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”
Support data for article "Stochastic forecasting of variable small data as a basis for analyzing an early stage of a cyber epidemic"
<p>Support data for article</p> <p>V. Kovtun, K. Grochla, V. Kharchenko, M. A. Haq, and A. Semenov, “Stochastic forecasting of variable small data as a basis for analyzing an early stage of a cyber epidemic,” Scientific Reports, vol. 13, no. 1. Springer Science and Business Media LLC, Dec. 20, 2023. doi: 10.1038/s41598-023-49007-2.</p> <div> <p>This research is part of the project No. 2022/45/P/ST7/03450 co-funded by the National Science Centre and the European Union Framework Programme for Research and Innovation Horizon 2020 under the Marie Skłodowska-Curie grant agreement No. 945339.</p> </div>
Code for Manuscript - Near-term lake water temperature forecasts can be used to anticipate the ecological dynamics of freshwater species -
<p>Code for Manuscript - Near-term lake water temperature forecasts can be used to anticipate the ecological dynamics of freshwater species -</p>
Forecasted crop yield anomalies for NUTS3 level regions in the Pannonian Basin
<p>The datasets contain crop yield anomaly forecasts on NUTS3 level for the Pannonian Basin 2002-2016. The files contain the crop yield anomaly forecasts calculated one and two months before the harvest. Further information about the methodology can be found here:</p> <p>https://www.sciencedirect.com/science/article/pii/S0168192323002873</p>
Forecasting extremes of football players' performance in matches
<p>This repository contains material auxiliary to paper titled "Forecasting extremes of football players' performance in matches", divided into the following parts.</p> <p>A. Athlete performance parameters, as generated from the Apex Pro Series, STATSports, Premium System607<br>2023, Sonra 4.0</p> <ul> <li>"Appendix A.pdf"</li> </ul> <p>B. Sample datasets used in modeling</p> <ul> <li>"Appendix B.xlsx" - an athelete's performance log as produced by STATSports system</li> <li>match-day-gps.csv - an athlete's GPS trace on a match day (MD)</li> <li>md-5-training-gps.csv - the athlete's GPS trace on a training session 5 days before MD</li> </ul> <p>C. Sample models and modeling results</p> <ul> <li>Z_cnt.py - sample pre-processed and aggregated GPS data, used further in modeling</li> <li>zenodo_gps_demo.py - a scipt examining a range of time vs. speed definitions of an interval that correlate training and match performace best</li> <li>zenodo_apx_demo.py - a script generating sample models from APX-Data</li> </ul>
Seasonal upwelling forecasts in the California Current System
<div> <div> <div> <div> <div> <div> <div> <p>Daily mean upwelling forecasts used for analysis in Amaya et al. <em>in review</em>, "Seasonal upwelling forecasts in the California Current System". Forecasts are based on daily mean wind stress data from four initialized hindcasts: CanESM5, CanCM4i, CESM1, and GFDL-SPEAR. Forecasts are for the period 1991-2021.</p> </div> </div> </div> </div> </div> </div> </div> <div> <div> <div> <div> <div> </div> </div> </div> </div> </div>
A comprehensive calibration approach for the Northwest River Forecast Center
<p>This dataset contains data to accompany the paper "A comprehensive calibration approach for the Northwest River Forecast Center", 2025, in prep. </p> <p> </p> <p><strong>CAMELS_all_locations</strong> - Calibration results using the NWRFC approach for all CAMELS locations in the NWRFC domain</p> <p><strong>CAMELS_NWRFC</strong> - Shape file and basin caracteristics for all CAMELS locations in the NWRFC domain</p> <p><strong>cb_2018_us_state_5m</strong> - Shape file with US state boundaries used in figure creation</p> <p><strong>nwrfc_basins_sf</strong> - Shape file with NWRFC basin delineations</p> <p><strong>NWRFC_Boundary</strong> - Shape file with the NWRFC service boundary</p> <p><strong>Optimization_CAMELS_FA</strong> - Full cross validation and calibration results with forcing adjustments applied for 4 NWRFC basins (FSSO3, SAKW1, WCHW1, WGCM8) </p> <p><strong>Optimization_CAMELS_noFA</strong> - Full cross validation and calibration results without forcing adjustments applied for 4 NWRFC basins (FSSO3, SAKW1, WCHW1, WGCM8) </p> <p><strong>world-administrative-boundaries</strong> - Shape file with country boundaries used in figure creation</p>
Downscaled North American Multi-Model Ensemble Forecast for the Pacific Northwest USA
<h1>Downscaled North American Multi-Model Ensemble Forecast of Meteorological Variables for the Pacific Northwest</h1> <p>Monthly retrospective hindcasts (1982-2010) and forecasts (2011-2020) of temperature and precipitation are acquired for the Pacific Northwest region of the United States from five models (CFSv2, NASA GEOS5v2, CanCM4i, GEM-NEMO, and NCAR-CCSM) participating in the North American Multi-Model Ensemble project <a href="https://www.zotero.org/google-docs/?WlFE7n">(Kirtman et al., 2014)</a>. These models, detailed in Table 1 with more recent information available in <a href="https://www.zotero.org/google-docs/?PjZZHw">(Becker et al., 2022)</a>, are initialized monthly to provide a forecast of 0-9 months at a 1.0̊ × 1.0̊ spatial resolution. The multi-model ensemble mean (ENSMEAN) is then generated for each initialization by simply averaging all considered models and their ensemble members. Monthly ENSMEAN forecast is bias-corrected and spatially downscaled to 1/24th degree using the methodology described in <a href="https://www.zotero.org/google-docs/?jwPLzP">Wood et al. (2002)</a> and <a href="https://www.zotero.org/google-docs/?2b3lkj">Barbero et al. (2017)</a> using historical meteorological data <a href="https://www.zotero.org/google-docs/?zN8gKh">(gridMET; Abatzoglou, 2013)</a> as the baseline. Then, the downscaled ENSMEAN data are temporally disaggregated to daily timescales using an analog approach. The closest analog month for the ENSMEAN forecast is found from the gridMET dataset by minimizing the root mean square error (RMSE) of monthly gridMET and forecast precipitation (excluding gridMET data for the target month). Other daily meteorological variables (such as maximum and minimum temperature, maximum and minimum relative humidity, wind speed, and specific humidity) are extracted from the same analog month to use as input for the coupled crop-hydrology model. As a last step to the analog approach, the process corrects the bias between the forecast and analog month to ensure that monthly mean temperature and accumulated precipitation match those of the original forecast. </p> <p>Table 1. List of NMME models used to create Ensemble Mean.