Engineering Commons^™

Supervised Machine Learning Techniques Applied To Low-Cost Air Quality Sensor Suites, Peter Wahman

All Undergraduate Theses and Capstone Projects

Low-cost PM sensors have garnered interest for their ability to reduce the cost of investigating PM concentrations in both indoor and outdoor spaces. They perform well in high concentration lab testing with correlation coefficients greater than 0.9. In real-world applications, the correlation coefficients drop significantly because of sensing floors and adverse ambient conditions. There are plenty of supervised machine learning techniques that aim to correct the measurements ranging from linear regression to more advanced neural networks and random forests. This work aims to use those more complicated techniques to adjust the measurements using other data sets gathered by a sensor …

Applications Of Drones In Atmospheric Chemistry, Travis J. Schuyler

Theses and Dissertations--Chemistry

The emission of greenhouse gases (GHGs) has changed the composition of the atmosphere during the Anthropocene. A major technical and scientific challenge is quantifying the resulting fugitive trace gas fluxes under variable meteorological conditions. Accurately documenting the sources and magnitude of GHGs emission is an important undertaking for discriminating contributions of different processes to radiative forcing. Therefore, the adverse environmental and health effects of undetected gas leaks motivates new methods of detecting, characterizing, and quantifying plumes of fugitive trace gases. Currently, there is no mobile platform able to quantify trace gases at altitudes(UASs), or drones, can be deployed on-site in …

Decomposing A Watershed’S Nitrate Signal Using Spatial Sampling And Continuous Sensor Data, Evan Clare

Theses and Dissertations--Civil Engineering

Watershed features, physiographic setting, geology, climate, and hydrologic processes combine to produce a time-variant nutrient concentration signal at the watershed outlet. Anthropogenic influences, such as increased agricultural pressures and urbanization, have increased overall nutrient loadings delivered to the fluvial network. The impact of such increased nutrient loadings on Kentucky’s drinking water remains a potential threat to the region.

By coupling spatial sampling of nitrate concentrations in surface water with contemporary nutrient and water quality sensor technology, a decomposition of the Upper South Elkhorn watershed’s nitrate signal and an estimation of source timing and loading in the watershed was completed. The …