University of Washington

Loss and Salvage Predictor

For model details and calibration methods see Tillotson et al. (2022).

Tillotson MD, Hassrick J, Collins AL, Corey P. 2022. Machine Learning Forecasts to Reduce Risk of Entrainment Loss of Endangered Salmonids at Large-Scale Water Diversions in the Sacramento-San Joaquin Delta, California. San Francisco Estuary and Watershed Science. https://doi.org/10.15447/sfews.2022v20iss2art3

Select Week Date

Unavailable dates silently adjusted.
Select Graphic Scaling

Set Annual Limits
Select Calibration
Loss for both species

Steelhead salvage & sum limits

Loss and Salvage Predictor Online Tool

This tool provides a graphical interface to a predictive model of loss and/or salvage of endangered steelhead and Winter Chinook salmon at the CVP and SWP pumping facilities at the southern end of the Sacramento-San Joaquin Delta.

Realtime forecast of Loss and Salvage are depicted over the water year, which begins October 1. The season is typically from December to mid-June. Weekly averaged environmental conditions and the prior week's observed loss/salvage are used to make a prediction of loss/salvage for the week. In addition, the following week's loss/salvage is made with the current week's loss/salvage and the following week's environmental conditions.

  1. The "Most Recent" run which uses current environmental conditions for the current week's forecast of loss/salvage and projects those conditions one week into the future for the next week's forecast of loss. The user can then adjust the conditions for a scenario modelling forecast.
  2. An historical run which depicts observed environmental conditions and observed loss/salvage.
  3. An hindcast of an historical year that was not included in the selected calibration data set. E.g., water year 2007 is "predicted" if using the 2009-2020 calibration data, and both the hindcast and the observation are depicted.

The User must select from the input areas:

  1. Current or historical forecast.
  2. Plot scaling according to the historical timing or the pre-set annual limits.
  3. (optional) Annual Loss/Salvage Limits which vary across species and years.
  4. Calibration set. Because management practices have varied over the years, older data may not reflect modern operations. Default: 2009-2020 Loss calibration for Winter Chinook and steelhead. Additionally, although loss is always computed for Winter Chinook, the user may select the legacy management target: "salvage" for steelhead.

Click "Run" or "Reset"

Environmental variables used for prediction include weekly averages of Old and Middle River flow (OMR), combined CVP and SWP exports, San Joaquin River flow at Vernalis, Sacramento River flow at Freeport, 5-day cumulative rainfall (inches) over the delta area, the water temperature at Mallard Island and the Delta Cross Channel gate status.

Graphics include: Observations for the current water year (small circles). The forecast window (green triangle) with high, median and low projections (short lines). The historical accumulated take (grey line) and 95% confidence bounds on the observed cumulative fraction of the total for the week (grey area).

Data Sources

Data sources for data used in Predictions