</p> <div> <table> <tbody> <tr> <td>Model </td> <td>Model Expansion </td> <td>Ensemble Size </td> <td>References</td> </tr> <tr> <td>NCEP- CFSv2 </td> <td>Climate Forecast System, version 2 </td> <td>24 </td> <td><a href="https://www.zotero.org/google-docs/?XTr15U">(Saha et al., 2014)</a></td> </tr> <tr> <td>NASA GEOS5v2</td> <td>Goddard Earth Observing System, version 5 </td> <td>4</td> <td><a href="https://www.zotero.org/google-docs/?fQzQZL">(Molod et al., 2020)</a></td> </tr> <tr> <td>CanCM4i </td> <td>Fourth Generation Canadian Coupled Global Climate Model </td> <td>10 </td> <td><a href="https://www.zotero.org/google-docs/?AoXCO8">(Merryfield et al., 2013)</a></td> </tr> <tr> <td>GEM - NEMO </td> <td>Global Environmental Multiscale Model – Nucleus for European Modelling of the Ocean </td> <td>10 </td> <td><a href="https://www.zotero.org/google-docs/?N4JwM9">(Lin et al., 2020)</a></td> </tr> <tr> <td>NCAR - CCSM </td> <td>Community Climate System Model </td> <td>10 </td> <td><a href="https://www.zotero.org/google-docs/?NMkImR">(Kirtman & Min, 2009)</a></td> </tr> </tbody> </table> </div> <p>The dataset has *.mat files which are MATLAB data files. </p> <h3>References</h3> <ol> <li> <p>Abatzoglou, J. T. (2013). Development of gridded surface meteorological data for ecological applications and modelling. International Journal of Climatology, 33(1), 121–131. <a href="https://doi.org/10.1002/joc.3413">https://doi.org/10.1002/joc.3413</a></p> </li> <li> <p>Barbero, R., Abatzoglou, J. T., & Hegewisch, K. C. (2017). Evaluation of Statistical Downscaling of North American Multimodel Ensemble Forecasts over the Western United States. Weather and Forecasting, 32(1), 327–341. https://doi.org/10.1175/WAF-D-16-0117.1</p> </li> <li> <p>Becker, E. J., Kirtman, B. P., L’Heureux, M., Muñoz, Á. G., & Pegion, K. (2022). A Decade of the North American Multimodel Ensemble (NMME): Research, Application, and Future Directions. Bulletin of the American Meteorological Society, 103(3), E973–E995. <a href="https://doi.org/10.1175/BAMS-D-20-0327.1">https://doi.org/10.1175/BAMS-D-20-0327.1</a></p> </li> <li> <p>Kirtman, B. P., & Min, D. (2009). Multimodel Ensemble ENSO Prediction with CCSM and CFS. Monthly Weather Review, 137(9), 2908–2930. https://doi.org/10.1175/2009MWR2672.1</p> </li> <li> <p>Kirtman, B. P., Min, D., Infanti, J. M., Kinter, J. L., Paolino, D. A., Zhang, Q., Dool, H. van den, Saha, S., Mendez, M. P., Becker, E., Peng, P., Tripp, P., Huang, J., DeWitt, D. G., Tippett, M. K., Barnston, A. G., Li, S., Rosati, A., Schubert, S. D., … Wood, E. F. (2014). The North American Multimodel Ensemble: Phase-1 Seasonal-to-Interannual Prediction; Phase-2 toward Developing Intraseasonal Prediction. Bulletin of the American Meteorological Society, 95(4), 585–601. <a href="https://doi.org/10.1175/BAMS-D-12-00050.1">https://doi.org/10.1175/BAMS-D-12-00050.1</a></p> </li> <li> <p>Lin, H., Merryfield, W. J., Muncaster, R., Smith, G. C., Markovic, M., Dupont, F., Roy, F., Lemieux, J.-F., Dirkson, A., Kharin, V. V., Lee, W.-S., Charron, M., & Erfani, A. (2020). The Canadian Seasonal to Interannual Prediction System Version 2 (CanSIPSv2). Weather and Forecasting, 35(4), 1317–1343. <a href="https://doi.org/10.1175/WAF-D-19-0259.1">https://doi.org/10.1175/WAF-D-19-0259.1</a></p> </li> <li> <p>Merryfield, W. J., Lee, W.-S., Boer, G. J., Kharin, V. V., Scinocca, J. F., Flato, G. M., Ajayamohan, R. S., Fyfe, J. C., Tang, Y., & Polavarapu, S. (2013). The Canadian Seasonal to Interannual Prediction System. Part I: Models and Initialization. Monthly Weather Review, 141(8), 2910–2945. <a href="https://doi.org/10.1175/MWR-D-12-00216.1">https://doi.org/10.1175/MWR-D-12-00216.1</a></p> </li> <li> <p>Molod, A., Hackert, E., Vikhliaev, Y., Zhao, B., Barahona, D., Vernieres, G., Borovikov, A., Kovach, R. M., Marshak, J., Schubert, S., Li, Z., Lim, Y.