Real-time streamflow forecasting: AI vs. Hydrologic insights

Krajewski, Witold F.; Ghimire, Ganesh R.; Demir, Ibrahim; Mantilla, Ricardo

doi:10.1016/j.hydroa.2021.100110

Real-time streamflow forecasting: AI vs. Hydrologic insights

Journal Article · Tue Nov 23 00:00:00 EST 2021 · Journal of Hydrology X

DOI:https://doi.org/10.1016/j.hydroa.2021.100110· OSTI ID:1842596

Krajewski, Witold F. ^[1]; ^[2]; Demir, Ibrahim ^[1]; Mantilla, Ricardo ^[3]

Univ. of Iowa, Iowa City, IA (United States). Iowa Flood Center
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Univ. of Manitoba, Winnipeg, MB (Canada)

In this paper, we propose a set of simple benchmarks for the evaluation of data-based models for real-time streamflow forecasting, such as those developed with sophisticated Artificial Intelligence (AI) algorithms. The benchmarks are also data-based and provide context to judge incremental improvements in the performance metrics from the more complicated approaches. The benchmarks include temporal and spatial persistence, persistence corrected for baseflow and streamflow, as well as river distance weighted runoff obtained from space-time distributed rainfall. In the development of the benchmarks, we use basic hydrologic insights such as flow aggregation by the river network, scale-dependence in basin response, streamflow partitioning into quick flow and baseflow, water travel time, and rainfall averaging by the basin width function. The study uses 140 streamflow gauges in Iowa that cover a range of basin scales between 7 and 37,000 km². The data cover 17 years. This work demonstrates that the proposed benchmarks can provide good performance according to several commonly used metrics. For example, streamflow forecasting at half of the test locations across years achieves a Kling-Gupta Efficiency (KGE) score of 0.6 or higher at one-day ahead lead time, and 20% of cases reach the KGE of 0.8 or higher. The proposed benchmarks are easy to implement and should prove useful for developers of data-based as well as physics-based hydrologic models and real-time data assimilation techniques.

View Accepted Manuscript (DOE)

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 1842596

Journal Information:: Journal of Hydrology X, Journal Name: Journal of Hydrology X Journal Issue: NA Vol. 13; ISSN 2589-9155

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (51)

