MINT: Model INTegration through Knowledge-Rich Data and Process Composition

Major societal and environmental challenges require forecasting how natural processes and human activities affect one another. There are many areas of the globe where climate affects water resources and therefore food availability, with major economic and social implications. Such analyses require integrating highly heterogeneous models from separate disciplines, resolving semantic, spatio-temporal, and execution mismatches which are largely done by hand today and may take more than 2 years. The Model INTegration (MINT) project will develop a modeling environment to reduce the time needed to develop new integrated models, while ensuring their utility and accuracy. Research areas include: 1) New principle-based semi-automatic ontology generation tools for modeling variables; 2) A novel workflow compiler using abductive reasoning to hypothesize new models and data transformation steps; 3) A new data discovery and integration framework that finds new sources of data, learns to extract information from both online sources and remote sensing data, and transforms the data into the format required by the models; 4) A new methodology for spatio-temporal scale selection; 5) New knowledge-guided machine learning algorithms for model parameterization to improve accuracy; 6) A novel framework for multi-modal scalable workflow execution; 9) Novel composable agroeconomic models.