Can Simple Machine Learning Tools Extend and Improve Temperature-Based Methods to Infer Streambed Flux?

Moghaddam, Mohammad A.; Ferré, Ty P. A.; Chen, Xingyuan; Chen, Kewei; Song, Xuehang; Hammond, Glenn

doi:10.3390/w13202837

Can Simple Machine Learning Tools Extend and Improve Temperature-Based Methods to Infer Streambed Flux?

Journal Article · Tue Oct 12 00:00:00 EDT 2021 · Water (Basel)

DOI:https://doi.org/10.3390/w13202837· OSTI ID:1825814

Moghaddam, Mohammad A.; ; Chen, Xingyuan; Chen, Kewei; Song, Xuehang; Hammond, Glenn

Temperature-based methods have been developed to infer 1D vertical exchange flux between a stream and the subsurface. Current analyses rely on fitting physically based analytical and numerical models to temperature time series measured at multiple depths to infer daily average flux. These methods have seen wide use in hydrologic science despite strong simplifying assumptions including a lack of consideration of model structural error or the impacts of multidimensional flow or the impacts of transient streambed hydraulic properties. We performed a “perfect-model experiment” investigation to examine whether regression trees, with and without gradient boosting, can extract sufficient information from model-generated subsurface temperature time series, with and without added measurement error, to infer the corresponding exchange flux time series at the streambed surface. Using model-generated, synthetic data allowed us to assess the basic limitations to the use of machine learning; further examination of real data is only warranted if the method can be shown to perform well under these ideal conditions. We also examined whether the inherent feature importance analyses of tree-based machine learning methods can be used to optimize monitoring networks for exchange flux inference.

View Journal Article

Research Organization:: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)

Sponsoring Organization:: USDOE; USDOE Office of Science (SC), Biological and Environmental Research (BER)

Grant/Contract Number:: AC02-05CH11231; AC05-76RL01830; NA0003525

OSTI ID:: 1825814

Alternate ID(s):: OSTI ID: 1835578

Report Number(s):: PNNL-SA--151168; PII: w13202837

Journal Information:: Water (Basel), Journal Name: Water (Basel) Journal Issue: 20 Vol. 13; ISSN 2073-4441; ISSN WATEGH

Publisher:: MDPI AGCopyright Statement

Country of Publication:: Switzerland

Language:: English

References (33)

