML concentration forecast. Due to the scarcity of observations, the forecasting system has been validated against a synthetic reality (i.e. the outputs from a ML modelling system). Different approaches can be tested to refine the system. The analysis of the results show that using integral definitions for the similarity function, based on the history of the meteorological situation, improves the system performance. The system accuracy depends on the region of application being better for larger regions. The method performs well to capture the spatial patterns but performs worse to capture the temporal variability, specially the extreme values. Despite the inherent limitations of using a synthetic reality to validate the system.</p> <p><strong>Dataset</strong></p> <p>The dataset is developed in Matlab format, and is comprised by:</p> <ul> <li>Matlab files with ML concentration maps derived from the dispersion simulations performed by Soto-Navarro et al. (2020). See the reference for a detailed description of the model and simulations.</li> <li>Matlab files with atmospheric fields from ERA5 dataset (sea level pressure (SLP) and wind speed (U<sub>10</sub>, V<sub>10. </sub><a href="https://climate.copernicus.eu/climate-reanalysis">https://climate.copernicus.eu/climate-reanalysis</a>).</li> <li>Matlab files with the grid information for the different regions and sub-regions of the Mediterranean Sea analyzed.</li> <li>Matlab scripts needed for the implementation and running of the analogs based model.</li> <li>A document describing the implementation procedure.</li> </ul> <p><strong>References</strong></p> <p>Soto-Navarro, J., Jordà, G., Deudero, S., Alomar, C., Amores, Á., and Compa, M.: 3D hotspots of marine litter in the Mediterranean: A modeling study, Mar. Pollut. Bull., 155, 111159, https://doi.org/10.1016/j.marpolbul.2020.111159, 2020.</p>
Global and regional long-term M4.95+ seismicity forecasts undergoing prospective evaluation
<p>Contains a stationary M5.95+ seismicity forecast derived from the Global Earthquake Activity Rate (GEAR1) model of Bird et al. (2015) and nineteen time-invariant M4.95+ earthquake forecasts participating in forecast experiments conducted by the Collaboratory for the Study of Earthquake Predictability (CSEP) in California, New Zealand, and Italy. Ten additional forecast files are included to properly perform comparative tests.</p> <p>Earthquake rates are expressed as number of M4.95+ earthquakes per 0.1<sup>o</sup> cell per year. Forecasts are stored in tab separated values files with the following fields (the first row is shown as an example):</p> <table> <tbody> <tr> <td>lon_min</td> <td>lon_max</td> <td>lat_min</td> <td>lat_1</td> <td>depth_0</td> <td>depth_1</td> <td>mag_0</td> <td>mag_1</td> <td>rate</td> <td>flag</td> </tr> <tr> <td>-125.4</td> <td>-125.3</td> <td>40.1</td> <td>40.2</td> <td>0.0</td> <td>30.0</td> <td>4.95</td> <td>5.05</td> <td>5.8499e-04</td> <td>1</td> </tr> </tbody> </table> <p>The data, forecasts, and tests are described in detail in the following publications and the references contained therein:</p> <p>Bayona, J.A., Savran, W.H., Iturrieta, P., Gerstenberger, M.C., Marzocchi, W., Schorlemmer, D., and Werner, M.J., Are Regionally Calibrated Seismicity Models more Informative than Global Models? Insights from California, New Zealand, and Italy. <em>in review</em>.</p> <p>Bayona, J.A., Savran, W.H., Rhoades, D.A. and Werner, M.J., 2022. Prospective evaluation of multiplicative hybrid earthquake forecasting models in California. <em>Geophysical Journal International</em>, <em>229</em>(3), pp.1736-1753.