Date of Award

12-2023

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

Committee Chair/Advisor

Dr. Nathan McNeese

Committee Member

Dr. Vidya Samadi

Committee Member

Dr. Feng Luo

Abstract

The powers that artificial intelligence (AI) has developed are astounding, with recent success in integrating into a human cognitive workflow. AI will attain its full potential only if, as part of its intelligence, it also actively teams up with humans to co-create solutions. Combining AI simulation with human understanding and strategic abilities through data convergence may optimize the process and provide a capacity akin to "teaming intelligence." This thesis will introduce the concepts of Human AI Convergence (HAC) capabilities for flood evacuation decision-making. The concept introduced in this thesis is the first step toward the HAC concept in weather disaster applications. This research demonstrates a synergy between humans and AI by integrating the data produced by humans through social media with an AI system to enhance a flood evacuation decision-making problem. The prediction from Long short-term memory (LSTM) and a river hydraulic model, i.e., Height Above Nearest Drainage (HAND), is integrated with human data from X (previously Twitter) to visualize flood inundation areas, which acts as a 3rd party agent for a HAC system. The goal is to synthesize and analyze HAC competence in flood evacuation emergency management and harness the full potential of AI as a partner in real-time planning and decision-making. This thesis has explored why HAC intelligence is essential to emergency planning and decision-making, providing a general structure for researchers to use HAC to devise effective systems that cooperate well and evaluate state-of-the-art, and, in doing so, providing a research agenda and a roadmap for future flood evacuation emergency management, rescue, and decision making. This state-of-the-art flood evacuation product stands to advance the frontier of human-AI collaborative research significantly.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.