ML-Based Streamflow Prediction in the Upper Colorado River Basin Using Climate Variables Time Series Data

• Published in: Hydrology Vol. 10; no. 2; p. 29
• Main Authors: Hosseinzadeh, Pouya, Nassar, Ayman, Boubrahimi, Soukaina Filali, Hamdi, Shah Muhammad
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2023
• Subjects: Accuracy; Agricultural production; Climate change; Deep learning; Environmental aspects; Ferries; Forecasting; Groundwater; Hydrologic data; Hydrology; Long short-term memory; Machine learning; Model testing; Multivariate analysis; Neural networks; Performance evaluation; Performance prediction; Precipitation; Precipitation (Meteorology); Prediction models; Rain; Regression analysis; River basins; Rivers; Runoff; Sensitivity analysis; Stream discharge; Stream flow; Streamflow; streamflow prediction; Temperature; Time series; time series regression; upper colorado river basin; Water resources; Watersheds; United States
• DOI: 10.3390/hydrology10020029
• ISSN: 2306-5338

Streamflow prediction plays a vital role in water resources planning in order to understand the dramatic change of climatic and hydrologic variables over different time scales. In this study, we used machine learning (ML)-based prediction models, including Random Forest Regression (RFR), Long Short-Term Memory (LSTM), Seasonal Auto- Regressive Integrated Moving Average (SARIMA), and Facebook Prophet (PROPHET) to predict 24 months ahead of natural streamflow at the Lees Ferry site located at the bottom part of the Upper Colorado River Basin (UCRB) of the US. Firstly, we used only historic streamflow data to predict 24 months ahead. Secondly, we considered meteorological components such as temperature and precipitation as additional features. We tested the models on a monthly test dataset spanning 6 years, where 24-month predictions were repeated 50 times to ensure the consistency of the results. Moreover, we performed a sensitivity analysis to identify our best-performing model. Later, we analyzed the effects of considering different span window sizes on the quality of predictions made by our best model. Finally, we applied our best-performing model, RFR, on two more rivers in different states in the UCRB to test the model’s generalizability. We evaluated the performance of the predictive models using multiple evaluation measures. The predictions in multivariate time-series models were found to be more accurate, with RMSE less than 0.84 mm per month, R-squared more than 0.8, and MAPE less than 0.25. Therefore, we conclude that the temperature and precipitation of the UCRB increases the accuracy of the predictions. Ultimately, we found that multivariate RFR performs the best among four models and is generalizable to other rivers in the UCRB.