Flood forecasting for River Mekong with data‐based models Shahzad, Khurram M.; Plate, Erich J. Water Resources Research, Vol. 50, Issue 9 https://doi.org/10.1002/2013WR015072	journal	September 2014
L band microwave remote sensing and land data assimilation improve the representation of prestorm soil moisture conditions for hydrologic forecasting: Estimation of Prestorm Soil Moisture Crow, W. T.; Chen, F.; Reichle, R. H. Geophysical Research Letters, Vol. 44, Issue 11 https://doi.org/10.1002/2017GL073642	journal	June 2017
Deep Learning and Machine Learning in Hydrological Processes Climate Change and Earth Systems a Systematic Review Ardabili, Sina; Mosavi, Amir; Dehghani, Majid Engineering for Sustainable Future: Selected papers of the 18th International Conference on Global Research and Education Inter-Academia – 2019, p. 52-62 https://doi.org/10.1007/978-3-030-36841-8_5	book	January 2020
Evaluating Methods to Predict Streamflow at Ungauged Sites Using Regional Flow Duration Curves: A Case Study Nruthya, K.; Srinivas, V. V. Aquatic Procedia, Vol. 4 https://doi.org/10.1016/j.aqpro.2015.02.083	journal	January 2015
Towards an integrated Flood Information System: Centralized data access, analysis, and visualization Demir, Ibrahim; Krajewski, Witold F. Environmental Modelling & Software, Vol. 50 https://doi.org/10.1016/j.envsoft.2013.08.009	journal	December 2013
Distributed long-term hourly streamflow predictions using deep learning – A case study for State of Iowa Xiang, Zhongrun; Demir, Ibrahim Environmental Modelling & Software, Vol. 131 https://doi.org/10.1016/j.envsoft.2020.104761	journal	September 2020
Regression modeling of streamflow, baseflow, and runoff using geographic information systems Zhu, Yuanhong; Day, Rick L. Journal of Environmental Management, Vol. 90, Issue 2 https://doi.org/10.1016/j.jenvman.2008.02.011	journal	February 2009
Role of coupled flow dynamics and real network structures on Hortonian scaling of peak flows Mantilla, Ricardo; Gupta, Vijay K.; J. Mesa, Oscar Journal of Hydrology, Vol. 322, Issue 1-4 https://doi.org/10.1016/j.jhydrol.2005.03.022	journal	May 2006
A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series Wang, Wen-Chuan; Chau, Kwok-Wing; Cheng, Chun-Tian Journal of Hydrology, Vol. 374, Issue 3-4 https://doi.org/10.1016/j.jhydrol.2009.06.019	journal	August 2009
Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling Gupta, Hoshin V.; Kling, Harald; Yilmaz, Koray K. Journal of Hydrology, Vol. 377, Issue 1-2 https://doi.org/10.1016/j.jhydrol.2009.08.003	journal	October 2009
Estimation of annual baseflow at ungauged sites in Indiana USA Ahiablame, Laurent; Chaubey, Indrajeet; Engel, Bernard Journal of Hydrology, Vol. 476 https://doi.org/10.1016/j.jhydrol.2012.10.002	journal	January 2013
Applications of hybrid wavelet–Artificial Intelligence models in hydrology: A review Nourani, Vahid; Hosseini Baghanam, Aida; Adamowski, Jan Journal of Hydrology, Vol. 514 https://doi.org/10.1016/j.jhydrol.2014.03.057	journal	June 2014
Forecasting daily streamflow using online sequential extreme learning machines Lima, Aranildo R.; Cannon, Alex J.; Hsieh, William W. Journal of Hydrology, Vol. 537 https://doi.org/10.1016/j.jhydrol.2016.03.017	journal	June 2016
Towards baseflow index characterisation at national scale in New Zealand Singh, Shailesh Kumar; Pahlow, Markus; Booker, Doug J. Journal of Hydrology, Vol. 568 https://doi.org/10.1016/j.jhydrol.2018.11.025	journal	January 2019
Investigating the role of antecedent SMAP satellite soil moisture, radar rainfall and MODIS vegetation on runoff production in an agricultural region Jadidoleslam, Navid; Mantilla, Ricardo; Krajewski, Witold F. Journal of Hydrology, Vol. 579 https://doi.org/10.1016/j.jhydrol.2019.124210	journal	December 2019
Improvement and evaluation of the Iowa Flood Center Hillslope Link Model (HLM) by calibration-free approach Quintero, Felipe; Krajewski, Witold F.; Seo, Bong-Chul Journal of Hydrology, Vol. 584 https://doi.org/10.1016/j.jhydrol.2020.124686	journal	May 2020
Decomposition ensemble model based on variational mode decomposition and long short-term memory for streamflow forecasting Zuo, Ganggang; Luo, Jungang; Wang, Ni Journal of Hydrology, Vol. 585 https://doi.org/10.1016/j.jhydrol.2020.124776	journal	June 2020