</p> <p>Bird, P., Jackson, D.D., Kagan, Y.Y., Kreemer, C. and Stein, R.S., 2015. GEAR1: A Global Earthquake Activity Rate Model Constructed from Geodetic Strain Rates and Smoothed SeismicityGEAR1: A Global Earthquake Activity Rate Model Constructed from Geodetic Strain Rates and Smoothed Seismicity. <em>Bulletin of the Seismological Society of America</em>, <em>105</em>(5), pp.2538-2554.</p> <p>Marzocchi W, Schorlemmer D, Wiemer S. Preface. Ann. Geophys. [Internet]. 2010Nov.5 [cited 2022Sep.16];53(3):III-VIII. Available from: https://www.annalsofgeophysics.eu/index.php/annals/article/view/4851</p> <p>Rhoades, D.A., Christophersen, A., Gerstenberger, M.C., Liukis, M., Silva, F., Marzocchi, W., Werner, M.J. and Jordan, T.H., 2018. Highlights from the first ten years of the New Zealand earthquake forecast testing center. <em>Seismological Research Letters</em>, <em>89</em>(4), pp.1229-1237.</p> <p>Savran, W.H., Bayona, J.A., Iturrieta, P., Asim, K.M., Bao, H., Bayliss, K., Herrmann, M., Schorlemmer, D., Maechling, P.J. and Werner, M.J., 2022. pycsep: A python toolkit for earthquake forecast developers. <em>Seismological Society of America</em>, <em>93</em>(5), pp.2858-2870.</p> <p>Schorlemmer, D., Gerstenberger, M.C., Wiemer, S., Jackson, D.D. and Rhoades, D.A., 2007. Earthquake likelihood model testing. <em>Seismological Research Letters</em>, <em>78</em>(1), pp.17-29.</p> <p>Werner, M.J., Zechar, J.D., Marzocchi, W. and Wiemer, S., 2010. Retrospective evaluation of the five-year and ten-year CSEP-Italy earthquake forecasts. <em>arXiv preprint arXiv:1003.1092</em>.</p> <p>Zechar, J.D., Gerstenberger, M.C. and Rhoades, D.A., 2010. Likelihood-based tests for evaluating space–rate–magnitude earthquake forecasts. <em>Bulletin of the Seismological Society of America</em>, <em>100</em>(3), pp.1184-1195.</p> <p>Zechar, J.D., Schorlemmer, D., Werner, M.J., Gerstenberger, M.C., Rhoades, D.A. and Jordan, T.H., 2013. Regional earthquake likelihood models I: First‐order results. <em>Bulletin of the Seismological Society of America</em>, <em>103</em>(2A), pp.787-798.</p>
Archive of NASA-Unified WRF model daily forecasting simulations for DOE TRACER IOP
<pre># Copyright 2022 NASA GSFC All rights reserved. # Creative commons attribution 4.0 international license NASA-Unified WRF model daily simulations for DOE TRACER IOP Document updated: 22 June 2022 Point of contact: Takamichi Iguchi (ESSIC UMD, Code612 NASA GSFC), takamichi.iguchi@nasa.gov Toshi Matsui (ESSIC UMD, Code612 NASA GSFC), toshihisa.matsui-1@nasa.gov Contents: ./READMEtracer.txt # this file ./namelist.wps.tracer_iop_31.template # namelist.wps file to configure WRF Pre-Processing System (WPS) ./namelist.input.real.tracer_iop_31.template # namelist.input file for NU-WRF model real.exe ./namelist.input.wrf.tracer_iop_31.template # namelist.input file for NU-WRF model wrf.exe ./${YYYY}${MM}${DD} # these directories contain files produced from 48-hours NU-WRF forecasting from 00UTC on ${YYYY}${MM}${DD}: pyplot_${YYYY}-${MM}-${DD}_${HH}${MN}${SC}.png # Plot for Composite radar reflectivity (dBZ) # PBL height (m) + 10-m horizontal wind (850hPa-level wind in plots before 06/02/2022), # OLR TOA (W m-2), and 5-mins-accumulated IC+CG lighting flash extent density (flash km-2) # Note that this composite dBZ is calculated from NSSL 2-moment microphysics for S-band, # not from POLARRIS radar simulator pyplot.gif # Gif annimation file combining the png plot files for 1~48 hours in the forecasting accprecip_${YYYY}-${MM}-${DD}_${HH}${MN}${SC}.png # Plot for 1, 3, 6-hours, and total accumulated surface