Articles | Volume 26, issue 3
https://doi.org/10.5194/hess-26-795-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-26-795-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
14 Feb 2022
Research article |
| 14 Feb 2022
| 14 Feb 2022
Evaluation and interpretation of convolutional long short-term memory networks for regional hydrological modelling
Department of Earth, Ocean and Atmospheric Sciences, University of British Columbia, Vancouver, BC V6T 1Z4, Canada
Valentina Radić
Department of Earth, Ocean and Atmospheric Sciences, University of British Columbia, Vancouver, BC V6T 1Z4, Canada
Related authors
No articles found.
Christina Draeger, Valentina Radić, Rachel H. White, and Mekdes Ayalew Tessema
The Cryosphere, 18, 17–42, https://doi.org/10.5194/tc-18-17-2024, https://doi.org/10.5194/tc-18-17-2024, 2024
Short summary
Short summary
Our study increases our confidence in using reanalysis data for reconstructions of past glacier melt and in using dynamical downscaling for long-term simulations from global climate models to project glacier melt. We find that the surface energy balance model, forced with reanalysis and dynamically downscaled reanalysis data, yields <10 % difference in the modeled total melt energy when compared to the same model being forced with observations at our glacier sites in western Canada.
Jonathan P. Conway, Jakob Abermann, Liss M. Andreassen, Mohd Farooq Azam, Nicolas J. Cullen, Noel Fitzpatrick, Rianne H. Giesen, Kirsty Langley, Shelley MacDonell, Thomas Mölg, Valentina Radić, Carleen H. Reijmer, and Jean-Emmanuel Sicart
The Cryosphere, 16, 3331–3356, https://doi.org/10.5194/tc-16-3331-2022, https://doi.org/10.5194/tc-16-3331-2022, 2022
Short summary
Short summary
We used data from automatic weather stations on 16 glaciers to show how clouds influence glacier melt in different climates around the world. We found surface melt was always more frequent when it was cloudy but was not universally faster or slower than under clear-sky conditions. Also, air temperature was related to clouds in opposite ways in different climates – warmer with clouds in cold climates and vice versa. These results will help us improve how we model past and future glacier melt.
Noel Fitzpatrick, Valentina Radić, and Brian Menounos
The Cryosphere, 13, 1051–1071, https://doi.org/10.5194/tc-13-1051-2019, https://doi.org/10.5194/tc-13-1051-2019, 2019
Short summary
Short summary
Measurements of surface roughness are rare on glaciers, despite being an important control for heat exchange with the atmosphere and surface melt. In this study, roughness values were determined through measurements at multiple locations and seasons and found to vary across glacier surfaces and to differ from commonly assumed values in melt models. Two new methods that remotely determine roughness from digital elevation models returned good performance and may facilitate improved melt modelling.
Mekdes Ayalew Tessema, Valentina Radić, Brian Menounos, and Noel Fitzpatrick
The Cryosphere Discuss., https://doi.org/10.5194/tc-2018-154, https://doi.org/10.5194/tc-2018-154, 2018
Preprint withdrawn
Short summary
Short summary
To force physics-based models of glacier melt, meteorological variables and energy fluxes are needed at or in vicinity of the glaciers in question. In the absence of observations detailing these variables, the required forcing is commonly derived by downscaling the coarse-resolution output from global climate models (GCMs). This study investigates how the downscaled fields from GCMs can successfully resolve the local processes driving surface melting at three glaciers in British Columbia.
Valentina Radić, Brian Menounos, Joseph Shea, Noel Fitzpatrick, Mekdes A. Tessema, and Stephen J. Déry
The Cryosphere, 11, 2897–2918, https://doi.org/10.5194/tc-11-2897-2017, https://doi.org/10.5194/tc-11-2897-2017, 2017
Short summary
Short summary
Our overall goal is to improve the numerical modeling of glacier melt in order to better predict the future of glaciers in Western Canada and worldwide.
Most commonly used models rely on simplifications of processes that dictate melting at a glacier surface, in particular turbulent processes of heat exchange. We compared modeled against directly measured turbulent heat fluxes at a valley glacier in British Columbia, Canada, and found that more improvements are needed in all the tested models.
S. H. Mernild, W. H. Lipscomb, D. B. Bahr, V. Radić, and M. Zemp
The Cryosphere, 7, 1565–1577, https://doi.org/10.5194/tc-7-1565-2013, https://doi.org/10.5194/tc-7-1565-2013, 2013
Related subject area
Subject: Rivers and Lakes | Techniques and Approaches: Modelling approaches
Estimating velocity distribution and flood discharge at river bridges using entropy theory – insights from computational fluid dynamics flow fields
Isotopic evaluation of the National Water Model reveals missing agricultural irrigation contributions to streamflow across the western United States
Timing of spring events changes under modelled future climate scenarios in a mesotrophic lake
Effects of high-quality elevation data and explanatory variables on the accuracy of flood inundation mapping via Height Above Nearest Drainage
A hybrid data-driven approach to analyze the drivers of lake level dynamics
Understanding the compound flood risk along the coast of the contiguous United States
Benchmarking high-resolution hydrologic model performance of long-term retrospective streamflow simulations in the contiguous United States
Sources of skill in lake temperature, discharge and ice-off seasonal forecasting tools
Past and future climate change effects on the thermal regime and oxygen solubility of four peri-alpine lakes
Exploring tracer information in a small stream to improve parameter identifiability and enhance the process interpretation in transient storage models
How do inorganic nitrogen processing pathways change quantitatively at daily, seasonal, and multiannual scales in a large agricultural stream?
Seasonal forecasting of lake water quality and algal bloom risk using a continuous Gaussian Bayesian network
Spatially referenced Bayesian state-space model of total phosphorus in western Lake Erie
Future water temperature of rivers in Switzerland under climate change investigated with physics-based models
Physical controls and a priori estimation of raising land surface elevation across the southwestern Bangladesh delta using tidal river management
Synthesizing the impacts of baseflow contribution on concentration–discharge (C–Q) relationships across Australia using a Bayesian hierarchical model
Calibrating 1D hydrodynamic river models in the absence of cross-section geometry using satellite observations of water surface elevation and river width
A global algorithm for identifying changing streamflow regimes: application to Canadian natural streams (1966–2010)
Streamflow drought: implication of drought definitions and its application for drought forecasting
Quantifying floodwater impacts on a lake water budget via volume-dependent transient stable isotope mass balance
River runoff in Switzerland in a changing climate – changes in moderate extremes and their seasonality
River runoff in Switzerland in a changing climate – runoff regime changes and their time of emergence
Machine-learning methods for stream water temperature prediction
Bathymetry and latitude modify lake warming under ice
Lake thermal structure drives interannual variability in summer anoxia dynamics in a eutrophic lake over 37 years
Reservoir evaporation in a Mediterranean climate: comparing direct methods in Alqueva Reservoir, Portugal
Diverging hydrological drought traits over Europe with global warming
Anthropogenic influence on the Rhine water temperatures
A new form of the Saint-Venant equations for variable topography
Simulations of future changes in thermal structure of Lake Erken: proof of concept for ISIMIP2b lake sector local simulation strategy
Assessment of the geomorphic effectiveness of controlled floods in a braided river using a reduced-complexity numerical model
Worldwide lake level trends and responses to background climate variation
Modeling inorganic carbon dynamics in the Seine River continuum in France
A data-based predictive model for spatiotemporal variability in stream water quality
Flooding in the Mekong Delta: the impact of dyke systems on downstream hydrodynamics
Reconstruction of the 1941 GLOF process chain at Lake Palcacocha (Cordillera Blanca, Peru)
Historical modelling of changes in Lake Erken thermal conditions
Improving lake mixing process simulations in the Community Land Model by using K profile parameterization
Upgraded global mapping information for earth system modelling: an application to surface water depth at the ECMWF
Sediment transport modelling in riverine environments: on the importance of grain-size distribution, sediment density, and suspended sediment concentrations at the upstream boundary
Replication of ecologically relevant hydrological indicators following a modified covariance approach to hydrological model parameterization
Lidar-based approaches for estimating solar insolation in heavily forested streams
Numerical study on the response of the largest lake in China to climate change
Unraveling the hydrological budget of isolated and seasonally contrasted subtropical lakes
Future projections of temperature and mixing regime of European temperate lakes
Conservative finite-volume forms of the Saint-Venant equations for hydrology and urban drainage
Modelling Lake Titicaca's daily and monthly evaporation
Principal components of thermal regimes in mountain river networks
Modelling the water balance of Lake Victoria (East Africa) – Part 1: Observational analysis
Modelling the water balance of Lake Victoria (East Africa) – Part 2: Future projections
Farhad Bahmanpouri, Tommaso Lazzarin, Silvia Barbetta, Tommaso Moramarco, and Daniele P. Viero
Hydrol. Earth Syst. Sci., 28, 3717–3737, https://doi.org/10.5194/hess-28-3717-2024, https://doi.org/10.5194/hess-28-3717-2024, 2024
Short summary
Short summary
The entropy model is a reliable tool to estimate flood discharge in rivers using observed level and surface velocity. Often, level and velocity sensors are placed on bridges, which may disturb the flow. Using accurate numerical models, we explored the entropy model reliability nearby a multi-arch bridge. We found that it is better to place sensors and to estimate the discharge upstream of bridges; downstream, the entropy model needs the river-wide distribution of surface velocity as input data.
Annie L. Putman, Patrick C. Longley, Morgan C. McDonnell, James Reddy, Michelle Katoski, Olivia L. Miller, and J. Renée Brooks
Hydrol. Earth Syst. Sci., 28, 2895–2918, https://doi.org/10.5194/hess-28-2895-2024, https://doi.org/10.5194/hess-28-2895-2024, 2024
Short summary
Short summary
Accuracy of streamflow estimates where water management and use are prevalent, such as the western US, reflect hydrologic modeling decisions. To evaluate process inclusion decisions, we equipped a hydrologic model with tracers and compared estimates to observations. The tracer-equipped model performed well, and differences between the model and observations suggest that the inclusion of water from irrigation may improve model performance in this region.
Jorrit P. Mesman, Inmaculada C. Jiménez-Navarro, Ana I. Ayala, Javier Senent-Aparicio, Dennis Trolle, and Don C. Pierson
Hydrol. Earth Syst. Sci., 28, 1791–1802, https://doi.org/10.5194/hess-28-1791-2024, https://doi.org/10.5194/hess-28-1791-2024, 2024
Short summary
Short summary
Spring events in lakes are key processes for ecosystem functioning. We used a coupled catchment–lake model to investigate future changes in the timing of spring discharge, ice-off, spring phytoplankton peak, and onset of stratification in a mesotrophic lake. We found a clear trend towards earlier occurrence under climate warming but also that relative shifts in the timing occurred, such as onset of stratification advancing more slowly than the other events.
Fernando Aristizabal, Taher Chegini, Gregory Petrochenkov, Fernando Salas, and Jasmeet Judge
Hydrol. Earth Syst. Sci., 28, 1287–1315, https://doi.org/10.5194/hess-28-1287-2024, https://doi.org/10.5194/hess-28-1287-2024, 2024
Short summary
Short summary
Floods are significant natural disasters that affect people and property. This study uses a simplified terrain index and the latest lidar-derived digital elevation maps (DEMs) to investigate flood inundation extent quality. We examined inundation quality influenced by different spatial resolutions and other variables. Results showed that lidar DEMs enhance inundation quality, but their resolution is less impactful in our context. Further studies on reservoirs and urban flooding are recommended.
Márk Somogyvári, Dieter Scherer, Frederik Bart, Ute Fehrenbach, Akpona Okujeni, and Tobias Krueger
EGUsphere, https://doi.org/10.5194/egusphere-2023-2111, https://doi.org/10.5194/egusphere-2023-2111, 2023
Short summary
Short summary
We study the drivers behind the changes in lake levels, via creating a series of models from least to more complex. In this study we have shown that the decreasing levels of the Groß Glienicker Lake in Germany are not simply the result of changes in climate, but it is affected by other processes. In our example reduced inflow from a growing forest, regionally sinking groundwater levels and the modifications in the local rainwater infrastructure together resulted in an increasing lake level loss.
Dongyu Feng, Zeli Tan, Donghui Xu, and L. Ruby Leung
Hydrol. Earth Syst. Sci., 27, 3911–3934, https://doi.org/10.5194/hess-27-3911-2023, https://doi.org/10.5194/hess-27-3911-2023, 2023
Short summary
Short summary
This study assesses the flood risks concurrently induced by river flooding and coastal storm surge along the coast of the contiguous United States using statistical and numerical models. We reveal a few hotspots of such risks, the critical spatial variabilities within a river basin and over the whole US coast, and the uncertainties of the risk assessment. We highlight the importance of weighing different risk measures to avoid underestimating or exaggerating the compound flood impacts.
Erin Towler, Sydney S. Foks, Aubrey L. Dugger, Jesse E. Dickinson, Hedeff I. Essaid, David Gochis, Roland J. Viger, and Yongxin Zhang
Hydrol. Earth Syst. Sci., 27, 1809–1825, https://doi.org/10.5194/hess-27-1809-2023, https://doi.org/10.5194/hess-27-1809-2023, 2023
Short summary
Short summary
Hydrologic models developed to assess water availability need to be systematically evaluated. This study evaluates the long-term performance of two high-resolution hydrologic models that simulate streamflow across the contiguous United States. Both models show similar performance overall and regionally, with better performance in minimally disturbed basins than in those impacted by human activity. At about 80 % of the sites, both models outperform the seasonal climatological benchmark.
François Clayer, Leah Jackson-Blake, Daniel Mercado-Bettín, Muhammed Shikhani, Andrew French, Tadhg Moore, James Sample, Magnus Norling, Maria-Dolores Frias, Sixto Herrera, Elvira de Eyto, Eleanor Jennings, Karsten Rinke, Leon van der Linden, and Rafael Marcé
Hydrol. Earth Syst. Sci., 27, 1361–1381, https://doi.org/10.5194/hess-27-1361-2023, https://doi.org/10.5194/hess-27-1361-2023, 2023
Short summary
Short summary
We assessed the predictive skill of forecasting tools over the next season for water discharge and lake temperature. Tools were forced with seasonal weather predictions; however, most of the prediction skill originates from legacy effects and not from seasonal weather predictions. Yet, when skills from seasonal weather predictions are present, additional skill comes from interaction effects. Skilful lake seasonal predictions require better weather predictions and realistic antecedent conditions.
Olivia Desgué-Itier, Laura Melo Vieira Soares, Orlane Anneville, Damien Bouffard, Vincent Chanudet, Pierre Alain Danis, Isabelle Domaizon, Jean Guillard, Théo Mazure, Najwa Sharaf, Frédéric Soulignac, Viet Tran-Khac, Brigitte Vinçon-Leite, and Jean-Philippe Jenny
Hydrol. Earth Syst. Sci., 27, 837–859, https://doi.org/10.5194/hess-27-837-2023, https://doi.org/10.5194/hess-27-837-2023, 2023
Short summary
Short summary
The long-term effects of climate change will include an increase in lake surface and deep water temperatures. Incorporating up to 6 decades of limnological monitoring into an improved 1D lake model approach allows us to predict the thermal regime and oxygen solubility in four peri-alpine lakes over the period 1850–2100. Our modeling approach includes a revised selection of forcing variables and provides a way to investigate the impacts of climate variations on lakes for centennial timescales.
Enrico Bonanno, Günter Blöschl, and Julian Klaus
Hydrol. Earth Syst. Sci., 26, 6003–6028, https://doi.org/10.5194/hess-26-6003-2022, https://doi.org/10.5194/hess-26-6003-2022, 2022
Short summary
Short summary
There is an unclear understanding of which processes regulate the transport of water, solutes, and pollutants in streams. This is crucial since these processes control water quality in river networks. Compared to other approaches, we obtained clearer insights into the processes controlling solute transport in the investigated reach. This work highlights the risks of using uncertain results for interpreting the processes controlling water movement in streams.
Jingshui Huang, Dietrich Borchardt, and Michael Rode
Hydrol. Earth Syst. Sci., 26, 5817–5833, https://doi.org/10.5194/hess-26-5817-2022, https://doi.org/10.5194/hess-26-5817-2022, 2022
Short summary
Short summary
In this study, we set up a water quality model using a 5-year paired high-frequency water quality dataset from a large agricultural stream. The simulations were compared with the 15 min interval measurements and showed very good fits. Based on these, we quantified the N uptake pathway rates and efficiencies at daily, seasonal, and yearly scales. This study offers an overarching understanding of N processing in large agricultural streams across different temporal scales.
Leah A. Jackson-Blake, François Clayer, Sigrid Haande, James E. Sample, and S. Jannicke Moe
Hydrol. Earth Syst. Sci., 26, 3103–3124, https://doi.org/10.5194/hess-26-3103-2022, https://doi.org/10.5194/hess-26-3103-2022, 2022
Short summary
Short summary
We develop a Gaussian Bayesian network (GBN) for seasonal forecasting of lake water quality and algal bloom risk in a nutrient-impacted lake in southern Norway. Bayesian networks are powerful tools for environmental modelling but are almost exclusively discrete. We demonstrate that a continuous GBN is a promising alternative approach. Predictive performance of the GBN was similar or improved compared to a discrete network, and it was substantially less time-consuming and subjective to develop.
Timothy J. Maguire, Craig A. Stow, and Casey M. Godwin
Hydrol. Earth Syst. Sci., 26, 1993–2017, https://doi.org/10.5194/hess-26-1993-2022, https://doi.org/10.5194/hess-26-1993-2022, 2022
Short summary
Short summary
Water within large water bodies is constantly moving. Consequently, water movement masks causal relationships that exist between rivers and lakes. Incorporating water movement into models of nutrient concentration allows us to predict concentrations at unobserved locations and at observed locations on days not sampled. Our modeling approach does this while accommodating nutrient concentration data from multiple sources and provides a way to experimentally define the impact of rivers on lakes.
Adrien Michel, Bettina Schaefli, Nander Wever, Harry Zekollari, Michael Lehning, and Hendrik Huwald
Hydrol. Earth Syst. Sci., 26, 1063–1087, https://doi.org/10.5194/hess-26-1063-2022, https://doi.org/10.5194/hess-26-1063-2022, 2022
Short summary
Short summary
This study presents an extensive study of climate change impacts on river temperature in Switzerland. Results show that, even for low-emission scenarios, water temperature increase will lead to adverse effects for both ecosystems and socio-economic sectors throughout the 21st century. For high-emission scenarios, the effect will worsen. This study also shows that water seasonal warming will be different between the Alpine regions and the lowlands. Finally, efficiency of models is assessed.
Md Feroz Islam, Paul P. Schot, Stefan C. Dekker, Jasper Griffioen, and Hans Middelkoop
Hydrol. Earth Syst. Sci., 26, 903–921, https://doi.org/10.5194/hess-26-903-2022, https://doi.org/10.5194/hess-26-903-2022, 2022
Short summary
Short summary
The potential of sedimentation in the lowest parts of polders (beels) through controlled flooding with dike breach (tidal river management – TRM) to counterbalance relative sea level rise (RSLR) in 234 beels of SW Bangladesh is determined in this study, using 2D models and multiple regression. Lower beels located closer to the sea have the highest potential. Operating TRM only during the monsoon season is sufficient to raise the land surface of most beels by more than 3 times the yearly RSLR.
Danlu Guo, Camille Minaudo, Anna Lintern, Ulrike Bende-Michl, Shuci Liu, Kefeng Zhang, and Clément Duvert
Hydrol. Earth Syst. Sci., 26, 1–16, https://doi.org/10.5194/hess-26-1-2022, https://doi.org/10.5194/hess-26-1-2022, 2022
Short summary
Short summary
We investigate the impact of baseflow contribution on concentration–flow (C–Q) relationships across the Australian continent. We developed a novel Bayesian hierarchical model for six water quality variables across 157 catchments that span five climate zones. For sediments and nutrients, the C–Q slope is generally steeper for catchments with a higher median and a greater variability of baseflow contribution, highlighting the key role of variable flow pathways in particulate and solute export.
