Matching Items (2)
Filtering by

Clear all filters

Description
In rural and urban areas of Nigeria, dependence on groundwater is increasing since the population is growing and high quality, treated municipal water is scarce. Municipal drinking water is often compromised because of old and leaking distribution pipes. About 58% of the water consumed in Lagos State, Nigeria, comes from

In rural and urban areas of Nigeria, dependence on groundwater is increasing since the population is growing and high quality, treated municipal water is scarce. Municipal drinking water is often compromised because of old and leaking distribution pipes. About 58% of the water consumed in Lagos State, Nigeria, comes from residential wells. However, a majority of residential wells are shallow wells that are constructed relatively close to septic tanks or pit latrines and are therefore subject to contamination. In certain parts of Africa, there is high potential of severe epidemic if water quality is not improved. With increasing reliance on groundwater, a need exists to monitor the quality of groundwater. This thesis develops a plan for a monitoring program for residential wells in Lagos State, Nigeria. The program focuses on ways by which owners can maintain reasonably good water quality, and on the role of government in implementing water quality requirements. In addition, this thesis describes a survey conducted in various areas of Lagos State to assess community awareness of the importance of groundwater quality and its impact on individuals and the community at large. The survey shows that 30% to 40% of the households have located their wells and septic tanks in the same general area. Various templates have been created to help the staff of a future monitoring program team to effectively gather information during site characterization. A "Questions and Answers" leaflet has been developed to educate citizens about the need for monitoring residential wells. 
ContributorsTalabi, Omogbemiga Adepitan (Author) / Edwards, David (Thesis advisor) / Hild, Nicholas (Committee member) / Olson, Larry (Committee member) / Arizona State University (Publisher)
Created2010
161715-Thumbnail Image.png
Description
Understanding the limits and capabilities of an AI system is essential for safe and effective usability of modern AI systems. In the query-based AI assessment paradigm, a personalized assessment module queries a black-box AI system on behalf of a user and returns a user-interpretable model of the AI system’s capabilities.

Understanding the limits and capabilities of an AI system is essential for safe and effective usability of modern AI systems. In the query-based AI assessment paradigm, a personalized assessment module queries a black-box AI system on behalf of a user and returns a user-interpretable model of the AI system’s capabilities. This thesis develops this paradigm to learn interpretable action models of simulator-based agents. Two types of agents are considered: the first uses high-level actions where the user’s vocabulary captures the simulator state perfectly, and the second operates on low-level actions where the user’s vocabulary captures only an abstraction of the simulator state. Methods are developed to interface the assessment module with these agents. Empirical results show that this method is capable of learning interpretable models of agents operating in a range of domains.
ContributorsMarpally, Shashank Rao (Author) / Srivastava, Siddharth (Thesis advisor) / Zhang, Yu (Committee member) / Fainekos, Georgios E (Committee member) / Arizona State University (Publisher)
Created2021