precipitation (mm) accprecip.gif # Gif annimation file combining the png plot files for 1~48 hours in the forecasting polarris_zh_zdr_rh_vr_${YYYY}_${MM}${DD}_${HH}${MN}${SC}.png # Plot from POLARRIS radar simulator in NU-WRF for QCed Reflectivity (dBZ), # differential reflectivity (dB), cross-polar correlation (-), and # radial velocity (m s-1) at 0.5 degree elevation angle polarris_zh_zdr_rh_vr.gif # Gif annimation file combining the png plot files roughly every hour # for 1~48 hours in the forecasting polarris_zh_4sweeps_${YYYY}_${MM}${DD}_${HH}${MN}${SC}.png # Plot from POLARRIS radar simulator in NU-WRF for QCed Reflectivity (dBZ) # at 0.5, 1.8, 4.0 and 8.0 degree elevation angles polarris_zh_4sweeps.gif # Gif annimation file combining the png plot files roughly every hour # for 1~48 hours in the forecasting # following files are produced 3 days late # day1 represent the first 0-24hr forecast, day2 represents the 24-48hr forecast. CFAD_con_day?.png # Convective part of Contoured Frequency of Altitude Diagrams CFAD_str_day?.png # Stratiform part of Contoured Frequency of Altitude Diagrams QVP_con_day?.png # Convective part of QVP-like domain-mean radar profiles QVP_str_day?.png # Stratiform part of QVP-like domain-mean radar profiles RadarFrac_day?.png # Composite Radar Horizontal Fraction (0-1) by different minimum reflectivity thresholds</pre>
An Objective Detection of Separation Scenario in Tropical Cyclone Trajectories Based on Ensemble Weather Forecast Data
<p>This repository contains the data used in "An Objective Detection of Separation Scenario in Tropical Cyclone Trajectories Based on Ensemble Weather Forecast Data" by Oettli and Kotsuki (submitted to Journal of Geophysical Research: Atmospheres).</p>
Рис. 11. Гидрометеоролого-технологическая блок-схема хоЗяйственных решений (di) и гидрометеорологических долгосрочных прогноЗов (Pi), необходимых для их принятия. Fig. 11. Hydrometeorological-technological block diagram of economic decisions (di) and hydrometeorological long-term forecasts (Pi) necessary for their adoption. in Review of methods for the forecast of mollusk's spat productivity in sea-farms of Primorye and probable ways of their enhancement
Рис. 11. Гидрометеоролого-технологическая блок-схема хоЗяйственных решений (di) и гидрометеорологических долгосрочных прогноЗов (Pi), необходимых для их принятия. Fig. 11. Hydrometeorological-technological block diagram of economic decisions (di) and hydrometeorological long-term forecasts (Pi) necessary for their adoption.
Рис. 5. Зависимость начала нереста приморского гребешка и тихоокеанской устрицы в Зал. Петра Великого от суммы поверхностных температур (март–июнь): 1 – начало нереста приморского гребешка; 2 – начало нереста тихоокеанской устрицы; 3 – сумма поверхностных температур За период с марта по июнь. in Review of methods for the forecast of mollusk's spat productivity in sea-farms of Primorye and probable ways of their enhancement
Рис. 5. Зависимость начала нереста приморского гребешка и тихоокеанской устрицы в Зал. Петра Великого от суммы поверхностных температур (март–июнь): 1 – начало нереста приморского гребешка; 2 – начало нереста тихоокеанской устрицы; 3 – сумма поверхностных температур За период с марта по июнь.
Рис. 9. Блок-схема прогноЗирования сроков установки коллекторов и оЖидаемого количества спата [Белогрудов, 1980]. in Review of methods for the forecast of mollusk's spat productivity in sea-farms of Primorye and probable ways of their enhancement
Рис. 9. Блок-схема прогноЗирования сроков установки коллекторов и оЖидаемого количества спата [Белогрудов, 1980].