-K., Andrews, L. C., Cullather, R., Koster, R., Achuthavarier, D., Carton, J., Coy, L., Friere, J. L. M., … Pawson, S. (2020). GEOS-S2S Version 2: The GMAO High-Resolution Coupled Model and Assimilation System for Seasonal Prediction. Journal of Geophysical Research: Atmospheres, 125(5), e2019JD031767. https://doi.org/10.1029/2019JD031767</p> </li> <li> <p>Saha, S., Moorthi, S., Wu, X., Wang, J., Nadiga, S., Tripp, P., Behringer, D., Hou, Y.-T., Chuang, H., Iredell, M., Ek, M., Meng, J., Yang, R., Mendez, M. P., Dool, H. van den, Zhang, Q., Wang, W., Chen, M., & Becker, E. (2014). The NCEP Climate Forecast System Version 2. Journal of Climate, 27(6), 2185–2208. https://doi.org/10.1175/JCLI-D-12-00823.1</p> </li> <li> <p>Wood, A. W., Maurer, E. P., Kumar, A., & Lettenmaier, D. P. (2002). Long-range experimental hydrologic forecasting for the eastern United States. Journal of Geophysical Research: Atmospheres, 107(D20), ACL 6-1-ACL 6-15. https://doi.org/10.1029/2001JD000659</p> </li> </ol>
Data from: Forecasting potential emergence of zoonotic diseases in Southeast Asia: network analysis identifies key rodent hosts
1. Within complex ecological systems, identifying animal species likely to play a key role in the emergence of infectious zoonotic diseases remains a major challenge. One approach consists of using information on current ecological and parasitological similarities among host species in order to predict the most likely pathways for future pathogen spillover. 2. Using field data acquired from 15 sympatric rodent species in various habitats in Thailand, Cambodia and Laos, we built networks based on shared parasites (17 helminth and 15 microparasite species) and shared habitats among rodent species and humans. We investigated the architectures of bipartite and unipartite networks using modularity, subgroups partitioning or node centrality, to assess the relative epidemiological importance of particular rodent species. 3. Our results showed that Rattus tanezumi, Bandicota savilei and R. exulans were consistently found to be members of subgroups that included humans in unipartite and bipartite networks on zoonotic agents and shared habitats. High values of centrality in shared zoonotic agents were found for the same three rodent species, whereas high values of shared habitats were observed for two of them. Although phylogenetically related rodent species likely shared both habitats and parasites, a lack of habitat specialisation was associated with increased zoonotic parasite sharing. 4. Our results emphasize the disproportionate importance of these three rodent species, through their high degree of connectivity with humans, which may represent a high risk for direct zoonotic spillover. Moreover, due to its high centrality in habitats, R. tanezumi may also play a key role as a bridge host. 5. The recent discovery of new arenaviruses in rodents in Southeast Asia, with associated disease in humans in Cambodia, provides an opportunity to test this empirically. The three rodent species identified using our network approach are some of the potential maintenance hosts for these new emerging arenaviruses. 6. Synthesis and applications. Our results on rodents and their pathogens in Southeast Asia show that network analysis has a high potential to improve the surveillance of emerging zoonotic pathogens by targeting key host species and potential "emerging' pathogen–rodent interactions in complex and heterogeneous landscapes.