Evaluating the performance of parallel subsurface simulators: An illustrative example with PFLOTRAN: Evaluating the Parallel Performance of Pflotran Hammond, G. E.; Lichtner, P. C.; Mills, R. T. Water Resources Research, Vol. 50, Issue 1 https://doi.org/10.1002/2012WR013483	journal	January 2014
Assessing the accuracy of 1-D analytical heat tracing for estimating near-surface sediment thermal diffusivity and water flux under transient conditions: Transient Heat Tracing Limits Rau, Gabriel C.; Cuthbert, Mark O.; McCallum, Andrew M. Journal of Geophysical Research: Earth Surface, Vol. 120, Issue 8 https://doi.org/10.1002/2015JF003466	journal	August 2015
Transient or steady-state? Using vertical temperature profiles to quantify groundwater-surface water exchange Anibas, Christian; Fleckenstein, Jan H.; Volze, Nina Hydrological Processes, Vol. 23, Issue 15 https://doi.org/10.1002/hyp.7289	journal	July 2009
Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction Prasad, Anantha M.; Iverson, Louis R.; Liaw, Andy Ecosystems, Vol. 9, Issue 2 https://doi.org/10.1007/s10021-005-0054-1	journal	March 2006
Multi-tracer investigation of river and groundwater interactions: a case study in Nalenggele River basin, northwest China Xu, Wei; Su, Xiaosi; Dai, Zhenxue Hydrogeology Journal, Vol. 25, Issue 7 https://doi.org/10.1007/s10040-017-1606-0	journal	June 2017
Do We Need More Training Data? Zhu, Xiangxin; Vondrick, Carl; Fowlkes, Charless C. International Journal of Computer Vision, Vol. 119, Issue 1 https://doi.org/10.1007/s11263-015-0812-2	journal	March 2015
Heat as a tracer to quantify water flow in near-surface sediments Rau, Gabriel C.; Andersen, Martin S.; McCallum, Andrew M. Earth-Science Reviews, Vol. 129 https://doi.org/10.1016/j.earscirev.2013.10.015	journal	February 2014
Gradient boosting machine for modeling the energy consumption of commercial buildings Touzani, Samir; Granderson, Jessica; Fernandes, Samuel Energy and Buildings, Vol. 158 https://doi.org/10.1016/j.enbuild.2017.11.039	journal	January 2018
Deep learning for compute-efficient modeling of BMP impacts on stream- aquifer exchange and water law compliance in an irrigated river basin Rohmat, Faizal I. W.; Labadie, John W.; Gates, Timothy K. Environmental Modelling & Software, Vol. 122 https://doi.org/10.1016/j.envsoft.2019.104529	journal	December 2019
Temporal and spatial variability of groundwater–surface water fluxes: Development and application of an analytical method using temperature time series Keery, John; Binley, Andrew; Crook, Nigel Journal of Hydrology, Vol. 336, Issue 1-2 https://doi.org/10.1016/j.jhydrol.2006.12.003	journal	March 2007
Spatial and temporal variability of streambed hydraulic conductivity in West Bear Creek, North Carolina, USA Genereux, David P.; Leahy, Scott; Mitasova, Helena Journal of Hydrology, Vol. 358, Issue 3-4 https://doi.org/10.1016/j.jhydrol.2008.06.017	journal	September 2008
Evaluation of CatBoost method for prediction of reference evapotranspiration in humid regions Huang, Guomin; Wu, Lifeng; Ma, Xin Journal of Hydrology, Vol. 574 https://doi.org/10.1016/j.jhydrol.2019.04.085	journal	July 2019
Downscaling SMAP soil moisture estimation with gradient boosting decision tree regression over the Tibetan Plateau Wei, Zushuai; Meng, Yizhuo; Zhang, Wen Remote Sensing of Environment, Vol. 225 https://doi.org/10.1016/j.rse.2019.02.022	journal	May 2019
A hybrid machine learning model to predict and visualize nitrate concentration throughout the Central Valley aquifer, California, USA Ransom, Katherine M.; Nolan, Bernard T.; A. Traum, Jonathan Science of The Total Environment, Vol. 601-602 https://doi.org/10.1016/j.scitotenv.2017.05.192	journal	December 2017
Analysis of temperature profiles for investigating stream losses beneath ephemeral channels: TEMPERATURE PROFILES BENEATH CHANNELS Constantz, Jim; Stewart, Amy E.; Niswonger, Richard Water Resources Research, Vol. 38, Issue 12 https://doi.org/10.1029/2001WR001221	journal	December 2002
Quantifying surface water-groundwater interactions using time series analysis of streambed thermal records: Method development: TIME SERIES THERMAL METHOD QUANTIFIES SW-GW Hatch, Christine E.; Fisher, Andrew T.; Revenaugh, Justin S. Water Resources Research, Vol. 42, Issue 10 https://doi.org/10.1029/2005WR004787	journal	October 2006
Heat as a tracer to determine streambed water exchanges: HEAT USED TO DETERMINE STREAMBED WATER EXCHANGES Constantz, Jim Water Resources Research, Vol. 44, Issue 4 https://doi.org/10.1029/2008WR006996	journal	April 2008
