Physical Sciences and Mathematics Commons^™

Use Of Uav Imagery And Nutrient Analyses For Estimation Of The Spatial And Temporal Contributions Of Cattle Dung To Nutrient Cycling In Grazed Ecosystems, Amanda Shine

Department of Agronomy and Horticulture: Dissertations, Theses, and Student Research

Nutrient inputs from cattle dung are crucial drivers of nutrient cycling processes in grazed ecosystems. These inputs are important both spatially and temporally and are affected by variables such as grazing strategy, water location, and the nutritional profile of forage being grazed. Past research has attempted to map dung deposition patterns in order to more accurately estimate nutrient input, but the large spatial extent of a typical pasture and the tedious nature of identifying and mapping individual dung pats has prohibited the development of a time- and cost-effective methodology. The first objective of this research was to develop and validate …

Towards Improving Accuracy And Interpretability Of Deep Learning Based On Satellite Image Classification, Yamile Patino Vargas

Dissertations and Theses

ABSTRACT

The study of satellite images provides a way to monitor changes in the surface of the Earth and the atmosphere. Convolutional Neural Networks (CNN) have shown accurate results in solving practical problems in multiple fields. Some of the more recognized fields using CNNs are satellite imagery processing, medicine, communication, transportation, and computer vision. Despite the success of CNNs, there remains a need to explain the network predictions further and understand what the network is determining as valuable information.

There are several frameworks and methodologies developed to explain how CNNs predict outputs and what their internal representations are [1, 4, …