Search for: All records

Abstract Lakes, ponds, and reservoirs (hereafter: “lakes”) are important sources of the greenhouse gases carbon dioxide (CO₂) and methane (CH₄). Emissions of CO₂and CH₄from lakes are regulated in part by in-lake processes, including the production and storage of gases in the lower parts of the water column (bottom waters). However, while substantial efforts have been made to improve estimates of greenhouse gas emissions from lakes, limited data on gas concentrations along depth profiles have prevented the incorporation of bottom-water processes in global emission estimates. Here, we present GHG-depths: the largest existing dataset of depth-profile CO₂and CH₄measurements worldwide, including 522 lakes across 38 countries and all seven continents. These data include contributions from 45 research teams and 56 published studies, totaling 2558 discrete sampling events. As global change continues to alter biogeochemical cycling in lakes, these data can help improve mechanistic models to better predict greenhouse gas production and emission from lakes worldwide. 

Abstract Harmful phytoplankton blooms driven by climate warming and nutrient pollution are a growing threat to freshwater ecosystems worldwide. Predicting these blooms is critical for managing water resources. However, process‐based models often struggle to capture the complex nonlinear dynamics of phytoplankton. Although machine learning (ML) offers powerful predictive capabilities, its “black‐box” nature has limited its adoption for management. In this study, we applied four ensemble ML algorithms, Extreme Gradient Boosting (XGBoost), Random Forest (RF), Gradient Boosting Machine (GBM), and Categorical Boosting (CatBoost), to model phytoplankton dynamics in two adjacent drinking‐water reservoirs. All models performed similarly; however, the XGBoost algorithm achieved the best performance in both reservoirs, with a root mean square error (RMSE) of 2.4–6.6 μg/L chlorophyll a and a Pearson correlation coefficient (r) of 0.83–0.86. To enhance the interpretability of these ML models, we applied explainable artificial intelligence (XAI) techniques, including Shapley Additive Explanations (SHAP) and partial dependence analyses (PDPs). Our XAI analysis revealed reservoir‐specific dynamics, with deep dissolved oxygen and water temperature more influential in one reservoir, whereas seasonality and water column stability were more critical in the other. We also observed opposing effects of thermal stratification, with high water temperatures and strong stratification stimulating phytoplankton in one reservoir and suppressing it in the other. Stability analyses confirmed that the SHAP explanations were robust to perturbations, boosting confidence in their interpretability. This study demonstrates the application of a stability‐constrained XAI framework to provide transparent and trustworthy ecological insights, offering a robust approach for data‐driven water quality management and forecasting. 

ABSTRACT The water quality of drinking water reservoirs is critical for human and ecosystem health. In this study, we examined the drivers of three metals, aluminum (Al), barium (Ba), and copper (Cu), across two drinking water reservoirs in southwestern Virginia, USA, over 4 years. One reservoir has a hypolimnetic oxygenation system; the other does not. We used time series modeling and multivariate analysis of water column chemistry, suspended sediment, inflow, and precipitation data to assess the relative roles of hydrologic and geochemical drivers of metal behaviors in the two reservoirs. Results suggest that Al concentrations were primarily influenced by high-flow events, consistent with the mobilization of clays from physical weathering. In contrast, Ba showed stronger sensitivity to geochemical drivers, specifically redox conditions. Drivers of Cu behavior were obscured by low Cu concentrations. For all metals, patterns varied among years. Our findings highlight the importance of long-term monitoring and integrated approaches to evaluate the drivers of metal dynamics in reservoir ecosystems and inform strategies for maintaining safe drinking water supplies. 

ABSTRACT Ecosystem states are often influenced by both concurrent and antecedent environmental drivers. However, the relative importance of antecedent conditions varies within and among ecosystems. Here, we analysed long‐term depth‐profile data from 382 temperate lakes across 10 countries to assess how differential changes in spring versus summer air temperature mediate summer water quality. We found that summer bottom‐water conditions were more associated with spring air temperatures, while surface‐water conditions were more associated with summer air temperatures. The relative influence of spring versus summer air temperature was mediated by lake morphometry, stratification and latitude. Across these lakes, summer air temperatures have increased more rapidly than spring air temperatures, potentially contributing to a growing thermal difference between surface and bottom waters (median = +0.5°C/decade). Consequently, our results demonstrate that predicting the ecological impacts of climate change may require considering spatial differences in ecological memory within ecosystems. 

Abstract As ecology becomes a more predictive discipline, identifying the intrinsic predictability, or stochasticity, of ecosystem variables across space and time is needed to help guide the development of ecological models and forecasts. For example, if an ecological time series has high intrinsic predictability, then a high‐performing model should presumably be able to replicate its dynamics. Conversely, if an ecological variable has low intrinsic predictability, then no model—regardless of its performance—will be able to replicate its dynamics. However, despite the proliferation of ecological models and forecasts, the intrinsic predictability of ecological variables remains largely unknown. To bridge this gap, we analyzed a >4‐year time series of high‐frequency sensor data collected from replicate freshwater ecosystems to determine how intrinsic predictability (quantified as permutation entropy) differs among ecological variables, seasons, and ecosystems. We observed greater differences in predictability among ecological variables and days of year than between ecosystems. Although intrinsic predictability was generally low for all variables, it was still significantly higher than white noise, indicating complex yet predictable dynamics. We observed the highest predictability for physical ecosystem variables (e.g., water temperature) and the lowest predictability for biological variables (e.g., phytoplankton biomass), with chemical variables (e.g., dissolved oxygen) intermediate. We observed substantial seasonal differences in predictability among variables: surface water temperature and dissolved organic matter exhibited their highest levels of predictability in autumn, whereas surface chlorophyll and bottom‐layer dissolved oxygen and temperature exhibited highest predictability in summer. Periods of anoxia (low oxygen) were associated with the highest levels of predictability in dissolved oxygen over the time series. Altogether, our analysis highlights how intrinsic predictability data can both guide ecological model development and improve our understanding of how ecological predictability varies across space and time. 

