Global Sustainable Energy Analysis Using Data-Driven Methods and Machine Learning Article Swipe
This study presents a comprehensive analysis of global sustainable energy trends using statistical techniques and machine learning methods. The research evaluates long-term patterns in renewable energy consumption, fossil fuel dependence, and the transition toward low-carbon systems from 1990 to 2022. Using a CRISP-DM data-science framework, the study performs data preparation, exploratory analysis, correlation assessments, regression modelling, and predictive analytics to understand the future trajectory of clean energy adoption. Two predictive machine-learning models—a Decision Tree Regressor and a Multi-Layer Perceptron Neural Network—were applied to forecast future energy consumption trends. Comparative evaluation shows that the Decision Tree model provides slightly higher accuracy for long-term forecasting, while the Neural Network captures non-linear patterns across regions more effectively. The results highlight increasing global adoption of solar, wind, and hydropower, while fossil fuel consumption continues to decline in most regions. The research also identifies major challenges, including regional inequalities in renewable access, policy gaps, and fluctuating economic conditions. Overall, the study concludes that a sustainable global energy transition is achievable through targeted policies, technological innovation, and integrated predictive modelling tools. This work provides an accessible reference for researchers, policymakers, and practitioners interested in renewable energy forecasting, global sustainability trends, and the application of machine-learning methods to environmental and energy datasets.
Related Topics To Compare & Contrast
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.5281/zenodo.17701542
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W7106499719