HydroForecast

Short-term, Seasonal and Extended

Three forecast horizons designed for organizations' decision-making:

  1. Short-term, designed for operations, marketing and emergency response, gives high-accuracy, hourly insight of the upcoming 10 days.
  2. Seasonal, designed for medium-term planning and coordination, provides insight for the upcoming 90 days.
  3. Extended, designed for long-term planning and risk mitigation, provides guidance up to 12 months into the future.

Proven Performance

HydroForecast swept a year long short-term flow forecasting competition hosted by the United States Bureau of Reclamation, CEATI and hydropower utilities and verified by RTI International.

In every competition region, HydroForecast was more accurate further into the future and provided better insight in both drought conditions and 1000-year storms.

See the forecasts in action

Spring freshet

Taylor River at Taylor Park, CO

Date:
April 1, 2019 - August 31, 2019
Min obs. flows:
25 cfs
Max obs. flows:
873 cfs

View case study ⇾
Spring freshet

Trinity River by Coffee Creek, CA

Date:
March 16, 2019 - June 15, 2019
Min obs. flows:
700 cfs
Max obs. flows:
5,150 cfs

View case study ⇾
Hurricane

Little Tennessee at Needmore, TN

Date:
August 31, 2021 - September 4, 2021
Min obs. flows:
713
Max obs. flows:
6560

View case study ⇾
Unavailable gauge data

Peribonka River, Québec

Date:
December 1, 2020 - January 15, 2021
Min obs. flows:
1,020 cfs
Max obs. flows:
4,560 cfs

View case study ⇾
Flashy rain storms

Little Tallapoosa by Newell, AL

Date:
November 1, 2019 - July 1, 2020
Min obs. flows:
288 cfs
Max obs. flows:
7,600 cf

View case study ⇾
Rain on snow

Trinity River by Coffee Creek, CA

Date:
March 16, 2021 - March 21, 2021
Min obs. flows:
140 cfs
Max obs. flows:
245 cfs

View case study ⇾
Low flows

James River by Arrowwood, ND

Date:
September 1, 2020 - April 17, 2021
Min obs. flows:
2 cfs
Max obs. flows:
10 cfs

View case study ⇾
High flows & flooding

Rouge River at Bell Falls, Québec

Date:
April 10, 2019 - June 1, 2019
Min obs. flows:
100 cms
Max obs. flows:
960 cms

View case study ⇾

How it works

HydroForecast learns to represent hydrologic processes by identifying relationships between satellite observations, basin characteristics, meteorological forecasts, and streamflow measurements.

Our approach is distinct from purely data-driven machine learning models in that we use physical science to guide and constrain the relationships between inputs and streamflow predictions. We believe that the best model is one grounded in scientific principles and enhanced by finding deep connections in the relationships between data.

HydroForecast’s Core Model has been trained on a wide range of hydrologic conditions and landscapes, and can be tuned for specific locations anywhere on Earth.