Long lead-time daily and monthly streamflow forecasting using machine learning methods Cheng, M.; Fang, F.; Kinouchi, T. Journal of Hydrology, Vol. 590 https://doi.org/10.1016/j.jhydrol.2020.125376	journal	November 2020
Predicting flood susceptibility using LSTM neural networks Fang, Zhice; Wang, Yi; Peng, Ling Journal of Hydrology, Vol. 594 https://doi.org/10.1016/j.jhydrol.2020.125734	journal	March 2021
A classification-based deep belief networks model framework for daily streamflow forecasting Chu, Haibo; Wei, Jiahua; Wu, Wenyan Journal of Hydrology, Vol. 595 https://doi.org/10.1016/j.jhydrol.2021.125967	journal	April 2021
Ensemble machine learning paradigms in hydrology: A review Zounemat-Kermani, Mohammad; Batelaan, Okke; Fadaee, Marzieh Journal of Hydrology, Vol. 598 https://doi.org/10.1016/j.jhydrol.2021.126266	journal	July 2021
A stacking ensemble model for hydrological post-processing to improve streamflow forecasts at medium-range timescales over South Korea Lee, Dong-Gi; Ahn, Kuk-Hyun Journal of Hydrology, Vol. 600 https://doi.org/10.1016/j.jhydrol.2021.126681	journal	September 2021
Space-time variability of low streamflows in river networks Furey, Peter R.; Gupta, Vijay K. Water Resources Research, Vol. 36, Issue 9 https://doi.org/10.1029/2000WR900136	journal	September 2000
Field studies of the storm event hydrologic response in an urbanizing watershed: FIELD STUDIES OF URBAN HYDROLOGIC RESPONSE Smith, James A.; Baeck, Mary Lynn; Meierdiercks, Katherine L. Water Resources Research, Vol. 41, Issue 10 https://doi.org/10.1029/2004WR003712	journal	October 2005
Improved methods for daily streamflow estimates at ungauged sites: DAILY STREAMFLOW ESTIMATES AT UNGAUGED SITES Shu, Chang; Ouarda, Taha B. M. J. Water Resources Research, Vol. 48, Issue 2 https://doi.org/10.1029/2011WR011501	journal	February 2012
The Influence of Spatial Variability of Width Functions on Regional Peak Flow Regressions Perez, Gabriel; Mantilla, Ricardo; Krajewski, Witold F. Water Resources Research, Vol. 54, Issue 10 https://doi.org/10.1029/2018WR023509	journal	October 2018
A Rainfall‐Runoff Model With LSTM‐Based Sequence‐to‐Sequence Learning Xiang, Zhongrun; Yan, Jun; Demir, Ibrahim Water Resources Research, Vol. 56, Issue 1 https://doi.org/10.1029/2019WR025326	journal	January 2020
Streamflow Estimation in Ungauged Catchments Using Regional Flow Duration Curve: Comparative Study Swain, Janaki Ballav; Patra, Kanhu Charan Journal of Hydrologic Engineering, Vol. 22, Issue 7 https://doi.org/10.1061/(ASCE)HE.1943-5584.0001509	journal	July 2017
Effect of River Network Geometry on Flood Frequency: A Tale of Two Watersheds in Iowa Ayalew, Tibebu B.; Krajewski, Witold F. Journal of Hydrologic Engineering, Vol. 22, Issue 8 https://doi.org/10.1061/(ASCE)HE.1943-5584.0001544	journal	August 2017
Development of Synthetic Rating Curves: Case Study in Iowa Quintero, Felipe; Rojas, Marcela; Muste, Marian Journal of Hydrologic Engineering, Vol. 26, Issue 1 https://doi.org/10.1061/(ASCE)HE.1943-5584.0002022	journal	January 2021
Fractal River Basins: Chance and Self‐Organization Rodriguez‐Iturbe, Ignacio; Rinaldo, Andrea; Levy, Ohad Physics Today, Vol. 51, Issue 7 https://doi.org/10.1063/1.882305	journal	July 1998
Forecasting flash floods using data-based mechanistic models and NORA radar rainfall forecasts Smith, P. J.; Panziera, L.; Beven, K. J. Hydrological Sciences Journal, Vol. 59, Issue 7 https://doi.org/10.1080/02626667.2013.842647	journal	January 2014
Evaluating model performance: towards a non-parametric variant of the Kling-Gupta efficiency Pool, Sandra; Vis, Marc; Seibert, Jan Hydrological Sciences Journal, Vol. 63, Issue 13-14 https://doi.org/10.1080/02626667.2018.1552002	journal	October 2018
Advances in real–time flood forecasting Young, Peter C. Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, Vol. 360, Issue 1796 https://doi.org/10.1098/rsta.2002.1008	journal	May 2002
Bridge-Mounted River Stage Sensors (BMRSS) Kruger, Anton; Krajewski, Witold F.; Niemeier, James J. IEEE Access, Vol. 4 https://doi.org/10.1109/ACCESS.2016.2631172	journal	January 2016
A Power Law Model for River Flow Velocity in Iowa Basins Ghimire, Ganesh Raj; Krajewski, Witold F.; Mantilla, Ricardo JAWRA Journal of the American Water Resources Association, Vol. 54, Issue 5 https://doi.org/10.1111/1752-1688.12665	journal	June 2018
