Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Smart water monitoring for better water quality - An affordable and sustainable way to predict unexpected environmental changes of water bodies

Yang, Chia-Wen LU (2023) In Master Thesis Series in Environmental Studies and Sustainability Science MESM02 20231
LUCSUS (Lund University Centre for Sustainability Studies)
Abstract
This article discusses the challenges associated with maintaining water quality, particularly the issue of eutrophication, and the importance of technology advancements for monitoring and managing water quality. The potential of machine learning is highlighted, along with the importance of affordable and effective water quality monitoring techniques. The study aims to identify factors contributing to eutrophication in Sweden, using various regression models, including Random Forest and XGBOOST. The exploratory data analysis showed that environmental parameters may not have a strong linear relationship with chlorophyll concentration, but other variables such as nutrient availability and light may play a more important role. The random... (More)
This article discusses the challenges associated with maintaining water quality, particularly the issue of eutrophication, and the importance of technology advancements for monitoring and managing water quality. The potential of machine learning is highlighted, along with the importance of affordable and effective water quality monitoring techniques. The study aims to identify factors contributing to eutrophication in Sweden, using various regression models, including Random Forest and XGBOOST. The exploratory data analysis showed that environmental parameters may not have a strong linear relationship with chlorophyll concentration, but other variables such as nutrient availability and light may play a more important role. The random forest model produced the most accurate predictions. The study also discusses the importance of technology diffusion in promoting sustainable water management practices in the Global South and emphasizes the need for collaboration between developed and developing countries. (Less)
Please use this url to cite or link to this publication:
author
Yang, Chia-Wen LU
supervisor
organization
course
MESM02 20231
year
type
H2 - Master's Degree (Two Years)
subject
keywords
Machine learning, technology diffusion, Water quality management, Sustainability Science, Affordable solutions
publication/series
Master Thesis Series in Environmental Studies and Sustainability Science
report number
2023:016
language
English
id
9117652
date added to LUP
2023-05-31 10:25:09
date last changed
2023-05-31 10:25:09
@misc{9117652,
  abstract     = {{This article discusses the challenges associated with maintaining water quality, particularly the issue of eutrophication, and the importance of technology advancements for monitoring and managing water quality. The potential of machine learning is highlighted, along with the importance of affordable and effective water quality monitoring techniques. The study aims to identify factors contributing to eutrophication in Sweden, using various regression models, including Random Forest and XGBOOST. The exploratory data analysis showed that environmental parameters may not have a strong linear relationship with chlorophyll concentration, but other variables such as nutrient availability and light may play a more important role. The random forest model produced the most accurate predictions. The study also discusses the importance of technology diffusion in promoting sustainable water management practices in the Global South and emphasizes the need for collaboration between developed and developing countries.}},
  author       = {{Yang, Chia-Wen}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Master Thesis Series in Environmental Studies and Sustainability Science}},
  title        = {{Smart water monitoring for better water quality - An affordable and sustainable way to predict unexpected environmental changes of water bodies}},
  year         = {{2023}},
}