Collecting remote sensing data from uncrewed aerial systems, also known as drones, is an efficient and widely recognized method for studying the effects of extreme windstorms. Windstorms, such as hurricanes, tornadoes, and straight-line winds, cause damage to both built and natural environments. Post-event damage surveys commonly use the Enhanced Fujita (EF) scale to relate structural damage to wind speeds; however, this scale has limited application in rural areas and forests. Rural areas, which constitute a significant portion of the US and face a high risk of windstorms, are typically sparsely populated with few structures. As a result, the relationship between wind speed and the impact on natural and agricultural systems remains highly uncertain. Remote sensing data, including high-resolution imagery and point clouds, can capture valuable perishable information about the distribution, orientation, and severity of damage, contributing to our understanding of windstorms. This research aims to develop workflows that analyze remote sensing data using computer vision and artificial intelligence techniques. By doing so, we seek to understand the wind hazard and response of both the built and natural environment, with a specific emphasis on forests.
Advisor Name: | Richard Wood | |
Email: | rwood@unl.edu | |
Website: | https://engineering.unl.edu/cee/richard-wood/ | |
Advisor College: | Engineering | |
Advisor Department: | Civil and Environmental Engineering | |
Potential Student Tasks: | Responsibilities will include reading and learning about artificial intelligence and machine learning techniques using remote sensing data and geomatics data. Additionally, this will involve field training for data collection, as well as data analysis with graduate student(s) and the faculty advisor. Trainees will attend regular meetings and present their progress throughout the semester. | |
Student Qualifications: | Students with an interest in data from drones, forests, civil engineering, and the natural environment, as well as artificial intelligence applications and other complementary fields, are encouraged to apply. Students from any major or field of study may apply, but this opportunity may be particularly appealing to those in Engineering, Natural Resources, Ecology, and Computer Science. | |
Training, Mentoring, and Workplace Community: | Student trainees can expect a close working relationship within an engaging team environment that is supportive and collaborative in nature. This entails frequent personal interactions with both the faculty advisor and a complementary relationship with a graduate student as well. Student schedules can be flexible, allowing for remote work when feasible, with resources accessible through the cloud or remote desktop. | |
Available Positions | 2 |