Bridging accuracy and interpretability: Comparative insights from interpretable and black-box models for CO₂ emission forecasting

Authors

  • Hrithik P. M. School of Chemical Engineering and Physical Sciences, Lovely Professional University, Phagwara 144411, India
  • Mohammad Shahfaraz Khan College of Economics and Business Administration, University of Technology and Applied Sciences-Salalah, Salalah 90212, Oman
  • Imran Azad College of Economics and Business Administration, University of Technology and Applied Sciences-Salalah, Salalah 90212, Oman
  • Mohammed Wamique Hisam College of Commerce and Business Administration, Dhofar University, Salalah 90211, Sultanate of Oman
  • Amir Ahmad Dar School of Chemical Engineering and Physical Sciences, Lovely Professional University, Phagwara 144411, India
  • Aseel Smerat Faculty of Educational Sciences, Al-Ahliyya Amman University, Amman 19328, Jordan
Article ID: 530
41 Views

DOI:

https://doi.org/10.18686/cest530

Keywords:

machine learning; interpretable models; CO2 emission; total energy production; total energy consumption

Abstract

The accurate and understandable carbon dioxide (CO2) emission prediction is necessary in developing effective climate policies especially in fast developing nations such as India. Although some highly developed machine learning (ML) models (e.g., XGBoost and LSTM) have a high predictive accuracy, they are black-box models and do not permit application directly in policy making. To fill this gap, this paper explores the possibility of interpretable ML models to predict CO2 emission with a small yet critical set of predictors: total energy production (TEP) and total energy consumption (TEC). Decision Trees, Explainable Boosting Machines (EBMs), and Generalized Additive Models (GAMs) were constructed to compare annual 1990–2023 data and compare them against traditional black-box solutions. These findings indicate that, in terms of accuracy and interpretability, EBMs and GAMs outperform traditional models, and their error measurements prove their high level of performance. SHAP (SHapley Additive Explanations) analysis also presented the fact that the increasing TEP and TEC have a great impact that contributes to the emissions, so it is necessary to consider renewable energy and energy-efficient solutions on a large scale. This paper, which combines strong forecasting with clear understanding, can assist in replicable analysis of applying interpretable models to climate policy, to achieve more specific interventions and effective monitoring of the reduction of emissions.

Downloads

Published

2026-01-04

How to Cite

P. M., H., Khan, M. S., Azad, I., Hisam, M. W., Dar, A. A., & Smerat, A. (2026). Bridging accuracy and interpretability: Comparative insights from interpretable and black-box models for CO₂ emission forecasting. Clean Energy Science and Technology, 4(1), 530. https://doi.org/10.18686/cest530

Issue

Vol. 4 No. 1 (2026)

Section

Article

License

Copyright (c) 2026 Hrithik P. M., Mohammad Shahfaraz Khan, Imran Azad, Mohammed Wamique Hisam, Amir Ahmad Dar, Aseel Smerat

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

References

1. Zhang Y, Liu H, Chen M. Interpretable boosting frameworks for clinical diagnostics: Balancing prediction and transparency. Journal of Medical Artificial Intelligence. 2025; 12(3): 145–162. DOI: https://doi.org/10.1016/j.engappai.2025.112489

2. Jiménez-Navarro M J, Lovrić M, Lovrić M, et al. Explainable deep learning on multi-target time series forecasting: An air pollution use case. Results in Engineering. 2024; 24: 103290. doi: 10.1016/j.rineng.2024.103290 DOI: https://doi.org/10.1016/j.rineng.2024.103290

3. Cai, J, Yang, H, Song, C, Xu, K. A novel graph convolutional network-based interpretable method for chiller energy consumption prediction considering the spatiotemporal coupling between variables. Energy. 2024; 312, 133639. doi: 10.1016/j.energy.2024.133639 DOI: https://doi.org/10.1016/j.energy.2024.133639

4. Zhou Y, Aslanidou I, Karlsson M, et al. An explainable AI model for power plant NOx emission control. Energy and AI. 2024; 15: 100326. doi: 10.1016/j.egyai.2023.100326 DOI: https://doi.org/10.1016/j.egyai.2023.100326

5. Anonna FR, Mohaimin MR, Ahmed A, et al. Machine Learning-Based Prediction of US CO2 Emissions: Developing Models for Forecasting and Sustainable Policy Formulation. Journal of Environmental and Agricultural Studies.2023; 4(3), 85–99. doi: 10.32996/jeas.2023.4.3.12 DOI: https://doi.org/10.32996/jeas.2023.4.3.12

6. Hosseini SM, Saifoddin A, Shirmohammadi R, et al. Forecasting of CO2 emissions in Iran based on time series and regression analysis. Energy Reports. 2019; 5: 619-631. doi: 10.1016/j.egyr.2019.05.004 DOI: https://doi.org/10.1016/j.egyr.2019.05.004

