Damian Zięba

Bitcoin is one of the cryptocurrencies that is gaining more popularity in recent years. Previous studies have shown that closing price alone is not enough to forecast stock market series. We introduce a new set of time series and demonstrate that a subset is necessary to improve directional accuracy based on a machine learning ensemble. In our experiments, we study which time series and machine learning algorithms deliver the best results. We found that the most relevant time series that contribute to improving directional accuracy are Open, High and Low, with the largest contribution of Low in combination with an ensemble of Gated Recurrent Unit network and a baseline forecast. The relevance of other Bitcoin-related features that are not price-related is negligible. The proposed method delivers similar performance to the state-of-the-art when observing directional accuracy.

Bitcoin is one of the cryptocurrencies that has gained popularity in recent years. Previous studies have shown that closing price alone is not enough to forecast its future level, and other price-related features are necessary to improve forecast accuracy. We introduce a new set of time series and demonstrate that a subset is necessary to improve directional accuracy based on a machine learning ensemble. In our experiments, we study which time series and machine learning algorithms deliver the best results. We found that the most relevant time series that contribute to improving directional accuracy are open, high, and low, with the largest contribution of low in combination with an ensemble of a gated recurrent unit network and a baseline forecast. The relevance of other Bitcoin-related features that are not price-related is negligible. The proposed method delivers similar performance to the state of the art when observing directional accuracy.

The concentration of indoor suspended particulate matter is considered to be one of the main factors that affect health and quality of life. In Poland, in response to the pressure of public opinion, a few thousand air purifiers have been installed in public buildings where children spend time. However, another factor that also impacts upon the quality of indoor air, namely increased CO₂ mixing ratios, is frequently overlooked. The only way to remove CO₂ excess from interiors is through intensive ventilation. This is often an action at odds with the need to maintain low concentrations of particulate matter in indoor air. Two methods are presented to assess the rate of air exchange using CO₂ or particulate matter as a tracer. One of the methods using indoor/outdoor PM (particulate matter) concentrations is based on the use of box models for analysis. The second one uses indoor CO₂ concentration change analysis. At the tested locations, they showed large deviations of the determined values of the air exchange coefficients from its limits. Both methods showed consistent ventilation parameters estimation.

Krakow is a city in southern Poland inhabited by about 741,000 people. However, Krakow’s agglomeration includes neighboring cities, hence more than 1 million people live there. The agglomeration is struggling with the problem of air pollution. In 2016, admissible average annual concentrations of PM10 (40 μg / m3) were exceeded at all measuring points. Furthermore, daily PM10 concentrations were regularly exceeded in the winter, which is associated with increased coal combustion during this period. Fortunately, interest in the subject of air quality in the world is constantly growing. People are more often aware of the negative impact on health of chemical compounds present in particulate matter (PM) such as Polycyclic Aromatic Hydrocarbons (PAHs), which were proved to be cancerogenic and mutagenic for people. That is why it is so important to study their presence in the ambient air. PM10 collected in the center of Wadowice (22.12.2016 – 13.10.2017) were investigated. PAHs were extracted from particulate matter and analysed applying the GC/MS technique. The results are discussed in the article.

Records of trace gas composition of the atmosphere originating from mountain stations are difficult to interpret in terms of continental gas balances due to complex topography and local wind patterns. Kasprowy Wierch station, located in the High Tatra Mountains, Poland, provides datasets to European GHG databases and can be used for regional and continental balances of trace gases in Earth’s atmosphere. Although it suffers from strong influence of local valley winds, the concentration record obtained at Kasprowy Wierch contains also a discernible fraction of methane (up to 100 ppb) emitted mainly by large regional source of this gas (Silesian Coal Basin) located ca. 150 km north-west of Kasprowy Wierch. Comparison of GOSAT satellite CH4 record in the pixel including High Tatras at the level of 850 hPa with the data obtained at Kasprowy Wierch mountain station revealed surprisingly good correlation, even for relatively short time intervals

Summary: Uptake of atmospheric hydrogen by soils constitutes the most important sink of this gas at the global scale. However, little is known about the strength and spatio‐temporal variability of this sink. We present the results of a systematic study aimed at characterizing hydrogen uptake by urban soils. The study was carried out at two field sites in K rakow, southern P oland. The measured fluxes of hydrogen to soils revealed distinct seasonality, with large values (up to 40 µmol hour ⁻¹ m ⁻² ) recorded during summer months and small values (between 5 and 10 µmol hour ⁻¹ m ⁻² ) during winter. Temperatures in the top 6 cm of the soil profile varied during the study from −9 to +24°C, while volumetric soil water content fluctuated between 15 and 50%. Measurable hydrogen fluxes were also observed when soil temperatures were less than zero. The results were interpreted in the context of seasonal changes of local climate and air and soil temperature, soil water content and amount of rainfall. Mixing conditions at the air–soil interface were also considered. Modelling of H ₂ uptake was performed with a two dimensional diffusion transport model, with contrasting assumptions about distribution and intensity of the hydrogen sink in the soil profile. The model results suggest that conditions in the uppermost soil layer exert a decisive control on measured hydrogen uptake rates. The measured hydrogen flux can be reproduced by the transport model only if significant reduction of the soil water content in the uppermost layer of the soil is postulated. This finding has important implications for the parameterization of hydrogen uptake rates in models of the global H ₂ budget.