This session focuses on the design and initial results from the Ecological Forecasting Initiative’s NEON forecasting challenge. The forecasting challenge is an open competition launched in 2020 that asks participants to make predictions for ecological data being collected by the National Ecological Observatory Network (NEON). It is similar to a data science challenge or model-intercomparison project except that it is a true forecast -- the validation data haven’t been collected yet at the time predictions are made. The Challenge revolves around five theme areas (Aquatic Ecosystems, Tick Populations, Ground Beetle Diversity, Vegetation Phenology, Terrestrial Ecosystem Fluxes) and the session will include talks describing the data, protocols, and initial results for each theme. We will also describe how individuals, teams, and classes can participate in the challenge, including the standards and cyberinfrastructure used. Across these forecast areas the primary scientific goals are to improve our predictive capacity in these five areas, to learn more about the patterns of predictability across different ecological processes, and determine what modeling frameworks, mechanistic processes, and statistical approaches best capture community, population, and ecosystem dynamics. Another major goal of the challenge is to create a community of practice that builds capacity for ecological forecasting by leveraging NEON data products. As such the session will also touch on outcomes of EFI’s recent forecast education and diversity workshops and the EFI Student Association’s “10 simple rules” for training yourself in an emerging field.