We developed a flare prediction model using machine learning, which is optimized to predict the maximum class of flares occurring in the following 24 h. Machine learning is used to devise algorithms that can learn from and make decisions on a huge am
ount of data. We used solar observation data during the period 2010-2015, such as vector magnetogram, ultraviolet (UV) emission, and soft X-ray emission taken by the Solar Dynamics Observatory and the Geostationary Operational Environmental Satellite. We detected active regions from the full-disk magnetogram, from which 60 features were extracted with their time differentials, including magnetic neutral lines, the current helicity, the UV brightening, and the flare history. After standardizing the feature database, we fully shuffled and randomly separated it into two for training and testing. To investigate which algorithm is best for flare prediction, we compared three machine learning algorithms: the support vector machine (SVM), k-nearest neighbors (k-NN), and extremely randomized trees (ERT). The prediction score, the true skill statistic (TSS), was higher than 0.9 with a fully shuffled dataset, which is higher than that for human forecasts. It was found that k-NN has the highest performance among the three algorithms. The ranking of the feature importance showed that the previous flare activity is most effective, followed by the length of magnetic neutral lines, the unsigned magnetic flux, the area of UV brightening, and the time differentials of features over 24 h, all of which are strongly correlated with the flux emergence dynamics in an active region.
Magnetic properties in the quasi-one-dimensional organic salt (TMTTF)2SbF6 are investigated by 13C NMR under pressures. Antiferromagnetic phase transition at ambient pressure (AFI) is confirmed. Charge-ordering is suppressed by pressure and is not ob
served under 8 kbar. For 5 < P < 20 kbar, a sharp spectrum and the rapid decrease of the spin-lattice relaxation rate 1/T1 were observed below about 4 K, attributed to a spin-gap transition. Above 20 kbar, extremely broadened spectrum and critical increase of 1/T1 were observed. This indicates that the system enters into another antiferromagnetic phase (AFII) under pressure. The slope of the antiferromagnetic phase transition temperature T_AFII, dT_AFII/dP, is positive, while T_AFI decreases with pressure. The magnetic moment is weakly incommensurate with the lattice at 30 kbar.
We investigate the transport properties of LixCoO2 thin films whose resistivities are nearly an order of magnitude lower than those of the bulk polycrystals. A metal-nonmetal transition occurs at ~0.8 in a biphasic domain, and the Seebeck coefficient
(S) is drastically increased at ~140 K (= T*) with increasing the Li concentration to show a peak of magnitude ~120 muV/K in the S-T curve of x = 0.87. We show that T* corresponds to a crossover temperature in the conduction, most likely reflecting the correlation-induced temperature dependence in the low-energy excitations.
