The increased occurrence of extreme weather events due to climate change has heightened the need to develop support decision systems that can help farmers to mitigate losses in agriculture. Environmental hazards, such as frost have a relevant economy impact on crops since they may cause several damages and injuries in sensitive crops and therefore lead to production losses. Probability of frost occurrences are heavily influenced by local climate conditions. In addition, the extent of damage due to frost also depends on the phenology stages of the crops present at the area of interest. Hence, an early frost warning system at local scale have the potential to minimize damage to the crops as one can deploy protection mechanisms. In this article, we present models for an early forecasting (24 hours and 48 hours) of frost occurrences using stacked machine learning models. We trained the machine-learning models with hourly historical data from local weather station. The trained model is validated within the timeframe when the crops (organic fruits) are most susceptible to frost for the area of study. We also show the applicability of the model by extrapolating it to a new region. Moreover, we also integrate the frost prediction model with a phenology monitoring system using very-high resolution satellite data and weather station data. This development is carried out within the framework of H2020 CYBELE project.