Liguang Jiang, Silja Westphal Christensen, and Peter Bauer-Gottwein
Hydrol. Earth Syst. Sci., 25, 6359–6379, https://doi.org/10.5194/hess-25-6359-2021, https://doi.org/10.5194/hess-25-6359-2021, 2021
Short summary
Short summary
River roughness and geometry are essential to hydraulic river models. However, measurements of these quantities are not available in most rivers globally. Nevertheless, simultaneous calibration of channel geometric parameters and roughness is difficult as they compensate for each other. This study introduces an alternative approach of parameterization and calibration that reduces parameter correlations by combining cross-section geometry and roughness into a conveyance parameter.
Masoud Zaerpour, Shadi Hatami, Javad Sadri, and Ali Nazemi
Hydrol. Earth Syst. Sci., 25, 5193–5217, https://doi.org/10.5194/hess-25-5193-2021, https://doi.org/10.5194/hess-25-5193-2021, 2021
Short summary
Short summary
Streamflow regimes are changing globally particularly in cold regions. We develop a novel algorithm for detecting shifting streamflow regimes using changes in first and second moments of ensemble streamflow features. This algorithm is generic and can be used globally. To showcase its application, we assess alterations in Canadian natural streams from 1966 to 2010 to provide the first temporally consistent, pan-Canadian assessment of change in natural streamflow regimes, coast to coast to coast.
Samuel J. Sutanto and Henny A. J. Van Lanen
Hydrol. Earth Syst. Sci., 25, 3991–4023, https://doi.org/10.5194/hess-25-3991-2021, https://doi.org/10.5194/hess-25-3991-2021, 2021
Short summary
Short summary
This paper provides a comprehensive overview of the differences within streamflow droughts derived using different identification approaches, namely the variable threshold, fixed threshold, and the Standardized Streamflow Index, including an analysis of both historical drought and implications for forecasting. Our results clearly show that streamflow droughts derived from different approaches deviate from each other in terms of drought occurrence, timing, duration, and deficit volume.
Janie Masse-Dufresne, Florent Barbecot, Paul Baudron, and John Gibson
Hydrol. Earth Syst. Sci., 25, 3731–3757, https://doi.org/10.5194/hess-25-3731-2021, https://doi.org/10.5194/hess-25-3731-2021, 2021
Short summary
Short summary
A volume-dependent transient isotopic mass balance model was developed for an artificial lake in Canada, in a context where direct measurements of surface water fluxes are difficult. It revealed that floodwater inputs affected the dynamics of the lake in spring but also significantly influenced the long-term water balance due to temporary subsurface storage of floodwater. Such models are paramount for understanding the vulnerability of lakes to changes in groundwater quantity and quality.
Regula Muelchi, Ole Rössler, Jan Schwanbeck, Rolf Weingartner, and Olivia Martius
Hydrol. Earth Syst. Sci., 25, 3577–3594, https://doi.org/10.5194/hess-25-3577-2021, https://doi.org/10.5194/hess-25-3577-2021, 2021
Short summary
Short summary
This study analyses changes in magnitude, frequency, and seasonality of moderate low and high flows for 93 catchments in Switzerland. In lower-lying catchments (below 1500 m a.s.l.), moderate low-flow magnitude (frequency) will decrease (increase). In Alpine catchments (above 1500 m a.s.l.), moderate low-flow magnitude (frequency) will increase (decrease). Moderate high flows tend to occur more frequent, and their magnitude increases in most catchments except some Alpine catchments.
Regula Muelchi, Ole Rössler, Jan Schwanbeck, Rolf Weingartner, and Olivia Martius
Hydrol. Earth Syst. Sci., 25, 3071–3086, https://doi.org/10.5194/hess-25-3071-2021, https://doi.org/10.5194/hess-25-3071-2021, 2021
Short summary
Short summary
Runoff regimes in Switzerland will change significantly under climate change. Projected changes are strongly elevation dependent with earlier time of emergence and stronger changes in high-elevation catchments where snowmelt and glacier melt play an important role. The magnitude of change and the climate model agreement on the sign increase with increasing global mean temperatures and stronger emission scenarios. This amplification highlights the importance of climate change mitigation.
Moritz Feigl, Katharina Lebiedzinski, Mathew Herrnegger, and Karsten Schulz
Hydrol. Earth Syst. Sci., 25, 2951–2977, https://doi.org/10.5194/hess-25-2951-2021, https://doi.org/10.5194/hess-25-2951-2021, 2021
Short summary
Short summary
In this study we developed machine learning approaches for daily river water temperature prediction, using different data preprocessing methods, six model types, a range of different data inputs and 10 study catchments. By comparing to current state-of-the-art models, we could show a significant improvement of prediction performance of the tested approaches. Furthermore, we could gain insight into the relationships between model types, input data and predicted stream water temperature.
Cintia L. Ramón, Hugo N. Ulloa, Tomy Doda, Kraig B. Winters, and Damien Bouffard
Hydrol. Earth Syst. Sci., 25, 1813–1825, https://doi.org/10.5194/hess-25-1813-2021, https://doi.org/10.5194/hess-25-1813-2021, 2021
Short summary
Short summary
When solar radiation penetrates the frozen surface of lakes, shallower zones underneath warm faster than deep interior waters. This numerical study shows that the transport of excess heat to the lake interior depends on the lake circulation, affected by Earth's rotation, and controls the lake warming rates and the spatial distribution of the heat flux across the ice–water interface. This work contributes to the understanding of the circulation and thermal structure patterns of ice-covered lakes.
Robert Ladwig, Paul C. Hanson, Hilary A. Dugan, Cayelan C. Carey, Yu Zhang, Lele Shu, Christopher J. Duffy, and Kelly M. Cobourn
Hydrol. Earth Syst. Sci., 25, 1009–1032, https://doi.org/10.5194/hess-25-1009-2021, https://doi.org/10.5194/hess-25-1009-2021, 2021
Short summary
Short summary
Using a modeling framework applied to 37 years of dissolved oxygen time series data from Lake Mendota, we identified the timing and intensity of thermal energy stored in the lake water column, the lake's resilience to mixing, and surface primary production as the most important drivers of interannual dynamics of low oxygen concentrations at the lake bottom. Due to climate change, we expect an increase in the spatial and temporal extent of low oxygen concentrations in Lake Mendota.
Carlos Miranda Rodrigues, Madalena Moreira, Rita Cabral Guimarães, and Miguel Potes
Hydrol. Earth Syst. Sci., 24, 5973–5984, https://doi.org/10.5194/hess-24-5973-2020, https://doi.org/10.5194/hess-24-5973-2020, 2020
Short summary
Short summary
In Mediterranean environments, evaporation is a key component of reservoir water budgets. Prediction of surface evaporation becomes crucial for adequate reservoir water management. This study provides an applicable method for calculating evaporation based on pan measurements applied at Alqueva Reservoir (southern Portugal), one of the largest artificial lakes in Europe. Moreover, the methodology presented here could be applied to other Mediterranean reservoirs.
Carmelo Cammalleri, Gustavo Naumann, Lorenzo Mentaschi, Bernard Bisselink, Emiliano Gelati, Ad De Roo, and Luc Feyen
Hydrol. Earth Syst. Sci., 24, 5919–5935, https://doi.org/10.5194/hess-24-5919-2020, https://doi.org/10.5194/hess-24-5919-2020, 2020
Short summary
Short summary
Climate change is anticipated to alter the demand and supply of water at the earth's surface. This study shows how hydrological droughts will change across Europe with increasing global warming levels, showing that at 3 K global warming an additional 11 million people and 4.5 ×106 ha of agricultural land will be exposed to droughts every year, on average. These effects are mostly located in the Mediterranean and Atlantic regions of Europe.
Alex Zavarsky and Lars Duester
Hydrol. Earth Syst. Sci., 24, 5027–5041, https://doi.org/10.5194/hess-24-5027-2020, https://doi.org/10.5194/hess-24-5027-2020, 2020
Short summary
Short summary
River water temperature is an important parameter for water quality and an important variable for physical, chemical and biological processes. River water is also used as a cooling agent by power plants and production facilities. We study long-term trends in river water temperature and correlate them to meteorological influences and power production or economic indices.
Cheng-Wei Yu, Ben R. Hodges, and Frank Liu
Hydrol. Earth Syst. Sci., 24, 4001–4024, https://doi.org/10.5194/hess-24-4001-2020, https://doi.org/10.5194/hess-24-4001-2020, 2020
Short summary
Short summary
This study investigates the effects of bottom slope discontinuity on the stability of numerical solutions for the Saint-Venant equations. A new reference slope concept is proposed to ensure smooth source terms and eliminate potential numerical oscillations. It is shown that a simple algebraic transformation of channel geometry provides a smooth reference slope while preserving the correct cross-sectional flow area and the piezometric pressure gradient that drives the flow.
Ana I. Ayala, Simone Moras, and Donald C. Pierson
Hydrol. Earth Syst. Sci., 24, 3311–3330, https://doi.org/10.5194/hess-24-3311-2020, https://doi.org/10.5194/hess-24-3311-2020, 2020
Short summary
Short summary
The impacts of different levels of global warming on the thermal structure of Lake Erken are assessed. We used the General Ocean Turbulence Model (GOTM) to simulate water temperature driven by meteorological scenarios supplied by the Inter-Sectoral Impact Model Intercomparison Project (ISIMIP) and tested its ability at different frequencies. Then, daily ISIMIP meteorological scenarios were disaggregated and assessed for the effects of climate change on lake thermal structure.
Luca Ziliani, Nicola Surian, Gianluca Botter, and Luca Mao
Hydrol. Earth Syst. Sci., 24, 3229–3250, https://doi.org/10.5194/hess-24-3229-2020, https://doi.org/10.5194/hess-24-3229-2020, 2020
Short summary
Short summary
Although geomorphic recovery is a key issue in many rivers worldwide, controlled floods have been rarely designed using geomorphological criteria. An integrated approach is used to assess the effects of different controlled-flood scenarios in a strongly regulated river. None of the controlled-flood strategies provide significant morphological benefits. Nevertheless, this study represents a significant contribution for the management and restoration of highly disturbed rivers.
