Advancing stream temperature prediction with a generalizable large-sample framework across CONUS river reaches

Bakar Siddik, Md Abu; Turner, Sean; Gomez-Velez, Jesus; Tanim, Ahad; Kao, Shih-Chieh

doi:10.1016/j.jhydrol.2025.134780

Advancing stream temperature prediction with a generalizable large-sample framework across CONUS river reaches

Journal Article · Fri Dec 12 23:00:00 EST 2025 · Journal of Hydrology

DOI:https://doi.org/10.1016/j.jhydrol.2025.134780· OSTI ID:3010625

^[1]; ^[1]; ^[1]; ^[1]; ^[1]

Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Accurately predicting stream temperature in ungauged basins remains a critical challenge for water resource management, thermoelectric power plant cooling, and ecosystem conservation. Large-sample machine learning models trained on hundreds of well-monitored river basins have shown remarkable performance; however, such models have yet to be developed solely using forcing data that can be readily extracted to simulate stream temperatures anywhere in the contiguous United States (CONUS). In this study, we present a scalable, large-sample deep learning framework using Long Short-Term Memory (LSTM) networks to simulate daily stream temperatures in ungauged basins across the CONUS. The framework leverages both modeled reanalysis of meteorological and streamflow inputs as well as static attributes available for all 2.7 million CONUS river reaches in the National Hydrography Dataset Plus (NHDPlusV2). By generating dynamical inputs from predefined thermally relevant upstream contributing areas, rather than the entire upstream basin, the model also offers improvements in very large basins where full-basin averaging can dilute the most important influences on stream temperature. Evaluated across 300 basins, the model achieves a median Mean Absolute Error (MAE) of 1.1 °C and a Nash-Sutcliffe Efficiency (NSE) of 0.95 on temporally and spatially distinct test folds—comparable to models trained exclusively using meteorological and streamflow observational data. The flexible, high-performing framework generalizes to any unmonitored river reach without significant regulation or unnatural thermal input immediately upstream, substantially expanding predictive capabilities in data-scarce regions.

View Accepted Manuscript (DOE)

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

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE); USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF)

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 3010625

Journal Information:: Journal of Hydrology, Journal Name: Journal of Hydrology Vol. 666; ISSN 0022-1694

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (34)

