DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Near-Real-Time Statistical Analysis and Visualization of Streamflow from a Deep-Learning Rainfall-Runoff Model

Journal Article · · Water Resources Management
 [1];  [2];  [3]
  1. Thuyloi University, Hanoi (Vietnam)
  2. University of Michigan, Ann Arbor, MI (United States); Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
  3. Helmholtz Centre for Environmental Research, Leipzig (Germany)

Near-real-time (NRT) streamflow data are critical importance for timely water resources management. Here, we developed an open-source tool, FlowStats, for NRT streamflow analysis and visualization in Germany, based on NRT meteorological data from the German Weather Service and simulated streamflow from a long short-term memory neural network (LSTM). The LSTM model achieved very good overall performance, median NSE of 0.80 for the test period across 1,479 catchments. FlowStats provides options for deriving various streamflow statistics, from normal and abnormal streamflow detection to drought and flood analyses. An example analysis from FlowStats revealed widespread below-normal to extreme low-flow conditions across Germany from March to May 2025, which weakened from June to September 2025. Drought analysis for September 2025 highlighted severe to extreme drought conditions in northwestern Germany, while flood classifications indicated that high-flow events occurred in southwestern Germany. FlowStats can be used for various hydrological assessments to support water resources management.

Research Organization:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Organization:
USDOE
Grant/Contract Number:
AC05-00OR22725
OSTI ID:
3030313
Journal Information:
Water Resources Management, Journal Name: Water Resources Management Journal Issue: 5 Vol. 40; ISSN 1573-1650; ISSN 0920-4741
Publisher:
SpringerCopyright Statement
Country of Publication:
United States
Language:
English

References (23)

A Global Assessment of Climate Change and Anthropogenic Effects on Changes in Streamflow journal March 2026
River flow forecasting through conceptual models part I — A discussion of principles journal April 1970
HydroEcoLSTM: A Python package with graphical user interface for hydro-ecological modeling with long short-term memory neural network journal March 2025
An overview of visualization and visual analytics applications in water resources management journal July 2022
Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling journal October 2009
Changes in streamflow statistical structure across the United States due to recent climate change journal May 2023
A review of hybrid deep learning applications for streamflow forecasting journal October 2023
The 2018–2020 Multi‐Year Drought Sets a New Benchmark in Europe journal March 2022
Global Warming Has Accelerated Significantly journal March 2026
Reassessing the projections of the World Water Development Report journal July 2019
Streamflow in the United States: Characteristics, trends, regime shifts, and extremes journal July 2024
CAMELSH: A Large-Sample Hourly Hydrometeorological Dataset and Attributes at Watershed-Scale for CONUS journal July 2025
Artificial intelligence for streamflow prediction in river basins: a use case in Mar Menor journal June 2025
Towards Accurate Flood Forecasting: Integrating Satellite Data, Hydrological Modeling, and Deep Learning journal November 2025
Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations journal January 2007
NeuralHydrology — A Python library for Deep Learning research in hydrology journal March 2022
Enabling Stakeholder Decision-Making With Earth Observation and Modeling Data Using Tethys Platform journal October 2019
Climate variability can outweigh the influence of climate mean changes for extreme precipitation under global warming journal February 2025
CAMELS-DE: hydro-meteorological time series and attributes for 1582 catchments in Germany journal December 2024
What made the June 2013 flood in Germany an exceptional event? A hydro-meteorological evaluation journal January 2015
The CAMELS data set: catchment attributes and meteorology for large-sample studies journal January 2017
Continuous streamflow prediction in ungauged basins: long short-term memory neural networks clearly outperform traditional hydrological models journal January 2023
HESS Opinions: Never train a Long Short-Term Memory (LSTM) network on a single basin journal September 2024