Benjamin M. Kraemer, Anton Seimon, Rita Adrian, and Peter B. McIntyre
Hydrol. Earth Syst. Sci., 24, 2593–2608, https://doi.org/10.5194/hess-24-2593-2020, https://doi.org/10.5194/hess-24-2593-2020, 2020
Short summary
Short summary
Lake levels go up and down due to natural variability in the climate. But the effects of natural variability on lake levels can sometimes be confused for the influence of humans. Here we used long-term data from 200 globally distributed lakes and an advanced statistical approach to show that the effects of natural variability on lake levels can be disentangled from other effects leading to better estimates of long-term changes that may be partially caused by humans.
Audrey Marescaux, Vincent Thieu, Nathalie Gypens, Marie Silvestre, and Josette Garnier
Hydrol. Earth Syst. Sci., 24, 2379–2398, https://doi.org/10.5194/hess-24-2379-2020, https://doi.org/10.5194/hess-24-2379-2020, 2020
Short summary
Short summary
Rivers have been recognized as an active part of the carbon cycle where transformations are associated with CO2 outgassing. To understand it, we propose a modeling approach with the biogeochemical model, pyNuts-Riverstrahler. We implemented it on the human-impacted Seine River. Sources of carbon to the river were characterized by field measurements in groundwater and in wastewater. Outgassing was the most important in streams, and peaks were simulated downstream of wastewater treatment effluent.
Danlu Guo, Anna Lintern, J. Angus Webb, Dongryeol Ryu, Ulrike Bende-Michl, Shuci Liu, and Andrew William Western
Hydrol. Earth Syst. Sci., 24, 827–847, https://doi.org/10.5194/hess-24-827-2020, https://doi.org/10.5194/hess-24-827-2020, 2020
Short summary
Short summary
This study developed predictive models to represent the spatial and temporal variation of stream water quality across Victoria, Australia. The model structures were informed by a data-driven approach, which identified the key controls of water quality variations from long-term records. These models are helpful to identify likely future changes in water quality and, in turn, provide critical information for developing management strategies to improve stream water quality.
Vo Quoc Thanh, Dano Roelvink, Mick van der Wegen, Johan Reyns, Herman Kernkamp, Giap Van Vinh, and Vo Thi Phuong Linh
Hydrol. Earth Syst. Sci., 24, 189–212, https://doi.org/10.5194/hess-24-189-2020, https://doi.org/10.5194/hess-24-189-2020, 2020
Short summary
Short summary
The Vietnamese Mekong Delta (VMD) is a rice bowl of not only Vietnam, but also the world; agriculture is the main source of livelihood in the delta. The VMD is facing threats related to water management and hydraulic structures. Dykes are built to protect agricultural crops in the floodplains and may influence water regimes downstream in the VMD. If the VMD floodplains are completely protected by dykes, yearly mean water levels could increase by 3 cm (at Can Tho) and 1.5 cm (at My Thuan).
Martin Mergili, Shiva P. Pudasaini, Adam Emmer, Jan-Thomas Fischer, Alejo Cochachin, and Holger Frey
Hydrol. Earth Syst. Sci., 24, 93–114, https://doi.org/10.5194/hess-24-93-2020, https://doi.org/10.5194/hess-24-93-2020, 2020
Short summary
Short summary
In 1941, the glacial lagoon Lake Palcacocha in the Cordillera Blanca (Peru) drained suddenly. The resulting outburst flood/debris flow consumed another lake and had a disastrous impact on the town of Huaraz 23 km downstream. We reconstuct this event through a numerical model to learn about the possibility of prediction of similar processes in the future. Remaining challenges consist of the complex process interactions and the lack of experience due to the rare occurrence of such process chains.
Simone Moras, Ana I. Ayala, and Don C. Pierson
Hydrol. Earth Syst. Sci., 23, 5001–5016, https://doi.org/10.5194/hess-23-5001-2019, https://doi.org/10.5194/hess-23-5001-2019, 2019
Short summary
Short summary
We used a hydrodynamic model to reconstruct daily historical water temperature of Lake Erken (Sweden) between 1961 and 2017 to demonstrate the ongoing effect of climate change on lake thermal conditions. The results show that the lake has warmed most rapidly in the last 30 years and that it is now subject to a longer and more stable stratification. The methods used here to reconstruct historical water temperature records can be easily extended to other lakes.
Qunhui Zhang, Jiming Jin, Xiaochun Wang, Phaedra Budy, Nick Barrett, and Sarah E. Null
Hydrol. Earth Syst. Sci., 23, 4969–4982, https://doi.org/10.5194/hess-23-4969-2019, https://doi.org/10.5194/hess-23-4969-2019, 2019
Short summary
Short summary
We improved lake mixing process simulations by applying a vertical mixing scheme, K profile parameterization (KPP), in the Community Land Model (CLM) version 4.5, developed by the National Center for Atmospheric Research. The current vertical mixing scheme in CLM requires an arbitrarily enlarged eddy diffusivity to enhance water mixing. The coupled CLM-KPP considers a boundary layer for eddy development. The improved lake model provides an important tool for lake hydrology and ecosystem studies.
Margarita Choulga, Ekaterina Kourzeneva, Gianpaolo Balsamo, Souhail Boussetta, and Nils Wedi
Hydrol. Earth Syst. Sci., 23, 4051–4076, https://doi.org/10.5194/hess-23-4051-2019, https://doi.org/10.5194/hess-23-4051-2019, 2019
Short summary
Short summary
Lakes influence weather and climate of regions, especially if several of them are located close by. Just by using upgraded lake depths, based on new or more recent measurements and geological methods of depth estimation, errors of lake surface water forecasts produced by the European Centre for Medium-Range Weather Forecasts became 12–20 % lower compared with observations for 27 lakes collected by the Finnish Environment Institute. For ice-off date forecasts errors changed insignificantly.
Jérémy Lepesqueur, Renaud Hostache, Núria Martínez-Carreras, Emmanuelle Montargès-Pelletier, and Christophe Hissler
Hydrol. Earth Syst. Sci., 23, 3901–3915, https://doi.org/10.5194/hess-23-3901-2019, https://doi.org/10.5194/hess-23-3901-2019, 2019
Short summary
Short summary
This article evaluates the influence of sediment representation in a sediment transport model. A short-term simulation is used to assess how far changing the sediment characteristics in the modelling experiment changes riverbed evolution and sediment redistribution during a small flood event. The study shows in particular that representing sediment with extended grain-size and grain-density distributions allows for improving model accuracy and performances.
Annie Visser-Quinn, Lindsay Beevers, and Sandhya Patidar
Hydrol. Earth Syst. Sci., 23, 3279–3303, https://doi.org/10.5194/hess-23-3279-2019, https://doi.org/10.5194/hess-23-3279-2019, 2019
Short summary
Short summary
The ecological impact of changes in river flow may be explored through the simulation of ecologically relevant flow indicators. Traditional approaches to model parameterization are not well-suited for this. To this end, this paper considers the ability of a
modified covariance approach, applied to five hydrologically diverse catchments. An overall improvement in consistency is observed, whilst timing and rate of change represent the best and worst replicated indicators respectively.
Jeffrey J. Richardson, Christian E. Torgersen, and L. Monika Moskal
Hydrol. Earth Syst. Sci., 23, 2813–2822, https://doi.org/10.5194/hess-23-2813-2019, https://doi.org/10.5194/hess-23-2813-2019, 2019
Short summary
Short summary
High stream temperatures can be detrimental to the survival of aquatic species such as endangered salmon. Stream temperatures can be reduced by shade provided by trees in riparian areas. Two lidar-based methods were effective at assessing stream shading. These methods can be used in place of expensive field measurements.
Dongsheng Su, Xiuqing Hu, Lijuan Wen, Shihua Lyu, Xiaoqing Gao, Lin Zhao, Zhaoguo Li, Juan Du, and Georgiy Kirillin
Hydrol. Earth Syst. Sci., 23, 2093–2109, https://doi.org/10.5194/hess-23-2093-2019, https://doi.org/10.5194/hess-23-2093-2019, 2019
Short summary
Short summary
In this study, freshwater lake model simulation results, verified by satellite and buoy observation data, were used to quantify recent climate change effects on the thermal regime of the largest lake in China. Results indicate that the FLake model can reproduce the lake thermal pattern nicely. The lake surface is warming, while the lake bottom has no significant trend. Climate change also caused an earlier ice-off and later ice-on, leading to an obvious change in the energy balance of the lake.
Chloé Poulin, Bruno Hamelin, Christine Vallet-Coulomb, Guinbe Amngar, Bichara Loukman, Jean-François Cretaux, Jean-Claude Doumnang, Abdallah Mahamat Nour, Guillemette Menot, Florence Sylvestre, and Pierre Deschamps
Hydrol. Earth Syst. Sci., 23, 1705–1724, https://doi.org/10.5194/hess-23-1705-2019, https://doi.org/10.5194/hess-23-1705-2019, 2019
Short summary
Short summary
This study investigates the water budget of two intertropical lake systems in the absence of long-term hydrological monitoring. By coupling dry season isotopic data with satellite imagery, we were able to provide quantitative constrains on the hydrological balance and show that these two lake systems can be considered miniature analogs of Lake Chad, making them important targets in the future setup of any large-scale program on the hydro-climatic evolution in the Sahel region.
Tom Shatwell, Wim Thiery, and Georgiy Kirillin
Hydrol. Earth Syst. Sci., 23, 1533–1551, https://doi.org/10.5194/hess-23-1533-2019, https://doi.org/10.5194/hess-23-1533-2019, 2019
Short summary
Short summary
We used models to project future temperature and mixing in temperate lakes. Lakes will probably warm faster in winter than in summer, making ice less frequent and altering mixing. We found that the layers that form seasonally in lakes (ice, stratification) and water clarity affect how lakes accumulate heat. Seasonal changes in climate were thus important. This helps us better understand how different lake types respond to warming and which physical changes to expect in the future.
Ben R. Hodges
Hydrol. Earth Syst. Sci., 23, 1281–1304, https://doi.org/10.5194/hess-23-1281-2019, https://doi.org/10.5194/hess-23-1281-2019, 2019
Short summary
Short summary
A new derivation of the equations for one-dimensional open-channel flow in rivers and storm drainage systems has been developed. The new approach solves some long-standing problems for obtaining well-behaved solutions with conservation forms of the equations. This research was motivated by the need for highly accurate models of large-scale river networks and the storm drainage systems in megacities. Such models are difficult to create with existing equation forms.
Ramiro Pillco Zolá, Lars Bengtsson, Ronny Berndtsson, Belen Martí-Cardona, Frederic Satgé, Franck Timouk, Marie-Paule Bonnet, Luis Mollericon, Cesar Gamarra, and José Pasapera
Hydrol. Earth Syst. Sci., 23, 657–668, https://doi.org/10.5194/hess-23-657-2019, https://doi.org/10.5194/hess-23-657-2019, 2019
Short summary
Short summary
The evaporation was computed at a daily time step and compared with the estimated evaporation using mean monthly meteorological observations. We found that the most reliable method of determining the annual lake evaporation is using the heat balance approach.
Daniel J. Isaak, Charles H. Luce, Gwynne L. Chandler, Dona L. Horan, and Sherry P. Wollrab
Hydrol. Earth Syst. Sci., 22, 6225–6240, https://doi.org/10.5194/hess-22-6225-2018, https://doi.org/10.5194/hess-22-6225-2018, 2018
Short summary
Short summary
Description of thermal regimes in flowing waters is key to understanding physical processes and improving bioassessments, but has been limited by sparse data sets. Using a large annual temperature data set from a mountainous area of the western U.S., we explored thermal regimes using principle component analysis. A small number of summary metrics adequately represented most of the variation in this data set given strong temporal coherence among sites.
Inne Vanderkelen, Nicole P. M. van Lipzig, and Wim Thiery
Hydrol. Earth Syst. Sci., 22, 5509–5525, https://doi.org/10.5194/hess-22-5509-2018, https://doi.org/10.5194/hess-22-5509-2018, 2018
Short summary
Short summary
Lake Victoria is the largest lake in Africa and one of the two major sources of the Nile river. The water level of Lake Victoria is determined by its water balance, consisting of lake precipitation and evaporation, inflow from rivers and lake outflow, controlled by two hydropower dams. Here, we present a water balance model for Lake Victoria, which closely represents the observed lake levels. The model results highlight the sensitivity of the lake level to human operations at the dam.
Inne Vanderkelen, Nicole P. M. van Lipzig, and Wim Thiery
Hydrol. Earth Syst. Sci., 22, 5527–5549, https://doi.org/10.5194/hess-22-5527-2018, https://doi.org/10.5194/hess-22-5527-2018, 2018
Short summary
Short summary
Lake Victoria is the second largest freshwater lake in the world and one of the major sources of the Nile River, which is controlled by two hydropower dams. In this paper we estimate the potential consequences of climate change for future water level fluctuations of Lake Victoria. Our results reveal that the operating strategies at the dam are the main controlling factors of future lake levels and that regional climate simulations used in the projections encompass large uncertainties.
Cited articles
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I. J., Harp, A., Irving, G., Isard, M., Jia, Y., Józefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D. G., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P. A., Vanhoucke, V., Vasudevan, V., Viégas, F. B., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., and Zheng, X.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems, abs/1603.0, https://www.tensorflow.org/ (last access: 20 November 2021), 2016.
Anderson, S.: andersonsam/cnn_lstm_era: First release (Version v1.0.0), Zenodo [code], https://doi.org/10.5281/ZENODO.5181175, 2021.
Anderson, S. and Radić, V.: Identification of local water resource vulnerability to rapid deglaciation in Alberta, Nat. Clim. Change, 10, 933–938, https://doi.org/10.1038/s41558-020-0863-4, 2020.
Arras, L., Arjona-Medina, J., Widrich, M., Montavon, G., Gillhofer, M., Müller, K.-R., Hochreiter, S., and Samek, W.: Explaining and Interpreting LSTMs BT – Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, edited by: Samek, W., Montavon, G., Vedaldi, A., Hansen, L. K., and Müller, K.-R., Springer International Publishing, Cham, 211–238, https://doi.org/10.1007/978-3-030-28954-6_11, 2019.
Assem, H., Ghariba, S., Makrai, G., Johnston, P., Gill, L., and Pilla, F.: Urban Water Flow and Water Level Prediction Based on Deep Learning, in: ECML PKDD 2017: Machine Learning and Knowledge Discovery in Databases, Springer, Cham, 317–329, https://doi.org/10.1007/978-3-319-71273-4_26, 2017.
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., and Samek, W.: On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation, PLoS ONE, 10, e0130140, https://doi.org/10.1371/journal.pone.0130140, 2015.
Bahremand, A.: HESS Opinions: Advocating process modeling and de-emphasizing parameter estimation, Hydrol. Earth Syst. Sci., 20, 1433–1445, https://doi.org/10.5194/hess-20-1433-2016, 2016.
Bengio, Y., Simard, P., and Frasconi, P.: Learning Long-term Dependencies with Gradient Descent is Difficult, IEEE T. Neural Netw., 5, 157–166, https://doi.org/10.1109/72.279181, 1994.
Bengio, Y., Courville, A., and Vincent, P.: Representation Learning: A Review and New Perspectives, IEEE T. Pattern Anal. Mach. Intel., 35, 1798–1828, https://doi.org/10.1109/TPAMI.2013.50, 2013.
Bergen, K. J., Johnson, P. A., de Hoop, M. V., and Beroza, G. C.: Machine learning for data-driven discovery in solid Earth geoscience, Science, 363,
6433, https://doi.org/10.1126/science.aau0323, 2019.
Bergström, S.: Development and application of a conceptual runoff model for Scandinavian catchments, SMHI Report RHO 7, Norrköping, 134 pp., URN urn:nbn:se:smhi:diva-5738, OAI: oai:DiVA.org:smhi-5738, DiVA, id: diva2:1456191, 1976.
Bingeman, A. K., Kouwen, N., and Soulis, E. D.: Validation of the Hydrological Processes in a Hydrological Model, J. Hydorl. Eng., 11, 451–463, https://doi.org/10.1061/(ASCE)1084-0699(2006)11:5(451), 2006.
Braithwaite, R. J.: Positive degree-day factors for ablation on the Greenland ice sheet studied by energy-balance modelling, J. Glaciol., 41, 153–160, https://doi.org/10.1017/S0022143000017846, 1995.
Burn, D. H., Abdul Aziz, O. I., and Pietroniro, A.: A Comparison of Trends in Hydrological Variables for Two Watersheds in the Mackenzie River Basin, Can. Water Resour. J./Revue canadienne des ressources hydriques, 29, 283–298, https://doi.org/10.4296/cwrj283, 2004.
Cannon, A. J.: Quantile regression neural networks: Implementation in R and application to precipitation downscaling, Comput. Geosci., 37, 1277–1284, https://doi.org/10.1016/j.cageo.2010.07.005, 2011.
Cannon, A. J.: Non-crossing nonlinear regression quantiles by monotone composite quantile regression neural network, with application to rainfall extremes, Stoch. Environ. Res. Risk Assess., 32, 3207–3225, https://doi.org/10.1007/s00477-018-1573-6, 2018.
Chakravarti, I. M., Laha, G. G., and Roy, J.: Handbook of Methods of Applied Statistics, vol. I, John Wiley and Sons, Hoboken, 392–394, 1967.
Chernos, M., MacDonald, R., and Craig, J.: Efficient Semi-Distributed Hydrological Modelling Workflow for Simulating Streamflow and Characterizing Hydrologic Processes, https://doi.org/10.22230/jwsm.2017v1n1a3, 2017.
Chernos, M., MacDonald, R. J., Nemeth, M. W., and Craig, J. R.: Current and future projections of glacier contribution to streamflow in the upper Athabasca River Basin, Can. Water Resour. J./Revue canadienne des ressources hydriques, 45, 324–344, https://doi.org/10.1080/07011784.2020.1815587, 2020.
Chollet, F.: Keras, GitHub, https://github.com/fchollet/keras (last access: 20 November 2021), 2015.
Clarke, G. K. C., Jarosch, A. H., Anslow, F. S., Radić, V., and Menounos, B.: Projected deglaciation of western Canada in the twenty-first century, Nat. Geosci., 8, 372, https://doi.org/10.1038/ngeo2407, 2015.
Comeau, L. E. L., Pietroniro, A., and Demuth, M. N.: Glacier contribution to the North and South Saskatchewan Rivers, Hydro. Process., 23, 2640–2653, https://doi.org/10.1002/hyp.7409, 2009.
Donahue, J., Hendricks, L. A., Rohrbach, M., Venugopalan, S., Guadarrama, S., Saenko, K., and Darrell, T.: Long-Term Recurrent Convolutional Networks for Visual Recognition and Description, IEEE T. Pattern Anal. Mach. Intel., 39, 677–691, https://doi.org/10.1109/TPAMI.2016.2599174, 2017.
Eaton, B. and Moore, R. D.: Regional Hydrology, in: Compendium of forest hydrology and geomorphology in British Columbia, edited by: Pike, R. G., Redding, T. E., Moore, R. D., Winkler, R. D., and Bladon, K. D., B. C. Ministry of Forests and Range, Victoria, British Columbia, 85–110, https://www.for.gov.bc.ca/hfd/pubs/docs/lmh/Lmh66.htm (last access: 10 February 2022), 2010.
Ellenson, A. N., Simmons, J. A., Wilson, G. W., Hesser, T. J., and Splinter, K. D.: Beach State Recognition Using Argus Imagery and Convolutional Neural Networks, Remote Sens., 12, 3953, https://doi.org/10.3390/rs12233953, 2020.
Environment and Climate Change Canada: National hydrometric network basin polygons, https://open.canada.ca/data/en/dataset/0c121878-ac23-46f5-95df-eb9960753375 (last access: 19 April 2021), 2016.
Essou, G. R. C., Sabarly, F., Lucas-Picher, P., Brissette, F., and Poulin, A.: Can Precipitation and Temperature from Meteorological Reanalyses Be Used for Hydrological Modeling?, J. Hydrometeorol., 17, 1929–1950, https://doi.org/10.1175/JHM-D-15-0138.1, 2016.
