Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Forecasting the Future of Sustainability: Integrating Machine Learning and Optimization for SDG Progress Modeling
The Sustainable Development Goals (SDGs) represent a comprehensive framework for aligning economic, social, and environmental priorities. Although widely adopted, progress toward these goals remains inconsistent and slow. Key barriers include fragmented data, insufficient institutional coordination,...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
AUC Knowledge Fountain
2026
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| Summary: | The Sustainable Development Goals (SDGs) represent a comprehensive framework for aligning economic, social, and environmental priorities. Although widely adopted, progress toward these goals remains inconsistent and slow. Key barriers include fragmented data, insufficient institutional coordination, and limited integration between engineering systems and sustainability policy. This study introduces a data-driven framework that leverages predictive modeling and optimization to assess and accelerate progress toward the SDGs. National datasets from 2000 to 2022 are used to develop a hybrid ensemble model combining Prophet and XGBoost to forecast country-level SDG Index scores through 2030. This ensemble approach captures both long-term temporal trends and complex nonlinear relationships among economic, environmental, and infrastructural variables, outperforming traditional statistical and single machine-learning models. Based on these forecasts, a linear optimization model is used to identify investment strategies that maximize sustainable development outcomes while satisfying economic and environmental constraints. The findings indicate that targeted engineering interventions, particularly in clean energy access, health systems, and industrial decarbonization, can substantially improve SDG performance when resources are allocated efficiently. While baseline projections reveal persistent structural disparities, optimized investment scenarios demonstrate that many developing and emerging economies could significantly reduce performance gaps by 2030. These global results are further interpreted through a national-level case study of Egypt which provides descriptive, predictive, and prescriptive insights into how structural development patterns shape SDG outcomes. This research integrates forecasting and decision-making, offering policymakers and engineers an evidence-based tool for designing strategies that balance growth, equity, and environmental sustainability. By connecting data analytics with engineering practice, the study provides a novel framework for translating sustainability objectives into measurable global progress. |
|---|