A study of climate parameters using wavelet methods in the statistical modeling language R, as well as project implementation in a cloud computing environment, is presented. The scalograms constructed using the Morlet wavelet made it possible to obtain a two-dimensional map of the distribution of signal energy over time and scales. Thanks to this map, the main periodic components of the climatic time series were identified, including the annual cycle and longer-term trends. The wavelet analysis has shown its effectiveness in identifying hidden patterns in non-stationary climate data. A cross-wavelet analysis was performed between the climatic time series, which made it possible to establish their relationship on different time scales. The graphs of the cross-wavelet analysis showed a pronounced correlation over the average periods (about 256 days), which corresponds to seasonal changes. The phase shift analysis indicated that changes in one parameter may precede changes in another, which is important for understanding cause-and-effect relationships in climate systems. Of particular importance in the work was the implementation of experiments in a cloud computing environment. Cloud computing has provided the ability to scale calculations and remotely access analysis results. The results demonstrate the effectiveness of using wavelet methods and cloud technologies in climate data analysis.