Projects

MULTISCALE is a SciDAC Earth System Modeling project with the primary goal of producing better climate models to serve as the scientific tools and predictive tools that will address the needs of both the climate sciences and policy-oriented communities. Here are notable features of MULTISCALE: (1) Grand challenges in projecting the future of the Earth's climate result from the interactions among small-scale features and large-scale structures of the ocean and atmosphere in climate models. (2) A generation of models that capture the structure and evolution of the climate system across a broad range of spatial and temporal scales is required. MULTISCALE is an integrated team of climate and computational scientists working to accelerate the development and integration of multiscale atmospheric and oceanic parameterizations into the Community Earth System Model (CESM).
MULTISCALE is jointly funded by the Biological and Environmental Research (BER) and Advanced Scientific Computing Research (ASCR) programs in the U.S. Department of Energy Office of Science.

Principle Investigator: Bill Collins - LBNL, Jim Hack - ORNL site PI

Scientific facilities and organizations constantly report and evaluate performance and impact based on publication metrics. One of the major problems with this process is that many facilities do not have an effective method of finding, tracking, or managing their publications. COBRA is a publication discovery and management system designed to automate the discovery of publications while providing a management solution and adding efficiency to the manual processes that are still necessary. The COBRA publication discovery and management system is the culmination of several years worth of work. It builds upon previous methods of publication discovery and adds a complete management system and infrastructure.

Neuromorphic computing is one proposed computing architecture for the beyond Moore's Law computing landscape. Neuromorphic computers are software/hardware systems that have implementations with features inspired by biological brains. Key research questions associated with neuromorphic computing are (1) how to program or train these architectures to perform tasks and (2) what supporting software is required in order to integrate these architectures into real systems and make them accessible to novice users. The goal of this project is to develop algorithms for training neuromorphic computers and supporting software for neuromorphic computers, including development environments, visualization tools, and hardware simulators.

There has been a recent surge of success in utilizing Deep Learning (DL) in imaging and speech applications for its relatively automatic feature generation and, in particular for convolutional neural networks (CNNs), high accuracy classification abilities. While these models learn their parameters through data-driven methods, model selection (as architecture construction) through hyper-parameter choices remains a tedious and highly intuition driven task. To address this, Multi-node Evolutionary Neural Networks for Deep Learning (MENNDL) is proposed as a method for automating network selection on computational clusters through hyper-parameter optimization performed via genetic algorithms.

EDEN is a visual analytics tool for exploratory analysis of multivariate data sets. Based on an interactive variant of parallel coordinates, EDEN includes statistical analytics that guide the user to significant associations in complex data sets without information loss.

While the term ‘innovation ecosystem’ is often utilized, the concept is rarely quantified. Oak Ridge National Lab conducted a ground-breaking application of natural language processing, link analysis and other computational techniques to transform text and numerical data into metrics on clean energy innovation activity and geography for the U.S. Department of Energy. The project demonstrates that a machine-assisted methodology gives the user a replicable method to rapidly identify, quantify and characterize clean energy innovation ecosystems.