The article discusses the use of a recurrent neural network in the task of predicting pollutants in the air based on simulated data in the form of a time series. Neural recurrent network models with long Short-Term Memory (LSTM) are used to build the forecast. Unidirectional LSTM (hereinafter simply LSTM), as well as bidirectional LSTM (Bidirectional LSTM, hereinafter Bi-LSTM). Both algorithms were applied for temperature, humidity, pollutant concentration, and other parameters, taking into account both seasonal and short-term changes. The Bi-LSTM network showed the best performance and the least errors.

Keywords: environmental monitoring, data analysis, forecasting, recurrent neural networks, long-term short-term memory, unidirectional, bidirectional

The article considers the possibility of integrating traditional folk crafts into modern design solutions using 3D modeling technology. Digital tools are being considered that make it possible to combine historical colors and modern forms. The possibility of using glass-like elements in the decoration of clothing and the role of cylindrical elements in modern design are described. The results of the created ornamental solutions in the Gzhel palette on 3D models of clothing are presented.

Keywords: digital tools, 3D models, visualization, glass beads, gzhel, design solutions, ornament, cultural heritage

The article deals with contemporary technology of decorating the front surface of the ceramic brick - the coloring of the polymer powder coatings, as well as the ability to create on the surface of the stretcher and degrade the visual effect of variations of the original brickwork of the brick.

Keywords: Brick, powder paints, degrade, design, polymer coating