Рис. 8. СвяЗь меЖду количеством личинок гребешка в планктоне раЗмером 250–275 мкм и количеством спата на коллекторах. Fig. 8. The relationship between the number of the Japanese scallop larvae in plankton with a size of 250 to 275 µm and the number of spat on collectors. in Review of methods for the forecast of mollusk's spat productivity in sea-farms of Primorye and probable ways of their enhancement
Рис. 8. СвяЗь меЖду количеством личинок гребешка в планктоне раЗмером 250–275 мкм и количеством спата на коллекторах. Fig. 8. The relationship between the number of the Japanese scallop larvae in plankton with a size of 250 to 275 µm and the number of spat on collectors.
Рис. 7. Сумма температур перед нерестом приморского гребешка (а) и количество спата на коллекторах (б). Fig. 7. The sum of temperatures before spawning of the Japanese scallop (a) and the number of spat on collectors (б). in Review of methods for the forecast of mollusk's spat productivity in sea-farms of Primorye and probable ways of their enhancement
Рис. 7. Сумма температур перед нерестом приморского гребешка (а) и количество спата на коллекторах (б). Fig. 7. The sum of temperatures before spawning of the Japanese scallop (a) and the number of spat on collectors (б).
Рис. 6. Сроки нереста приморского гребешка (1), роста и раЗвития его личи- нок в планктоне от начала нереста до раЗмеров 150 мкм (2) и от 150 мкм до 250–275 мкм (3). in Review of methods for the forecast of mollusk's spat productivity in sea-farms of Primorye and probable ways of their enhancement
Рис. 6. Сроки нереста приморского гребешка (1), роста и раЗвития его личи- нок в планктоне от начала нереста до раЗмеров 150 мкм (2) и от 150 мкм до 250–275 мкм (3).
Рис. 1. Среднемесячная температура воды в б. Новгородская на поверхно- сти: 1 – За период 1931–1973 гг.; 2 – За 1977 г.; 3 – За 1978 г.; 4 – За 1979 г.; 5 – За 1980 г.; 6 – За 1981 г.; 7 – температура нереста (18ºС). in Review of methods for the forecast of mollusk's spat productivity in sea-farms of Primorye and probable ways of their enhancement
Рис. 1. Среднемесячная температура воды в б. Новгородская на поверхно- сти: 1 – За период 1931–1973 гг.; 2 – За 1977 г.; 3 – За 1978 г.; 4 – За 1979 г.; 5 – За 1980 г.; 6 – За 1981 г.; 7 – температура нереста (18ºС).
Рис. 2. График вЗаимосвяЗи меЖду суммой средних месячных температур воды марта и апреля и датами начала нереста. in Review of methods for the forecast of mollusk's spat productivity in sea-farms of Primorye and probable ways of their enhancement
Рис. 2. График вЗаимосвяЗи меЖду суммой средних месячных температур воды марта и апреля и датами начала нереста.