Eum, H.-I., Dibike, Y., and Prowse, T.: Climate-induced alteration of hydrologic indicators in the Athabasca River Basin, Alberta, Canada, J. Hydrol., 544, 327–342, https://doi.org/10.1016/j.jhydrol.2016.11.034, 2017.
Farr, T. G., Rosen, P. A., Caro, E., Crippen, R., Duren, R., Hensley, S., Kobrick, M., Paller, M., Rodriguez, E., Roth, L., Seal, D., Shaffer, S., Shimada, J., Umland, J., Werner, M., Oskin, M., Burbank, D., and Alsdorf, D.: The Shuttle Radar Topography Mission, Rev. Geophys., 45, 2005RG000183, https://doi.org/10.1029/2005RG000183, 2007.
Finsterwalder, S. and Schunk, H.: Der suldenferner, Zeitschrift des Deutschen und Osterreichischen Alpenvereins, 18, 72–89, 1887.
Fleming, S. W. and Whitfield, P. H.: Spatiotemporal mapping of ENSO and PDO surface meteorological signals in British Columbia, Yukon, and southeast Alaska, Atmos.-Ocean, 48, 122–131, https://doi.org/10.3137/AO1107.2010, 2010.
Fleming, S. W., Bourdin, D. R., Campbell, D., Stull, R. B., and Gardner, T.: Development and Operational Testing of a Super-Ensemble Artificial Intelligence Flood-Forecast Model for a Pacific Northwest River, J. Am. Water Resour. Assoc., 51, 502–512, https://doi.org/10.1111/jawr.12259, 2015.
Fleming, S. W., Garen, D. C., Goodbody, A. G., McCarthy, C. S., and Landers, L. C.: Assessing the new Natural Resources Conservation Service water supply forecast model for the American West: A challenging test of explainable, automated, ensemble artificial intelligence, J. Hydrol., 602, 126782, https://doi.org/10.1016/j.jhydrol.2021.126782, 2021a.
Fleming, S. W., Vesselinov, V. V., and Goodbody, A. G.: Augmenting geophysical interpretation of data-driven operational water supply forecast modeling for a western US river using a hybrid machine learning approach, J. Hydrol., 597, 126327, https://doi.org/10.1016/j.jhydrol.2021.126327, 2021b.
Fountain, A. G. and Tangborn, W. V.: The Effect of Glaciers on Streamflow Variations, Water Resour. Res., 21, 579–586, https://doi.org/10.1029/WR021i004p00579, 1985.
Freeze, R. A. and Harlan, R. L.: Blueprint for a physically-based, digitally-simulated hydrologic response model, J. Hydrol., 9, 237–258, https://doi.org/10.1016/0022-1694(69)90020-1, 1969.
Gagne II, D. J., Haupt, S. E., Nychka, D. W., and Thompson, G.: Interpretable Deep Learning for Spatial Analysis of Severe Hailstorms, Mon. Weather Rev., 147, 2827–2845, https://doi.org/10.1175/MWR-D-18-0316.1, 2019.
Gauch, M. and Lin, J.: A Data Scientist's Guide to Streamflow Prediction, ArXiv: preprint, abs/2006.12975 https://arxiv.org/abs/2006.12975 (last access: 10 February 2022), 2020.
Gauch, M., Kratzert, F., Klotz, D., Nearing, G., Lin, J., and Hochreiter, S.: Rainfall–runoff prediction at multiple timescales with a single Long Short-Term Memory network, Hydrol. Earth Syst. Sci., 25, 2045–2062, https://doi.org/10.5194/hess-25-2045-2021, 2021.
Goodfellow, I., Bengio, Y., and Courville, A.: Deep Learning, MIT Press, ISBN 0262035618, https://www.deeplearningbook.org/ (last access: 20 November 2021), 2016.
Government of Canada: Areas of Non-Contributing Drainage within Total Gross Drainage Areas of the AAFC Watersheds Project – 2013, https://open.canada.ca/data/en/dataset/adb2e613-f193-42e2-987e-2cc9d90d2b7a
(last access: 11 May 2021), 2020.
Halverson, M. J. and Fleming, S. W.: Complex network theory, streamflow, and hydrometric monitoring system design, Hydrol. Earth Syst. Sci., 19, 3301–3318, https://doi.org/10.5194/hess-19-3301-2015, 2015.
Ham, Y.-G., Kim, J.-H., and Luo, J.-J.: Deep learning for multi-year ENSO forecasts, Nature, 573, 568–572, https://doi.org/10.1038/s41586-019-1559-7, 2019.
Hastie, T., Tibshirani, R., and Friedman, J. H.: The elements of statistical learning: data mining, inference, and prediction, 2nd Edn., Springer, New York, https://doi.org/10.1007/978-0-387-84858-7, 2009.
Hayashi, M., van der Kamp, G., and Rosenberry, D. O.: Hydrology of Prairie Wetlands: Understanding the Integrated Surface-Water and Groundwater Processes, Wetlands, 36, 237–254, https://doi.org/10.1007/s13157-016-0797-9, 2016.
Hedstrom, N. R. and Pomeroy, J. W.: Measurements and modelling of snow interception in the boreal forest, Hydrol. Process., 12, 1611–1625, https://doi.org/10.1002/(SICI)1099-1085(199808/09)12:10/11<1611::AID-HYP684>3.0.CO;2-4, 1998.
Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Horányi, A., Muñoz-Sabater, J., Nicolas, J., Peubey, C., Radu, R., Schepers, D., Simmons, A., Soci, C., Abdalla, S., Abellan, X., Balsamo, G., Bechtold, P., Biavati, G., Bidlot, J., Bonavita, M., de Chiara, G., Dahlgren, P., Dee, D., Diamantakis, M., Dragani, R., Flemming, J., Forbes, R., Fuentes, M., Geer, A., Haimberger, L., Healy, S., Hogan, R. J., Hólm, E., Janisková, M., Keeley, S., Laloyaux, P., Lopez, P., Lupu, C., Radnoti, G., de Rosnay, P., Rozum, I., Vamborg, F., Villaume, S., and Thépaut, J.-N.: The ERA5 global reanalysis, Q. J. Roy. Meteorol. Soc., 146, 1999–2049, https://doi.org/10.1002/qj.3803, 2020.
Hochreiter, S. and Schmidhuber, J.: Long Short-Term Memory, Neural Comput., 9, 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735, 1997.
Hock, R.: Temperature index melt modelling in mountain areas, J. Hydrol., 282, 104–115, https://doi.org/10.1016/S0022-1694(03)00257-9, 2003.
Hoinkesand, H. and Steinacker, R.: Hydrometeorological implications of the mass balance of Hintereisferner, 1952–53 to 1968–69, in: Snow and Ice-Symposium-Neiges et Glaces, Proceedings of the Moscow Symposium, August 1971: Actes du Colloque de Moscou, aoüt 1971,: IAHS-AISH Publ. No. 104, 144–149, https://www.researchgate.net/publication/265083119_Hydrometeorological_implications_of_the_mass_balance_of_Hintereisferner_1952-53_to_1968-69
(last access: 10 February 2022), 1975.
Hsieh, W. W. and Tang, B.: Interannual variability of accumulated snow in the Columbia Basin, British Columbia, Water Resour. Res., 37, 1753–1759, https://doi.org/10.1029/2000WR900410, 2001.
Hsieh, W. W., Yuval, Li, J., Shabbar, A., and Smith, S.: Seasonal Prediction with Error Estimation of Columbia River Streamflow in British Columbia, J. Water Resour. Pl. Manage., 129, 146–149, https://doi.org/10.1061/(asce)0733-9496(2003)129:2(146), 2003.
Hsu, K., Gupta, H. V., and Sorooshian, S.: Artificial Neural Network Modeling of the Rainfall-Runoff Process, Water Resour. Res., 31, 2517–2530, https://doi.org/10.1029/95WR01955, 1995.
Hussain, D., Hussain, T., Khan, A. A., Naqvi, S. A. A., and Jamil, A.: A deep learning approach for hydrological time-series prediction: A case study of Gilgit river basin, Earth Sci. Inform., 13, 915–927, https://doi.org/10.1007/s12145-020-00477-2, 2020.
Jost, G., Moore, R. D., Menounos, B., and Wheate, R.: Quantifying the contribution of glacier runoff to streamflow in the upper Columbia River Basin, Canada, Hydrol. Earth Syst. Sci., 16, 849–860, https://doi.org/10.5194/hess-16-849-2012, 2012.
Karpathy, A., Johnson, J., and Li, F.-F.: Visualizing and Understanding Recurrent Networks, arXiv: preprint, abs/1506.0, 1506.02078,
https://arxiv.org/abs/1506.02078v2 (last access: 10 February 2022), 2015.
Karpatne, A., Ebert-Uphoff, I., Ravela, S., Babaie, H. A., and Kumar, V.: Machine Learning for the Geosciences: Challenges and Opportunities, IEEE T. Knowledge Data Eng., 31, 1544–1554, https://doi.org/10.1109/TKDE.2018.2861006, 2019.
Kingma, D. P. and Ba, J.: Adam: A Method for Stochastic Optimization, arXiv: preprint, abs/1412.6980, https://arxiv.org/abs/1412.6980 (last access: 10 February 2022), 2017.
Kiros, R., Salakhutdinov, R., and Zemel, R. S.: Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models, arXiv: preprint, abs/1411.2, https://arxiv.org/abs/1411.2539 (last access: 10 February 2022), 2014.
Kratzert, F., Klotz, D., Brenner, C., Schulz, K., and Herrnegger, M.: Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks, Hydrol. Earth Syst. Sci., 22, 6005–6022, https://doi.org/10.5194/hess-22-6005-2018, 2018.
Kratzert, F., Klotz, D., Herrnegger, M., Sampson, A. K., Hochreiter, S., and Nearing, G. S.: Toward Improved Predictions in Ungauged Basins: Exploiting the Power of Machine Learning, Water Resour. Res., 55, 11344–11354, https://doi.org/10.1029/2019WR026065, 2019a.
