A Data-Driven Approach to Air Pollution Management with Self-Tuning Deep Regression Neural Network

Air Qualities (AQ) are developed to be a serious environmental and health concern as a result of worldwide population growth. A predictive model for air quality is essential for the timely prevention and management of air pollution. This study proposes a novel Self Tuning Deep Regression Neural Network (STDRNN) for identifying air pollution in the environment using deep neural network. The Air Quality Index (AQI) dataset is employed as the primary source of input data. The methodology begins with a data pre processing phase where the input data finds the missing data and shows the duplicate AQ values using data imputation and remove outlier method. This is followed by feature construction where the each AQ label is converted into an integer AQ value and scaling the features to a similar range using feature encoding and feature scaling method. The AQI data are then given to the STDRNN model for training and testing, enabling accurate prediction. The performance of the proposed model is evaluated using standard metrics such as RMSE, MSE and R2 coefficient. Using the python software AQI dataset shows the comparative analysis with existing methods on similar datasets demonstrates the superiority of the proposed approach in terms of selection performance. This work highlights the potential of STDRNN in advancing the accuracy of the model as well as its promising potential applications.