- Climate change has become one of the most critical global challenges, influencing environmental stability, agriculture, and human livelihoods. Accurate analysis and prediction of climate trends are essential for developing effective mitigation and adaptation strategies. Traditional statistical approaches often struggle to capture complex relationships present in large-scale climate datasets. To address this limitation, this study proposes an intelligent climate prediction framework based on machine learning techniques and spatiotemporal data analytics. Historical climate data containing temporal attributes such as year and month along with spatial parameters including latitude and longitude are used to analyse long-term temperature variations. The proposed system applies multiple machine learning algorithms, including Linear Regression, Random Forest, Support Vector Regression, and K-Nearest Neighbor, to identify patterns and predict future climate trends. Data preprocessing and feature extraction techniques are employed to improve model performance and reduce noise in the dataset. Experimental evaluation demonstrates that ensemble-based models provide higher predictive accuracy compared to traditional regression approaches. The results highlight the effectiveness of machine learning models in interpreting climate data and forecasting temperature variations. This research contributes to the development of intelligent climate monitoring systems that can support environmental research, policy planning, and sustainable development initiatives. \\
Professor et al. (Thu,) studied this question.