Prediction Of Water Quality In River

Solution Overview

 

The River Krishna and its tributaries drain three important states of South India. The river water plays a very important role in the overall socio-economic development of Andhra Pradesh. It is very helpful if we can predict the pollution level based on studies and data, which will be very helpful for the government to implement further plans for the prevention of water pollution and enhancing the water quality.

 

I have used the data which is made available by the Indian Government for research and analysis on their site.

 

Here is the link to the CSV file of Water quality of River Krishna.

 

This dataset has huge data with parameters such as pH, Temperature, Nitrate Content, Conductivity, and Fecal Coliform that helps us to evaluate water quality.

 

I have used Machine Learning in Azure and processed this data that will help us to predict the quality of River Krishna for years. It is necessary to make a detailed study of the water quality of the river, to estimate the level of pollution and also the main sources of pollution. Correlation studies explain the relationships, between dissolved solids concentration and land use of the basins. This can be useful for planning land use controls in the integrated water quality management program.

 

Technical Architecture

 

In Azure, I have selected ->Data Analytics and Machine Learning. Then created an ML workspace. Then in ML studio, I have created a new experiment. The technical architecture is the following: 

1. Uploaded data.
2. Build and validate a model.
3. Created a web service that uses your trained models to make fast, live predictions
    
    

Solution Details

 

After creating a new experiment in ML Studio

1. I have uploaded the dataset from the following website.
2. Then I begin by identifying columns that add little-to-no value for predictive modeling.
3. I define values that are non-continuous by casting them as categorical.
4. Cleaned data, we must make sure our dataset contains no missing, “null”, or “NA” values.
5. Model Building.
6. Training the Model.
7. Model Evaluation.
8. Published to the gallery.
9. Set up the web service.

The prediction can help in planning land use controls in an integrated water quality management program.

 

Relevant screenshots of services used from the Azure portal

 

 

 

 

 

 

 

 

Solution URLs

 

Here I am sharing my solution, you can copy it in your ML dashboard and can play around this.