Using Knowledge-Guided Machine Learning To Assess Patterns of Areal Change in Waterbodies across the Contiguous United States.

Lake and reservoir surface areas are an important proxy for freshwater availability. Advancements in machine learning (ML) techniques and increased accessibility of remote sensing data products have enabled the analysis of waterbody surface area dynamics on broad spatial scales. However, interpreting the ML results remains a challenge. While ML provides important tools for identifying patterns, the resultant models do not include mechanisms. Thus, the "black-box" nature of ML techniques often lacks ecological meaning. Using ML, we characterized temporal patterns in lake and reservoir surface area change from 1984 to 2016 for 103,930 waterbodies in the contiguous United States. We then employed knowledge-guided machine learning (KGML) to classify all waterbodies into seven ecologically interpretable groups representing distinct patterns of surface area change over time. Many waterbodies were classified as having "no change" (43%), whereas the remaining 57% of waterbodies fell into other groups representing both linear and nonlinear patterns. This analysis demonstrates the potential of KGML not only for identifying ecologically relevant patterns of change across time but also for unraveling complex processes that underpin those changes.

Benthic habitat is an integral part of freshwater Mysis ecology.

Diel vertical migration (DVM) is common in aquatic organisms. The trade-off between reduced predation risk in deeper, darker waters during the day and increased foraging opportunities closer to the surface at night is a leading hypothesis for DVM behaviour.Diel vertical migration behaviour has dominated research and assessment frameworks for Mysis, an omnivorous mid-trophic level macroinvertebrate that exhibits strong DVM between benthic and pelagic habitats and plays key roles in many deep lake ecosystems. However, some historical literature and more recent evidence indicate that mysids also remain on the bottom at night, counter to expectations of DVM.We surveyed the freshwater Mysis literature using Web of Science (WoS; 1945-2019) to quantify the frequency of studies on demographics, diets, and feeding experiments that considered, assessed, or included Mysis that did not migrate vertically but remained in benthic habitats. We supplemented our WoS survey with literature searches for relevant papers published prior to 1945, journal articles and theses not listed in WoS, and additional references known to the authors but missing from WoS (e.g. only 47% of the papers used to evaluate in situ diets were identified by WoS).Results from the survey suggest that relatively little attention has been paid to the benthic components of Mysis ecology. Moreover, the literature suggests that reliance on Mysis sampling protocols using pelagic gear at night provides an incomplete picture of Mysis populations and their role in ecosystem structure and function.We summarise current knowledge of Mysis DVM and provide an expanded framework that more fully considers the role of benthic habitat. Acknowledging benthic habitat as an integral part of Mysis ecology will enable research to better understand the role of Mysis in food web processes.