Developing an Automated Water Quality Prediction System using Machine Learning

Local Chapter Kigali, Rwanda Chapter

Coordinated byRwanda ,

Status: Completed

Project Duration: 20 May 2023 - 30 Jun 2023

Open Source resources available from this project

Project background.

Rwanda is a landlocked country located in East Africa, with a population of approximately 13 million people. Despite efforts to improve access to clean water, access remains a critical challenge, particularly in rural areas. According to UNICEF, only 47% of the population has access to basic water services, and only 32% have access to safely managed drinking water services. One of the challenges in ensuring access to clean water is predicting and monitoring water quality. Traditional water quality prediction and monitoring methods are often time-consuming, costly, and may not provide timely and accurate information. This can lead to delays in identifying and addressing water quality issues, putting public health and agricultural productivity at risk.

Machine learning has the potential to revolutionize water quality prediction and monitoring by providing a faster, more accurate, and cost-effective method for predicting water quality. By analyzing large datasets of water quality parameters, machine learning models can identify patterns and relationships between different parameters, enabling accurate predictions of water quality.

The problem.

Access to clean water is a critical challenge in many parts of the world, including Rwanda. Water quality prediction is important for ensuring the availability of safe and clean water for drinking, agriculture, and other purposes. However, traditional methods for water quality prediction are often time-consuming and costly, and they may not provide accurate and timely information. To address this challenge, the Omdena Rwanda Chapter has initiated a project to develop an automated water quality prediction system using machine learning.

Project goals.

In this project, the Omdena Rwanda Chapter’s primary goal in this project is to develop an accurate and efficient machine learning model that can predict water quality based on a range of parameters such as Electrical conductivity of water, Amount of organic carbon in ppm, Amount of Trihalomethanes in μg/L, and turbidity. The model will be trained on a large dataset of historical water quality data and will be designed to provide predictions for water quality.

Project plan.

  • Week 1

    Research previous work and Data Collection

  • Week 2

    Data Collection

  • Week 3

    Exploratory Data Analysis

  • Week 4

    Preprocessing and feature engineering

  • Week 5

    Model Development

  • Week 6

    Model Training

  • Week 7

    Model Analysis and Interpretation

  • Week 8

    App Development

Learning outcomes.

Machine Learing, preprocessing, feature extraction, machine learning modeling, and app development

Share project on: