Using Deep Learning to Fill Spatio-Temporal Data Gaps in
Hydrological Monitoring Networks

Ren, Huiying; Cromwell, Erol; Kravitz, Ben

doi:10.5194/hess-2019-196

Cited by 28 publications

(24 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Water Resources Research previous studies in Hanford site (Ren et al, 2019). We observe similar nesting patterns in between scatter-density contour of the TTDs (Figures 14a-14c) and the river stage WPSs (Figures 14d-14f).…”

Section: 1029/2019wr026470supporting

confidence: 77%

River Dynamics Control Transit Time Distributions and Biogeochemical Reactions in a Dam‐Regulated River Corridor

Song

Zachara

Shuai

et al. 2020

Water Resources Research

Self Cite

View full text Add to dashboard Cite

Transit time distributions (TTDs) exert important controls on biogeochemical processes in watershed systems. TTDs are often assumed to follow time-invariant exponential, lognormal, or heavy-tailed power law distributions in headwater or low-order streams. However, under dynamic hydrological forcing, transit time could exhibit more complex distribution patterns with strong spatial and temporal variability. In this study, we used a numerical particle tracking approach to characterize TTDs along the Hanford Reach of the Columbia River under the influences of river stage fluctuations and evaluate the associated effects on biogeochemical reaction potentials within the river corridor. Particle tracking was conducted using velocity fields simulated by high-resolution three-dimensional groundwater flow models that capture both the river stage fluctuations and physical heterogeneity. Our results revealed that multifrequency flow variations led to multimodal TTDs that varied in time and space. Such characteristics can only be captured by multiyear numerical simulations supported by multiyear field monitoring. Dam-induced high-frequency (subweekly) flow variations increased additional hydrologic exchange flows with short (subweekly) transit times, which accounted for up to 44% of reactant consumption in the river corridor along the Hanford Reach. The dam-induced river stage fluctuations have more significant impacts on faster biogeochemical reactions because they cause a larger fraction of shorter transit times. Numerical particle tracking provides an efficient alternative for characterizing TTDs for large complex systems where in situ field experiments are not feasible. Such a numerical approach is thus essential for improving large-scale biogeochemical modeling from watersheds to basins.

show abstract

Section: 1029/2019wr026470supporting

confidence: 77%

River Dynamics Control Transit Time Distributions and Biogeochemical Reactions in a Dam‐Regulated River Corridor

Song

Zachara

Shuai

et al. 2020

Water Resources Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…The well network was built to monitor the attenuation of legacy contaminants. The water elevation dynamics in each groundwater well are driven by river stage fluctuations, which in turn influence contaminant recharge to groundwater and lead to highly complex transport behaviors of the contaminants at the site [ Arntzen, et al ., 2006, Ren, et al ., 2019, Zachara, et al ., 2016].…”

Section: Methodsmentioning

confidence: 99%

Dissolved oxygen dynamics reveal biogeochemical tipping points driven by river corridor hydrology

Kaufman

Ghosh

Grate

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Riverbeds can have an important impact on large-scale fluxes of biogeochemically active solutes in river corridor systems. The hyporheic zone is an important area of both hydrology and biogeochemistry, particularly in a hydropeaked river system where rapid variations in river stage height, hydraulic gradients, and residence times occur. We measured several biogeochemical and hydrological parameters at three different subsurface depths in the riverbed of the Columbia River in Washington state, a complex hydropeaked river system with significant subsurface heterogeneity. During the study, episodes of significant dissolved oxygen (DO) change were observed. The DO signal changes were the most apparent, compared to more modest changes in other biogeochemical markers. While DO is often associated with biological activity, we ultimately found that the notable DO excursions were associated with hydrologic gradients. Here we describe hydrologic perturbations and biogeochemical responses in terms of hydrobiogeochemical regimes. Two different forms of DO response to hydraulic gradient perturbation were observed, defining different hydrobiogeochemical regimes. The system tips abruptly from one regime to the other, exhibiting threshold behavior that is uncaptured in current estimations of cumulative influences of subsurface processes from reach to earth system scales.Plain language summaryThe water in a river is constantly flowing in and out of the river’s bed. While it is in the bed, microbes process environmentally and ecologically important nutrients and other compounds. The exchange of water between the river and the riverbed is largely controlled by the stage of the river. Many processes, both natural and human, can cause rapid changes in the river stage. These rapid stage changes can cause abrupt changes in the riverbed’s ability to process nutrients and other compounds. In this study, we use dissolved oxygen as a window into riverbed microbial and chemical processing. We see that relatively rapid changes in river stage can cause abrupt changes in the concentrations of chemicals in the riverbed, indicating fundamental changes in how the riverbed processes are occurring. Understanding these abrupt and fundamental changes is important to our overall understanding of the ecological function of river corridor systems.3 key pointsA hydrobiogeochemical regime is defined by the functional form of the relationship of a hydrologic perturbation and biogeochemical marker.Short-term hydrologic perturbations drive tipping points between distinct hydrobiogeochemical regimes.Linear and hysteretic dissolved oxygen dynamics define distinct regimes as observed throughout the hyporheic zone.

show abstract

“…These gaps could be caused by both issues with sensor maintenance or technical limitations under certain conditions (weather, etc) and inconsistencies in the data acquisition practices on the local level. Recently, ML based solutions for time series augmentation have been used to fill in gaps in historical monitoring data (Gao et al, 2018;Ren et al, 2019). However, this kind of gap filling still requires enough good quality training data in the existing time series fragments to be effective.…”

Section: Suggestions For Improving Multi-source Water Quality Data Compilationmentioning

confidence: 99%

GRQA: Global River Water Quality Archive

Virro¹,

Amatulli²,

Kmoch³

et al. 2021

Preprint

View full text Add to dashboard Cite

Abstract. A major problem related to global water quality analysis and modelling has been the lack of available good quality and consistent water quality measurement datasets with a global spatial coverage. Current study aims to contribute into improving the global datasets on water quality by aggregating and harmonizing five national, continental and global datasets: CESI, GEMSTAT, GLORICH, WATERBASE and WQP. The GRQA compilation involved converting observation data from the five sources into a common format and harmonizing the corresponding metadata, flagging outliers, calculating time series characteristics and detecting duplicate observations from sources with a spatial overlap. The final dataset extends the spatial and temporal coverage of previously available water quality data and contains 42 parameters and over 16 million measurements around the globe covering the 1898–2020 time period. Metadata in the form of statistical tables, maps and figures are provided along with observation time series. The GRQA dataset, supplementary metadata and ﬁgures are available for download on the DataCite and OpenAire enabled repository of the University of Tartu, DataDOI, http://dx.doi.org/10.23673/re-273 (Virro et al., 2021).

show abstract

Using Deep Learning to Fill Spatio-Temporal Data Gaps in Hydrological Monitoring Networks

Cited by 28 publications

References 48 publications

River Dynamics Control Transit Time Distributions and Biogeochemical Reactions in a Dam‐Regulated River Corridor

River Dynamics Control Transit Time Distributions and Biogeochemical Reactions in a Dam‐Regulated River Corridor

Dissolved oxygen dynamics reveal biogeochemical tipping points driven by river corridor hydrology

GRQA: Global River Water Quality Archive

Contact Info

Product

Resources

About