Times series store information on how a variable changes over time. This is a key property of many types of geoscience data. The dynamics of the data are evaluated in an expected order on the basis of fixed intervals, such as years, months, days, hours, minutes, or seconds. Since the first systematic meteorological observations, knowledge of climate characteristics has been used in investigations of climate evolution over time. With sets of historical observations and climate models, forecasting is possible but still extremely difficult. One iconic example illustrates the level of difficulty in weather/climate forecasting, and the sensitivity of models to small changes in input data is reflected by the so-called butterfly effect (Pascu 2012). The “butterfly” is the shape of Lorenz’s strange attractor and is a common graphical explanation of chaos theory (El-Basha et al. 2016). The most common daily usage is a weather forecast that can potentially be valid for the next several hours but is never 100% correct. Weather reflects just a slice of the greater atmosphere dynamics at a given moment and must be forecasted considering climate conditions. To assess climate conditions and types correctly, at least 30 years of observations are needed. This period is the interval recommended by the World Meteorological Organization (WMO). According to the WMO, climate reflects the average weather conditions at a particular location over a long period, ranging from months to thousands or millions of years ( https://wmo.int/topics/climate ). High-quality climate data are necessary if precise climate predictions are expected. This task normally involves massive databases, long-term time series from various sources, complex algorithms, and high-speed computer clusters.