Hybrid Metaheuristic Optimized Extreme Learning Machine for Sustainability Focused CO 2 Emission Prediction Using Globalization-Driven Indicators

Mahmoud Almsallti, Ahmad Bassam Alzubi and Oluwatayomi Rereloluwa Adegboye ()
Additional contact information
Mahmoud Almsallti: Business Administration Department, Institute of Graduate Research and Studies, University of Mediterranean Karpasia, Mersin-10, TR-10 Mersin, Northern Cyprus, Lefkosa 99010, Turkey
Ahmad Bassam Alzubi: Business Administration Department, Institute of Graduate Research and Studies, University of Mediterranean Karpasia, Mersin-10, TR-10 Mersin, Northern Cyprus, Lefkosa 99010, Turkey
Oluwatayomi Rereloluwa Adegboye: Business Administration Department, Institute of Graduate Research and Studies, University of Mediterranean Karpasia, Mersin-10, TR-10 Mersin, Northern Cyprus, Lefkosa 99010, Turkey

Sustainability, 2025, vol. 17, issue 15, 1-28

Abstract: The escalating threat of climate change has intensified the global urgency to accurately predict carbon dioxide (CO 2 ) emissions for sustainable development, particularly in developing economies experiencing rapid industrialization and globalization. Traditional Extreme Learning Machines (ELMs) offer rapid learning but often yield unstable performance due to random parameter initialization. This study introduces a novel hybrid model, Red-Billed Blue Magpie Optimizer-tuned ELM (RBMO-ELM) which harnesses the intelligent foraging behavior of red-billed blue magpies to optimize input-to-hidden layer weights and biases. The RBMO algorithm is first benchmarked on 15 functions from the CEC2015 test suite to validate its optimization effectiveness. Subsequently, RBMO-ELM is applied to predict Indonesia’s CO 2 emissions using a multidimensional dataset that combines economic, technological, environmental, and globalization-driven indicators. Empirical results show that the RBMO-ELM significantly surpasses several state-of-the-art hybrid models in accuracy (higher R 2 ) and convergence efficiency (lower error). A permutation-based feature importance analysis identifies social globalization, GDP, and ecological footprint as the strongest predictors underscoring the socio-economic influences on emission patterns. These findings offer both theoretical and practical implications that inform data-driven Artificial Intelligence (AI) and Machine Learning (ML) applications in environmental policy and support sustainable governance models.

Keywords: Machine Learning (ML); Extreme Learning Machine (ELM); sustainability; sustainable development; Artificial Intelligence (AI); hybrid metaheuristic optimization; CO 2 emission prediction (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/17/15/6783/pdf (application/pdf)
https://www.mdpi.com/2071-1050/17/15/6783/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:17:y:2025:i:15:p:6783-:d:1710021

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().