Deep learning approaches for improving prediction of daily stream temperature in data‐scarce, unmonitored, and dammed basins Rahmani, Farshid; Shen, Chaopeng; Oliver, Samantha Hydrological Processes, Vol. 35, Issue 11 https://doi.org/10.1002/hyp.14400	journal	November 2021
Implementation of Artificial Neural Networks in Modeling the Water-Air Temperature Relationship of the River Drava Hadzima-Nyarko, Marijana; Rabi, Anamarija; Šperac, Marija Water Resources Management, Vol. 28, Issue 5 https://doi.org/10.1007/s11269-014-0557-7	journal	March 2014
Least square support vector machine-based variational mode decomposition: a new hybrid model for daily river water temperature modeling Heddam, Salim; Ptak, Mariusz; Sojka, Mariusz Environmental Science and Pollution Research, Vol. 29, Issue 47 https://doi.org/10.1007/s11356-022-20953-0	journal	May 2022
River/stream water temperature forecasting using artificial intelligence models: a systematic review Zhu, Senlin; Piotrowski, Adam P. Acta Geophysica, Vol. 68, Issue 5 https://doi.org/10.1007/s11600-020-00480-7	journal	September 2020
River flow forecasting through conceptual models part I — A discussion of principles Nash, J. E.; Sutcliffe, J. V. Journal of Hydrology, Vol. 10, Issue 3 https://doi.org/10.1016/0022-1694(70)90255-6	journal	April 1970
Evaluation of daily stream temperature predictions (1979–2021) across the contiguous United States using a spatiotemporal aware machine learning algorithm Diaz, Jeremy; Oliver, Samantha; Gorski, Galen Environmental Modelling & Software, Vol. 193 https://doi.org/10.1016/j.envsoft.2025.106655	journal	September 2025
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
The role of riparian vegetation density, channel orientation and water velocity in determining river temperature dynamics Garner, Grace; Malcolm, Iain A.; Sadler, Jonathan P. Journal of Hydrology, Vol. 553 https://doi.org/10.1016/j.jhydrol.2017.03.024	journal	October 2017
Machine learning unravels controls on river water temperature regime dynamics Wade, Jeffrey; Kelleher, Christa; Hannah, David M. Journal of Hydrology, Vol. 623 https://doi.org/10.1016/j.jhydrol.2023.129821	journal	August 2023
A machine learning model for estimating the temperature of small rivers using satellite-based spatial data Philippus, Daniel; Sytsma, Anneliese; Rust, Ashley Remote Sensing of Environment, Vol. 311 https://doi.org/10.1016/j.rse.2024.114271	journal	September 2024
River temperature research and practice: Recent challenges and emerging opportunities for managing thermal habitat conditions in stream ecosystems Ouellet, Valerie; St-Hilaire, André; Dugdale, Stephen J. Science of The Total Environment, Vol. 736 https://doi.org/10.1016/j.scitotenv.2020.139679	journal	September 2020
Modified equilibrium temperature models for cold-water streams: EQUILIBRIUM TEMPERATURE FOR COLD-WATER STREAMS Herb, William R.; Stefan, Heinz G. Water Resources Research, Vol. 47, Issue 6 https://doi.org/10.1029/2010WR009586	journal	June 2011
Subannual Streamflow Responses to Rainfall and Snowmelt Inputs in Snow‐Dominated Watersheds of the Western United States Hammond, John C.; Kampf, Stephanie K. Water Resources Research, Vol. 56, Issue 4 https://doi.org/10.1029/2019WR026132	journal	April 2020
Multi‐Task Deep Learning of Daily Streamflow and Water Temperature Sadler, J. M.; Appling, A. P.; Read, J. S. Water Resources Research, Vol. 58, Issue 4 https://doi.org/10.1029/2021WR030138	journal	April 2022
Stream Temperature Prediction in a Shifting Environment: Explaining the Influence of Deep Learning Architecture Topp, Simon N.; Barclay, Janet; Diaz, Jeremy Water Resources Research, Vol. 59, Issue 4 https://doi.org/10.1029/2022WR033880	journal	April 2023
Deep Learning Advances Arctic River Water Temperature Predictions Chang, Shuyu Y.; Schwenk, Jon; Solander, Kurt C. Water Resources Research, Vol. 61, Issue 6 https://doi.org/10.1029/2024WR039053	journal	May 2025
A nonlinear regression model for weekly stream temperatures Mohseni, Omid; Stefan, Heinz G.; Erickson, Troy R. Water Resources Research, Vol. 34, Issue 10 https://doi.org/10.1029/98WR01877	journal	October 1998
US Power Production at Risk from Water Stress in a Changing Climate Ganguli, Poulomi; Kumar, Devashish; Ganguly, Auroop R. Scientific Reports, Vol. 7, Issue 1 https://doi.org/10.1038/s41598-017-12133-9	journal	September 2017
Optimizing Selective Withdrawal from Reservoirs to Manage Downstream Temperatures with Climate Warming Rheinheimer, David E.; Null, Sarah E.; Lund, Jay R. Journal of Water Resources Planning and Management, Vol. 141, Issue 4 https://doi.org/10.1061/(ASCE)WR.1943-5452.0000447	journal	April 2015
