Woodson Lees Ferry WY flow forecast - Revision history

JeffreyJLukas at 16:24, 10 December 2025

2025-12-10T16:24:38Z

← Older revision		Revision as of 12:24, 10 December 2025
Line 2:		Line 2:
	[[File:WY2026.Forecast.png\|thumb\|600px\|Figure 1a. Random forest model forecast of Water Year 2026 naturalized streamflow for the Colorado River at Lees Ferry, AZ. (Source: David Woodson)]]		[[File:WY2026.Forecast.png\|thumb\|600px\|Figure 1a. Random forest model forecast of Water Year 2026 naturalized streamflow for the Colorado River at Lees Ferry, AZ. (Source: David Woodson)]]

	[[File:WY2026.variableImportance.png\|thumb\|600px\|Figure 1b. Two measures of the 'variable importance' (added value) of the four predictors in the random forest forecast model of WY ~~2025~~ streamflow shown in Figure 1. (Source: David Woodson)]]		[[File:WY2026.variableImportance.png\|thumb\|600px\|Figure 1b. Two measures of the 'variable importance' (added value) of the four predictors in the random forest forecast model of WY 2026 streamflow shown in Figure 1. (Source: David Woodson)]]

	This experimental streamflow forecast procedure ('randomWoods') 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/LFnatFlow1906-2024.2024.9.12.xlsx Reclamation annual natural flow for the Colorado River at Lees Ferry, AZ] for water years 1921 through the most recent year as the predictand, and the following predictors:		This experimental streamflow forecast procedure ('randomWoods') 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/LFnatFlow1906-2024.2024.9.12.xlsx Reclamation annual natural flow for the Colorado River at Lees Ferry, AZ] for water years 1921 through the most recent year as the predictand, and the following predictors:

JeffreyJLukas: /* WY 2024 forecast and validation */

2025-11-10T23:06:50Z

WY 2024 forecast and validation

← Older revision		Revision as of 19:06, 10 November 2025
Line 29:		Line 29:
	Figure 2b shows the 'variable importance' for each predictor over the 1921-2024 training period; each variable does add value to the forecast, and AMO has the highest importance.		Figure 2b shows the 'variable importance' for each predictor over the 1921-2024 training period; each variable does add value to the forecast, and AMO has the highest importance.

	===WY 2024 forecast and ~~validation~~===		===WY 2024 forecast and verification===

	[[File:Woodson_WY2024_Forecast.png\|thumb\|600px\|Figure 3a. Random forest model forecast of Water Year 2024 naturalized streamflow for the Colorado River at Lees Ferry, AZ. (Source: David Woodson)]]		[[File:Woodson_WY2024_Forecast.png\|thumb\|600px\|Figure 3a. Random forest model forecast of Water Year 2024 naturalized streamflow for the Colorado River at Lees Ferry, AZ. (Source: David Woodson)]]

JeffreyJLukas: /* WY 2025 forecast and validation */

2025-11-10T23:06:37Z

WY 2025 forecast and validation

← Older revision		Revision as of 19:06, 10 November 2025
Line 17:		Line 17:
	Figure 2b shows the 'variable importance' for each predictor over the 1921-2025 training period; each variable does add value to the forecast, and AMO has the highest importance.		Figure 2b shows the 'variable importance' for each predictor over the 1921-2025 training period; each variable does add value to the forecast, and AMO has the highest importance.

	===WY 2025 forecast and ~~validation~~===		===WY 2025 forecast and verification===

	[[File:WY2025.Forecast.png\|thumb\|600px\|Figure 2a. Random forest model forecast of Water Year 2025 naturalized streamflow for the Colorado River at Lees Ferry, AZ. (Source: David Woodson)]]		[[File:WY2025.Forecast.png\|thumb\|600px\|Figure 2a. Random forest model forecast of Water Year 2025 naturalized streamflow for the Colorado River at Lees Ferry, AZ. (Source: David Woodson)]]

JeffreyJLukas: /* WY 2026 Forecast */

2025-11-10T23:02:45Z

WY 2026 Forecast

← Older revision		Revision as of 19:02, 10 November 2025
Line 11:		Line 11:
	For example, for the Water Year 2026 forecast (October 2025 - September 2026 total natural flow), the PDO and AMO predictors are the July 2025 through September 2025 averages, and the CESM-LE precipitation and temperature predictors are the forecasted October 2025 through September 2026 averages. The random forest forecast is a 600-member ensemble.		For example, for the Water Year 2026 forecast (October 2025 - September 2026 total natural flow), the PDO and AMO predictors are the July 2025 through September 2025 averages, and the CESM-LE precipitation and temperature predictors are the forecasted October 2025 through September 2026 averages. The random forest forecast is a 600-member ensemble.