Uncertainty in thermal time series analysis estimates of streambed water flux: UNCERTAINTY IN THERMAL TIME SERIES OF WATER Shanafield, Margaret; Hatch, Christine; Pohll, Greg Water Resources Research, Vol. 47, Issue 3 https://doi.org/10.1029/2010WR009574	journal	March 2011
Percolation measurements based on heat flow through soil with special reference to paddy fields Suzuki, Seitaro Journal of Geophysical Research, Vol. 65, Issue 9 https://doi.org/10.1029/JZ065i009p02883	journal	September 1960
Steady one-dimensional fluid flow in a semi-infinite porous medium with sinusoidal surface temperature Stallman, R. W. Journal of Geophysical Research, Vol. 70, Issue 12 https://doi.org/10.1029/JZ070i012p02821	journal	June 1965
Characterization of transport in an acidic and metal-rich mountain stream based on a lithium tracer injection and simulations of transient storage Bencala, Kenneth E.; McKnight, Diane M.; Zellweger, Gary W. Water Resources Research, Vol. 26, Issue 5 https://doi.org/10.1029/WR026i005p00989	journal	May 1990
Improved surrogates in inertial confinement fusion with manifold and cycle consistencies Anirudh, Rushil; Thiagarajan, Jayaraman J.; Bremer, Peer-Timo Proceedings of the National Academy of Sciences, Vol. 117, Issue 18 https://doi.org/10.1073/pnas.1916634117	journal	April 2020
1DTempPro: Analyzing Temperature Profiles for Groundwater/Surface-water Exchange: Ground Water xx, no. xx: xx-xx Voytek, Emily B.; Drenkelfuss, Anja; Day-Lewis, Frederick D. Groundwater, Vol. 52, Issue 2 https://doi.org/10.1111/gwat.12051	journal	April 2013
1DTempPro V2: New Features for Inferring Groundwater/Surface-Water Exchange Koch, Franklin W.; Voytek, Emily B.; Day-Lewis, Frederick D. Groundwater, Vol. 54, Issue 3 https://doi.org/10.1111/gwat.12369	journal	September 2015
Comparison of Heat and Bromide as Ground Water Tracers Near Streams Constantz, Jim; Cox, Marisa H.; Su, Grace W. Ground Water, Vol. 41, Issue 5 https://doi.org/10.1111/j.1745-6584.2003.tb02403.x	journal	September 2003
Use of an Electromagnetic Seepage Meter to Investigate Temporal Variability in Lake Seepage Rosenberry, Donald O.; Morin, Roger H. Ground Water, Vol. 42, Issue 1 https://doi.org/10.1111/j.1745-6584.2004.tb02451.x	journal	January 2004
Heat as a Ground Water Tracer Anderson, Mary P. Ground Water, Vol. 43, Issue 6 https://doi.org/10.1111/j.1745-6584.2005.00052.x	journal	August 2005
Assessment of the Advanced Very High-Resolution Radiometer (AVHRR) for Snowfall Retrieval in High Latitudes Using CloudSat and Machine Learning Ehsani, Mohammad Reza; Behrangi, Ali; Adhikari, Abishek Journal of Hydrometeorology https://doi.org/10.1175/jhm-d-20-0240.1	journal	April 2021
A survey of cross-validation procedures for model selection Arlot, Sylvain; Celisse, Alain Statistics Surveys, Vol. 4, Issue 0 https://doi.org/10.1214/09-SS054	journal	January 2010
Can Deep Learning Extract Useful Information about Energy Dissipation and Effective Hydraulic Conductivity from Gridded Conductivity Fields? Moghaddam, Mohammad A.; Ferre, Paul A. T.; Ehsani, Mohammad Reza Water, Vol. 13, Issue 12 https://doi.org/10.3390/w13121668	journal	June 2021
Coupling a three-dimensional subsurface flow and transport model with a land surface model to simulate stream–aquifer–land interactions (CP v1.0) Bisht, Gautam; Huang, Maoyi; Zhou, Tian Geoscientific Model Development, Vol. 10, Issue 12 https://doi.org/10.5194/gmd-10-4539-2017	journal	January 2017
Efficient surrogate modeling methods for large-scale Earth system models based on machine-learning techniques Lu, Dan; Ricciuto, Daniel Geoscientific Model Development, Vol. 12, Issue 5 https://doi.org/10.5194/gmd-12-1791-2019	journal	January 2019
A Field Exercise on Groundwater Flow Using Seepage Meters and Mini-piezometers Lee, David R.; Cherry, John A. Journal of Geological Education, Vol. 27, Issue 1 https://doi.org/10.5408/0022-1368-27.1.6	journal	January 1979

Similar Records

The importance of explicitly representing the streambed in watershed models

Journal Article · Sat Dec 16 19:00:00 EST 2023 · Hydrological Processes · OSTI ID:2242547

Related Subjects

54 ENVIRONMENTAL SCIENCES
groundwater monitoring
groundwater recharge
groundwater-surface water interactions
integrated hydrologic models
machine learning

Can Simple Machine Learning Tools Extend and Improve Temperature-Based Methods to Infer Streambed Flux?

Citation Formats

References (33)

Similar Records

Related Subjects