Kratzert, F., Klotz, D., Shalev, G., Klambauer, G., Hochreiter, S., and Nearing, G.: Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets, Hydrol. Earth Syst. Sci., 23, 5089–5110, https://doi.org/10.5194/hess-23-5089-2019, 2019b.
Krizhevsky, A., Sutskever, I., and Hinton, G. E.: ImageNet Classification with Deep Convolutional Neural Networks, in: Advances in Neural Information Processing Systems 25, edited by: Pereira, F., Burges, C. J. C., Bottou, L., and Weinberger, K. Q., Curran Associates, Inc., 1097–1105, https://papers.nips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html (last acces: 10 February 2022), 2012.
LaBaugh, J. W., Winter, T. C., and Rosenberry, D. O.: Hydrologic functions of prairie wetlands, Great Plains Res., 8, 17–37, 1998.
LeCun, Y., Boser, B., Denker, J. S., Howard, R. E., Habbard, W., Jackel, L. D., and Henderson, D.: Handwritten Digit Recognition with a Back-Propagation Network, in: Advances in Neural Information Processing Systems, Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 396–404, https://proceedings.neurips.cc/paper/1989/file/53c3bce66e43be4f209556518c2fcb54-Paper.pdf (last access: 10 February 2022), 1990.
Lima, A. R., Cannon, A. J., and Hsieh, W. W.: Forecasting daily streamflow using online sequential extreme learning machines, J. Hydrol., 537, 431–443, https://doi.org/10.1016/j.jhydrol.2016.03.017, 2016.
Lima, A. R., Hsieh, W. W., and Cannon, A. J.: Variable complexity online sequential extreme learning machine, with applications to streamflow prediction, J. Hydrol., 555, 983–994, https://doi.org/10.1016/j.jhydrol.2017.10.037, 2017.
Maier, H. R. and Dandy, G. C.: The Use of Artificial Neural Networks for the Prediction of Water Quality Parameters, Water Resour. Res., 32, 1013–1022, https://doi.org/10.1029/96WR03529, 1996.
Maier, H. R. and Dandy, G. C.: Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications, Environ. Model. Softw., 15, 101–124, https://doi.org/10.1016/S1364-8152(99)00007-9, 2000.
Maier, H. R., Jain, A., Dandy, G. C., and Sudheer, K. P.: Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions, Environ. Model. Softw., 25, 891–909, https://doi.org/10.1016/j.envsoft.2010.02.003, 2010.
Marçais, J. and de Dreuzy, J.-R.: Prospective Interest of Deep Learning for Hydrological Inference, Groundwater, 55, 688–692, https://doi.org/10.1111/gwat.12557, 2017.
Marsh, C. B., Pomeroy, J. W., and Wheater, H. S.: The Canadian Hydrological Model (CHM) v1.0: a multi-scale, multi-extent, variable-complexity hydrological model – design and overview, Geosci. Model Dev., 13, 225–247, https://doi.org/10.5194/gmd-13-225-2020, 2020.
Marshall, S. J., White, E. C., Demuth, M. N., Bolch, T., Wheate, R., Menounos, B., Beedle, M. J., and Shea, J. M.: Glacier Water Resources on the Eastern Slopes of the Canadian Rocky Mountains, Can. Water Resour. J./Revue canadienne des ressources hydriques , 36, 109–134, https://doi.org/10.4296/cwrj3602823, 2011.
McGovern, A., Lagerquist, R., John Gagne, D., Jergensen, G. E., Elmore, K. L., Homeyer, C. R., and Smith, T.: Making the Black Box More Transparent: Understanding the Physical Implications of Machine Learning, B. Am. Meteorol. Soc., 100, 2175–2199, https://doi.org/10.1175/BAMS-D-18-0195.1, 2019.
Meier, M. F. and Tangborn, W. V.: Distinctive characteristics of glacier runoff, US Geological Survey Professional Paper 424-B, US Geological Survey, 14–16, 1961.
Mengistu, S. G. and Spence, C.: Testing the ability of a semidistributed hydrological model to simulate contributing area, Water Resour. Res., 52, 4399–4415, https://doi.org/10.1002/2016WR018760, 2016.
Met Office: Cartopy: a cartographic python library with a matplotlib interface, Zenodo, https://doi.org/10.5281/zenodo.1182735, 2018.
Milly, P. C. D., Betancourt, J., Falkenmark, M., Hirsch, R. M., Kundzewicz, Z. W., Lettenmaier, D. P., and Stouffer, R. J.: Stationarity Is Dead: Whither Water Management?, Science, 319, 573–574, https://doi.org/10.1126/science.1151915, 2008.
Moore, R. D., Fleming, S. W., Menounos, B., Wheate, R., Fountain, A., Stahl, K., Holm, K., and Jakob, M.: Glacier change in western North America: influences on hydrology, geomorphic hazards and water quality, Hydrol. Process., 23, 42–61, https://doi.org/10.1002/hyp.7162, 2009.
Moore, R. D., Spittlehouse, D. L., Whitfield, P. H., and Stahl, K.: Weather and Climate, in: Compendium of forest hydrology and geomorphology in British Columbia, edited by: Pike, R. G., Redding, T. E., Moore, R. D., Winkler, R. D., and Bladon, K. D., B. C. Ministry of Forests and Range, Victoria, British Columbia, 47–84, https://www.for.gov.bc.ca/hfd/pubs/docs/lmh/Lmh66.htm (last access: 10 February 2022), 2010.
Muhammad, A., Evenson, G. R., Stadnyk, T. A., Boluwade, A., Jha, S. K., and Coulibaly, P.: Impact of model structure on the accuracy of hydrological modeling of a Canadian Prairie watershed, J. Hydrol.: Reg. Stud., 21, 40–56, https://doi.org/10.1016/j.ejrh.2018.11.005, 2019.
Nash, J. E. and Sutcliffe, J. V: River flow forecasting through conceptual models part I – A discussion of principles, J. Hydrol., 10, 282–290, https://doi.org/10.1016/0022-1694(70)90255-6, 1970.
Naz, B. S., Frans, C. D., Clarke, G. K. C., Burns, P., and Lettenmaier, D. P.: Modeling the effect of glacier recession on streamflow response using a coupled glacio-hydrological model, Hydrol. Earth Syst. Sci., 18, 787–802, https://doi.org/10.5194/hess-18-787-2014, 2014.
Odon, P., West, G., and Stull, R.: Evaluation of Reanalyses over British Columbia. Part I: Daily and Extreme 2 m Temperature, J. Appl. Meteorol. Clim., 57, 2091–2112, https://doi.org/10.1175/JAMC-D-18-0058.1, 2018.
Odon, P., West, G., and Stull, R.: Evaluation of Reanalyses over British Columbia. Part II: Daily and Extreme Precipitation, J. Appl. Meteorol. Clim., 58, 291–315, https://doi.org/10.1175/JAMC-D-18-0188.1, 2019.
Painter, S. L., Coon, E. T., Atchley, A. L., Berndt, M., Garimella, R., Moulton, J. D., Svyatskiy, D., and Wilson, C. J.: Integrated surface/subsurface permafrost thermal hydrology: Model formulation and proof-of-concept simulations, Water Resour. Res., 52, 6062–6077, https://doi.org/10.1002/2015WR018427, 2016.
Penman, H. L. and Keen, B. A.: Natural evaporation from open water, bare soil and grass, P. Roy. Soc. A, 193, 120–145, https://doi.org/10.1098/rspa.1948.0037, 1948.
Petsiuk, V., Das, A., and Saenko, K.: RISE: Randomized Input Sampling for Explanation of Black-box Models, arXiv: preprint, 1806.07421,
https://arxiv.org/abs/1806.07421 (last access: 10 February 2022), 2018.
Pomeroy, J. W. and Gray, D. M.: Saltation of snow, Water Resour. Res., 26, 1583–1594, https://doi.org/10.1029/WR026i007p01583, 1990.
Pomeroy, J. W. and Li, L.: Prairie and arctic areal snow cover mass balance using a blowing snow model, J. Geophys. Res.-Atmos., 105, 26619–26634, https://doi.org/10.1029/2000JD900149, 2000.
Pomeroy, J. W., Gray, D. M., Brown, T., Hedstrom, N. R., Quinton, W. L., Granger, R. J., and Carey, S. K.: The cold regions hydrological model: A platform for basing process representation and model structure on physical evidence, Hydrol. Process., 21, 2650–2667, https://doi.org/10.1002/hyp.6787, 2007.
Quick, M. C. and Pipes, A.: U. B. C. Watershed Model/Le modèle du bassin versant U. C.B, Hydrolog. Sci. J., 22, 153–161, https://doi.org/10.1080/02626667709491701, 1977.
Radic, V., Bliss, A., Beedlow, A. C., Hock, R., Miles, E., and Cogley, J. G.: Regional and global projections of twenty-first century glacier mass changes in response to climate scenarios from global climate models, Clim. Dynam., 42, 37–58, https://doi.org/10.1007/s00382-013-1719-7, 2014.
Rasouli, K., Hsieh, W. W., and Cannon, A. J.: Daily streamflow forecasting by machine learning methods with weather and climate inputs, J. Hydrol., 414–415, 284–293, https://doi.org/10.1016/j.jhydrol.2011.10.039, 2012.
Razavian, A. S., Azizpour, H., Sullivan, J., and Carlsson, S.: CNN Features Off-the-Shelf: An Astounding Baseline for Recognition, in: 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 512–519, https://doi.org/10.1109/CVPRW.2014.131, 2014.
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., and Prabhat: Deep learning and process understanding for data-driven Earth system science, Nature, 566, 195–204, https://doi.org/10.1038/s41586-019-0912-1, 2019.
RGI Consortium: Randolph Glacier Inventory (RGI) – A Dataset of Global Glacier Outlines, https://doi.org/10.7265/N5-RGI-60, 2017.
Rumelhart, D. E., Hinton, G. E., and Williams, R. J.: Learning Internal Representations by Error Propagation, Institute for Cognitive Science, University of California, San Diego, https://apps.dtic.mil/sti/citations/ADA164453 (last access: 10 February 2022), 1985.
Schnorbus, M., Werner, A., and Bennett, K.: Impacts of climate change in three hydrologic regimes in British Columbia, Canada, Hydrol. Process., 28, 1170–1189, https://doi.org/10.1002/hyp.9661, 2014.
