The Accelerated Climate Modeling for Energy (ACME) project is a newly launched project sponsored by the Earth System Modeling (ESM) program within U.S. Department of Energy's (DOE’s) Office of Biological and Environmental Research. ACME is an unprecedented collaboration among eight national laboratories and six partner institutions to develop and apply the most complete, leading-edge climate and Earth system models to challenging and demanding climate-change research imperatives. It is the only major national modeling project designed to address DOE mission needs to efficiently utilize DOE leadership computing resources now and in the future. While the project capabilities will address the critical science questions, its modeling system and related capabilities also can be flexibly applied by the DOE research community to address mission-specific climate change applications from U.S. Energy Sector Vulnerabilities to Climate Change and Extreme Weather.
Filter Projects
Area of Research
Quantum computing promises a platform for efficiently solving certain types problems thought to be intractable for traditional computers. The number of qubits needed to be competitive with classical computers varies dramatically depending on the problem. This project seeks to determine the maximum quantum operation rate for a given cooling capacity.
Developing a ground-based, quantum-secured, authenticated time distribution system for the energy grid.
The Oak Ridge National Laboratory's Computational Data Analytics Group's has worked over 12 years in creating text analytics systems to quickly discover meaningful information from raw data. These capabilities focus on six key areas, emphasizing high performance over very large sets of raw documents.
Collecting and Extracting: Collecting millions of documents from databases, Internet, Social Media, and hard drives; extracting text from hundreds of file formats; and translating this information into multiple languages.
Storing and Indexing: Storing and indexing millions of documents in search servers, distributed file systems (MapReduce), relational databases, and file systems.
Recommending: Filtering the full content of millions of documents to recommend the most valuable and relevant information based on a user’s own information, or user selections, or a user’s interactions with information.
Categorize: Grouping items based on the full content of documents using supervised and semi-supervised machine learning methods and targeted search lists.
Clustering: Creating a hierarchical group of documents based on similarity using unsupervised learning methods on the full content of each document.
Visualizing: Showing hierarchies, groups, and relationships among documents that helps the user quickly understand their value, and to see new connections.
This work has resulted in eight issued ( 7,072,883 7,315,858 7,693,903 7,805,446 7,937,389 8,473,314 8,825,710 9,256,649) and one pending patents , several commercial licenses (including Pro2Serve and TextOre), a spin off company (Global Security Information Analysts LLC (GSIA)), an R&D 100 Awards, and scores of peer reviewed research publications.
Collecting and Extracting: Collecting millions of documents from databases, Internet, Social Media, and hard drives; extracting text from hundreds of file formats; and translating this information into multiple languages.
Storing and Indexing: Storing and indexing millions of documents in search servers, distributed file systems (MapReduce), relational databases, and file systems.
Recommending: Filtering the full content of millions of documents to recommend the most valuable and relevant information based on a user’s own information, or user selections, or a user’s interactions with information.
Categorize: Grouping items based on the full content of documents using supervised and semi-supervised machine learning methods and targeted search lists.
Clustering: Creating a hierarchical group of documents based on similarity using unsupervised learning methods on the full content of each document.
Visualizing: Showing hierarchies, groups, and relationships among documents that helps the user quickly understand their value, and to see new connections.
This work has resulted in eight issued ( 7,072,883 7,315,858 7,693,903 7,805,446 7,937,389 8,473,314 8,825,710 9,256,649) and one pending patents , several commercial licenses (including Pro2Serve and TextOre), a spin off company (Global Security Information Analysts LLC (GSIA)), an R&D 100 Awards, and scores of peer reviewed research publications.
Situ combines anomaly detection and data visualization to provide a distributed, streaming platform for discovery and explanation of suspicious behavior to enhance situation awareness.
Security event data, such as intrusion detection system alerts, provide a starting point for analysis, but are information impoverished. To provide context, analysts must manually gather and synthesize relevant data from myriad sources within their enterprise and external to it. Analysts search system logs, network flows, and firewall data; they search IP blacklists and reputation lists, software vulnerability information, malware and threat data, OS and application vendor blogs, and news sites. All of these sources are manually searched for data relevant to the event being investigated. Relevant results must then be brought together and synthesized to put the event in context and make decisions about its importance and impact.
Modern computer network defense systems rely primarily on signature-based intrusion detection tools, which generate alerts when patterns that are pre-determined to be malicious are encountered in network data streams. Signatures are created reactively, and only after manual analysis of a network intrusion. There is no ability to detect intrusions that are new, or variants of an existing attack. There is no ability to adapt the detectors to the patterns unique to a network environment.
The Oak Ridge Cyber Analytics (ORCA) Attack Variant Detector (AVD) is a sensor that uses machine learning technology to analyze behaviors in channels of communication between individual computers. Using examples of attack and non-attack traffic in the target environment, the ORCA sensor is trained to recognize and discriminate between malicious and normal traffic types. The machine learning provides an insight that would be difficult for a human to explicitly code as a signature because it evaluates many interdependent metrics simultaneously.
The Oak Ridge Cyber Analytics (ORCA) Attack Variant Detector (AVD) is a sensor that uses machine learning technology to analyze behaviors in channels of communication between individual computers. Using examples of attack and non-attack traffic in the target environment, the ORCA sensor is trained to recognize and discriminate between malicious and normal traffic types. The machine learning provides an insight that would be difficult for a human to explicitly code as a signature because it evaluates many interdependent metrics simultaneously.
Big data demands the need for intelligent, recommender agents that can enhance a person’s situational or domain awareness of their environment. The ability to have a keen awareness and availability of relevant information provides a critical competitive edge. Unfortunately, there is simply too much data streaming too quickly for a person to manually process, analyze, and take action within a reasonable amount of time. In an attempt to alleviate this challenge, many people subscribe to relevant Internet information. There may be forms of subscriptions with the most common being Really Simple Syndication (RSS), blogs, even Facebook and Twitter. The concept is simple, when new information is posted to the site; a subscriber sees a list of this new information. The subscriber then has the option of following a link to read more. This approach is a very useful and successful model for monitoring this data, but it does have some significant drawbacks. In practice, the feeds of new information become quite lengthy, and contain more information than can be practically read. Furthermore, there can be a significant number of items that have little interest to the subscriber. Thus, the ability to find new and relevant information proves critical. We have developed a content-based recommender system that addresses both of these problems. The flexibility of input allows the system to be adaptable to industry and government use cases and data sets such as news feeds, resumes, proposal requests, etc.
The Verification, Validation and Uncertainty Quantification (VVUQ) for machine learning project identified processes and techniques to conduct VVUQ on machine learning applications.
ORNL has played a key role in developing novel Big Data toolkits in the context of syndromic disease surveillance. Our platform, the Oak Ridge Bio-surveillance Toolkit (ORBiT) enables large-scale analysis of heterogeneous data sources, including environmental, climate/weather related data, prescriptions records and other novel data streams emerging from social media (e.g., Twitter, Instagram). ORBiT is targeted at developing novel statistical and machine learning tools instead of acting as a central data collection interface from these heterogeneous resources. Additionally, it also provides an application programming interface (API) that can be used by end-users to target specific bio-surveillance applications. Machine learning tools are tightly integrated with visualization tools in a web-based framework to aid the end users or analysts in exploring potential links between heterogeneous data sets, detecting patterns/correlations across multiple data streams, identifying emerging disease outbreaks, forecasting emerging epidemics, and monitoring control strategies. ORBiT is implemented as a component-based, plug-and-play toolkit that exploits existing distributed cloud-based analytics frameworks.