Tools
Tools
Dharne, Sneha Ramesh (2024) Big Data-Powered Temperature Prediction Using PySpark and Time Series Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (889kB) | Preview |
Abstract
In this study, I used predictive modelling techniques to predict global temperature trends using ARIMA, SARIMA, XGBoost and Linear Regression. However, given the growing demand for accurate climate predictions in a number of sectors, the research also assesses how the models perform with historical temperature data. I assess the models based on performance metric, Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and R-squared (R²). By comparing the MSE (0.2269), RMSE (0.4764), and R² (0.9882) results it can be seen that XGBoost delivered the most promising performance to dealing with complicated non-linear phenomena. SARIMA also had good result: it has MSE of 0.3311, RMSE of 0.5754 and R² of 0.9828, which follows the seasonal trends. However, ARIMA was a success, but was less accurate. Linear Regression’s results were much worse, with MSE of 32.1586, RMSE of 5.6709 and R² of 0.1689. Furthermore, the temperature patterns across Europe and Ireland were analyzed using Power BI visualizations. From these findings, it is important that suitable models be used for temperature prediction, and XGBoost is the most reliable model for scalable and accurate forecasting.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Tomer, Vikas UNSPECIFIED |
| Subjects: | G Geography. Anthropology. Recreation > GE Environmental Sciences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 02 Sep 2025 10:18 |
| Last Modified: | 02 Sep 2025 10:18 |
| URI: | https://norma.ncirl.ie/id/eprint/8694 |
Actions (login required)
 |
View Item |