RTI International

United States
  • Booth: 11088

RTI International is an independent, nonprofit research institute dedicated to improving the human condition. We help developing countries and communities address complex problems in education, health, food security, energy, environment, governance, and economic development.

For more information, visit www.rti.org


  • STPredict
    STPredict uses machine learning to forecast flows and guide decisions in the Columbia River Basin....

  • Energy traders make profits (or incur losses) by buying and selling energy. To guide their trading, they use software models and weather forecasting to make predictions about the future prices of all forms of energy. Public utilities generate or buy electricity to distribute to their customers and, to keep costs low, they forecast the cost of power from multiple sources to adjust their portfolio accordingly. 

    In the Pacific Northwest, hydroelectric power represents 50-60% of generated electricity, making water supply forecasts more important there than other regions in the U.S. Most organizations that trade power in the Pacific Northwest use the U.S. government’s deterministic forecast called the Single Trace Procedure (STP) to inform trade decisions related to hydropower production.

    Researchers in RTI’s Center for Water Resources have developed a “forecast of the forecast” of the STP. While the current STP is released only once a week, RTI’s STPredict offers daily forecasts that give traders the ability to anticipate changes to the STP before the official forecast is available. We have also developed our own forecast for the Columbia Basin, the RTI-Forecast. This is a forecast of reservoir inflows with improved accuracy, which can be distributed to customers at timely intervals, offering strategic value for improved financial decisions.

    Both forecasts are developed from a combination of classic hydrological forecast models and techniques in combination with a Recurrent Neural Network (RNN) to refine forecast outputs.  The RNN component improves the fit of the forecast based on user-defined statistical metrics and “learning” from a historical training data set.  During development, a validation period was run to assess the performance of a forecast based on a data set that the model did not train from to mimic a real-time system. 

    The STPredict is trained to forecast the changes in the NWRFC STP, while the RTI-Forecast is trained to forecast actual observed inflows, both over an approximate 10-year training period.  These forecast models are continuously retrained and improved over time with the addition of new data.

    Benefits include:

    • Two daily forecasts (STPredict and RTI’s CBF) for four locations – Grand Coulee, The Dalles, Lower Granite and Chief Joseph
    • Forecasts based on historical simulated accuracy and comparisons to forecast and observed inflows
    • Continuously improved accuracy through the integration of machine learning
  • RTI Water Forecast Portal, powered by AmanziTM
    The RTI Water Forecast Portal is a web-based interface that provides customized hydrologic forecast information for specific users and water management decisions....

  • The RTI Water Forecast Portal is a web-based interface that provides customized hydrologic forecast information for specific locations and water management decisions.Users access their site via a secure login and password to view forecasts. Hydrologic forecast information is presented in flexible maps and plots that are designed to add local context and facilitate decision-making.The portal can ingest both publicly available forecasts as well as custom modeling performed by RTI or on-site by the end-user. Example users and applications include:

    • Reservoir operations and generation guidance for hydropower
    • Reservoir operations for flood management
    • Withdrawal or reservoir operations guidance for or water supply
    • Scheduling and safety guidance for marine or in-water construction
    • Scheduling and safety guidance for navigation, recreation or other streamflow-dependent activities
    • Guidance for road closures, issuance of warnings for flood impact mitigation

    For these and other applications, the RTI Water Forecast Portal provide

    • Easy, direct access to hydrologic forecasts for your locations
    • Straightforward web-based interface conveying both geospatial and hydrologic information
    • Hourly to weekly streamflow forecasts extending 18 hours to 10 days into the future
    • Synthesis of multiple hydrometeorological data streams for enhanced forecast interpretation
    • Integration of location-specific or decision-specific contexts, such as thresholds
    • Advanced analysis and post-processing, such as bias adjustment and uncertainty estimation
    • Scalable forecast services, from synthesis of public datasets through custom modeling
    • Accelerated access to ongoing RTI research and development leading to improved forecast products
  • Amanzi Hydrologic Risk Assessment Tool
    The Amanzi Hydrologic Risk Assessment Tool (Amanzi HRAT) is a web-based toolset to allow users to estimate of the probability of specific events or failure conditions occurring within their hydrologic system....

  • The RTI Hydrologic Risk Assessment Tool is a collection and linkage of utilities to perform stochastic rainfall-runoff frequency analysis through a web-based interface. Example applications of the tool are screening and intermediate level hydrology hazard information for dam safety risk assessments. Major components of the toolset include

    • multiple methods of precipitation frequency analysis to generate annual exceedance probability distributions
    • commonly used hydrologic models to perform stochastic rainfall-runoff modeling and route sampled events through catchments, reaches and reservoirs of the user’s system
    • data storage and utilities to perform pre- and post-processing routines necessary to estimate multiple output hydrologic frequency options
    • straightforward and intuitive interface to guide users through the process and display results

    Typical outputs of Amanzi HRAT are annual exceedance probability of critical hydrologic variables that characterize risk in a user’s system, such as

    • Annual exceedance probability of a specified maximum reservoir elevation
    • Annual exceedance probability of reservoir outflow
    • Annual exceedance probability of flow at a specified stream location

Send Email

Type your information and click "Send Email" to send an email to this exhibitor. To return to the previous screen without saving, click "Reset".

For Technical Support with this webpage, please contact support.