Search for: All records

ABSTRACT Salt pollution has become prominent over the past 80 years in freshwater ecosystems across the Midwest United States. This study focuses on chloride dynamics in Lake Wingra, a shallow, urban lake in Madison, Wisconsin. Since the 1940s, chloride concentrations have risen 30‐fold to over 100 mg L⁻¹. While still below the chronic chloride water quality threshold of 230 mg L⁻¹, local stakeholders have a set goal of reducing concentrations to 40 mg L⁻¹. Here we investigate the interplay of precipitation and road salt application in driving observed chloride dynamics in the lake using a dynamic model. We then use the model to project future chloride concentrations under a range of road salt reduction scenarios. We find that under current road salt application rates, mean chloride concentrations in Lake Wingra will stabilize between 116 and 168 mg L⁻¹. Under a 75% salt reduction scenario, chloride concentrations will decrease to 42 mg/L by the 2050s. 

Abstract Limnological understanding of the role snow plays in under‐ice thermal dynamics is mainly based on studies of clear‐water lakes. Very little is known about the role snow plays in the thermal dynamics of dystrophic lakes. We conducted a whole lake experiment on a small, 8 m deep dystrophic bog lake in northern Wisconsin, where we removed all snowfall over two consecutive winters. Due to weather variability, only 1 year had predominantly black ice. Under these conditions, the lake rapidly cooled in early and mid‐winter, compared to snow covered conditions that insulated the lake from heat loss. The lake also rapidly gained heat in late winter resulting in isothermal conditions well in advance of ice‐off. These results show how water clarity modulates the influence of snow on under‐ice thermal dynamics, which is relevant to futures with snow droughts. 

Abstract Hybrid Knowledge‐Guided Machine Learning (KGML) models, which are deep learning models that utilize scientific theory and process‐based model simulations, have shown improved performance over their process‐based counterparts for the simulation of water temperature and hydrodynamics. We highlight the modular compositional learning (MCL) methodology as a novel design choice for the development of hybrid KGML models in which the model is decomposed into modular sub‐components that can be process‐based models and/or deep learning models. We develop a hybrid MCL model that integrates a deep learning model into a modularized, process‐based model. To achieve this, we first train individual deep learning models with the output of the process‐based models. In a second step, we fine‐tune one deep learning model with observed field data. In this study, we replaced process‐based calculations of vertical diffusive transport with deep learning. Finally, this fine‐tuned deep learning model is integrated into the process‐based model, creating the hybrid MCL model with improved overall projections for water temperature dynamics compared to the original process‐based model. We further compare the performance of the hybrid MCL model with the process‐based model and two alternative deep learning models and highlight how the hybrid MCL model has the best performance for projecting water temperature, Schmidt stability, buoyancy frequency, and depths of different isotherms. Modular compositional learning can be applied to existing modularized, process‐based model structures to make the projections more robust and improve model performance by letting deep learning estimate uncertain process calculations. 

Many research and monitoring networks in recent decades have provided publicly available data documenting environmental and ecological change, but little is known about the status of efforts to synthesize this information across networks. We convened a working group to assess ongoing and potential cross‐network synthesis research and outline opportunities and challenges for the future, focusing on the US‐based research network (the US Long‐Term Ecological Research network, LTER) and monitoring network (the National Ecological Observatory Network, NEON). LTER‐NEON cross‐network research synergies arise from the potentials for LTER measurements, experiments, models, and observational studies to provide context and mechanisms for interpreting NEON data, and for NEON measurements to provide standardization and broad scale coverage that complement LTER studies. Initial cross‐network syntheses at co‐located sites in the LTER and NEON networks are addressing six broad topics: how long‐term vegetation change influences C fluxes; how detailed remotely‐sensed data reveal vegetation structure and function; aquatic‐terrestrial connections of nutrient cycling; ecosystem response to soil biogeochemistry and microbial processes; population and species responses to environmental change; and disturbance, stability and resilience. This initial work offers exciting potentials for expanded cross‐network syntheses involving multiple long‐term ecosystem processes at regional or continental scales. These potential syntheses could provide a pathway for the broader scientific community, beyond LTER and NEON, to engage in cross‐network science. These examples also apply to many other research and monitoring networks in the US and globally, and can guide scientists and research administrators in promoting broad‐scale research that supports resource management and environmental policy.