Schnorbus, M. A., Bennett, K. E., Werner, A. T., and Berland, A. J.: Hydrologic Impacts of Climate Change in the Peace, Campbell and Columbia Watersheds, British Columbia, Canada, Pacific Climate Impacts Consortium, University of Victoria, Victoria, BC, 157 pp., 2011.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D.: Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization, Int. J. Comput. Vision, 128, 336–359, https://doi.org/10.1007/s11263-019-01228-7, 2016.
Shaw, D. A., Vanderkamp, G., Conly, F. M., Pietroniro, A., and Martz, L.: The Fill–Spill Hydrology of Prairie Wetland Complexes during Drought and Deluge, Hydrol. Process., 26, 3147–3156, https://doi.org/10.1002/hyp.8390, 2012.
Shen, C.: A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists, Water Resour. Res., 54, 8558–8593, https://doi.org/10.1029/2018WR022643, 2018.
Shen, C., Laloy, E., Elshorbagy, A., Albert, A., Bales, J., Chang, F.-J., Ganguly, S., Hsu, K.-L., Kifer, D., Fang, Z., Fang, K., Li, D., Li, X., and Tsai, W.-P.: HESS Opinions: Incubating deep-learning-powered hydrologic science advances as a community, Hydrol. Earth Syst. Sci., 22, 5639–5656, https://doi.org/10.5194/hess-22-5639-2018, 2018.
Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W., and Woo, W.: Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting, in: Advances in Neural Information Processing Systems 28, edited by: Cortes, C., Lawrence, N. D., Lee, D. D., Sugiyama, M., and Garnett, R., Curran Associates, Inc., 802–810, https://proceedings.neurips.cc/paper/2015/file/07563a3fe3bbe7e3ba84431ad9d055af-Paper.pdf (last access: 10 February 2022), 2015.
Shook, K. R. and Pomeroy, J. W.: Memory effects of depressional storage in Northern Prairie hydrology, Hydrol. Process., 25, 3890–3898, https://doi.org/10.1002/hyp.8381, 2011.
Shrestha, R. R., Schnorbus, M. A., Werner, A. T., and Berland, A. J.: Modelling spatial and temporal variability of hydrologic impacts of climate change in the Fraser River basin, British Columbia, Canada, Hydrol. Process., 26, 1840–1860, https://doi.org/10.1002/hyp.9283, 2012.
Shrestha, R. R., Bonsal, B. R., Bonnyman, J. M., Cannon, A. J., and Najafi, M. R.: Heterogeneous snowpack response and snow drought occurrence across river basins of northwestern North America under 1.0 ∘C to 4.0 ∘C global warming, Climatic Change, 164, 40, https://doi.org/10.1007/s10584-021-02968-7, 2021.
Sinclair, K. E. and Marshall, S. J.: Temperature and vapour-trajectory controls on the stable-isotope signal in Canadian Rocky Mountain snowpacks, J. Glaciol., 55, 485–498, https://doi.org/10.3189/002214309788816687, 2009.
Snauffer, A. M., Hsieh, W. W., Cannon, A. J., and Schnorbus, M. A.: Improving gridded snow water equivalent products in British Columbia, Canada: multi-source data fusion by neural network models, The Cryosphere, 12, 891–905, https://doi.org/10.5194/tc-12-891-2018, 2018.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R.: Dropout: A Simple Way to Prevent Neural Networks from Overfitting, J. Mach. Learn. Res., 15, 1929–1958, 2014.
Stahl, K. and Moore, R. D.: Influence of watershed glacier coverage on summer streamflow in British Columbia, Canada, Water Resour. Res., 42, 1–5, https://doi.org/10.1029/2006WR005022, 2006.
Stahl, K., Moore, R. D., Shea, J. M., Hutchinson, D., and Cannon, A. J.: Coupled modelling of glacier and streamflow response to future climate scenarios, Water Resour. Res., 44, 1–13, https://doi.org/10.1029/2007WR005956, 2008.
Statistics Canada: Boundary Files, 2016 Census, https://www12.statcan.gc.ca/census-recensement/2011/geo/bound-limit/bound-limit-2016-eng.cfm
(last access: 19 April 2021), 2016.
Sutskever, I., Vinyals, O., and Le, Q. V.: Sequence to sequence learning with neural networks, in: Proceedings of the 27th International Conference on Neural Information Processing Systems – Volume 2 (NIPS'14), MIT Press, Cambridge, MA, USA, 3104–3112, https://proceedings.neurips.cc/paper/2014/file/a14ac55a4f27472c5d894ec1c3c743d2-Paper.pdf (last access: 10 February 2022), 2014.
Toms, B. A., Barnes, E. A., and Ebert-Uphoff, I.: Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability, J. Adv. Model. Earth Syst., 12, e2019MS002002, https://doi.org/10.1029/2019MS002002, 2020.
Trubilowicz, J. W., Shea, J. M., Jost, G., and Moore, R. D.: Suitability of North American Regional Reanalysis (NARR) output for hydrologic modelling and analysis in mountainous terrain, Hydrol. Process., 30, 2332–2347, https://doi.org/10.1002/hyp.10795, 2016.
Unduche, F., Tolossa, H., Senbeta, D., and Zhu, E.: Evaluation of four hydrological models for operational flood forecasting in a Canadian Prairie watershed, Hydrolog. Sci. J., 63, 1133–1149, https://doi.org/10.1080/02626667.2018.1474219, 2018.
Van, S. P., Le, H. M., Thanh, D. V., Dang, T. D., Loc, H. H., and Anh, D. T.: Deep learning convolutional neural network in rainfall–runoff modelling, J. Hydroinform., 22, 541–561, https://doi.org/10.2166/hydro.2020.095, 2020.
Vandal, T., Kodra, E., Ganguly, S., Michaelis, A., Nemani, R., and Ganguly, A. R.: DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution, in Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'17), Association for Computing Machinery, New York, NY, USA, 1663–1672, https://doi.org/10.1145/3097983.3098004, 2017.
Van Rossum, G. and Drake, F. L.: Python 3 Reference Manual, CreateSpace, Scotts Valley, CA, ISBN 978-1-4414-1269-0, 2009.
Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R. J., Darrell, T., and Saenko, K.: Sequence to Sequence – Video to Text, in: 2015 IEEE International Conference on Computer Vision (ICCV), 4534–4542, https://doi.org/10.1109/ICCV.2015.515, 2015.
Vickers, G., Buzza, S., Schmidt, D., and Mullock, J.: The Weather of the Canadian Prairies, NAV CANADA, https://www.navcanada.ca/en/lawm-prairies-en.pdf (last access: 10 February 2022), 2001.
Vincent, L. A., Zhang, X., Brown, R. D., Feng, Y., Mekis, E., Milewska, E. J., Wan, H., and Wang, X. L.: Observed Trends in Canada's Climate and Influence of Low-Frequency Variability Modes, J. Climate, 28, 4545–4560, https://doi.org/10.1175/JCLI-D-14-00697.1, 2015.
Water Survey of Canada HYDAT data: https://wateroffice.ec.gc.ca/mainmenu/historical_data_index_e.html (last access: 19 April 2021), 2022.
Wheater, H. and Gober, P.: Water security in the Canadian Prairies: science and management challenges, Philos. T. Roy. Soc. A, 371, 1–21, https://doi.org/10.1098/rsta.2012.0409, 2013.
Whitfield, P. H., Cannon, A. J., and Reynolds, C. J.: Modelling Streamflow in Present and Future Climates: Examples from the Georgia Basin, British Columbia, Can. Water Resour. J./Revue canadienne des ressources hydriques, 27, 427–456, https://doi.org/10.4296/cwrj2704427, 2002.
Whitfield, P. H., Moore, R. D. (Dan), Fleming, S. W., and Zawadzki, A.: Pacific Decadal Oscillation and the Hydroclimatology of Western Canada – Review and Prospects, Can. Water Resour. J./Revue canadienne des ressources hydriques, 35, 1–28, https://doi.org/10.4296/cwrj3501001, 2010.
Woo, M.-K. and Thorne, R.: Streamflow in the Mackenzie Basin, Canada, Arctic, 56, 328–340, https://doi.org/10.14430/arctic630, 2003.
Xu, X., Frey, S. K., Boluwade, A., Erler, A. R., Khader, O., Lapen, D. R., and Sudicky, E.: Evaluation of variability among different precipitation products in the Northern Great Plains, J. Hydrol.: Reg. Stud., 24, 100608, https://doi.org/10.1016/j.ejrh.2019.100608, 2019.
Yosinski, J., Clune, J., Bengio, Y., and Lipson, H.: How transferable are features in deep neural networks?, in: Proceedings of the 27th International Conference on Neural Information Processing Systems – Volume 2 (NIPS'14), MIT Press, Cambridge, MA, USA, 3320–3328, https://proceedings.neurips.cc/paper/2014/file/375c71349b295fbe2dcdca9206f20a06-Paper.pdf (last access: 10 February 2022), 2014.
Zealand, C. M., Burn, D. H., and Simonovic, S. P.: Short term streamflow forecasting using artificial neural networks, J. Hydrol., 214, 32–48, https://doi.org/10.1016/S0022-1694(98)00242-X, 1999.
Zeiler, M. D. and Fergus, R.: Visualizing and
Understanding Convolutional Networks, in: Computer Vision – ECCV 2014, Zurich, Switzerland, 818–833, https://doi.org/10.1007/978-3-319-10590-1_53, 2014.
Zhang, X., Harvey, K. D., Hogg, W. D., and Yuzyk, T. R.: Trends in Canadian streamflow, Water Resour. Res., 37, 987–998, https://doi.org/10.1029/2000WR900357, 2001.
Short summary
We develop and interpret a spatiotemporal deep learning model for regional streamflow prediction at more than 200 stream gauge stations in western Canada. We find the novel modelling style to work very well for daily streamflow prediction. Importantly, we interpret model learning to show that it has learned to focus on physically interpretable and physically relevant information, which is a highly desirable quality of machine-learning-based hydrological models.
We develop and interpret a spatiotemporal deep learning model for regional streamflow prediction...
