Deep learning for water quality.

Understanding and predicting the quality of inland waters are challenging, particularly in the context of intensifying climate extremes expected in the future. These challenges arise partly due to complex processes that regulate water quality, and arduous and expensive data collection that exacerbate the issue of data scarcity. Traditional process-based and statistical models often fall short in predicting water quality. In this Review, we posit that deep learning represents an underutilized yet promising approach that can unravel intricate structures and relationships in high-dimensional data. We demonstrate that deep learning methods can help address data scarcity by filling temporal and spatial gaps and aid in formulating and testing hypotheses via identifying influential drivers of water quality. This Review highlights the strengths and limitations of deep learning methods relative to traditional approaches, and underscores its potential as an emerging and indispensable approach in overcoming challenges and discovering new knowledge in water-quality sciences.

Light and flow regimes regulate the metabolism of rivers.

Mean annual temperature and mean annual precipitation drive much of the variation in productivity across Earth's terrestrial ecosystems but do not explain variation in gross primary productivity (GPP) or ecosystem respiration (ER) in flowing waters. We document substantial variation in the magnitude and seasonality of GPP and ER across 222 US rivers. In contrast to their terrestrial counterparts, most river ecosystems respire far more carbon than they fix and have less pronounced and consistent seasonality in their metabolic rates. We find that variation in annual solar energy inputs and stability of flows are the primary drivers of GPP and ER across rivers. A classification schema based on these drivers advances river science and informs management.

The metabolic regimes of 356 rivers in the United States.

A national-scale quantification of metabolic energy flow in streams and rivers can improve understanding of the temporal dynamics of in-stream activity, links between energy cycling and ecosystem services, and the effects of human activities on aquatic metabolism. The two dominant terms in aquatic metabolism, gross primary production (GPP) and aerobic respiration (ER), have recently become practical to estimate for many sites due to improved modeling approaches and the availability of requisite model inputs in public datasets. We assembled inputs from the U.S. Geological Survey and National Aeronautics and Space Administration for October 2007 to January 2017. We then ran models to estimate daily GPP, ER, and the gas exchange rate coefficient for 356 streams and rivers across the continental United States. We also gathered potential explanatory variables and spatial information for cross-referencing this dataset with other datasets of watershed characteristics. This dataset offers a first national assessment of many-day time series of metabolic rates for up to 9 years per site, with a total of 490,907 site-days of estimates.

Nutrient limitation and physiology mediate the fine-scale (de)coupling of biogeochemical cycles.

Nutrients in the environment are coupled over broad timescales (days to seasons) when organisms add or withdraw multiple nutrients simultaneously and in ratios that are roughly constant. But at finer timescales (seconds to days), nutrients become decoupled if physiological traits such as nutrient storage limits, circadian rhythms, or enzyme kinetics cause one nutrient to be processed faster than another. To explore the interactions among these coupling and decoupling mechanisms, we introduce a model in which organisms process resources via uptake, excretion, growth, respiration, and mortality according to adjustable trait parameters. The model predicts that uptake can couple the input of one nutrient to the export of another in a ratio reflecting biological demand stoichiometry, but coupling occurs only when the input nutrient is limiting. Temporal nutrient coupling may, therefore, be a useful indicator of ecosystem limitation status. Fine-scale patterns of nutrient coupling are further modulated by, and potentially diagnostic of, physiological traits governing growth, uptake, and internal nutrient storage. Together, limitation status and physiological traits create a complex and informative relationship between nutrient inputs and exports. Understanding the mechanisms behind that relationship could enrich interpretations of fine-scale time-series data such as those now emerging from in situ solute sensors.