skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Real-time Social Internet Data to Guide Forecasting Models

Abstract

Our goal is to improve decision support by monitoring and forecasting events using social media, mathematical models, and quantifying model uncertainty. Our approach is real-time, data-driven forecasts with quantified uncertainty: Not just for weather anymore. Information flow from human observations of events through an Internet system and classification algorithms is used to produce quantitatively uncertain forecast. In summary, we want to develop new tools to extract useful information from Internet data streams, develop new approaches to assimilate real-time information into predictive models, validate approaches by forecasting events, and our ultimate goal is to develop an event forecasting system using mathematical approaches and heterogeneous data streams.

Authors:
 [1]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE; National Inst. of Health (NIH) (United States)
OSTI Identifier:
1325660
Report Number(s):
LA-UR-16-27157
DOE Contract Number:
AC52-06NA25396
Resource Type:
Technical Report
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING

Citation Formats

Del Valle, Sara Y. Real-time Social Internet Data to Guide Forecasting Models. United States: N. p., 2016. Web. doi:10.2172/1325660.
Del Valle, Sara Y. Real-time Social Internet Data to Guide Forecasting Models. United States. doi:10.2172/1325660.
Del Valle, Sara Y. 2016. "Real-time Social Internet Data to Guide Forecasting Models". United States. doi:10.2172/1325660. https://www.osti.gov/servlets/purl/1325660.
@article{osti_1325660,
title = {Real-time Social Internet Data to Guide Forecasting Models},
author = {Del Valle, Sara Y.},
abstractNote = {Our goal is to improve decision support by monitoring and forecasting events using social media, mathematical models, and quantifying model uncertainty. Our approach is real-time, data-driven forecasts with quantified uncertainty: Not just for weather anymore. Information flow from human observations of events through an Internet system and classification algorithms is used to produce quantitatively uncertain forecast. In summary, we want to develop new tools to extract useful information from Internet data streams, develop new approaches to assimilate real-time information into predictive models, validate approaches by forecasting events, and our ultimate goal is to develop an event forecasting system using mathematical approaches and heterogeneous data streams.},
doi = {10.2172/1325660},
journal = {},
number = ,
volume = ,
place = {United States},
year = 2016,
month = 9
}

Technical Report:

Save / Share:
  • We examined publicly accessible Wikipedia access logs to determine if safeguard relevant events would be evident through increases in visits to articles related to that event.
  • The theory and programming of statistical tests for evaluating the Real-Time Air-Quality Model (RAM) using the Regional Air Pollution Study (RAPS) data base are fully documented in four volumes. Moreover, the tests are generally applicable to other model evaluation problems. Volume 4 discusses the application and interpretation of the statistical programs, particularly with regard to use on the RAM. In general, there is no set procedure for evaluating an air-quality model because of the different reasons for evaluating models and many subjective decisions to be made during the process. However, guidelines are presented to cover a wide variety of evaluationmore » needs, with attention to data preparation, classification, analysis, selection and application of tests, and interpretation of results. Several methods of diagnosing causes of poor model performance are discussed and some sample program outputs are also provided.« less
  • The theory and programming of statistical tests for evaluating the Real-Time Air-Quality Model (RAM) using the Regional Air Pollution Study (RAPS) data base are fully documented in four volumes. Moreover, the tests are generally applicable to other model evaluation problems. Volume 3 presents the software used in the statistical tests for evaluating the RAM. Six statistical tests are described, with attention to the programming philosophy behind them. Also presented is a review of the auxiliary software that sort, retrieve, format, and display the data.
  • The format of the weather data received from the National Weather Service is extremely inconvenient for building engineers to read, especially for trending historical data; therefore, a weather parsing program was created by NREL building engineers to simplify the data. The weather-parsing program collects current weather conditions for over 4,000 sites around the world and allows access to the data via a web page designed by NREL building researchers. The database provides data for some locations from late 1998 through today. Users can request data to be sent to them via e-mail by using the interactive web page.
  • This thesis develops a prototyping facility to support accurate exploratory modeling of the temporal structure of real-time, concurrent software systems on a parallel-processor architecture. The hierarchical bus parallel processor architecture, called the Real Time Cluster Star (RTCS*), is the hardware on which an executive operating system, the Extended Multi-Computer Real Time Executive (E-MCORTEX), provides the capability for concurrent real time processing. The prototyping facility is a tool to aid the system designer to assess the tasking structure and the resulting temporal behavior of concurrent multiprocess systems. This facility allows an early modeling of a proposed real-time system so that themore » system's design flaws can be discovered and corrected before the system is fully developed.« less