7. Fauvel K, Lin T, Masson V, et al. Xcm: An explainable convolutional neural network for multivariate time series classification. Mathematics. 2021; 9(23): 3137. doi: 10.3390/math9233137 DOI: https://doi.org/10.3390/math9233137

8. Baset A, Jradi M. Data-driven decision support for smart and efficient building energy retrofits: A review.Applied System Innovation. 2024; 8(1): 5. doi: 10.3390/asi8010005 DOI: https://doi.org/10.3390/asi8010005

9. Eshraghi P, Talami R, Dehnavi AN, et al. Adopting Explainable-AI to investigate the impact of urban morphology design on energy and environmental performance in dry-arid climates. Advances in Building Energy Research. 2025; 19(4): 1–35. doi: 10.48550/ARXIV.2412.12183- DOI: https://doi.org/10.1080/17512549.2025.2513280

10. Olawumi MA, Oladapo BI. AI-driven predictive models for sustainability. Journal of Environmental Management. 2025; 373: 123472. doi: 10.1016/j.jenvman.2024.123472 DOI: https://doi.org/10.1016/j.jenvman.2024.123472

11. Dumont Le Brazidec J, Vanderbecken P, Farchi A, et al. Deep learning applied to CO 2 power plant emissions quantification using simulated satellite images. Geoscientific Model Development. 2024; 17(5): 1995-2014. doi: 10.5194/gmd-17-1995-2024

12. Triebe O, Hewamalage H, Pilyugina P, et al. NeuralProphet: Explainable Forecasting at Scale. Arxiv Preprint Arxiv. 2021; doi: 10.48550/ARXIV.2111.15397

13. Nguyen VN, Tarełko W, Sharma P, et al. Potential of Explainable Artificial Intelligence in Advancing Renewable Energy: Challenges and Prospects. Energy & Fuels. 2024; 38(3): 1692-1712. doi: 10.1021/acs.energyfuels.3c04343 DOI: https://doi.org/10.1021/acs.energyfuels.3c04343

14. Schiller J, Stiller S, Ryo M. Artificial intelligence in environmental and Earth system sciences: explainability and trustworthiness. Artificial Intelligence Review. 2025; 58(10). doi: 10.1007/s10462-025-11165-2 DOI: https://doi.org/10.1007/s10462-025-11165-2

15. Bhavani BD, Sreeja K, Prasanna MS, et al. Machine learning models for prediction and forecasting of CO₂ emission with exploratory data analysis. Turkish Journal of Computer and Mathematics Education (TURCOMAT). 2023; 14(3): 955–962. doi: 10.17762/turcomat.v14i03.14174

16. Budennyy SA, Lazarev VD, Zakharenko NN, et al. Eco2ai: carbon emissions tracking of machine learning models as the first step towards sustainable ai//Doklady mathematics. Moscow: Pleiades Publishing. 2022; 106(Suppl 1): S118–S128. doi: 10.48550/ARXIV.2208.00406 DOI: https://doi.org/10.1134/S1064562422060230

17. Dumont Le Brazidec J, Vanderbecken P, Farchi A, et al. Deep learning applied to CO 2 power plant emissions quantification using simulated satellite images. Geoscientific Model Development. 2024; 17(5): 1995-2014. doi: 10.5194/gmd-17-1995-2024 DOI: https://doi.org/10.5194/gmd-17-1995-2024

18. Li T, Wang L, Qiu Z, et al. Reconstructing global daily co2 emissions via machine learning. Arxiv Preprint Arxiv. 2024; doi: 10.48550/ARXIV.2407.20057

19. Ma Y, Liu H, Wang S. Nonparametric approaches for analyzing carbon emission: from statistical and machine learning perspectives. Arxiv Preprint Arxiv. 2023; doi: 10.48550/ARXIV.2303.14900

20. Abdulmalik R, Srivastava G. Forecasting of Transportation-related CO2 Emissions in Canada with Different Machine Learning Algorithms. Advances in Artificial Intelligence and Machine Learning. 2023; 03(03): 1295-1312. doi: 10.54364/aaiml.2023.1176 DOI: https://doi.org/10.54364/AAIML.2023.1176

21. Qiao Q, Eskandari H, Saadatmand H, et al. An interpretable multi-stage forecasting framework for energy consumption and CO2 emissions for the transportation sector. Energy. 2024; 286: 129499. doi: 10.1016/j.energy.2023.129499 DOI: https://doi.org/10.1016/j.energy.2023.129499

22. Clement T, Nguyen HTT, Kemmerzell N, et al. Beyond explaining: XAI-based adaptive learning with SHAP clustering for energy consumption prediction. Arxiv Preprint Arxiv. 2024; doi: 10.48550/arxiv.2402.04982