Model/Technique Registration (*=required): Information about your group/project:     Name(s) and e-mail (s) (please list primary contact first)*: Marlon Núñez mnunez@uma.es     Associated Institution/Project name/Group name*: Universidad de Málaga, Space Weather Group     Website url(s): http://spaceweather.uma.es     Logo(s): Information about your method:     Forecasting method name*: UMASEP     Shorthand unique identifier for your method (methodname_version, e.g. ModelName_1 or ModelName_201201): UMASEP_ver1.4     Short description*: UMASEP makes real-time predictions of the time interval within which the integral proton flux is expected to meet or surpass the Space Weather Prediction Center thresholds of J (E > 10 MeV) = 10 pfu and J (E > 100 MeV) = 1 pfu, and the intensity of the first hours of well‐ and poorly connected SEP events. This forecaster analyzes flare and near‐Earth space environment data (soft X‐ray, differential and integral proton fluxes). When there is a differential proton flux enhancement, UMASEP tries to recognize the type of connectivity of the observed situation by using two forecasting models. The purpose of the first model is to identify precursors of well‐connected events by empirically estimating the magnetic connectivity from the associated CME/flare process zone to the near‐Earth environment and identifying the flare temporally associated with the phenomenon. The second model identifies precursors of poorly connected events by using a regression model that checks whether the differential proton flux behaviour is similar to that in the beginning phases of previous historically poorly connected SEP events and thus deduce similar consequences. An additional module applies a higher‐level analysis for inferring additional information about the situation by filtering out inconsistent preliminary forecasts and estimating the intensity of the first hours of the predicted SEP events. The high‐level module periodically retrieves solar data and, in the case of well‐connected events, automatically identifies the associated flare and active region.      Model Inputs*: GOES Soft X-ray flux GOES differential proton fluxes (Goes's channels P3 to P11) GOES integral proton flux (E>10 MeV and E>100 MeV) GOES edited event list Model Outputs*: Graphical forecast file Textual forecast file XML forecast file References: Núñez, M. (2011), Predicting solar energetic proton events (E > 10 MeV), Space Weather, 9, S07003, doi:10.1029/2010SW000640. Núñez, M. (2015), Real-time prediction of the occurrence and intensity of the first hours of > 100 MeV solar energetic proton events, Space Weather, 13, doi:10.1002/2015SW001256. Further Model Details:     (1)* Is the forecast made continuously (e.g. probability for the next 24 hours, or a time series), or event-triggered (e.g. by a flare or CME). Forecasts are made continuously (every 5 minutes) in terms of the intensity-time profile of >10 MeV and >100 MeV integral proton fluxs for the next hours. (2)* Is the forecast human generated, human generated but model-based, model-based, or other. Model-based  (3)* If model-based: is the model empirical, physics-based or both. Empirical