Data and GrADS scripts needed to reproduce the figures in the article "Probabilistic forecasts of near-term climate change: verification for temperature and precipitation changes from years 1971-2000 to 2011-2020"
<p>Data and GrADS scripts needed to reproduce the figures in the article "Probabilistic forecasts of near-term climate change: verification for temperature and precipitation changes from years 1971-2000 to 2011-2020", submitted for publication in Climate Dynamics.</p> <p>Please see the file README for further details.</p> <p> </p>
R code to accompany 'Teleconnection-based evaluation of seasonal forecast quality''
<p>R code for the diagnostic published in 'Teleconnection-based evaluation of seasonal forecast quality' DOI: 10.1007/s00382-020-05327-x</p>
Model output data for compressible EULAG dynamical core in COSMO: convective-scale Alpine weather forecasts
<p>The archive contains model output data for article "Compressible EULAG dynamical core in COSMO: convective-scale Alpine weather forecasts" to be published in Monthly Weather Review.</p> <p>The article presents the semi-implicit compressible EULAGas a newdynamical core for convective-scale<br> numerical weather prediction. The core is implemented within the infrastructure of the<br> operational model of the Consortium for Small Scale Modeling (COSMO), forming the NWP<br> COSMO-EULAG model (CE). This regional high-resolution implementation of the dynamical<br> core complements its global implementation in the Finite-Volume Module of ECMWF’s Integrated<br> Forecasting System. The paper documents the first operational-like application of the dynamical<br> core for realistic weather forecasts. After discussing the formulation of the core and its coupling<br> with the host model, the paper considers several high-resolution prognostic experiments over<br> complex Alpine orography. Standard verification experiments examine the sensitivity of the CE<br> forecast to the choice of the advection routine and assess the forecast skills against those of the<br> default COSMO Runge-Kutta dynamical core at the 2.2 km grid showing a general improvement.<br> The skills are also compared using satellite observations for a weak-flow convective Alpine weather<br> case-study, showing favorable results. Additional validation of the new CE framework for partly<br> convection-resolving forecasts using 1.1 km, 0.55 km, 0.22 km, and 0.1 km grids, designed to<br> challenge its numerics and test the dynamics-physics coupling, demonstrates its high robustness in<br> simulating multi-phase flows over complex mountain terrain, with slopes reaching 85 degrees, and<br> the flow’s realistic representation.</p>
Dataset for "Comparative Analysis of Machine Learning Models to Forecast Flaring Capability of Solar Active Regions: A Parameter Based Approach"
<p>This CSV file contains the values of 14 selected magnetic features along with the active region class for all the regions used in our study. As discussed in the paper, these 14 magnetic features characterize the properties of active regions. All these magnetic features are obtained from the HMI SHARP data series which provides open-sourced vector magnetic field information of solar active regions. the column named 'AR_class' carries information about the class of active regions i.e., 1 for flaring regions and 0 for non-flaring regions.</p>
S1 What Are the Key Drivers Controlling the Qualityof Seasonal Streamflow Forecasts?
<p>Recent technological advances in representation of processes in numerical climate models have led to skillful predictions, which can consequently increase the confidence of hydrological predictions and usability of hydroclimatic services. Given that many water-related stakeholders are affected by seasonal hydrological variations, there is a need to manage such variations to their advantage through better understanding of the drivers that influence hydrological predictability. Here we analyze the seasonal forecasts of streamflow volumes across about 35,400 basins in Europe, which lie along a strong gradient in terms of climatology, scale, and hydrological regime. We then link the seasonal volumetric errors to various physiographic-hydroclimatic descriptors and meteorological biases in order to identify the key drivers controlling predictability. Streamflow volumes over Europe are well predicted, yet with some geographic and seasonal variability; however, the predictability deteriorates with increasing lead time particularly in the winter months. Nevertheless, we show that the forecast quality is well correlated to a set of descriptors, which vary depending on the initialization month. The forecast quality of seasonal streamflow volumes is strongly dependent on the basin's hydrological regime, with limited predictability in relatively flashy basins. On the contrary, snow and/or baseflow dominated regions with long recessions show high streamflow predictability. Finally, climatology and precipitation forecast biases are also related to streamflow predictability, highlighting the importance of developing robust bias adjustment methods. Overall, this investigation shows that the seasonal streamflow predictability can be clustered, and hence regionalized, based on a priori knowledge of local hydroclimatic conditions.</p>
