Designated neural network modules are combined to mimic numerically-discretized diffusion-sorption equations, which allows learning “missing pieces” in system understanding and their uncertainties.
Water Resources Research
Using Big Data for Monitoring Network Design and Beyond
Large data sets can be generated using deep learning to improve the design of observation networks for monitoring subsurface flow and transport.
Understanding Enhanced Arsenic Pollution in Shallow Lakes
A new study explains why the arsenic that has accumulated in lake bottom sediments is more harmful to the lake ecosystems in shallow lakes.
Disentangling River Water Turbidity and its Flow
A new study shows why fine sediments in rivers are not simply proportional to the water flow across the United States.
High-Frequency Monitoring Reveals Riverine Nitrogen Removal
Years of daily readings provide an unprecedented view into how a submerged aquatic meadow kept nitrogen from reaching the St. Lawrence Estuary as well as insights on how climate change may alter it.
Deep Learning for Hydrologic Projections Under Climate Change
Extrapolation or not? Big data may help deep learning to go places where it has not been before by transferring learned hydrologic relationships.
Surprise Hydrological Shifts Imperil Water Resources
Mounting evidence suggests the need for improved water planning strategies and revamped hydrological models.
The Fate of a Lake After a Dramatic Mining Disaster
Researchers tracked long-term sediment dynamics in Canada’s Quesnel Lake following the 2014 failure of a dam that spilled record-breaking amounts of contaminated mining waste.
Bangladeshis Feel Increased Consequences of Sedimentation
In northern Bangladesh, residents are losing their livelihoods, homes, and personal safety when water carries sand and gravel into their communities.
How Wildfires Affect Snow in the American West
Data from 45 burned sites help researchers better understand climate change and wildfires’ impact on snowpack.