Woodson Lees Ferry WY flow forecast: Difference between revisions
Created page with "This streamflow forecast uses a machine learning (random forest) model trained on [https://www.usbr.gov/lc/region/g4000/NaturalFlow/LFnatFlow1906-2023.2023.8.17.xlsx Reclamati..." |
No edit summary |
||
| Line 1: | Line 1: | ||
This streamflow forecast uses a machine learning (random forest) model trained on [https://www.usbr.gov/lc/region/g4000/NaturalFlow/LFnatFlow1906-2023.2023.8.17.xlsx Reclamation annual natural flow for the Colorado River at Lees Ferry, AZ] for water years 1921-2023 as the predictand | This experimental streamflow forecast uses a machine learning (random forest) model trained on [https://www.usbr.gov/lc/region/g4000/NaturalFlow/LFnatFlow1906-2023.2023.8.17.xlsx Reclamation annual natural flow for the Colorado River at Lees Ferry, AZ] for water years 1921-2023 as the predictand. The predictors include: | ||
*[https://www.ncei.noaa.gov/pub/data/cmb/ersst/v5/index/ersst.v5.pdo.dat Pacific Decadal Oscillation] (PDO) index, July-August-September average preceding the water year being forecast | |||
*[https://www1.ncdc.noaa.gov/pub/data/cmb/ersst/v5/index/ersst.v5.amo.dat Atlantic Multidecadal Oscillation (AMO) index, July-August-September average preceding the water year being forecast | |||
*[https://www.cesm.ucar.edu/community-projects/lens/data-sets) Community Earth System Model - Large Ensemble (CESM-LE) forecasts of precipitation and minimum temperature, October through September average coinciding with the water year being forecast | |||
For example, for the 2024 water year forecast (October 2023 - September 2024 total natural flow), PDO and AMO predictors are July 2023 through September 2023 monthly averages, and the CESM-LE precipitation and temperature predictors are October 2023 through September 2024 monthly averages. The random forest forecast is a 600-member ensemble. | |||
The second plot below shows the 'variable importance' for each predictor over the 1921-2023 training period; each variable does add value (this is how the variables were selected), and AMO and PDO have the highest importance. | The second plot below shows the 'variable importance' for each predictor over the 1921-2023 training period; each variable does add value (this is how the variables were selected), and AMO and PDO have the highest importance. | ||
Revision as of 11:25, 27 November 2023
This experimental streamflow forecast uses a machine learning (random forest) model trained on Reclamation annual natural flow for the Colorado River at Lees Ferry, AZ for water years 1921-2023 as the predictand. The predictors include:
- Pacific Decadal Oscillation (PDO) index, July-August-September average preceding the water year being forecast
- [https://www1.ncdc.noaa.gov/pub/data/cmb/ersst/v5/index/ersst.v5.amo.dat Atlantic Multidecadal Oscillation (AMO) index, July-August-September average preceding the water year being forecast
- [https://www.cesm.ucar.edu/community-projects/lens/data-sets) Community Earth System Model - Large Ensemble (CESM-LE) forecasts of precipitation and minimum temperature, October through September average coinciding with the water year being forecast
For example, for the 2024 water year forecast (October 2023 - September 2024 total natural flow), PDO and AMO predictors are July 2023 through September 2023 monthly averages, and the CESM-LE precipitation and temperature predictors are October 2023 through September 2024 monthly averages. The random forest forecast is a 600-member ensemble.
The second plot below shows the 'variable importance' for each predictor over the 1921-2023 training period; each variable does add value (this is how the variables were selected), and AMO and PDO have the highest importance.