Classification of Watsan and Energy Technologies Using Machine Learning Techniques

  • Hala Al Nuaimi

    Student thesis: Master's Thesis

    Abstract

    The water and sanitation technologies to be implemented in a community need to be accessible and affordable by all people living in the area and more importantly, to be sustainable. Based on a study done by the Rural Water Supply Network, 15% to 30% of installed infrastructure of water supply and sanitation (watsan) in rural areas of developing countries are currently not operating [4]. The reason for this high rate of failure is due to inappropriate watsan technologies that were implemented. The available decision support system are mostly guidance documents or technical fact sheets which make it important to have a smart decision-making support tool that is effective, efficient, and easy to use. This research presents a decision framework that can be used to select and implement appropriate watsan technologies. This decision model is made up of three modules, namely assessment, evaluation, and management. The assessment module itself has two components. The first component includes an analysi called the capacity factor analysis that is used to assess the capacity of a community to manage local water and sanitation services. The second component is a decision support system that is used to select sustainable watsan technologies, classified by their capacity requirement level metric. This research focuses on the second component, the decision support system (DSS) for the selection of watsan technologies, and more specifically on the classification of the watsan technology options used in the DSS. The classification methods proposed are based on Machine Learning algorithms. A large set of water supply technologies is used to demonstrate the application of the proposed classification method with three classification algorithms. The three classification algorithms were studied, tested and evaluated in this research.
    Date of AwardDec 2021
    Original languageAmerican English

    Keywords

    • Machine learning
    • Decision Support Systems
    • Watsan
    • Random Forest
    • Support Vector Machine
    • Logistic Regression.

    Cite this

    '