	===WY 2026 ~~Forecast~~===		===WY 2026 forecast===

	Figure 2a shows the naturalized streamflow forecast for Water Year 2026, in green, compared to the historical streamflows, 1921-2025, on which the model is calibrated (black line). The uncertainty in the forecasted 2025 streamflow (i.e., the distribution of the 600 model ensemble members) 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 9.1 maf. The green semi-violin density plot shows that the main bulk of ensemble members are narrowly distributed around a peak at 8.0 maf. The long, skinny tail extending to 20 maf indicates that while a wet year is not precluded by the model, it is seen as a much less probable outcome than a dry year.		Figure 2a shows the naturalized streamflow forecast for Water Year 2026, in green, compared to the historical streamflows, 1921-2025, on which the model is calibrated (black line). The uncertainty in the forecasted 2025 streamflow (i.e., the distribution of the 600 model ensemble members) 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 9.1 maf. The green semi-violin density plot shows that the main bulk of ensemble members are narrowly distributed around a peak at 8.0 maf. The long, skinny tail extending to 20 maf indicates that while a wet year is not precluded by the model, it is seen as a much less probable outcome than a dry year.

JeffreyJLukas: /* Overview */

2025-11-10T22:35:00Z

Overview

← Older revision		Revision as of 18:35, 10 November 2025
Line 3:		Line 3:

	[[File:WY2026.variableImportance.png\|thumb\|600px\|Figure 1b. Two measures of the 'variable importance' (added value) of the four predictors in the random forest forecast model of WY 2025 streamflow shown in Figure 1. (Source: David Woodson)]]		[[File:WY2026.variableImportance.png\|thumb\|600px\|Figure 1b. Two measures of the 'variable importance' (added value) of the four predictors in the random forest forecast model of WY 2025 streamflow shown in Figure 1. (Source: David Woodson)]]


	This experimental streamflow forecast procedure ('randomWoods') 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/LFnatFlow1906-2024.2024.9.12.xlsx Reclamation annual natural flow for the Colorado River at Lees Ferry, AZ] for water years 1921 through the most recent year as the predictand, and the following predictors:		This experimental streamflow forecast procedure ('randomWoods') 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/LFnatFlow1906-2024.2024.9.12.xlsx Reclamation annual natural flow for the Colorado River at Lees Ferry, AZ] for water years 1921 through the most recent year as the predictand, and the following predictors:

JeffreyJLukas: /* WY 2026 Forecast */

2025-11-10T22:34:51Z

WY 2026 Forecast

← Older revision		Revision as of 18:34, 10 November 2025
Line 14:		Line 14:
	===WY 2026 Forecast===		===WY 2026 Forecast===

	Figure 2a shows the naturalized streamflow forecast for Water Year 2026, in green, compared to the historical streamflows, 1921-2025, on which the model is calibrated (black line). The uncertainty in the forecasted 2025 streamflow (i.e., the distribution of the 600 model ensemble members) 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 9.1 maf. The green semi-violin density plot shows that the main bulk of ensemble members are narrowly distributed around a peak at 8.0 maf. The long, skinny tail extending to 20 maf indicates that while a wet year is not precluded by the model, it is seen as a much less probable outcome.		Figure 2a shows the naturalized streamflow forecast for Water Year 2026, in green, compared to the historical streamflows, 1921-2025, on which the model is calibrated (black line). The uncertainty in the forecasted 2025 streamflow (i.e., the distribution of the 600 model ensemble members) 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 9.1 maf. The green semi-violin density plot shows that the main bulk of ensemble members are narrowly distributed around a peak at 8.0 maf. The long, skinny tail extending to 20 maf indicates that while a wet year is not precluded by the model, it is seen as a much less probable outcome than a dry year.

	Figure 2b shows the 'variable importance' for each predictor over the 1921-2025 training period; each variable does add value to the forecast, and AMO has the highest importance.		Figure 2b shows the 'variable importance' for each predictor over the 1921-2025 training period; each variable does add value to the forecast, and AMO has the highest importance.

JeffreyJLukas: /* WY 2025 Forecast and validation */

2025-11-10T22:34:05Z

WY 2025 Forecast and validation

← Older revision		Revision as of 18:34, 10 November 2025
Line 18:		Line 18:
	Figure 2b shows the 'variable importance' for each predictor over the 1921-2025 training period; each variable does add value to the forecast, and AMO has the highest importance.		Figure 2b shows the 'variable importance' for each predictor over the 1921-2025 training period; each variable does add value to the forecast, and AMO has the highest importance.