Exploring Persistence in Streamflow Forecasting Ghimire, Ganesh Raj; Krajewski, Witold F. JAWRA Journal of the American Water Resources Association, Vol. 56, Issue 3 https://doi.org/10.1111/1752-1688.12821	journal	December 2019
Automated Base Flow Separation and Recession Analysis Techniques Arnold, J. G.; Allen, P. M.; Muttiah, R. Ground Water, Vol. 33, Issue 6 https://doi.org/10.1111/j.1745-6584.1995.tb00046.x	journal	November 1995
Use of Streamflow Data to Estimate Base Flow/Ground-Water Recharge For Wisconsin1: Use of Streamflow Data to Estimate Base Flow/Ground-Water Recharge for Wisconsin Gebert, Warren A.; Radloff, Mandy J.; Considine, Ellen J. JAWRA Journal of the American Water Resources Association, Vol. 43, Issue 1 https://doi.org/10.1111/j.1752-1688.2007.00018.x	journal	February 2007
Scientific Verification of Deterministic River Stage Forecasts Welles, Edwin; Sorooshian, Soroosh Journal of Hydrometeorology, Vol. 10, Issue 2 https://doi.org/10.1175/2008JHM1022.1	journal	April 2009
Hydrologic Verification: A Call for Action and Collaboration Welles, Edwin; Sorooshian, Soroosh; Carter, Gary Bulletin of the American Meteorological Society, Vol. 88, Issue 4 https://doi.org/10.1175/BAMS-88-4-503	journal	April 2007
Multi-Radar Multi-Sensor (MRMS) Quantitative Precipitation Estimation: Initial Operating Capabilities Zhang, Jian; Howard, Kenneth; Langston, Carrie Bulletin of the American Meteorological Society, Vol. 97, Issue 4 https://doi.org/10.1175/BAMS-D-14-00174.1	journal	April 2016
Real-Time Flood Forecasting and Information System for the State of Iowa Krajewski, Witold F.; Ceynar, Daniel; Demir, Ibrahim Bulletin of the American Meteorological Society, Vol. 98, Issue 3 https://doi.org/10.1175/BAMS-D-15-00243.1	journal	March 2017
A Streamflow and Water Level Forecasting Model for the Ganges, Brahmaputra, and Meghna Rivers with Requisite Simplicity Palash, Wahid; Jiang, Yudan; Akanda, Ali S. Journal of Hydrometeorology, Vol. 19, Issue 1 https://doi.org/10.1175/JHM-D-16-0202.1	journal	January 2018
Streamflow Forecasting without Models Krajewski, Witold F.; Ghimire, Ganesh R.; Quintero, Felipe Journal of Hydrometeorology, Vol. 21, Issue 8 https://doi.org/10.1175/JHM-D-19-0292.1	journal	August 2020
Extending the Predictability of Hydrometeorological Flood Events Using Radar Rainfall Nowcasting Vivoni, Enrique R.; Entekhabi, Dara; Bras, Rafael L. Journal of Hydrometeorology, Vol. 7, Issue 4 https://doi.org/10.1175/JHM514.1	journal	August 2006
Analysis of National Weather Service Stage Forecast Errors Zalenski, Grace; Krajewski, Witold F.; Quintero, Felipe Weather and Forecasting, Vol. 32, Issue 4 https://doi.org/10.1175/WAF-D-16-0219.1	journal	July 2017
Prediction of daily flow duration curves and streamflow for ungauged catchments using regional flow duration curves Mohamoud, Yusuf M. Hydrological Sciences Journal, Vol. 53, Issue 4 https://doi.org/10.1623/hysj.53.4.706	journal	August 2008
Comparison of Artificial Intelligence Techniques for river flow forecasting Firat, M. Hydrology and Earth System Sciences, Vol. 12, Issue 1 https://doi.org/10.5194/hess-12-123-2008	journal	January 2008
Application of data-based mechanistic modelling for flood forecasting at multiple locations in the Eden catchment in the National Flood Forecasting System (England and Wales) Leedal, D.; Weerts, A. H.; Smith, P. J. Hydrology and Earth System Sciences, Vol. 17, Issue 1 https://doi.org/10.5194/hess-17-177-2013	journal	January 2013
Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks Kratzert, Frederik; Klotz, Daniel; Brenner, Claire Hydrology and Earth System Sciences, Vol. 22, Issue 11 https://doi.org/10.5194/hess-22-6005-2018	journal	January 2018

Similar Records

Scale-Dependent Value of QPF for Real-Time Streamflow Forecasting

Journal Article · Sun Jul 18 20:00:00 EDT 2021 · Journal of Hydrometeorology · OSTI ID:1811378

Insights From Dayflow: A Historical Streamflow Reanalysis Dataset for the Conterminous United States

Journal Article · Sun Jan 29 19:00:00 EST 2023 · Water Resources Research · OSTI ID:1922544

Related Subjects

54 ENVIRONMENTAL SCIENCES
Artificial intelligence
Benchmarking
Hydrologic insights
Iowa
Persistence
Real-time streamflow forecasting

Real-time streamflow forecasting: AI vs. Hydrologic insights

Citation Formats

References (51)

Similar Records

Related Subjects