Nitrogen contamination in groundwater of the Southern Lake Michigan region endangers both the potability of well water in the region and contributes a source of ‘legacy nitrogen’ to the surface waters of the southern Lake Michigan region. Using a data-driven approach leveraging machine learning and GIS, this graduate student scholars project will for the first time provide an estimate of how much nitrate is stored within the aquifers of the Upper Mississippi River Basin and Lake Michigan watersheds.
Found 133 Results
Application of Automated Remote Sensing and Deep Learning to Small Reservoir Identification and Water Quality Modeling in Lake Michigan Watersheds
The overarching goal of this graduate student scholars project is to better evaluate the effects of small dams and reservoirs on changing the flow of nutrients to downstream water bodies and water quality across Lake Michigan Watersheds. There are two primary objectives associated with this goal: (1). Small reservoir identification through a combination of remote-sensing and deep-learning approaches and reservoir dataset development with associated information (reservoir location, surface area, storage volume, catchment drainage area, and residence time). 2). Using hydrologic modelling and USGS water quality data collected above and below reservoirs to quantify the spatially and temporally varying effects of small reservoirs on water quality (nutrient runoff and retention). This proposed research is of pressing concern due to increased release of legacy contaminants to surface and groundwater around Lake Michigan.
Aquatic invasive species pose a serious threat to aquatic ecosystems. In the Great Lakes, new fish species that are non-native to the environment have been introduced due to transoceanic activities. These species compete with native species causing a heavy toll on the environment and economy by shifting ecological balances and disrupting food chains. While many methods exist to sample fish, due to the increasing availability of underwater video, fish can now be sampled by crowd sourcing or using Image recognition techniques. These methods have highlighted the challenges associated with identifying fish based on their appearance against a cluttered background. This graduate student scholars project aims to identify and model fish behavior in underwater video using machine learning methods that are suited for classification of classification of time series data. Video data of round goby (Neogobius melanostomus) from literature will be used to test the approach. The methods proposed here will significantly increase the usability of existing datasets and enable the creation of life-like animations for use in virtual training environments.
Assessing the ecological impacts of Eastern Banded Killifish: a native transplant species rapidly expanding its range in Illinois and Indiana
In North America, there are two subspecies of Banded Killifish (Fundulus diaphanus): the Eastern Banded Killifish (F. d. diaphanus) and the Western Banded Killifish (F. d. menona). While Banded Killifish are considered secure across their range, some populations of Western Banded Killifish are considered Vulnerable or Threatened and populations of Eastern Banded Killifish are expanding rapidly into new regions. Subtle differences in the ecology between subspecies has been found to have strong effects on community composition and energy pathways in freshwater ecosystems. Potential ecological differences between Eastern and Western Banded Killifish are unstudied, therefore through this graduate student scholars project we seek to investigate the trophic ecology of Banded Killifish populations from Illinois and Indiana. Using stable isotope analysis, we can determine whether there is an ecological difference in trophic position and dietary niche width between the two subspecies, as well as how the invasion of the Eastern subspecies could impact the Western subspecies and freshwater communities or ecosystems more generally.
Cities can be shaped to mitigate potential risks and improve the safety of citizens. However, modifying the urban setting to expand autonomous vehicle safety could negatively impact the community’s water systems health. This graduate student scholars research project aims to leverage a shift in transportation technologies, in a period of climate crisis, for the benefit and safety of people and natural systems – including water systems. This researcher will compile ideas on a multidisciplinary effort, representing different aspects of the city and diverse effects on the influence of technology in urban water systems to present a comprehensive document that questions the possible outcomes in the physical, political, and social aspects.
Using Habitat Suitability Modeling to Determine the Vulnerability of Rare Illinois Plant Species to Climate Change
Through this graduate student scholars project, I will expand the impact of my research using habitat suitability modeling (HSM) to map the distribution of Illinois wetland rare plant species and assess their vulnerability to climate change. Using HSM, I will determine the required niche conditions for two species, Epilobium strictum and Rhynchospora alba and identify locations of suitable habitat in Illinois. To evaluate the accuracy of my models, I will conduct field monitoring of all known populations, as well as sites designated as suitable by the models to potentially discover new populations. The monitoring data collected will be added to the HSM, which I will use to test the possible response of these species to predicted climate scenarios. Rare plant conservation efforts require informed climate strategies to implement urgently-needed species protections and prevent unnecessary climate extinctions.