Climate change mitigation relies heavily on understanding carbon storage dynamics in terrestrial ecosystems. This study examines the relationship between carbon storage (kg/m2) and various climatic variables, including precipitation, temperature, humidity, and radiation. Machine learning models such as Random Forest (RF), Gradient Tree Boost (GTB), Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Multiple Regression (MR) were applied. Among these, Random Forest exhibited the highest explanatory power (R2 = 0.95, Adj. R2 = 0.75, F-score = 4.721, Accuracy = 0.67), while ANN showed the highest predictive accuracy (Accuracy = 0.80). The results underline the significant role of climatic factors in shaping carbon dynamics, emphasizing the integration of machine learning-based models in carbon capture and sequestration (CCS) strategies. Furthermore, carbon storage dynamics in Utah from 1991 to 2020 were analyzed using remote sensing data and multiple regression models. Carbon storage was found to be highest in forested areas, wetlands, and natural grasslands, while agricultural and wildfire-affected zones exhibited lower carbon stocks. Climatic factors, particularly precipitation, temperature, and humidity, were identified as significant drivers of carbon sequestration, with moderate precipitation and favorable temperatures enhancing carbon retention. The study highlights the importance of region-specific CCS strategies, which rely on accurate climate-driven carbon storage assessments, for ensuring sustainable resource management and mitigating anthropogenic climate impacts.