Integrated Weather Station with Air Pollution Station Prediction Using Convolutional Long Short-Term Memory (ConvLSTM) Method

A major problem now facing Indonesian society is the increasing levels of air pollution and the deteriorating air conditions due to pollution. This pollution not only damages the environment and affects the climate, but can also have adverse effects on public health, such as respiratory diseases. This condition emphasizes the importance of measuring air pollution levels in various regions. This research aims to combine weather data and pollution data to predict air pollution levels. To get accurate data on weather conditions and pollution, a sophisticated technology is needed to support this research. The utilization of the Internet of Things (IoT) is one of the solutions used in this research and allows for efficient merging of weather and pollution data through the creation of IoT-based weather stations. The data will be analyzed using a quantitative approach, emphasizing the creation and application of the Convolutional Long Short-Term Memory (ConvLSTM) model. This model is particularly effective in understanding both the spatial and temporal aspects of the data. By using this approach, it is anticipated that predictions of air pollution levels will become more accurate and efficient than with traditional methods. Additionally, it aims to support informed decision-making for pollution control and raise public awareness about preventing air pollution.