<![CDATA[Increasing air pollution, especially in urban areas, is a serious issue that has a negative impact on public health and the environment. Accurate prediction of air pollution levels is critical to supporting mitigation efforts and data-driven decision-making. This study aims to develop an air pollution prediction model using the Simpson Integration method, a numerical approach used to calculate integrals with a high degree of accuracy. The data used included concentrations of pollutants such as PM2.5, PM10, and NO2 taken from daily measurements for one year. This method utilizes an interpolation algorithm to model changes in pollutant concentrations as a function of time. Simpson integration is used to calculate the area under the daily pollutant curve that represents the accumulated exposure to air pollution. The results show that this method is able to provide accurate predictions with an average error rate of less than 5% compared to actual data. This model has advantages in computational efficiency over conventional methods such as simple linear regression analysis. These findings prove that Simpson Integration can be effectively applied in air quality prediction and provide important information for governments and the public. This system is expected to support the development of an air pollution early warning system to increase public awareness and help formulate more responsive environmental policies.]]>
Copyrights © 2023