Elevation-dependent warming of streams in mountainous regions: implications for temperature modeling and headwater climate refugia Isaak, Daniel J.; Luce, Charles H. Canadian Water Resources Journal / Revue canadienne des ressources hydriques, Vol. 48, Issue 2 https://doi.org/10.1080/07011784.2023.2176788	journal	February 2023
Permutation importance: a corrected feature importance measure Altmann, André; Toloşi, Laura; Sander, Oliver Bioinformatics, Vol. 26, Issue 10 https://doi.org/10.1093/bioinformatics/btq134	journal	April 2010
The Stream-Catchment (StreamCat) Dataset: A Database of Watershed Metrics for the Conterminous United States Hill, Ryan A.; Weber, Marc H.; Leibowitz, Scott G. JAWRA Journal of the American Water Resources Association, Vol. 52, Issue 1 https://doi.org/10.1111/1752-1688.12372	journal	December 2015
Spatial variation of water temperature characteristics and behavior in a Devon river system Webb, B. W.; Walling, D. E. Freshwater Biology, Vol. 16, Issue 5 https://doi.org/10.1111/j.1365-2427.1986.tb01002.x	journal	October 1986
The thermal regime of rivers: a review Caissie, D. Freshwater Biology, Vol. 51, Issue 8 https://doi.org/10.1111/j.1365-2427.2006.01597.x	journal	August 2006
A Comparison of Statistical Approaches for Predicting Stream Temperatures Across Heterogeneous Landscapes Wehrly, Kevin E.; Brenden, Travis O.; Wang, Lizhu JAWRA Journal of the American Water Resources Association, Vol. 45, Issue 4 https://doi.org/10.1111/j.1752-1688.2009.00341.x	journal	August 2009
What do warming waters mean for fish physiology and fisheries? Little, Alexander G.; Loughland, Isabella; Seebacher, Frank Journal of Fish Biology, Vol. 97, Issue 2 https://doi.org/10.1111/jfb.14402	journal	June 2020
Long Short-Term Memory Hochreiter, Sepp; Schmidhuber, Jürgen Neural Computation, Vol. 9, Issue 8 https://doi.org/10.1162/neco.1997.9.8.1735	journal	November 1997
Effects of climate change and wildfire on stream temperatures and salmonid thermal habitat in a mountain river network Isaak, Daniel J.; Luce, Charles H.; Rieman, Bruce E. Ecological Applications, Vol. 20, Issue 5 https://doi.org/10.1890/09-0822.1	journal	July 2010
ERA5-Land: a state-of-the-art global reanalysis dataset for land applications Muñoz-Sabater, Joaquín; Dutra, Emanuel; Agustí-Panareda, Anna Earth System Science Data, Vol. 13, Issue 9 https://doi.org/10.5194/essd-13-4349-2021	journal	January 2021
Stream temperature prediction in ungauged basins: review of recent approaches and description of a new physics-derived statistical model Gallice, A.; Schaefli, B.; Lehning, M. Hydrology and Earth System Sciences, Vol. 19, Issue 9 https://doi.org/10.5194/hess-19-3727-2015	journal	January 2015
Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets Kratzert, Frederik; Klotz, Daniel; Shalev, Guy Hydrology and Earth System Sciences, Vol. 23, Issue 12 https://doi.org/10.5194/hess-23-5089-2019	journal	January 2019
Machine-learning methods for stream water temperature prediction Feigl, Moritz; Lebiedzinski, Katharina; Herrnegger, Mathew Hydrology and Earth System Sciences, Vol. 25, Issue 5 https://doi.org/10.5194/hess-25-2951-2021	journal	January 2021
Continuous streamflow prediction in ungauged basins: long short-term memory neural networks clearly outperform traditional hydrological models Arsenault, Richard; Martel, Jean-Luc; Brunet, Frédéric Hydrology and Earth System Sciences, Vol. 27, Issue 1, p. 139-157 https://doi.org/10.5194/hess-27-139-2023	journal	January 2023
Machine learning in stream and river water temperature modeling: a review and metrics for evaluation Corona, Claudia Rebecca; Hogue, Terri Sue Hydrology and Earth System Sciences, Vol. 29, Issue 12 https://doi.org/10.5194/hess-29-2521-2025	journal	June 2025

Similar Records

HydroEcoLSTM: A Python package with graphical user interface for hydro-ecological modeling with long short-term memory neural network

Journal Article · Fri Jan 03 23:00:00 EST 2025 · Ecological Informatics · OSTI ID:2510856

Deep Learning Advances Arctic River Water Temperature Predictions

Journal Article · Thu May 29 00:00:00 EDT 2025 · Water Resources Research · OSTI ID:2574173

CONUS-wide Projected Flood Frequency Estimates, Version 1.0

Dataset · Wed Oct 01 00:00:00 EDT 2025 · OSTI ID:3001986

Related Subjects

Hydrology
Large-sample machine learning
Stream temperature

Advancing stream temperature prediction with a generalizable large-sample framework across CONUS river reaches

Citation Formats

References (34)

Similar Records

Related Subjects