Advancing Machine Learning-Based Streamflow Prediction Through Event Greedy Selection, Asymmetric Loss Function, and Rainfall Forecasting Uncertainty

Authors:
Open Access
Publisher website
Google Scholar
Abstract
This paper advances machine learning (ML)-based streamflow prediction by strategically selecting rainfall events, introducing a new loss function, and addressing rainfall forecast uncertainties. Focusing on the Iowa River Basin, we applied the stochastic storm transposition (SST) method to create realistic rainfall events, which were input into a hydrological model to generate corresponding streamflow data for training and testing deterministic and probabilistic ML models. Long short-term memory (LSTM) networks were employed to predict streamflow up to 12 h ahead. An active learning approach was used to identify the most informative rainfall events, reducing data generation effort. Additionally, we introduced a novel asymmetric peak loss function to improve peak streamflow prediction accuracy. Incorporating rainfall forecast uncertainties, our probabilistic LSTM model provided uncertainty quantification for streamflow predictions. Performance evaluation using different metrics improved the accuracy and reliability of our models. These contributions enhance flood forecasting and decision-making while significantly reducing computational time and costs.
Funding Information
  • National Science Foundation (2226936)
  • US Department of Education (ED#P116S210005)

This publication has 46 references indexed in Scilit: