National framework for ranking lakes by potential for anthropogenic hydro-alteration

Data-driven modelling for assessing trophic status in marine ecosystems using machine learning approaches

Assessing eutrophication in coastal and transitional waters is of utmost importance, yet existing Trophic Status Index (TSI) models face challenges like multicollinearity, data redundancy, inappropriate aggregation methods, and complex classification schemes. To tackle these issues, we developed a novel tool that harnesses machine learning (ML) and artificial intelligence (AI), enhancing the reliability and accuracy of trophic status assessments. Our research introduces an improved data-driven methodology specifically tailored for transitional and coastal (TrC) waters, with a focus on Cork Harbour, Ireland, as a case study. Our innovative approach, named the Assessment Trophic Status Index (ATSI) model, comprises three main components: the selection of pertinent water quality indicators, the computation of ATSI scores, and the implementation of a new classification scheme. To optimize input data and minimize redundancy, we employed ML techniques, including advanced deep learning methods. Specifically, we developed a CHL prediction model utilizing ten algorithms, among which XGBoost demonstrated exceptional performance, showcasing minimal errors during both training (RMSE = 0.0, MSE = 0.0, MAE = 0.01) and testing (RMSE = 0.0, MSE = 0.0, MAE = 0.01) phases. Utilizing a novel linear rescaling interpolation function, we calculated ATSI scores and evaluated the model's sensitivity and efficiency across diverse application domains, employing metrics such as R2, the Nash-Sutcliffe efficiency (NSE), and the model efficiency factor (MEF). The results consistently revealed heightened sensitivity and efficiency across all application domains. Additionally, we introduced a brand new classification scheme for ranking the trophic status of transitional and coastal waters. To assess spatial sensitivity, we applied the ATSI model to four distinct waterbodies in Ireland, comparing trophic assessment outcomes with the Assessment of Trophic Status of Estuaries and Bays in Ireland (ATSEBI) System. Remarkably, significant disparities between the ATSI and ATSEBI System were evident in all domains, except for Mulroy Bay. Overall, our research significantly enhances the accuracy of trophic status assessments in marine ecosystems. The ATSI model, combined with cutting-edge ML techniques and our new classification scheme, represents a promising avenue for evaluating and monitoring trophic conditions in TrC waters. The study also demonstrated the effectiveness of ATSI in assessing trophic status across various waterbodies, including lakes, rivers, and more. These findings make substantial contributions to the field of marine ecosystem management and conservation.

A comprehensive data set of physical and human-dimensional attributes for China's lake basins

Lakes provide water-related ecosystem services that support human life and production. Nevertheless, climate changes and anthropogenic interventions remarkably altered lake and basin hydrology in recent decades, which pose a significant threat to lacustrine ecosystems. Therefore, assessments of lacustrine ecosystems require the spatial and temporal characteristics of key physical and human-dimensional attributes for lakes and lake basins. To facilitate stakeholders obtaining comprehensive data of lake basins in China, we compiled the comprehensive data set for China's lake basins (CODCLAB) mostly from publicly available data sources based on spatial analysis and mathematical statistics methods in this study. The CODCLAB is available in three data formats, including raster layers (Level 1) in "tiff" format, vector shapefiles (Level 2), and attribute tables (Level 3). It covers 767 lakes (>10 km²) in China and their basin extent associating with 34 variables organized into five categories: Hydrology, Topography, Climate, Anthropogenic, and Soils. This unique database will provide basic data for research on the physical processes and socioeconomic activities related to these lakes and their basins in China and expect to feed a broad user community for their application in different areas.

Comparison of caddisfly (Insecta, Trichoptera) assemblages from lake and river habitats of the Huron Mountains of Michigan (USA)

The caddisfly assemblages of six lakes and 12 1^st-4^th order streams of the Huron Mountains of northern Upper Michigan (USA) were sampled monthly with ultraviolet lights during June-September 2019. A total of 169 species representing 63 genera and 19 families was collected, including five species not found elsewhere in Michigan and two species endemic to the state. Species assemblages between lotic and lentic habitats were distinct from each other, with 11 species indicating lakes and 23 indicating rivers. Despite the taxonomic differences, biomass of functional feeding groups (FFGs) was similar between lakes and rivers, except for higher biomass of predators in the former and higher biomass of filtering collectors in the latter. The FFG biomass of both habitat types was dominated (50-70%) by shredders. Considering the undisturbed condition of the habitats, the caddisfly assemblages and FFG biomass of the Huron Mountains can serve as regional biological monitoring reference conditions.

Global hydro-environmental lake characteristics at high spatial resolution

Here we introduce the LakeATLAS dataset, which provides a broad range of hydro-environmental characteristics for more than 1.4 million lakes and reservoirs globally with an area of at least 10 ha. LakeATLAS forms part of the larger HydroATLAS data repository and expands the existing datasets of sub-basin and river reach descriptors by adding equivalent information for lakes and reservoirs in a compatible structure. Matching its HydroATLAS counterparts, version 1.0 of LakeATLAS contains data for 56 variables, partitioned into 281 individual attributes and organized in six categories: hydrology; physiography; climate; land cover & use; soils & geology; and anthropogenic influences. LakeATLAS derives these attributes by processing and reformatting original data from well-established global digital maps at 15 arc-second (~500 m) grid cell resolution and assigns the information spatially to each lake by aggregating it within the lake, in a 3-km vicinity buffer around the lake, and/or within the entire upstream drainage area of the lake. The standardized format of LakeATLAS ensures versatile applicability in hydro-ecological assessments from regional to global scales.

Measurement(s)	hydro-environmental characteristics • lake • water body • hydrographic feature
Technology Type(s)	digital curation
Sample Characteristic - Environment	freshwater environment • aquatic environment
Sample Characteristic - Location	Earth (planet)

Natural and anthropogenic controls on lake water-level decline and evaporation-to-inflow ratio in the conterminous United States

Lake water levels are integral to lake function, but hydrologic changes from land and water management may alter lake fluctuations beyond natural ranges. We constructed a conceptual model of multifaceted drivers of lake water-levels and evaporation-to-inflow ratio (Evap:Inflow). Using a structural equation modeling framework, we tested our model on 1) a national subset of lakes in the conterminous United States with minimal water management to describe natural drivers of lake hydrology and 2) five ecoregional subsets of lakes to explore regional variation in water management effects. Our model fit the national and ecoregional datasets and explained up to 47% of variation in Evap:Inflow, 38% of vertical water-level decline, and 79% of horizontal water-level decline (littoral exposure). For lakes with minimal water management, Evap:Inflow was related to lake depth (β = -0.31) and surface inflow (β = -0.44); vertical decline was related to annual climate (e.g., precipitation β = -0.18) and water management (β = -0.21); and horizontal decline was largely related to vertical decline (β = 0.73) and lake morphometry (e.g., depth β = -0.18). Anthropogenic effects varied by ecoregion and likely reflect differences in regional water management and climate. In the West, water management indicators were related to greater vertical decline (β = 0.38), whereas in the Midwest, these indicators were related to more stable and full lake levels (β = -0.22) even during drought conditions. National analyses show how human water use interacts with regional climate resulting in contrasting impacts to lake hydrologic variation in the US.

Risk and Impact Assessment of Dams in the Contiguous United States Using the 2018 National Inventory of Dams Database

Aging water infrastructure in the United States (U.S.) is a growing concern. In the U.S., over 90,000 dams were registered in the 2018 National Inventory of Dams (NID) database, and their average age was 57 years old. Here, we aim to assess spatiotemporal patterns of the growth of artificial water storage of the existing dams and their hazard potential and potential economic benefit. In this study, we use more than 70,000 NID-registered dams to assess the cumulative hazard potential of dam failure in terms of the total number and the cumulative maximum storage of dams over the 12 National Weather Service River Forecast Center (RFC) regions. In addition, we also estimate potential economic benefits of the existing dams based on their cumulative storage capacity. Results show that the ratios of the cumulative storage capacity to the long-term averaged precipitation range from 8% (Mid-Atlantic) to 50% (Colorado), indicating the significant anthropogenic contribution to the land surface water budget. We also find that the cumulative storage capacity of the dams with high (probable loss of human life is if the dam fails) and significant (potential economic loss and environmental damage with no probable casualty) hazard potential ranges from 50% (North Central) to 98% (Missouri and Colorado) of the total storage capacity within the corresponding region. Surprisingly, 43% of the dams with either high or significant potential hazards have no Emergency Action Plan. Potential economic benefits from the existing dams range from $0.7 billion (Mid Atlantic) to $15.4 billion (West Gulf). Spatiotemporal patterns of hazard potential and economic benefits from the NID-registered dams indicate a need for the development of region-specific preparation, emergency, and recovery plans for dam failure. This study provides an insight about how big data, such as the NID database, can provide actionable information for community resilience toward a safer and more sustainable environment.