Data fusion and analysis tools to enable machine learning for systems biology and bioenergy

The need for a predictive understanding of the dynamics of biological systems— encompassing the dynamic interactions of plants, microbes, and their environment—is critical to advancing operational and scientific efforts as well as innovations within the bioeconomy (e.g. for biofuels, biomanufacturing and agriculture). This understanding can be derived from complex multimodal inter-related datasets. However, we are currently better at collecting these datasets than we are at efficiently using them. Or there is a lack of tools which can effectively fuse and analyze these multimodal datasets to provide the needed understanding. Subsurface Insights will develop software for multimodal biological and environmental data fusion and analysis. This software will be open source. We will provide hosted deployments of this software as well as consulting services around it. In Phase I we successfully developed an initial version of this software. We used it to ingest, fuse and analyze a complex multiyear dataset collected by the Great Lakes Bioenergy Research Center. We released the software as open source on github. In Phase I we will further develop this software and test it on multiple complex datasets from four DOE funded products. We will work with beta customers in academia and national labs to test the functionality and ease of use of this software so we can bring it to market. This tool will support the US bioeconomy by advancing capabilities in biological and environmental data analytics. Applications include biofuels, biomanufacturing, agriculture and forestry.