The increasing impact of climate change, including rising average temperatures and altered precipitation patterns, has led to changes in the prevalence and distribution of climate-sensitive diseases (CSDs), such as Dengue Hemorrhagic Fever (DHF). DHF remains a significant public health concern in Indonesia, particularly in Banda Aceh, due to its high incidence. The burden on healthcare systems is substantial, contributing to increased morbidity and mortality, especially among vulnerable populations. This study aimed to integrate climate data with machine learning methods to develop predictive models for DHF incidence. Data from 2010 to 2023 included DHF case counts and monthly climate variables such as humidity, rainfall, temperature, and wind speed. The predictive models employed Gradient Boosting, Support Vector Regression (SVR), Random Forest, and Linear Regression algorithms. Model performance was evaluated by comparing prediction accuracy using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) metrics. The results demonstrated that the Linear Regression model predicted monthly DHF incidence with greater accuracy than the other models, as indicated by lower MAE and RMSE values. These findings suggest that integrating climate data with machine learning provides an effective tool for early warning systems for DHF, supporting public health planning and interventions in Banda Aceh City, particularly in anticipation of an increase in DHF cases.