Abstract
Currently, the control and analysis of the parameters of the microclimate plays a particularly important role in various fields, including production, laboratory work and Environmental Research. Microclimate parameters — temperature, humidity, air pressure and other physical indicators-are of great importance in determining the efficiency of production processes and product quality. When working with large amounts of data, especially when analyzing microclimatic data, which is characterized by a large number of dimensions and parameters, clustering methods acquire particular importance. Clustering is the process of dividing data into groups or clusters based on similarities and differences within them. Such methods, including such as DBSCAN (Density-Based Spatial Clustering of Applications with Noise), can help detect anomalies in the data and detect malfunctions or violations in the operation of the system. This article discusses the methods used for clustering microclimate parameters and their mathematical models. The features and advantages of the DBSCAN method are analyzed, as well as its effectiveness in identifying clusters and anomalies in microclimatic data. The article will give specific examples of using the DBSCAN method, with the help of which mathematical formulas and calculations are proposed for the effective analysis and management of microclimate parameters. By deepening the understanding of the mathematical foundations of clustering methods and their role in the analysis of microclimate parameters, we strive to offer new approaches and solutions in the management and optimization of microclimate systems.