Woodson Lees Ferry WY flow forecast: Difference between revisions

Revision as of 11:37, 27 November 2023

Overview

This experimental streamflow forecast procedure was developed by David Woodson as a part of his PhD research at the University of Colorado Boulder. He now produces the forecast as a side project. The 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, and the following predictors:

Pacific Decadal Oscillation (PDO) index, July-August-September average preceding the water year being forecast
Atlantic Multidecadal Oscillation (AMO) index, July-August-September average preceding the water year being forecast
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.

WY 2024 Forecast

Figure 1 shows the streamflow forecast for Water Year 2024, in green, compared to the historical streamflows, 1921-2023, on which the model is calibrated (black line). The uncertainty in the forecasted 2024 streamflow (i.e., the distribution of the 600 model ensemble member) is depicted in two ways: The green boxplot shows the extent of the interquartile range (25th-75th percentiles) and the median or most-probable forecast (50th percentile), which is 10.8 maf. The green semi-violin density plot shows that the forecast has a bimodal distribution with many members clustered around 7 maf, indicating potential for a very dry year and a smaller second mode around 18 maf, indicating there is some potential for another wet year.

Figure 2 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.

@@ Line 1: / Line 1: @@
-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:
+===Overview===
+This experimental streamflow forecast procedure was developed by David Woodson as a part of his PhD research at the University of Colorado Boulder. He now produces the forecast as a side project. The 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, and the following predictors:
 *[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
@@ Line 5: / Line 7: @@
 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.
+===WY 2024 Forecast===
+Figure 1 shows the streamflow forecast for Water Year 2024, in green, compared to the historical streamflows, 1921-2023, on which the model is calibrated (black line). The uncertainty in the forecasted 2024 streamflow (i.e., the distribution of the 600 model ensemble member) is depicted in two ways: The green boxplot shows the extent of the interquartile range (25th-75th percentiles) and the median or most-probable forecast (50th percentile), which is 10.8 maf. The green semi-violin density plot shows that the forecast has a bimodal distribution with many members clustered around 7 maf, indicating potential for a very dry year and a smaller second mode around 18 maf, indicating there is some potential for another wet year.
+Figure 2 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.