AI-driven Data Analysis for Sustainable Development

Rufat E. Azizov; Nigar Ismayilova

doi:10.14710/jsp.2025.29834

DOI: https://doi.org/10.14710/jsp.2025.29834

AI-driven Data Analysis for Sustainable Development

Rufat E. Azizov

- Azerbaijan State Oil and Industry University, Azerbaijan

*Nigar Ismayilova - Department of General and Applied Mathematics, Azerbaijan State Oil and Industry University, Azerbaijan

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

BibTex Citation Data :

@article{JSP29834,
    author = {Rufat Azizov and Nigar Ismayilova},
    title = {AI-driven Data Analysis for Sustainable Development},
    journal = {Journal of Sustainability Perspectives},
  volume = {5},
    number = {2},
    year = {2025},
    keywords = {},
    abstract = { Sustainable development is a global challenge which requires an innovative approach merging environmental science, economics, policy-making, and artificial intelligence. The data-driven approach using intelligent methodologies is valuable for evaluating and mitigating environmental impacts. This study exploits data from different sources and machine learning methods to analyze key sustainability indicators, focusing on CO2 emissions, ecological footprint, and load capacity factor. The analysis emphasizes advanced feature selection techniques and predictive modelling to identify the most significant economic, industrial, agricultural, and environmental factors that affect sustainability. Comparative analysis shows differences between the importance of indicators established through expert-driven decisions across various scientific fields and AI-driven assessments. The research attempts to solve the problem following a multi-step process: (1) clustering of countries based on environmental indicators to identify patterns and classify according to similar performance; (2) evaluation of the socio-economic and environmental factors’ impact on CO2 emissions using machine learning; (3) predicting future trends in emissions and sustainability metrics through high-level artificial intelligence techniques such as Hidden Markov models. This study will potentially serve policymakers, enabling data-driven decision-making to promote sustainable development efforts. The results demonstrate the value of interdisciplinary approaches to deal with sustainability challenges and to stimulate a balanced path toward economic growth and environmental protection. },
   issn = {2797-7137},   pages = {171--182}  doi = {10.14710/jsp.2025.29834},
    url = {https://ejournal2.undip.ac.id/index.php/jsp/article/view/29834}
}

Citation Format:

Abstract

Sustainable development is a global challenge which requires an innovative approach merging environmental science, economics, policy-making, and artificial intelligence. The data-driven approach using intelligent methodologies is valuable for evaluating and mitigating environmental impacts. This study exploits data from different sources and machine learning methods to analyze key sustainability indicators, focusing on CO2 emissions, ecological footprint, and load capacity factor. The analysis emphasizes advanced feature selection techniques and predictive modelling to identify the most significant economic, industrial, agricultural, and environmental factors that affect sustainability. Comparative analysis shows differences between the importance of indicators established through expert-driven decisions across various scientific fields and AI-driven assessments. The research attempts to solve the problem following a multi-step process: (1) clustering of countries based on environmental indicators to identify patterns and classify according to similar performance; (2) evaluation of the socio-economic and environmental factors’ impact on CO2 emissions using machine learning; (3) predicting future trends in emissions and sustainability metrics through high-level artificial intelligence techniques such as Hidden Markov models. This study will potentially serve policymakers, enabling data-driven decision-making to promote sustainable development efforts. The results demonstrate the value of interdisciplinary approaches to deal with sustainability challenges and to stimulate a balanced path toward economic growth and environmental protection.

Fulltext

Article Metrics:

Article Info

Section: Original Articles

Language : EN

In Vol 5, No 2: December 2025

Recent articles

Breaking the Waste Cycle: How Central Mindanao University Cut Waste from 30 Tons to 2 Tons Sustainable University Strategy and Assessing Its Performance in Green Rankings Understanding Academic Transport Emissions - Insights from an Italian Medium-Size Public University More recent articles

