PREDICTING GAS TURBINE EMISSIONS THROUGH OPERATIONAL ANALYTIC
DOI:
https://doi.org/10.69980/c1we7y89Keywords:
Gas turbine emissions, Operational analytics, Machine learning, Carbon monoxide prediction, Nitrogen oxides predictionAbstract
The performance of gas turbines and minimize their environmental effects in contemporary power generation systems, it is crucial to accurately predict the emissions produced by these machines. Based on the data gathered from an industrial gas turbine, this study suggests a framework for predicting carbon monoxide (CO) and nitrogen oxides (NOx) emission from the gas turbine based on operational parameters. The data set contains 36,733 hourly measurements over a period of 5 years, from 2011 to 2015, of ambient conditions, turbine operating conditions and emission measurement. Data preprocessing, exploratory analysis, and multiple machine learning regression models were used for assessing the predictive performance based on Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and coefficient of determination (R²). The results showed that ensemble based models performed better in predicting the accuracy of the prediction as they were able to capture the nonlinear relationship between the operational variables and the emissions characteristics effectively. The turbine inlet temperature, compressor discharge pressure, exhaust pressure in gas turbine and energy yield in turbines were determined as the main parameters affecting the emission behavior through the feature importance analysis. It is proposed that the framework can be used for reliable predictive modeling to enable operational analytics to support real-time emission monitoring, intelligent process optimization and sustainable gas turbine operation.
References
1.Al-mahmodi, A. F., Munusamy, Y., Esmaiel, H., Atta, M. R., Alammar, M. M., & Baarimah, A. O. (2026). Explainable AI Framework for Operational Mode Classification in Hybrid Renewable Energy Systems. Case Studies in Thermal Engineering, 107736.
2.AlQemlas, T., Saber, A., Abdelfattah, A., Mokhiamar, O., Amine, S., & Gazo-Hanna, E. (2026). Artificial Intelligence-Driven Fault Detection and Predictive Maintenance in Renewable Energy Systems: A Review. Eng. Sci, 39(2061), 2061.
3.Dirik, M. (2022). Prediction of NOx emissions from gas turbines of a combined cycle power plant using an ANFIS model optimized by GA. Fuel, 321, 124037.
4.dos Santos Coelho, L., Ayala, H. V. H., & Mariani, V. C. (2024). CO and NOx emissions prediction in gas turbine using a novel modeling pipeline based on the combination of deep forest regressor and feature engineering. Fuel, 355, 129366.
5.Galiounas, E., Tranter, T. G., Owen, R. E., Robinson, J. B., Shearing, P. R., & Brett, D. J. (2022). Battery state-of-charge estimation using machine learning analysis of ultrasonic signatures. Energy and AI, 10, 100188.
6.Gil-Font, J., Hatte, M. A., Bailey, M. R., Navarrete, N., Ventura-Espinosa, J., Goulas, A., ... & Hernandez, L. (2020). Improving heat transfer of stabilised thermal oil-based tin nanofluids using biosurfactant and molecular layer deposition. Applied Thermal Engineering, 178, 115559.
7.He, X. (2021). Influence of cooking energy for people’s health in rural China: Based on CLDS data in 2014. Energy Reports, 7, 279-288.
8.Huang, D., Tang, S., Zhou, D., & Hao, J. (2022). Nox emission estimation in gas turbines via interpretable neural network observer with adjustable intermediate layer considering ambient and boundary conditions. Measurement, 189, 110429.
9.Kathirvelu, K., Yesudhas, A. V. P., & Ramanathan, S. (2023). Spectral unmixing based random forest classifier for detecting surface water changes in multitemporal pansharpened Landsat image. Expert Systems with Applications, 224, 120072.
10.Li, J., Han, J., Niu, D., & Jiang, X. Z. (2024). Fast and accurate gas turbine emission prediction based on a light and enhanced transformer model. Fuel, 376, 132750.
11.Liu, Z., & Karimi, I. A. (2020). Gas turbine performance prediction via machine learning. Energy, 192, 116627.
12.Lu, Z., Wang, H., He, G., Chen, Y., Li, Z., Zheng, Z., ... & Wang, H. (2025). Optimization framework for multi-objective energy management strategy in hybrid electric vehicles integrating explainable artificial intelligence. Applied Energy, 399, 126484.
13.McGarry, C., Dixon, J., Flower, J., Bukhsh, W., Brand, C., Bell, K., & Galloway, S. (2024). Electrified heat and transport: Energy demand futures, their impacts on power networks and what it means for system flexibility. Applied Energy, 360, 122836.
14.Naghibi, A. (2024). Exploring explainable ensemble machine learning methods for long-term performance prediction of industrial gas turbines: A comparative analysis. Engineering Applications of Artificial Intelligence, 138, 109318.
15.Pachauri, N. (2024). An emission predictive system for CO and NOx from gas turbine based on ensemble machine learning approach. Fuel, 366, 131421.
16.Potts, R., Hackney, R., & Leontidis, G. (2023). Tabular machine learning methods for predicting gas turbine emissions. Machine Learning and Knowledge Extraction, 5(3), 1055-1075.
17.Rengasamy, P., & Rajesh, R. (2025). Explainable artificial intelligence framework for wind turbine fault detection using random forest-extreme gradient boosting hybrid model. Results in Engineering, 107446.
18.Roy, A., Pramanik, S., Mitra, K., & Chakraborty, M. (2025). Advanced hybrid neural network techniques for minimizing gas turbine emissions. World Journal of Engineering, 22(6), 1214-1234.
19.Saqib, S. M., Shahzad, T., Tariq, M. U., Mazhar, T., & Hamam, H. (2025). Explainable and counterfactual lasso regression for resilient micro gas turbine power prediction in smart grids. Sustainable Computing: Informatics and Systems, 101284.
20.UCI Machine Learning Repository. (2019). Gas Turbine CO and NOx Emission Data Set [Data set]. University of California, Irvine. https://doi.org/10.24432/C5WC95
21.Wood, D. A. (2023). Long-term atmospheric pollutant emissions from a combined cycle gas turbine: Trend monitoring and prediction applying machine learning. Fuel, 343, 127722.
22.Wu, W., Lin, Y. T., Liao, P. H., Aziz, M., & Kuo, P. C. (2023). Prediction of CO–NOx emissions from a natural gas power plant using proper machine learning models. Energy Technology, 11(7), 2300041.
23.Xiao, M., Yang, B., Wang, S., Zhang, Z., & He, Y. (2023). Fine coordinate attention for surface defect detection. Engineering Applications of Artificial Intelligence, 123, 106368.
24.Xie, M., Zhou, M., Chen, L., Zhang, F., Xiao, N., Chen, X., ... & Zhao, Y. (2024). Techno-economic assessment of the modified Allam cycle configurations with multi-stage pump/compressor for efficient operation in hot regions. Energy Conversion and Management, 306, 118291.
25.Yin, J., Zhang, H., Zahra, A., Tayyab, M., Dong, X., Ahmad, I., & Ahmad, N. (2021). Exchange rate forecasting based on combined fuzzification strategy and advanced optimization algorithm. Processes, 9(12), 2204.
26.Zeinalipour, K., Barriere, L., Ghelardi, D., & Gori, M. (2026). Application of machine learning models for carbon monoxide and nitrogen oxides emission prediction in gas turbines. In Neural Networks: Overview of Current Theories and Applications (pp. 247-260). Singapore: Springer Nature Singapore.
