A novel artificial intelligence algorithm for predicting air quality by analysing the pollutant levels in air quality data in tamilnadu

•Data generation or collection.•It preprocesses the data, i.e., eliminating the missing values, reducing the redundant values, and selecting only the necessary data elements.•Implement the TFO algorithm for training the dataset, predicting, and creating an air quality index.•A testing dataset is classified using the TFO algorithm.•Implementing them in real-time to find the applicability of the model. Pollution acquires many forms, such as water, air, noise, heat, and light, whereas air pollution immediately affects human health. Controlling air pollution is a critical task because the sources of air pollution are more and different. Measuring and forecasting the severity level of air pollution helps the public to take safety actions immediately. Hence measuring air pollution precisely and automatically has become the need of the hour. This paper presents a novel Termite Fly Optimization Algorithm (TPO) for predicting the level of air pollution in various places. Based on the pollutants level measured from the air, the TFO algorithm estimates the human health mapping with the termites level in the search space. The high level of pollutants mixed in the air is mapped with the severity level of human health. This paper uses the worst-case comparison between the data and the termites' behavior. The prediction made through this model is converted into an index called the Air quality index (AQI). An open-source dataset is used to train the model, and a real-time dataset of air pollution from Chennai, Manali, is obtained to evaluate its prediction. Air pollution is predicted according to the AQI index. The results are compared with existing models, and the performance is verified.