Radiation Belt Forecast Model and Framework (RBFMF) 10 Hour Hindcast Validation Data
<div><strong>Archived data for the manuscript “On the Performance of a Real-Time Electron Radiation Belt Specification Model” Staples et al., submitted to Space Weather, 2024.</strong></div> <div> </div> <div>Data in these files specify the radiation belt through phase space density (PSD) in adiabatic coordinate system. Simulated PSD is from the Radiation Belt Forecast Model and Framework (RBFMF) 10 hour hindcast, and measured PSD is from an intercalibrated multi-mission observatory (Van Allen Probes, GOES 13, 15, GPS, MMS, and THEMIS). For detailed description of the method used in the computation of this data, see sections 2 and 3 of the submitted manuscript.</div> <div> </div> <div>The THEMIS, Van Allen Probe, MMS, and GOES data used in computations is publicly available via http://cdaweb.gsfc.nasa.gov </div> <div>The GPS data is available via https://www.ngdc.noaa.gov/stp/space-weather/satellite-data/satellite-systems/gps/</div> <div> </div> <div>Data Preperation: </div> <div>Adam Kellerman, akellerman@atmos.ucla.edu </div> <div>Frances Staples, frances.staples@atmos.ucla.edu</div> <div> </div> <div>Support for this work was provided by NASA grants 80NSSC20K1402 and 80NSSC23K0096, and NSF grant 2149782.</div> <div> </div> <div><strong>'PSD_10hrHC_Jan2016-Oct2018.mat'</strong></div> <div>Matlab data file format.</div> <div>Data time period: January 2016 - October 2018. </div> <div> Variable Descriptions:</div> <div>time - Serial date.</div> <div>InvMu - 1st adiabatic invariant coordinate, mu.</div> <div>InvK - 2nd adiabatic invariant coordinate, k.</div> <div>lstar - 3rd adiabatic invariant coordinate, l*.</div> <div>psd_sim - 10 hour radiaiton belt hindcast. Simulated PSD has dimensions corresponding to (time,lstar,mu,k). </div> <div>psd_obs - PSD observed by multi-mission dataset, with dimensions matching the simulated PSD (time, lstar, mu, k). </div> <div> </div> <div><strong>'PSD_10hrHC_Mar2019-Dec2020.mat'</strong></div> <div>Matlab data file format.</div> <div>Data time period March 2019 - December 2020. </div> <div> <div>Variable Descriptions:</div> </div> <div>time - Serial date.</div> <div>InvMu - 1st adiabatic invariant coordinate, mu.</div> <div>InvK - 2nd adiabatic invariant coordinate, k.</div> <div>lstar - 3rd adiabatic invariant coordinate, l*.</div> <div>psd_sim - 10 hour radiaiton belt hindcast. Simulated PSD has dimensions corresponding to (time,lstar,mu,k). </div> <div>psd_gps - PSD observed by the GPS constellation, with dimensions matching the simulated PSD (time, lstar, mu, k). </div> <div> </div> <div><strong>'RBSP_beacondata_Jan2016-Oct2018.mat'</strong></div> <div>Matlab data file format.</div> <div>Data time period January 2016 - October 2018. </div> <div>Variable Descriptions:</div> <div>time - Serial date.</div> <div>InvMu - 1st adiabatic invariant coordinate, mu.</div> <div>InvK - 2nd adiabatic invariant coordinate, k.</div> <div>lstar - 3rd adiabatic invariant coordinate, l*. l* dimensions correpond to the dimensions of the 2nd invariant, K (time, K)</div> <div>psd - real time PSD observed from Van Allen Probe b (beacon data), with dimensions corresponding to (time,mu,k). </div> <div>psd_err - observed error of beacon PSD data (i.e. Beacon_PSD - FinalRBSP_PSD).</div> <div>psd_q - observed quotient of beacon PSD data (i.e., Beacon_PSD/FinalRBSP_PSD).</div> <div> </div> <div><strong>'README.txt'</strong></div> <div>Downloadable file descriptions. </div>
Data from: Forecasting animal distribution through individual habitat selection: Insights for population inference and transferable predictions
<p>Habitat selection models frequently use data collected from a small geographic area over a short window of time to extrapolate patterns of relative abundance to unobserved areas or periods of time. However, these types of models often poorly predict how animals will use habitat beyond the place and time of data collection because space-use behaviors vary between individuals and are context-dependent. Here, we present a modelling workflow to advance predictive distribution performance by explicitly accounting for individual variability in habitat selection behavior and dependence on environmental context. Using global positioning system (GPS) data collected from 238 individual pronghorn, (<em>Antilocapra americana</em>), across 3 years in Utah, we combine individual-year-season-specific exponential habitat-selection models with weighted mixed-effects regressions to both draw inference about the drivers of habitat selection and predict space-use in areas/times where/when pronghorn were not monitored. We found a tremendous amount of variation in both the magnitude and direction of habitat selection behavior across seasons, but also across individuals, geographic regions, and years. We were able to attribute portions of this variation to season, movement strategy, sex, and regional variability in resources, conditions, and risks. We were also able to partition residual variation into inter- and intra-individual components. We then used the results to predict population-level, spatially and temporally dynamic, habitat-selection coefficients across Utah, resulting in a temporally dynamic map of pronghorn distribution at a 30x30m resolution but an extent of 220,000km2. We believe our transferable workflow can provide managers and researchers alike a way to turn limitations of traditional habitat selection models - variability in habitat selection - into a tool to understand and predict species-habitat associations across space and time.</p>
