Applying machine learning in the investigation of the link between the high-velocity streams of charged solar particles and precipitation-induced floods.

This study explores a possible link between solar activity and floods caused by precipitation. For this purpose, discrete blocks of data for 89 separate flood events in Europe in the period 2009-2018 were used. Solar activity parameters with a time lag of 0-11 days were used as input data of the model, while precipitation data in the 12 days preceding the flood were used as output data. The level of randomness of the input and output time series was determined by correlation analysis, while the potential causal relationship was established by applying machine learning classification predictive modeling. A total of 25 distinct machine-learning algorithms and four model ensembles were applied. It was shown that in 81% of cases, the designed model could explain the occurrence or absence of precipitation-induced floods 9 days in advance. Differential proton flux in the 0.068-0.115 MeV and integral proton flux > 2.5 MeV were found to be the most important factors for forecasting precipitation-induced floods. The study confirmed that machine learning is a valuable technique for establishing nonlinear relationships between solar activity parameters and the onset of floods induced by precipitation.

Strain-specific helper T cell profile in the gut-associated lymphoid tissue.

C57BL/6, BALB/c and NOD mice are among the most frequently used strains in autoimmunity research. NOD mice spontaneously develop type 1 diabetes (T1D) and they are prone to induction of experimental autoimmune encephalomyelitis (EAE). Both diseases can be routinely induced in C57BL/6 mice, but not in BALB/c mice. Also, C57BL/6 mice are generally considered T helper (Th)1-biased and BALB/c Th2-biased mice. Having in mind increasingly appreciated role of gut associated lymphoid tissue (GALT) cells in autoimmunity, especially in relation to gut Th17 and regulatory T (Treg) cells, our aim was to determine if there are differences in proportion of CD4+ T cell populations in mesenteric lymph nodes and Peyer's patches of these mouse strains. Lower proportion of Treg was observed in NOD PP, Th2 cells dominated in BALB/c mice in mesenteric lymph nodes (MLN) and Peyer's patches (PP), while Th1 cells prevailed in C57BL/6 MLN. Intradermal immunization of mice with complete Freund's adjuvant resulted in significant difference in Th cell distribution in GALT of NOD mice. Differences were less pronounced in C57BL/6 mice, while GALT of BALB/c mice was almost unresponsive to the immunization. The observed strain- and tissue-dependent changes in Treg proportion after the immunization was probably a consequence of different CCR2 or CCR6-related migration patterns and/or in situ Treg proliferation. In conclusion, NOD, a highly autoimmunity-prone mouse strain, exhibits more profound GALT-related immune response upon immunization compared to the strains that are less prone to autoimmunity.