Reducing CO2 emissions in district heating systems (DHS) is a critical step toward achieving sustainable energy solutions and mitigating climate change. This study aims to evaluate the influence of various weather parameters, such as solar radiation, wind speed, and ambient temperature, on CO2 emissions in DHS operations. By utilizing a unique dataset collected hourly from a local weather station and energy monitoring systems, correlation analysis and classification and regression random forests methodology were employed to identify key relationships and trends. The academic importance of this work lies in its novel application of data-driven approaches to optimize DHS performance, leveraging unique hourly data to address the complex dynamics of energy transfer and emissions. The findings reveal that the current data collection interval of one hour is insufficient to capture the rapid changes in energy transmission, with shorter intervals of one to three minutes being recommended. Additionally, outside temperature, solar radiation, wind speed, and wind direction were identified as critical factors influencing CO2 emissions, providing valuable insights for enhancing control strategies in DHS operations. This research highlights the potential for use of data analytics to improve energy efficiency and reduce emissions in DHS, offering practical guidance for system operators. By identifying weather-related influences on emissions, the study contributes to ongoing efforts to decarbonize district heating and promote environmentally sustainable energy practices.