Data from: Evaluating Window Size Effects on Univariate Time Series Forecasting with Machine Learning
<p>In the realm of time series prediction modeling, the window size (w) is a critical hyperparameter that determines the number of time units included in each example provided to a learning model. This hyperparameter is crucial because it allows the learning model to recognize both long-term and short-term trends, as well as seasonal patterns, while reducing sensitivity to random noise. This study aims to elucidate the impact of window size on the performance of machine learning algorithms in univariate time series forecasting tasks. To achieve this, we employed 40 time series from two different domains, conducting experiments with varying window sizes using four types of machine learning algorithms: Bagging, Boosting, Stacking, and a Recurrent Neural Network (RNN) architecture. The results reveal that increasing the window size generally enhances the evaluation metric values up to a stabilization point, beyond which further increases do not significantly improve predictive accuracy. This stabilization effect was observed in both domains when w values exceeded 100 time steps. Moreover, the study found that RNN architectures do not consistently outperform ensemble models in various univariate time series forecasting scenarios.</p>
Dataset of historical hourly information of four european wind farms for wind energy forecasting and maintenance
<p><strong>If you use this dataset please cite this paper: Sánchez-Soriano, J.; Paniagua-Falo, P.J.; Gómez Muñoz, C.Q. Historical Hourly Information of Four European Wind Farms for Wind Energy Forecasting and Maintenance. Data 2025, 10, 38. <a href="https://doi.org/10.3390/data10030038" target="_blank" rel="noopener">https://doi.org/10.3390/data10030038</a></strong></p> <p>For an electric company, having an accurate forecast of the expected electrical production and maintenance from its wind farms is crucial. This information is essential for operating in various existing markets such as Iberian Energy Market Operator - Spanish Hub (OMIE in its Spanish acronym), Portuguese Hub (OMIP in its Spanish acronym), and Iberian electricity market between the Kingdom of Spain and the Portuguese Republic (MIBEL in its Spanish acronym), among others. The accuracy of these forecasts is vital for estimating the costs and benefits of the handling of electricity. This article explains the process of creating the complete dataset, which includes the acquisition of the hourly information of four European wind farms as well as a description of the structure and content of the dataset which amounts to 2 years of hourly information. The wind farms are in three countries, two from Auvergne-Rhône-Alpes (France), Aragon (Spain) and the Piemonte region (Italy). The presented dataset is available and accessible to improve the forecasting and management of wind farms, especially for the detection of faults and the elaboration of a preventive maintenance plan.</p> <p>The full description of the characteristics of the dataset, as well as its components, format and methodology, can be found here: "Historical Hourly Information of Four European Wind Farms for Wind Energy Forecasting and Maintenance". Data 2025, 10, 38. <a href="https://doi.org/10.3390/data10030038" target="_blank" rel="noopener">https://doi.org/10.3390/data10030038</a></p>
Spatial Autocorrelation and Entropy for Renewable Energy Forecasting
<p>Additional resources of the paper "Spatial Autocorrelation and Entropy for Renewable Energy Forecasting".</p> <p>The repository includes:</p> <p>- Datasets;</p> <p>- Prediction system and instructions;</p> <p>- Additional experimental results. </p>
Road surface temperature forecast study HKI-TKU 0708
<p>This dataset includes road weather station measurements, radar and HARMONIE forecast data related<br> to manuscript entitled "Verification of road surface temperature forecasts utilizing data from mobile sensors".<br> The manuscript will be submitted to a scientific journal for publication. Road weather model output<br> data is also included.</p> <p>Each folder contains ReaMe file for the folder's data.</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.