Time Series Machine Learning Predictions: Moving from modeling to production environment

The increasing in Earth Observation data availability (e.g., Landsat, Sentinel) and cross-cutting themes reference data (e.g., EuroCROPS, WorldCereal, Glance, GBIF), combined with the development of new machine learning approaches, such as semantic segmentation, auto-encoder, gradient descent tree, and autoML, opened several possibilities for producing time-series spatial predictions.

However several challenges are involved in deploying ML models in a production environment considering large amount of data, including: (1) data reading/writing optimization, (2) feature selection, (3) hyper-parameter optimization, (4) time-series reconstruction, and (6) efficient parallelization.

In this presentation Dr. Leandro Leal Parente shares lessons learned and the computational infrastructure implemented by OpenGeoHub for producing global time-series predictions (grassland, soil carbon, FAPAR, and GPP products) within the context of Open-Earth-Monitor cyberinfrastructure (OEMC) and Global Pasture Watch projects.