A hybrid deep learning approach to predict hourly riverine nitrate concentrations using routine monitored data.

With high-frequency data of nitrate (NO-N) concentrations in waters becoming increasingly important for understanding of watershed system behaviors and ecosystem managements, the accurate and economic acquisition of high-frequency NO-N concentration data has become a key point. This study attempted to use coupled deep learning neural networks and routine monitored data to predict hourly NO-N concentrations in a river. The hourly NO-N concentration at the outlet of the Oyster River watershed in New Hampshire, USA, was predicted through neural networks with a hybrid model architecture coupling the Convolutional Neural Networks and the Long Short-Term Memory model (CNN-LSTM).

Existing wetland conservation programs miss nutrient reduction targets.

Restoring wetlands will reduce nitrogen contamination from excess fertilization but estimates of the efficacy of the strategy vary widely. The intervention is often described as effective for reducing nitrogen export from watersheds to mediate bottom-level hypoxia threatening marine ecosystems. Other research points to the necessity of applying a suite of interventions, including wetland restoration to mitigate meaningful quantities of nitrogen export.

Prediction of riverine daily minimum dissolved oxygen concentrations using hybrid deep learning and routine hydrometeorological data.

Dissolved oxygen (DO) depletion is a severe threat to aquatic ecosystems. Hence, using easily available routine hydrometeorological variables without DO as inputs to predict the daily minimum DO concentration in rivers has huge practical significance in the watershed management. The daily minimum DO concentrations at the outlet of the Oyster River watershed in New Hampshire, USA, were predicted by a set of deep learning neural networks using meteorological data and high-frequency water level, water temperature, and specific conductance (CTD) data measured within the watershed.

US climate policy yields water quality cobenefits in the Mississippi Basin and Gulf of Mexico.

We utilize a coupled economy-agroecology-hydrology modeling framework to capture the cascading impacts of climate change mitigation policy on agriculture and the resulting water quality cobenefits. We analyze a policy that assigns a range of United States government's social cost of carbon estimates ($51, $76, and $152/ton of CO-equivalents) to fossil fuel-based CO emissions. This policy raises energy costs and, importantly for agriculture, boosts the price of nitrogen fertilizer production.

Spatial dimensions of water quality value in New England river networks.

Households' willingness to pay (WTP) for water quality improvements-representing their economic value-depends on where improvements occur. Households often hold higher values for improvements close to their homes or iconic areas. Are there other areas where improvements might hold high value to individual households, do effects on WTP vary by type of improvement, and can these areas be identified even if they are not anticipated by researchers? To answer these questions, we integrated a water quality model and map-based, interactive choice experiment to estimate households' WTP for water quality improvements throughout a river network covering six New England states.

Spatial and temporal heterogeneity of methane ebullition in lowland headwater streams and the impact on sampling design.

Headwater streams are known sources of methane (CH) to the atmosphere, but their contribution to global scale budgets remains poorly constrained. While efforts have been made to better understand diffusive fluxes of CH in streams, much less attention has been paid to ebullitive fluxes. We examine the temporal and spatial heterogeneity of CH ebullition from four lowland headwater streams in the temperate northeastern United States over a 2-yr period.

Long-term ecological research and the COVID-19 anthropause: A window to understanding social-ecological disturbance.

The period of disrupted human activity caused by the COVID-19 pandemic, coined the "anthropause," altered the nature of interactions between humans and ecosystems. It is uncertain how the anthropause has changed ecosystem states, functions, and feedback to human systems through shifts in ecosystem services. Here, we used an existing disturbance framework to propose new investigation pathways for coordinated studies of distributed, long-term social-ecological research to capture effects of the anthropause.

Superlinear scaling of riverine biogeochemical function with watershed size.

River networks regulate carbon and nutrient exchange between continents, atmosphere, and oceans. However, contributions of riverine processing are poorly constrained at continental scales. Scaling relationships of cumulative biogeochemical function with watershed size (allometric scaling) provide an approach for quantifying the contributions of fluvial networks in the Earth system.

Controls of Chloride Loading and Impairment at the River Network Scale in New England.

Chloride contamination of rivers due to nonpoint sources is increasing throughout developed temperate regions due to road salt application in winter. We developed a river-network model of chloride loading to watersheds to estimate road salt application rates and investigated the meteorological factors that control riverine impairment by chloride at concentrations above thresholds protective of aquatic organisms. Chloride loading from road salt was simulated in the Merrimack River watershed in New Hampshire, which has gradients in development density.

Influences of agricultural land use composition and distribution on nitrogen export from a subtropical watershed in China.

Despite the significant impacts of agricultural land on nonpoint source (NPS) nitrogen (N) pollution, little is known about the influence of the distribution and composition of different agricultural land uses on N export at the watershed scale. We used the Soil and Water Assessment Tool (SWAT) to quantify how agricultural distribution (i.e.

Characterizing storm-event nitrate fluxes in a fifth order suburbanizing watershed using in situ sensors.

Land use influences the distribution of nonpoint nitrogen (N) sources in urbanizing watersheds and storm events interact with these heterogeneous sources to expedite N transport to aquatic systems. In situ sensors provide high frequency and continuous measurements that may reflect storm-event N variability more accurately compared to grab samples. We deployed sensors from April to December 2011 in a suburbanizing watershed (479 km2) to characterize storm-event nitrate-N (NO3-N) and conductivity variability.

Extreme rainfall, vulnerability and risk: a continental-scale assessment for South America.

Extreme weather continues to preoccupy society as a formidable public safety concern bearing huge economic costs. While attention has focused on global climate change and how it could intensify key elements of the water cycle such as precipitation and river discharge, it is the conjunction of geophysical and socioeconomic forces that shapes human sensitivity and risks to weather extremes. We demonstrate here the use of high-resolution geophysical and population datasets together with documentary reports of rainfall-induced damage across South America over a multi-decadal, retrospective time domain (1960-2000).

Coastal eutrophication as a driver of salt marsh loss.

Salt marshes are highly productive coastal wetlands that provide important ecosystem services such as storm protection for coastal cities, nutrient removal and carbon sequestration. Despite protective measures, however, worldwide losses of these ecosystems have accelerated in recent decades. Here we present data from a nine-year whole-ecosystem nutrient-enrichment experiment.

Nitrous oxide emission from denitrification in stream and river networks.

Nitrous oxide (N(2)O) is a potent greenhouse gas that contributes to climate change and stratospheric ozone destruction. Anthropogenic nitrogen (N) loading to river networks is a potentially important source of N(2)O via microbial denitrification that converts N to N(2)O and dinitrogen (N(2)). The fraction of denitrified N that escapes as N(2)O rather than N(2) (i.