Global Water Quality of Inland Waters with Harmonized Landsat-8 and Sentinel-2 Using Cloud-Computed Machine Learning
(2023) In Remote Sensing 15(5).- Abstract
Modeling inland water quality by remote sensing has already demonstrated its capacity to make accurate predictions. However, limitations still exist for applicability in diverse regions, as well as to retrieve non-optically active parameters (nOAC). Models are usually trained only with water samples from individual or local groups of waterbodies, which limits their capacity and accuracy in predicting parameters across diverse regions. This study aims to increase data availability to understand the performance of models trained with heterogeneous databases from both remote sensing and field measurement sources to improve machine learning training. This paper seeks to build a dataset with worldwide lake characteristics using data from... (More)
Modeling inland water quality by remote sensing has already demonstrated its capacity to make accurate predictions. However, limitations still exist for applicability in diverse regions, as well as to retrieve non-optically active parameters (nOAC). Models are usually trained only with water samples from individual or local groups of waterbodies, which limits their capacity and accuracy in predicting parameters across diverse regions. This study aims to increase data availability to understand the performance of models trained with heterogeneous databases from both remote sensing and field measurement sources to improve machine learning training. This paper seeks to build a dataset with worldwide lake characteristics using data from water monitoring programs around the world paired with harmonized data of Landsat-8 and Sentinel-2. Additional feature engineering is also examined. The dataset is then used for model training and prediction of water quality at the global scale, time series analysis and water quality maps for lakes in different continents. Additionally, the modeling performance of nOACs are also investigated. The results show that trained models achieve moderately high correlations for SDD, TURB and BOD (R2 = 0.68) but lower performances for TSM and NO3-N (R2 = 0.43). The extreme learning machine (ELM) and the random forest regression (RFR) demonstrate better performance. The results indicate that ML algorithms can process remote sensing data and additional features to model water quality at the global scale and contribute to address the limitations of transferring and retrieving nOAC. However, significant limitations need to be considered, such as calibrated harmonization of water data and atmospheric correction procedures. Moreover, further understanding of the mechanisms that facilitate nOAC prediction is necessary. We highlight the need for international contributions to global water quality datasets capable of providing extensive water data for the improvement of global water monitoring.
(Less)
- author
- Arias-Rodriguez, Leonardo F. ; Tüzün, Ulaş Firat ; Duan, Zheng LU ; Huang, Jingshui ; Tuo, Ye and Disse, Markus
- organization
- publishing date
- 2023-03
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- global modeling, harmonize RS data, machine learning, remote sensing, water quality
- in
- Remote Sensing
- volume
- 15
- issue
- 5
- article number
- 1390
- publisher
- MDPI AG
- external identifiers
-
- scopus:85149941197
- ISSN
- 2072-4292
- DOI
- 10.3390/rs15051390
- language
- English
- LU publication?
- yes
- id
- 4b66e14e-5ceb-4cc0-b092-f04c5ebcbf8a
- date added to LUP
- 2023-05-22 15:38:01
- date last changed
- 2023-05-22 15:38:01
@article{4b66e14e-5ceb-4cc0-b092-f04c5ebcbf8a,
abstract = {{<p>Modeling inland water quality by remote sensing has already demonstrated its capacity to make accurate predictions. However, limitations still exist for applicability in diverse regions, as well as to retrieve non-optically active parameters (nOAC). Models are usually trained only with water samples from individual or local groups of waterbodies, which limits their capacity and accuracy in predicting parameters across diverse regions. This study aims to increase data availability to understand the performance of models trained with heterogeneous databases from both remote sensing and field measurement sources to improve machine learning training. This paper seeks to build a dataset with worldwide lake characteristics using data from water monitoring programs around the world paired with harmonized data of Landsat-8 and Sentinel-2. Additional feature engineering is also examined. The dataset is then used for model training and prediction of water quality at the global scale, time series analysis and water quality maps for lakes in different continents. Additionally, the modeling performance of nOACs are also investigated. The results show that trained models achieve moderately high correlations for SDD, TURB and BOD (R<sup>2</sup> = 0.68) but lower performances for TSM and NO3-N (R<sup>2</sup> = 0.43). The extreme learning machine (ELM) and the random forest regression (RFR) demonstrate better performance. The results indicate that ML algorithms can process remote sensing data and additional features to model water quality at the global scale and contribute to address the limitations of transferring and retrieving nOAC. However, significant limitations need to be considered, such as calibrated harmonization of water data and atmospheric correction procedures. Moreover, further understanding of the mechanisms that facilitate nOAC prediction is necessary. We highlight the need for international contributions to global water quality datasets capable of providing extensive water data for the improvement of global water monitoring.</p>}},
author = {{Arias-Rodriguez, Leonardo F. and Tüzün, Ulaş Firat and Duan, Zheng and Huang, Jingshui and Tuo, Ye and Disse, Markus}},
issn = {{2072-4292}},
keywords = {{global modeling; harmonize RS data; machine learning; remote sensing; water quality}},
language = {{eng}},
number = {{5}},
publisher = {{MDPI AG}},
series = {{Remote Sensing}},
title = {{Global Water Quality of Inland Waters with Harmonized Landsat-8 and Sentinel-2 Using Cloud-Computed Machine Learning}},
url = {{http://dx.doi.org/10.3390/rs15051390}},
doi = {{10.3390/rs15051390}},
volume = {{15}},
year = {{2023}},
}