AUTHOR=Saif-Ul-Allah Muhammad Waqas , Khan Javed , Ahmed Faisal , Salman Chaudhary Awais , Gillani Zeeshan , Hussain Arif , Yasin Muhammad , Ul-Haq Noaman , Khan Asad Ullah , Bazmi Aqeel Ahmed , Ahmad Zubair , Hasan Mudassir TITLE=Computationally Inexpensive 1D-CNN for the Prediction of Noisy Data of NOx Emissions From 500 MW Coal-Fired Power Plant JOURNAL=Frontiers in Energy Research VOLUME=Volume 10 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.945769 DOI=10.3389/fenrg.2022.945769 ISSN=2296-598X ABSTRACT=Coal-fired power plants have been in the use to meet the energy requirements in the countries where coal reserves are in abundance and are the key source of NOx emissions. Owing to the serious environmental and health concerns associated with NOx emissions, much work has been carried out to reduce NOx emissions. Sophisticated artificial intelligence techniques have been employed during the past few decades such as LSSVM, ANN, LSTM, and GRU to develop the NOx prediction model. Several studies have investigated DNN models for accurate NOx emission prediction. However, there is a need to investigate DNN based NOx prediction model that is accurate as well as computationally inexpensive. Recently a new artificial intelligence technique, convolutional neural network (CNN) has been introduced and proved to be superior for image class prediction accuracy. According to the best of the author’s knowledge, not much work has been done on the utilization of CNN on NOx emissions from coal-fired power plants. Therefore, this study investigated the prediction performance and computational time of 1-dimensional CNN (1d-CNN) on NOx emissions data from 500MW coal-fired power plant. The variation of hyperparameters of LSTM, GRU, and 1d-CNN were investigated and the performance metrics such as RMSE and computational time were recorded to obtain optimal hyperparameters. The obtained optimal values of hyperparameters of LSTM, GRU, and 1d-CNN were then employed for models’ development and consequently, the models were tested on test data. 1d-CNN NOx emissions model improved the training efficiency in terms of RMSE by 70.6% and 60.1% compared to LSTM and GRU, respectively. Also, the testing efficiency for 1d-CNN improved by 10.2% and 15.7% compared to LSTM and GRU respectively. Moreover, 1d-CNN (26 seconds) reduced the training time by 83.8% and 50% compared to LSTM (160 seconds) and GRU (52 seconds), respectively. Results reveal that 1d-CNN is more accurate, more stable, and computationally inexpensive compared to LSTM and GRU on NOx emissions data from the 500MW power plant.