Water Quality Analysis Using Machine Learning Algorithms
Shkurin, Aleksei (2016)
Mikkelin ammattikorkeakoulu
2016
All rights reserved
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-201604013772
https://urn.fi/URN:NBN:fi:amk-201604013772
Tiivistelmä
Data analysis is one of the key engines of progress in most of areas of the research in natural sciences, including environmental sciences. Nowadays, continuous development and technological progress provide us with universal and advanced tools for data analysis, such as machine learning algorithms.
The purpose of the research behind this thesis is to provide examples to the engineers and scientists working in environmental field of how these models can be implemented towards the environmental tasks.
The data used for the research is water quality data, produced during the STREAMES (STream REAch Management, an Expert System) project, initially aiming at producing tools for increasing the quality of European rivers.
In this report one will find examples of data imputation, regression, classification, clusterization and feature selection tasks using machine learning algorithms, such as: random forest, support vector machines, neural networks, k-nearest neighbours, and k-means clustering.
The purpose of the research behind this thesis is to provide examples to the engineers and scientists working in environmental field of how these models can be implemented towards the environmental tasks.
The data used for the research is water quality data, produced during the STREAMES (STream REAch Management, an Expert System) project, initially aiming at producing tools for increasing the quality of European rivers.
In this report one will find examples of data imputation, regression, classification, clusterization and feature selection tasks using machine learning algorithms, such as: random forest, support vector machines, neural networks, k-nearest neighbours, and k-means clustering.