Forecasting the risk of invasion by alien species in response to climate change has become a crucial goal in ecology and biodiversity conservation. Due to their ease of implementation, correlative species distribution models (SDMs) are extremely appealing for explaining and predicting the risk of species establishment under climate change. However, there are some caveats to forecasting with species distribution models which can present barriers to the development of robust risk maps in support of IAS policy and decision making: 1) uneven data availability arising from geographic sampling bias; 2) forecasts are not accompanied with a measure of uncertainty; and 3) the heavy influence of the chosen statistical model or algorithm on predicted risk. To address these problems, we have developed a risk modeling workflow using data from the TrIAS project. The workflow is based on GBIF data and openly published environmental data layers characterizing climate and land cover. It requires only a species name and generates an ensemble of machine learning algorithms stacked together as a meta-model to produce the final risk map at 1 km2 resolution. Risk maps are generated automatically for standard IPCC greenhouse gas emission scenarios (RCP) and are accompanied by maps illustrating the confidence of each individual prediction across space, thus enabling the intuitive visualization and understanding of how the confidence of the model varies across space and RCP. The effects of sampling bias are accounted for using the sampling effort of the higher taxon the modelled species belongs to (e.g vascular plants). Our risk maps provide an evidence-base in anticipation of alien species under future climate change in Belgium. They can be used to support risk assessments and guide surveillance efforts on alien species in Belgium. Our open source workflow and ancillary data products can be used to generate risk and confidence maps across Europe.