Supplementary data for "Timely vaccine strain selection and genomic surveillance improves evolutionary forecast accuracy of seasonal influenza A/H3N2"
<p>Supplementary materials associated with the manuscript by Huddleston and Bedford titled "Timely vaccine strain selection and genomic surveillance improves evolutionary forecast accuracy of seasonal influenza A/H3N2".</p>
Dataset CO2 Emission per GDP Forecast 2020-2100
<p>The dataset includes Business as Usual (BAU) forecast of world global CO2 emissions per GDP (Cp$) for 2020-2100.</p> <p>The CO2 emission forecast is from the publication “<em>Dataset Global Warming Forecast using Acceleration Factors</em>” [6]. According to this publication, the CO2 emissions without international transport will change from 33,803 MtCO2/y in 2020 to 70,191 MtCO2/y in 2100, a 108% increase.</p> <p>The GDP forecast applies a parabolic trendline of the last 30 years. According to this calculation, the world GDP will change from 126.3 MM$/y in 2020 to 728.1 MM$/y in 2100, a 476% increase.</p> <p>CO2 emissions per GDP (Cp$) are calculated by dividing the CO2 emissions per year by the GDP in the same year.</p> <p>The world 0.000268 tCO2/$GDP Cp$ in 2020 will decrease by 64% in 2100 to 0.000096 tCO2/$GDP.</p>
Photovoltaic generation data, for 3 years, regarding the 2022-3 Competition on solar generation forecasting
<p>These data were released under the 2022-3 Competition on solar generation forecasting.</p> <p>Please check our competitions: <a href="http://www.gecad.isep.ipp.pt/smartgridcompetitions">www.gecad.isep.ipp.pt/smartgridcompetitions</a></p> <p> </p> <p>The data set comprises the power generated by photovoltaic panels and data collected from a near weather station. The data was collected in 5 minutes periods. Data comprises:</p> <ul> <li>Hour</li> <li>Starting minute (inclusive) </li> <li>Ending minute (exclusive) </li> <li>Generated power (kW)</li> <li>Temperature (ºC) </li> <li>Dewpoint (ºC)</li> <li>Pressure (hPa) </li> <li>Wind Direction (Degrees)</li> <li>Wind Speed (KM/h)</li> <li>Wind Speed Gust (KM/h)</li> <li>Humidity (%)</li> <li>Hourly Precipitation (mm)</li> <li>Daily rain (mm)</li> <li>Solar Radiation (Watts/m2)</li> </ul> <p><br>The data set represents raw data without any treatment, this means that it is possible to find errors. Data can have missing data or missing reading periods, and a fixed zero (0) value, indicating a failure in the system readings.</p> <p> </p> <p>We would be grateful if you could acknowledge the use of this dataset in your publications. Please use the Zenodo publication to cite this work.</p>
Code and extensive data for training neural networks for radiation, used in "Implementation of a machine-learned gas optics parameterization in the ECMWF Integrated Forecasting System: RRTMGP-NN 2.0""
<p>Data and code used in a paper submitted to JAMES titled :<em> Implementation of a machine-learned gas optics parameterization in the ECMWF Integrated Forecasting System</em></p> <p>1) The files <strong>ml_training_*.7z</strong> contain extensive datasets (in NetCDF format) for training neural network versions of the RRTMGP gas optics scheme as described in the paper. The datasets are read by <a href="https://github.com/peterukk/rte-rrtmgp-nn/blob/main/examples/rrtmgp-nn-training/ml_train.py">ml_train.py.</a></p> <p>2) The ML datasets were in turn generated using the input profiles (in NetCDF format) inside <strong>inputs_to_RRTMGP.zip </strong>by running the Fortran programs <code>rrtmgp_sw_gendata_rfmipstyle.F90 and rrtmgp_lw_gendata_rfmipstyle.F90 </code>in <em>rte-rrtmgp-nn/examples/rrtmgp-nn-training</em>, which call the RRTMGP gas optics scheme, The input profiles contain <strong>millions of columns, hundreds of perturbation experiments (including hypercube-sampled gas concentrations), are derived from several different data sources (including CAMS reanalysis, GCM, and CKDMIP-MMM), and span present-day, preindustrial, and future atmospheric conditions.</strong> They could be used to generate training data for developing emulators of the full RTE+RRTMGP radiation scheme, not just gas optics (see nn_dev on the <a href="https://github.com/peterukk/rte-rrtmgp-nn">RTE+RRTMGP-NN repository on Github</a>, used in a previous paper where different emulation methods were compared)</p> <p>3) The Fortran and Python code used for data generation and NN training are found in<a href="https://github.com/peterukk/rte-rrtmgp-nn/tree/main/examples/rrtmgp-nn-training"> <em>rte-rrtmgp-nn/examples/rrtmgp-nn-training</em> </a>on the main branch on Github; <strong>an archived version is also included here </strong>(<strong>rte-rrtmgp-nn-2.0.zip</strong>). See the readme in the above sub-directory for further information.</p> <p> </p>
