Rainfall-runoff modeling and streamflow prediction using deep learning algorithms have been studied significantly in the last few years. The majority of these studies focus on the simulation and testing of historical datasets. Deployment and operation of a real-time streamflow forecast model using deep learning will face additional data and computational challenges such as inaccurate rainfall forecast data and real-time data assimilation with limited studies guiding on these difficulties. We proposed a real-time streamflow forecast framework that includes pre-event model training using deep learning, real-time data acquisition, and post-event analysis. We implemented the framework for 124 USGS gauged watersheds across Iowa to forecast 120-hour streamflow rates since April 2021. This is the first time deep learning models have been used to predict streamflow in real-time operational settings at a large scale, and we anticipate seeing more real-time implementations of deep learning models in the future.
In this project, we proposed a framework for real-time operational streamflow forecasting using deep learning algorithms as shown in Figure 1. We also implemented the framework with the deep learning models in April 2021 in the state of Iowa. In this study, we evaluated the framework using forecast results from April to September 2021. Model performance comparison and post-event analysis are also presented as part of the analysis. Sample results with the evaluations are shown in Figure 2.
Related Articles
- Xiang, Z. and Demir, I., 2022. Real-Time Streamflow Forecasting Framework, Implementation and Post-Analysis Using Deep Learning. EarthArXiv. (DOI: https://doi.org/10.31223/X5BW6R)
The real-time forecasting framework with deep learning models including three phases as pre-event training operations (in blue), real-time forecasting operations (in red), and post-event analysis operations (in green)
Two sample watershed streamflow forecast model results at the lead time of 18 hours from April 1, 2021 to Sep 30, 2021.