Arora NK, Mishra I. United Nations Sustainable Development Goals 2030 and environmental sustainability: race against time. Environmental Sustainability. 2019;2(4):339–42. https://doi.org/10.1007/s42398-019-00092-y
United Nations Sustainable Development Goals https://sdgs.un.org/
Souza JT de, Francisco AC de, Piekarski CM, Prado GF do, Oliveira LG de. Data mining and machine learning in the context of sustainable evaluation: a literature review. IEEE Latin America Transactions. 2019;17(03):372–82. https://doi.org/10.1109/TLA.2019.8863307
Andries A, Morse S, Murphy R, Lynch J, Woolliams E, Fonweban J. Translation of Earth observation data into sustainable development indicators: An analytical framework. Sustainable Development. 2019 May 1;27(3):366–76
Pande CB, Egbueri JC, Costache R, Sidek LM, Wang Q, Alshehri F, et al. Predictive modeling of land surface temperature (LST) based on Landsat-8 satellite data and machine learning models for sustainable development. Journal of Cleaner Production. 2024;444:141035. https://doi.org/https://doi.org/10.1016/j.jclepro.2024.141035
Yao Z, Lum Y, Johnston A, Mejia-Mendoza LM, Zhou X, Wen Y, et al. Machine learning for a sustainable energy future. Nature Reviews Materials. 2023;8(3):202–15. https://doi.org/10.1038/s41578-022-00490-5
Poli Giuliano and Cuntò S and ME. A Data-Driven Approach to Monitor Sustainable Development Transition in Italian Regions Through SDG 11 Indicators. In: Gervasi Osvaldo and Murgante B and GC and TD and CRAMA and FLMN, editor. Computational Science and Its Applications – ICCSA 2024 Workshops. Cham: Springer Nature Switzerland; 2024. p. 337–55
Jabbari M, Shafiepour Motlagh M, Ashrafi K, Abdoli G. Differentiating countries based on the sustainable development proximities using the SDG indicators. Environment, Development and Sustainability. 2020 Oct 1;22(7):6405–23. https://doi.org/10.1007/s10668-019-00489-z
da Silva J, Fernandes V, Limont M, Rauen WB. Sustainable development assessment from a capital's perspective: Analytical structure and indicator selection criteria. Journal of Environmental Management. 2020;260:110147
Chen IC. Predicting regional sustainable development to enhance decision-making in brownfield redevelopment using machine learning algorithms. Ecological Indicators. 2024;163:112117. https://www.sciencedirect.com/science/article/pii/S1470160X24005740
Isabel Molina-Gómez N, Rodríguez-Rojas K, Calderón-Rivera D, Luis Díaz-Arévalo J, López-Jiménez PA. Using machine learning tools to classify sustainability levels in the development of urban ecosystems. Sustainability (Switzerland). 2020 Apr 1;12(8). https://doi.org/10.3390/SU12083326
Abd El-Aal MF. The relationship between CO2 emissions and macroeconomics indicators in low and high-income countries: using artificial intelligence. Environment, Development and Sustainability. 2024; https://doi.org/10.1007/s10668-024-04880-3
Sinaga KP, Hussain I, Yang MS. Entropy K-Means Clustering with Feature Reduction under Unknown Number of Clusters. IEEE Access. 2021;9:67736–51. https://doi.org/10.1007/s10994-013-5337-8
Elghazel H, Aussem A. Unsupervised feature selection with ensemble learning. Machine Learning. 2015 Jan 1;98(1–2):157–80. https://doi.org/10.1109/ACCESS.2021.3077622
Li S, Siu YW, Zhao G. Driving Factors of CO2 Emissions: Further Study Based on Machine Learning. Frontiers in Environmental Science. 2021 Aug 23;9. https://doi.org/10.3389/fenvs.2021.721517
Li X, Ren A, Li Q. Exploring Patterns of Transportation-Related CO2 Emissions Using Machine Learning Methods. Sustainability (Switzerland). 2022 Apr 1;14(8). https://doi.org/10.3390/su14084588
Castelli, T., Mocenni, C., & Dimitri, G. M. (2024). A machine learning approach to assess Sustainable Development Goals food performances: The Italian case. Plos one, 19(1), e0296465
García-Rodríguez, A., et al. (2025). Sustainable visions: unsupervised machine learning insights on global development goals. PloS one, 20(3), e0317412
Mathrani, A., Wang, J., Li, D., & Zhang, X. (2023). Clustering analysis on sustainable development goal indicators for forty-five asian countries. Sci, 5(2), 14
Li J, Irfan M, Samad S, Ali B, Zhang Y, Badulescu D, et al. (2023) The Relationship between Energy Consumption, CO2 Emissions, Economic Growth, and Health Indicators. International Journal of Environmental Research and Public Health. 20(3). https://doi.org/10.3390/ijerph20032325
The Paris agreement https://unfccc.int/process-and-meetings/the-paris-agreement
COP29 declarations https://cop29.az/en/pages/cop29-declaration-on-green-digital-action
Kumari, S., & Singh, S. K. (2023). Machine learning-based time series models for effective CO2 emission prediction in India. Environmental Science and Pollution Research, 30(55), 116601-116616
World Bank Data. https://data.worldbank.org/
Likas, A., Vlassis, N., & Verbeek, J. J. (2003). The global k-means clustering algorithm. Pattern recognition, 36(2), 451-461
Januzaj, Y., Beqiri, E., & Luma, A. (2023). Determining the Optimal Number of Clusters using Silhouette Score as a Data Mining Technique. International Journal of Online & Biomedical Engineering, 19(4)
Yadav, A., Jha, C. K., & Sharan, A. (2020). Optimizing LSTM for time series prediction in Indian stock market. Procedia Computer Science, 167, 2091-2100
Hanif, M., Sami, F., Hyder, M., & Ch, M. I. (2017). Hidden Markov model for time series prediction. Journal of Asian Scientific Research, 7(5), 196-205
Cao W, Zhu W, Demazeau Y. Multi-Layer Coupled Hidden Markov Model for Cross-Market Behavior Analysis and Trend Forecasting. IEEE Access. 2019;7:158563–74. https://doi.org/10.1109/ACCESS.2019.2950437
CO2 emissions by country https://www.worldometers.info/co2-emissions/co2-emissions-by-country/

Last update:

No citation recorded.

Last update:

No citation recorded.

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

In order to be accepted and published by Journal of Sustainability Perspectives, the author (s) who submit a manuscript should complete the review process. Journal of Sustainability Perspectives articles are distributed under a Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0).

The copyright of received articles is assigned to the author (s). The author (s) have the right to the articles that have been published. The Editorial Team of Journal of Sustainability Perspectives and the Author(s) strive to ensure that no errors occur in the articles that have been published, both data errors and statements in the articles. Authors who publish in this journal agree to the following terms:

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
The journal allows the authors to hold the copyright and retain publishing rights without restrictions.
Authors can enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) before and during submission, as it can lead to productive exchanges and earlier and greater citation of published work.