Skip to content

Latest commit

 

History

History
82 lines (61 loc) · 3.62 KB

README.md

File metadata and controls

82 lines (61 loc) · 3.62 KB
Raw

CHLA and TSS inference through Machine Learning

This repository features a Machine Learning and Remote Sensing technique to predict the concentration of Chlorophyll-a and Total Suspended Solid in water bodies.

This method was developed by Vizlab | X-Reality and GeoInformatics Lab as an alternative to monitor Total Suspended Solids (TSS) and chlorophyll-a concentration, two critical parameters to monitor water quality. Since directly collecting samples for laboratory analysis can be expensive, this methodology estimates this information through remote sensing and Machine Learning (ML) techniques. This method was accessed and evaluated separately in two study areas, where both TSS and chlorophyll-a models achieved R-squared values above 0.8

Results

Published articles

For a more in-depth understanding of the method, please consider reading the published paper below that employed and validated this method. To cite each of them please consult the How to cite section.

A Method for Chlorophyll-a and Suspended Solids Prediction through Remote Sensing and Machine Learning

Authors: Lucas Silveira Kupssinskü, Tainá Thomassim Guimarães, Eniuce Menezes de Souza, Daniel C. Zanotta, Mauricio Roberto Veronez and Luiz Gonzaga, Jr

Published in: Sensors MDPI

Table of contents

Requirements

numpy
pandas
sklearn
keras
scipy
seaborn
matplotlib

Usage

This code is ready to run on google colab environment, the data is also avaliable in this repository. Just follow the link bellow and import the xls data files into your environment.

Google Colab

How to cite

If you find our work useful in your research please consider citing our paper:

@article{Silveira_Kupssinsk__2020, 
  title={A Method for Chlorophyll-a and Suspended Solids Prediction through 
         Remote Sensing and Machine Learning}, 
  volume={20}, 
  ISSN={1424-8220}, 
  url={http://dx.doi.org/10.3390/s20072125}, 
  DOI={10.3390/s20072125}, 
  number={7}, 
  journal={Sensors}, 
  publisher={MDPI AG}, 
  author={Silveira Kupssinskü, Lucas and 
          Thomassim Guimarães, Tainá and 
          Menezes de Souza, Eniuce and 
          C. Zanotta, Daniel and 
          Roberto Veronez, Mauricio and 
          Gonzaga, Luiz and 
          Mauad, Frederico Fábio}, 
  year={2020}, 
  month={Apr}, 
  pages={2125}
}

Credits

This work is credited to the Vizlab | X-Reality and GeoInformatics Lab and the following authors and developers: Lucas Silveira Kupssinskü and Tainá Thomassim Guimarães

License

MIT Licence (https://mit-license.org/)