Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 11 views

    Concept Note WRC

    Uploaded by

    Alex Kuhudzai
    This document proposes developing an artificial intelligence water quality prediction model to address South Africa's problem of microbial contamination in its rivers and dams. The model would use multi-task deep learning to capture the correlation between different waterbody sections' quality, improving on current methods. It would provide a reliable basis for water pollution management and monitoring. The project would uniquely combine quantitative projections with AI and be the first such model applied in South Africa. The output would be a water quality prediction model with an estimated total budget of R290,000.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Concept Note WRC

    Uploaded by

    Alex Kuhudzai
    11 views2 pages
    This document proposes developing an artificial intelligence water quality prediction model to address South Africa's problem of microbial contamination in its rivers and dams. The model would use multi-task deep learning to capture the correlation between different waterbody sections' quality, improving on current methods. It would provide a reliable basis for water pollution management and monitoring. The project would uniquely combine quantitative projections with AI and be the first such model applied in South Africa. The output would be a water quality prediction model with an estimated total budget of R290,000.

    Original Description:

    PhD concept note

    Original Title

    Concept note WRC[1]

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document proposes developing an artificial intelligence water quality prediction model to address South Africa's problem of microbial contamination in its rivers and dams. The model would use multi-task deep learning to capture the correlation between different waterbody sections' quality, improving on current methods. It would provide a reliable basis for water pollution management and monitoring. The project would uniquely combine quantitative projections with AI and be the first such model applied in South Africa. The output would be a water quality prediction model with an estimated total budget of R290,000.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    11 views2 pages

    Concept Note WRC

    Uploaded by

    Alex Kuhudzai
    This document proposes developing an artificial intelligence water quality prediction model to address South Africa's problem of microbial contamination in its rivers and dams. The model would use multi-task deep learning to capture the correlation between different waterbody sections' quality, improving on current methods. It would provide a reliable basis for water pollution management and monitoring. The project would uniquely combine quantitative projections with AI and be the first such model applied in South Africa. The output would be a water quality prediction model with an estimated total budget of R290,000.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 2

    Title: USING ARTIFICAL INTELLIGENCE TO CREATE A WATER QUALITY

    PREDICTION MODEL

    Thematic Area
    THEME 3: WATER QUALITY AND HEALTH

    Motivation: Background to your proposal


    South Africa’s rivers and dams have a “severe” problem of microbial contamination
    from faecal pollutants; 53% of the sites that were recently sampled are a risk to
    people’s health risk if crops eaten raw are irrigated using this water, a new
    government report states. Only 42% indicated a low risk, according to the
    department of water and sanitation’s National State of Water Report 2022.

    Full-contact recreational activities such as swimming, washing laundry and baptisms


    are now no longer ideal in areas such as the Vaal, where the water quality of the Vaal
    dam continues to deteriorate. The contamination of water resources by faecal
    pollutants poses significant risks to human and animal health because numerous
    pathogens are associated with faeces. According to the above report by DWS
    “Surface water resources are usually not suitable for domestic activities such as
    drinking without any sort of treatment and this is evident in the data,”. “The
    microbiological results indicate that all the collected samples had high microbial
    contamination and the water from that source was not suitable for drinking.”

    This would pose a high risk of infection to humans if water was consumed directly
    from the source. Treating the water at the household level can reduce the potential
    health risk in situations where water is not severely polluted. There was a low risk
    of infection if water was consumed after limited treatment in 42% of the sampled
    sites.
    What is the problem you envision to solve.
    Water quality prediction is a fundamental and necessary task for the prevention and
    management of water environment pollution. Due to the fluidity of water, different
    sections of the same waterbody have similar trends in their water quality. The present
    water quality prediction methods cannot exploit the correlation between the water
    quality of each section to deeply capture information because they do not take into
    account how similar the water quality is between sections. In order to address this
    issue, it is important to construct a water quality prediction model based on multi-
    task deep learning, taking the chemical oxygen demand (COD) of the water
    environment.
    Specific aims of the project.
    The aim of this project is to develop an application prediction model, which
    can provide new methods for water quality management and a reliable basis for river
    prevention and control, and effectively improve the efficiency of water pollution
    monitoring.

    Indicate what makes your project unique


    The uniqueness of this project lies in the facts that
    1. This project combines quantitative mathematical projections that use
    statistical classifiers to determine the water quality of an area with artificial
    intelligence to produce the said model, and
    2. It is the first time that such a model will be developed and applied in South
    Africa.

    What is the specific Project Output(s)


    The project output would be a Water Quality Prediction Model.

    Estimated total budget (incl. VAT)


    Task Name Cost
    Data Collection R35 000
    Draft Model Application R65 000
    Site Visit and Water Sampling R145 000
    Final Model R45 000
    Total Cost R290 000

    You might also like