Abstract Seasonality in environmental conditions plays a fundamental role in shaping lake ecosystems. However, patterns of seasonality vary worldwide, and these patterns are shifting over time amid global change. Thus, it is increasingly important to evaluate how seasons and seasonality are represented in lake ecosystem research. Here, we used a literature review and global data analysis to synthesize approaches for conceptualizing seasons and seasonality in lakes. We found that a wide range of criteria are used to delineate discrete seasons in published literature, including fixed dates (e.g., months, solstice/equinox), environmental thresholds (e.g., temperature and precipitation cutoffs), and lake‐specific indicators (e.g., ice cover, plankton phenology). Analyzing data from lakes worldwide, we found that using different criteria to define the same season resulted in divergent interpretations of ecosystem states. Based on our synthesis, we offer recommendations for how to incorporate seasonality into lake research and communications amid global change. 

Abstract While there is a diversity of approaches for modeling phytoplankton blooms, their accuracy in predicting the onset and manifestation of a bloom is still lagging behind what is needed to support effective management. We outline a framework that integrates trait theory and ecosystem modeling to improve bloom prediction. This framework builds on the concept that the phenology of blooms is determined by the dynamic interaction between the environment and traits within the phytoplankton community. Phytoplankton groups exhibit a collection of traits that govern the interplay of processes that ultimately control the phases of bloom initiation, maintenance, and collapse. An example of process‐trait mapping is used to demonstrate a more consistent approach to bloom model parameterization that allows better alignment with models and laboratory‐ and ecosystem‐scale datasets. Further approaches linking statistical‐mechanistic models to trait parameter databases are discussed as a way to help optimize models to better simulate bloom phenology and allow them to support a wider range of management needs. 

Abstract Data science skills (e.g., analyzing, modeling, and visualizing large data sets) are increasingly needed by undergraduates in the life sciences. However, a lack of both student and instructor confidence in data science skills presents a barrier to their inclusion in undergraduate curricula. To reduce this barrier, we developed four teaching modules in the Macrosystems EDDIE (for environmental data-driven inquiry and exploration) program to introduce undergraduate students and instructors to ecological forecasting, an emerging subdiscipline that integrates multiple data science skills. Ecological forecasting aims to improve natural resource management by providing future predictions of ecosystems with uncertainty. We assessed module efficacy with 596 students and 26 instructors over 3 years and found that module completion increased students’ confidence in their understanding of ecological forecasting and instructors’ likelihood to work with long-term, high-frequency sensor network data. Our modules constitute one of the first formalized data science curricula on ecological forecasting for undergraduates. 

Abstract Near‐term ecological forecasting can be used to improve operational resource management in freshwater ecosystems. Here, we developed a framework that uses water temperature forecasting as a tool to predict the migrations of Atlantic salmon (Salmo salar) and European eel (Anguilla anguilla) between freshwater and the sea. We used historical observations of lake water temperature and fish migrations from an internationally important long‐term monitoring site (the Burrishoole catchment, Ireland) to generate daily probabilistic predictions (0%–100%) of when relatively large numbers of fish migrate. For this, we produced daily lake water temperature forecasts that extended up to 34 days into the future using Forecasting Lake and Reservoir Ecosystems (FLARE), an open‐source ensemble‐based forecasting system. We used this system to forecast lake water temperature conditions associated with percentile‐based fish migrations. Two metrics, P66 and P95, were used to indicate days with migrations in excess of 66% and 95%, respectively, of the historical daily fish counts. The results were first validated against water temperature observations, with an overall root mean squared error (RMSE) of 0.97°C. Our forecasts outperformed two other possible water temperature forecasting approaches, using site climatology (1.36°C) and site persistence (1.19°C). The predictions for fish migrations performed better for the P66 metric than for the more extreme P95 metric based on the continuous ranked probability score (CRPS), and the best results were obtained for the salmon downstream migration. This forecasting approach with quantified uncertainty levels has the potential to assist decision making, especially in the face of increased risks for these species. We conclude by discussing the scalability of the framework to other settings as a tool aimed at supporting management practices in real time. 

Abstract Phytoplankton blooms create harmful toxins, scums, and taste and odor compounds and thus pose a major risk to drinking water safety. Climate and land use change are increasing the frequency and severity of blooms, motivating the development of new approaches for preemptive, rather than reactive, water management. While several real-time phytoplankton forecasts have been developed to date, none are both automated and quantify uncertainty in their predictions, which is critical for manager use. In response to this need, we outline a framework for developing the first automated, real-time lake phytoplankton forecasting system that quantifies uncertainty, thereby enabling managers to adapt operations and mitigate blooms. Implementation of this system calls for new, integrated ecosystem and statistical models; automated cyberinfrastructure; effective decision support tools; and training for forecasters and decision makers. We provide a research agenda for the creation of this system, as well as recommendations for developing real-time phytoplankton forecasts to support management.