In this study we develop a set of solar proton event (SPE) forecast models with NOAA scales by Multi Layer Perceptron (MLP), one of neural network methods, using GOES solar X-ray flare data from 1976 to 2011. Our MLP models are the first attempt to forecast the SPE scales by the neural network method. The combinations of X-ray flare class, impulsive time, and location are used for input data. For this study we make a number of trials by changing the number of layers and nodes as well as combinations of the input data. To find the best model, we use the summation of F-scores weighted by SPE scales, where F-score is the harmonic mean of PODy (recall) and precision (positive predictive value), in order to minimize both misses and false alarms. We find that the MLP models are much better than the multiple linear regression model and one layer MLP model gives the best result.

The solar proton telescope (SPT) is considered as one of the scientific instruments to be installed in instruments for the study of space storm (ISSS) which is determined for next generation small satellite-1 (NEXTSat-1). The SPT is the instrument that acquires the information on energetic particles, especially the energy and flux of proton, according to the solar activity in the space radiation environment. We performed the simulation to determine the specification of the SPT using geometry and tracking 4 (GEANT4). The simulation was performed in the range of 0.6-1,000 MeV considering that the proton, which is to be detected, corresponds to the high energy region according to the solar activity in the space radiation environment. By using aluminum as a blocking material and adjusting the energy detection range, we determined total 7 channels (0.6~5, 5~10, 10~20, 20~35, 35~52, 52~72, and >72 MeV) for the energy range of SPT. In the SPT, the proton energy was distinguished using linear energy transfer to compare with or discriminate from relativistic electron for the channels P1-P3 which are the range of less than 20 MeV, and above those channels, the energy was determined on the basis of whether silicon semiconductor detector (SSD) signal can pass or not. To determine the optimal channel, we performed the conceptual design of payload which uses the SSD. The designed SPT will improve the understanding on the capture and decline of solar energetic particles at the radiation belt by measuring the energetic proton.