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.

An Assessment of the Climate Change Impacts on the Distribution of the Glacial Relict Woodpecker Three-Toed Woodpecker Picoides tridactylus.

The Three-Toed Woodpecker Picoides tridactylus is a rare and endangered woodpecker on the Balkan Peninsula. Despite being widely distributed in Northern Europe, its distribution on the Balkan Peninsula is limited to high-altitude forest habitats, where it represents a glacial relict. Assessing the climate change impacts on its distribution can be crucial for improving the conservation and future survival of this specialist species on the Balkan Peninsula. We used species distribution modelling (SDM) to identify its potential distribution in the past (last interglacial and last glacial maximum), present, and future (2050 and 2070). Our results indicate that this species had the greatest distribution during the last glacial maximum, after which its distribution contracted to areas where suitable environment persisted (high altitudes). The largest territory of the Balkan Peninsula has an unsuitable environment for the species to inhabit, while highly suitable habitats have the smallest share in the total area of suitable habitats. All future models show a decrease in the area of suitable habitats compared with the current period, indicating that global warming has a negative effect on the distribution of the species. We recommend that conservation activities must be of greater extent to ensure the species' survival in the Balkans.