Case Study

Trinity River

Spring freshet
  • Location: Coffee Creek, CA, USA
  • Dates: Mar 16, 2019 to Jun 15, 2019
  • Observed Flows: 700 to 5150 cfs


HydroForecast’s theory-guided machine learning approach allows it to accumulate and store SWE volumes and translate them into runoff at the right time and volume more accurately than traditional approaches. 

Forecasted flows 24 hours ahead (in cubic feet per second)

Event Description

The hydrologically diverse Trinity River is born in the mountainous, snow-capped Trinity “Alps” region where flows rush through canyons amid steep hillslopes. The river continues downstream to mid-elevations, picks up Coffee Creek, and flows into Trinity Lake and Dam. The lower subwatersheds below the dam are distinct from the headwaters and are characterized by wide, agricultural valleys rich in minerals. The Trinity is the largest tributary into the Klamath River system, though before it reaches the confluence a significant volume is diverted via the Central Valley Project that transfers significant volume into the Sacramento River.

The forecast point for the Rodeo is in the upper Trinity River before it meets Coffee Creek, marked by the USGS 11523200 streamflow gauge. This part of the Trinity River forms the main stem into Trinity Lake, and is the second greatest flow contributor to the Central Valley Project.

Forecasted flows 120 hours ahead  (in cubic feet per second)

The spring snowmelt season is the most active and most important for establishing the baselines for the many uses of the Trinity river system. The evaluation statistics suggest that the model understands hydrologic behavior in the upper Trinity basin by tracking frozen precipitation as SWE, maintaining the basin’s states accurately, and producing runoff in the right timing and volume as the freshet occurs. HydroForecast’s incorporation of earth observation satellite imagery allows it to ingest and update conditions across the basin in near-real time and to translate those conditions into inflow forecasts.