Environmental Monitoring Commons^™

Data Fusion And Synergy Of Active And Passive Remote Sensing; An Application For Freeze Thaw Detections, Zahra Sharifnezhadazizi

Dissertations and Theses

There has been a recent evolvement in the field of remote sensing after increase of number satellites and sensors data which could be fused to produce new data and products. These efforts are mainly focused on using of simultaneous observations from different platforms with different spatial and temporal resolutions. The research dissertation aims to enhance the synergy use of active and passive microwave observations and examine the results in detection land freeze and thaw (FT) predictions. Freeze thaw cycles particularly in high-latitude regions have a crucial role in many applications such as agriculture, biogeochemical transitions, hydrology and ecosystem studies. The …

Long Term Nutrient And Chlorophyll A Dynamics Across Long Island Sound And Impacts On Dissolved Oxygen Conditions Within The Western Sound (1991-2019), Sherry Perreira

Dissertations and Theses

Nitrogen overload, eutrophication, and hypoxia have been challenging and persistent water quality problems in Long Island Sound (LIS) over the past decades with major impacts on commercial industries, ecology, and recreational activities in the region. Recognizing these problems, the EPA enforced three phases of the Clean Water Act (CWA) to reduce nitrogen loads in an effort to improve this important estuary. This study examines how nitrogen (NH₃, NO_x & TDN), chlorophyll a (CHLA), and dissolved oxygen (DO) concentrations changed in LIS over the past 30 years, in response to water quality regulations as well as changes in …

On The Improvements Of Boundary-Layer Representation For High Resolution Weather Forecasting In Costal-Urban Environments, David Melecio-Vazquez

Dissertations and Theses

As large urban centers around the world become more densely populated, the global conversion from natural to man-made land surfaces will only increase. These land-use changes affect the urban surface energy budget which in turn changes the structure of the planetary boundary layer (PBL) above. With current high-performance computing systems, meteorological and built environment information can be better utilized to quantify the anthropogenic effects of these modifications. Although these systems have improved forecasting near-surface weather conditions, a comprehensive approach to represent urban impacts on the PBL is still limited. Improved PBL representation can lead to better weather and climate forecasts, …

Toward Closing The Urban Surface Energy Balance Using Satellite Remote Sensing, Joshua Hrisko

Dissertations and Theses

The energy exchanges at the Earth’s surface are responsible for many of the processes that govern weather, climate, human health, and energy use. This exchange, commonly known as the surface energy balance (SEB), determines the near-surface thermodynamic state by partitioning the available energy into surface fluxes. The net all-wave radiation is often the primary energy source, while the heat storage and sensible and latent heat fluxes account for the majority of energy distributed elsewhere. While the SEB of various natural environments(trees, crops, soils) has been well-observed and modeled, the urban surface energy balance remains elusive. This is due to the …

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, …