Data from: Influence of topography and the underlying surface of the Bohai Sea on wind and gust forecasts
<p class="MsoNormal"><span>Accurate gust forecasts can reduce potential threats to people's lives and properties, but we need more reliable forecasting methods and models. A recent development is the meteorologically stratified gust factor (MSGF) model, which is more accurate in forecasting gusts than the previous gust factor model. The regional terrain and underlying surface both have crucial effects on the gust factor. We therefore combined observations from the China Meteorological Administration over the ocean surface and along the coast with the MSGF model to explore the influence of topography and the underlying surface on wind and gust forecasts. The regional terrain and underlying surface affected the peak gust climatologies, the mean wind speed, the mean prevailing wind direction and the gust factors. The topography and the underlying surface had different impacts in different ranges of the mean wind speed. The strong turbulence that causes changes in the gust factor under light winds is not initiated over rough underlying surfaces. When the mean wind speed is >2.5 m s<sup>−1</sup>, the underlying surface influences both the wind speed and the gust factor. A rough underlying surface stimulates stronger turbulence and increases the gust speed and gust factor, whereas a smooth underlying surface directly increases the mean wind speed and the gust speed by different magnitudes to reduce the difference between them, thus decreasing the gust factor. We evaluated the ability of the MSGF model to forecast gusts and verified a method combining the products of a numerical model and the MSGF model in gust forecasts.</span></p>
Data for: A new paradigm for medium-range severe weather forecasts: Probabilistic random forest-based predictions
<p>Historical observations of severe weather and simulated severe weather environments (i.e., features) from the Global Ensemble Forecast System v12 (GEFSv12) Reforecast Dataset (GEFS/R) are used in conjunction to train and test random forest (RF) machine learning (ML) models to probabilistically forecast severe weather out to days 4–8. RFs are trained with ~9 years of the GEFS/R and severe weather reports to establish statistical relationships. Feature engineering is briefly explored to examine alternative methods for gathering features around observed events, including simplifying features using spatial averaging and increasing the GEFS/R ensemble size with time-lagging. Validated RF models are tested with ~1.5 years of real-time forecast output from the operational GEFSv12 ensemble and are evaluated alongside expert human-generated outlooks from the Storm Prediction Center (SPC). Both RF-based forecasts and SPC outlooks are skillful with respect to climatology at days 4 and 5 with diminishing skill thereafter. The RF-based forecasts exhibit tendencies to slightly underforecast severe weather events, but they tend to be well-calibrated at lower probability thresholds. Spatially averaging predictors during RF training allows for prior-day thermodynamic and kinematic environments to generate skillful forecasts, while time-lagging acts to expand the forecast areas, increasing resolution but decreasing overall skill. The results highlight the utility of ML-generated products to aid SPC forecast operations into the medium range.</p>
Forecasting with news sentiment: Evidence with UK newspapers
<p>These are datasets of economic sentiments derived from Uk newspapers using a dictionary and support vector machines. For more information on the application refer to : </p> <p>Rambaccussing, D. and Kwiatkowski, A., 2020. Forecasting with news sentiment: Evidence with UK newspapers. <em>International Journal of Forecasting</em>, <em>36</em>(4), pp.1501-1516.</p> <p>https://www.sciencedirect.com/science/article/pii/S0169207020300595</p> <p> </p> <p> </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.