	===WY 2025 ~~Forecast~~ and validation===		===WY 2025 forecast and validation===

	[[File:WY2025.Forecast.png\|thumb\|600px\|Figure 2a. Random forest model forecast of Water Year 2025 naturalized streamflow for the Colorado River at Lees Ferry, AZ. (Source: David Woodson)]]		[[File:WY2025.Forecast.png\|thumb\|600px\|Figure 2a. Random forest model forecast of Water Year 2025 naturalized streamflow for the Colorado River at Lees Ferry, AZ. (Source: David Woodson)]]
Line 26:		Line 26:
	Figure 2a shows the naturalized streamflow forecast for Water Year 2025, in green, compared to the historical streamflows, 1921-2024, on which the model is calibrated (black line). The uncertainty in the forecasted 2025 streamflow (i.e., the distribution of the 600 model ensemble members) 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 10.2 maf. The green semi-violin density plot shows that within the main bulk of ensemble members below 12.5 maf, there is a peak around 9.0 maf, and a smaller peak around 11.5 maf. The long tail extending to 20 maf indicates there is some potential for a wet year, though less so than for the FY2024 forecast.		Figure 2a shows the naturalized streamflow forecast for Water Year 2025, in green, compared to the historical streamflows, 1921-2024, on which the model is calibrated (black line). The uncertainty in the forecasted 2025 streamflow (i.e., the distribution of the 600 model ensemble members) 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 10.2 maf. The green semi-violin density plot shows that within the main bulk of ensemble members below 12.5 maf, there is a peak around 9.0 maf, and a smaller peak around 11.5 maf. The long tail extending to 20 maf indicates there is some potential for a wet year, though less so than for the FY2024 forecast.

	The observed naturalized Lees Ferry streamflow for WY2025 ended up at 8.5 maf, or slightly below the 25th percentile ~~of the~~ forecast.		The observed naturalized Lees Ferry streamflow for WY2025 ended up at 8.5 maf, so slightly below the 25th percentile forecast.

	Figure 2b shows the 'variable importance' for each predictor over the 1921-2024 training period; each variable does add value to the forecast, and AMO has the highest importance.		Figure 2b shows the 'variable importance' for each predictor over the 1921-2024 training period; each variable does add value to the forecast, and AMO has the highest importance.

JeffreyJLukas: /* WY 2024 Forecast */

2025-11-10T22:33:36Z

WY 2024 Forecast

← Older revision		Revision as of 18:33, 10 November 2025
Line 30:		Line 30:
	Figure 2b shows the 'variable importance' for each predictor over the 1921-2024 training period; each variable does add value to the forecast, and AMO has the highest importance.		Figure 2b shows the 'variable importance' for each predictor over the 1921-2024 training period; each variable does add value to the forecast, and AMO has the highest importance.

	===WY 2024 ~~Forecast~~===		===WY 2024 forecast and validation===

	[[File:Woodson_WY2024_Forecast.png\|thumb\|600px\|Figure 3a. Random forest model forecast of Water Year 2024 naturalized streamflow for the Colorado River at Lees Ferry, AZ. (Source: David Woodson)]]		[[File:Woodson_WY2024_Forecast.png\|thumb\|600px\|Figure 3a. Random forest model forecast of Water Year 2024 naturalized streamflow for the Colorado River at Lees Ferry, AZ. (Source: David Woodson)]]

JeffreyJLukas: /* WY 2024 Forecast */

2025-11-10T22:33:20Z

WY 2024 Forecast

← Older revision		Revision as of 18:33, 10 November 2025
Line 38:		Line 38:
	Figure 3a shows the naturalized 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 like WY2023.		Figure 3a shows the naturalized 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 like WY2023.

	The observed naturalized Lees Ferry streamflow for WY2024 ended up at 12.1 maf, ~~or slightly below~~ the ~~25th~~ percentile ~~of the~~ forecast.		The observed naturalized Lees Ferry streamflow for WY2024 ended up at 12.1 maf, so somewhat above the 50th percentile forecast.

	Figure 3b shows the 'variable importance' for each predictor over the 1921-2023 training period; each variable does add value to the forecast, and AMO and PDO have the highest importance.		Figure 3b shows the 'variable importance' for each predictor over the 1921-2023 training period; each variable does add value to the forecast, and AMO and PDO have the highest importance.

JeffreyJLukas: /* WY 2024 Forecast */

2025-11-10T22:32:00Z

WY 2024 Forecast

← Older revision		Revision as of 18:32, 10 November 2025
Line 37:		Line 37:

	Figure 3a shows the naturalized 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 like WY2023.		Figure 3a shows the naturalized 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 like WY2023.

			The observed naturalized Lees Ferry streamflow for WY2024 ended up at 12.1 maf, or slightly below the 25th percentile of the forecast.

	Figure 3b shows the 'variable importance' for each predictor over the 1921-2023 training period; each variable does add value to the forecast, and AMO and PDO have the highest importance.		Figure 3b shows the 'variable importance' for each predictor over the 1921-2023 training period; each variable does add value to the forecast, and AMO and PDO have the highest importance.