Enhancing Monthly Streamflow Prediction Using Meteorological Factors and Machine Learning Models in the Upper Colorado River Basin

Aug 5, 2026

Upload by Ivy

Streamflow prediction is essential for planning future developments and safety measures along river basins, especially under climate change pressures. This study forecasts monthly streamflow at Lees Ferry in the Upper Colorado River Basin by combining 30 years of monthly streamflow observations with meteorological drivers including snow water equivalent, temperature, and precipitation. Four machine learning approaches are trained and compared across historical-only and combined-feature settings, including sequence window analyses.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages62

Reading Time2 h 36 min

AccessFree to download

Abstract

Data and Study Design

Machine Learning Models and Feature Experiments

Evaluation and Results

Generalizability Tests

Utah State University DigitalCommons@USU | All Graduate Theses and Dissertations, Fall
2023 to Present | Graduate Studies | | --- | --- | | 8-2024
Enhancing Monthly Streamflow Prediction Using Meteorological Factors and Machine Learning Models in the Upper Colorado River Basin
Saichand Thota Utah State University
Follow this and additional works at: [https://digitalcommons.usu.edu/etd2023](https://digitalcommons.usu.edu/etd2023)
Part of the Computer Sciences Commons, Natural Resources and Conservation Commons, and the Water Resource Management Commons | | Recommended Citation Thota, Saichand, "Enhancing Monthly Streamflow Prediction Using Meteorological Factors and Machine Learning Models in the Upper Colorado River Basin" (2024) . All Graduate Theses and Dissertations, Fall 2023 to Present. 239. [https://digitalcommons.usu.edu/etd2023/239](https://digitalcommons.usu.edu/etd2023/239) This Thesis is brought to you for free and open access by the Graduate Studies at DigitalCommons@USU. It has been accepted for inclusion in All Graduate Theses and Dissertations, Fall 2023 to Present by an authorized administrator of DigitalCommons@USU. For more information, please [contact](contact digitalcommons@usu.edu)[ digitalcommons@usu.edu](contact digitalcommons@usu.edu). ENHANCING MONTHLY STREAMFLOW PREDICTION USING METEOROLOGICAL FACTORS AND MACHINE LEARNING MODELS IN THE UPPER COLORADO RIVER BASIN by Saichand Thota A thesis submitted in partial fulfillment of the requirements for the degree of MASTER OF SCIENCE in Computer Science Approved: Hamid Karimi, Ph.D. D. Richard Cutler, Ph.D. Committee Member Vice Provost of Graduate Studies UTAH STATE UNIVERSITY Logan, Utah ii Copyright © Saichand Thota 2024 All Rights Reserved iii ABSTRACT Enhancing Monthly Streamflow Prediction Using Meteorological Factors and Machine Learning Models in the Upper Colorado River Basin by Saichand Thota, Master of Science Utah State University, 2024 Major Professor: Soukaina Filali Boubrahimi, Ph.D. Department: Computer Science Streamflow prediction is crucial for planning future developments and safety measures along river basins, especially with climate change challenges. In this study, we utilized monthly streamflow data from the United States Bureau of Reclamation and meteorological data (snow water equivalent, temperature, and precipitation) from the various weather monitoring stations of the Snow Telemetry Network within the Upper Colorado River Basin to forecast monthly streamflow at Lees Ferry, a specific location along the Colorado River in the basin. Four machine learning models—Random Forest Regression, Long short-term memory, Gated Recurrent Unit, and Seasonal Auto-Regressive Integrated Moving Average— were trained using 30 years of monthly data (1991-2020), split into 80% for training (1991-2014) and 20% for testing (2015-2020) . Initially, only historical streamflow data were used for predictions, followed by including meteorological factors to assess their impact on streamflow. Subsequently, sequence analysis was conducted to explore various inputoutput sequence window combinations. We then evaluated the influence of each factor on streamflow by testing all possible combinations to identify the optimal feature combination for prediction. Our results indicate that the Random Forest Regression model consistently outperformed others, especially after integrating all meteorological factors with historical iv streamflow data. The best performance was achieved with a 24-month look-back period to predict 12 months of streamflow, yielding a Root Mean Square Error of 2.25 and R-squared (R2 ) of 0 .80. Finally, to assess model generalizability, we tested the best model at other locations-Greenwood Springs (Colorado River), Maybell (Yampa River), and Archuleta (San Juan) in the basin. (61 pages) v PUBLIC ABSTRACT Enhancing Monthly Streamflow Prediction Using Meteor

FAQs

What location and target variable does the thesis focus on for streamflow prediction?

The study forecasts monthly streamflow at Lees Ferry, using Lees Ferry streamflow as the target variable.

Which meteorological factors are used as inputs alongside historical streamflow?

Meteorological inputs include snow water equivalent, temperature, and precipitation derived from weather monitoring stations in the Snow Telemetry Network.

Which model performed best and under what input window setting?

Random Forest Regression performed best, achieving the top results with a 24-month look-back period to predict 12 months of streamflow (RMSE 2.25, R-squared 0.80).

How was the model’s generalizability evaluated in the thesis?

The best model was tested at additional locations within the basin: Greenwood Springs (Colorado River), Maybell (Yampa River), and Archuleta (San Juan).

Aug 5, 2026

Upload by Ivy