Frost forecast is an important issue in climate research because of its economic impact on several industries. In this study, we propose GRAST-Frost, a graph neural network (GNN) with spatio-temporal architecture, which is used to predict minimum temperatures and the incidence of frost. We developed an IoT platform capable of acquiring weather data from an experimental site, in addition data was collected from 10 weather stations in close proximity to the aforementioned site. The model considers spatial and temporal relations while processing multiple time series simultaneously. Performing predictions of 6, 12, 24 and 48 hours in advance, this model outperforms classical time series forecasting methods including, linear and non-linear machine learning methods, simple deep learning architectures and non-graph deep learning models. In addition, we show that our model significantly improves on the current state of the art of frost forecasting methods.