ML-Based Streamflow Prediction in the Upper Colorado River Basin Using Climate Variables Time Series Data
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-...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-01-01
|
Series: | Hydrology |
Subjects: | |
Online Access: | https://www.mdpi.com/2306-5338/10/2/29 |
_version_ | 1797620694725427200 |
---|---|
author | Pouya Hosseinzadeh Ayman Nassar Soukaina Filali Boubrahimi Shah Muhammad Hamdi |
author_facet | Pouya Hosseinzadeh Ayman Nassar Soukaina Filali Boubrahimi Shah Muhammad Hamdi |
author_sort | Pouya Hosseinzadeh |
collection | DOAJ |
description | 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. |
first_indexed | 2024-03-11T08:45:20Z |
format | Article |
id | doaj.art-c53810b21af24c11af50e59fa2995d9e |
institution | Directory Open Access Journal |
issn | 2306-5338 |
language | English |
last_indexed | 2024-03-11T08:45:20Z |
publishDate | 2023-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Hydrology |
spelling | doaj.art-c53810b21af24c11af50e59fa2995d9e2023-11-16T20:51:32ZengMDPI AGHydrology2306-53382023-01-011022910.3390/hydrology10020029ML-Based Streamflow Prediction in the Upper Colorado River Basin Using Climate Variables Time Series DataPouya Hosseinzadeh0Ayman Nassar1Soukaina Filali Boubrahimi2Shah Muhammad Hamdi3Department of Computer Science, Utah State University, Logan, UT 84322, USADepartment of Civil and Environmental Engineering, Utah State University, Logan, UT 84322, USADepartment of Computer Science, Utah State University, Logan, UT 84322, USADepartment of Computer Science, Utah State University, Logan, UT 84322, USAStreamflow 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.https://www.mdpi.com/2306-5338/10/2/29streamflow predictionmachine learningtime series regressionupper colorado river basin |
spellingShingle | Pouya Hosseinzadeh Ayman Nassar Soukaina Filali Boubrahimi Shah Muhammad Hamdi ML-Based Streamflow Prediction in the Upper Colorado River Basin Using Climate Variables Time Series Data Hydrology streamflow prediction machine learning time series regression upper colorado river basin |
title | ML-Based Streamflow Prediction in the Upper Colorado River Basin Using Climate Variables Time Series Data |
title_full | ML-Based Streamflow Prediction in the Upper Colorado River Basin Using Climate Variables Time Series Data |
title_fullStr | ML-Based Streamflow Prediction in the Upper Colorado River Basin Using Climate Variables Time Series Data |
title_full_unstemmed | ML-Based Streamflow Prediction in the Upper Colorado River Basin Using Climate Variables Time Series Data |
title_short | ML-Based Streamflow Prediction in the Upper Colorado River Basin Using Climate Variables Time Series Data |
title_sort | ml based streamflow prediction in the upper colorado river basin using climate variables time series data |
topic | streamflow prediction machine learning time series regression upper colorado river basin |
url | https://www.mdpi.com/2306-5338/10/2/29 |
work_keys_str_mv | AT pouyahosseinzadeh mlbasedstreamflowpredictionintheuppercoloradoriverbasinusingclimatevariablestimeseriesdata AT aymannassar mlbasedstreamflowpredictionintheuppercoloradoriverbasinusingclimatevariablestimeseriesdata AT soukainafilaliboubrahimi mlbasedstreamflowpredictionintheuppercoloradoriverbasinusingclimatevariablestimeseriesdata AT shahmuhammadhamdi mlbasedstreamflowpredictionintheuppercoloradoriverbasinusingclimatevariablestimeseriesdata |