Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Integration of remote sensing and Mexican water quality monitoring system using an extreme learning machine

Arias-Rodriguez, Leonardo F. ; Duan, Zheng LU ; Díaz-Torres, José de Jesús ; Basilio Hazas, Mónica ; Huang, Jingshui ; Kumar, Bapitha Udhaya ; Tuo, Ye and Disse, Markus (2021) In Sensors 21(12).
Abstract

Remote Sensing, as a driver for water management decisions, needs further integration with monitoring water quality programs, especially in developing countries. Moreover, usage of remote sensing approaches has not been broadly applied in monitoring routines. Therefore, it is necessary to assess the efficacy of available sensors to complement the often limited field measurements from such programs and build models that support monitoring tasks. Here, we integrate field measurements (2013–2019) from the Mexican national water quality monitoring system (RNMCA) with data from Landsat-8 OLI, Sentinel-3 OLCI, and Sentinel-2 MSI to train an extreme learning machine (ELM), a support vector regression (SVR) and a linear regression (LR) for... (More)

Remote Sensing, as a driver for water management decisions, needs further integration with monitoring water quality programs, especially in developing countries. Moreover, usage of remote sensing approaches has not been broadly applied in monitoring routines. Therefore, it is necessary to assess the efficacy of available sensors to complement the often limited field measurements from such programs and build models that support monitoring tasks. Here, we integrate field measurements (2013–2019) from the Mexican national water quality monitoring system (RNMCA) with data from Landsat-8 OLI, Sentinel-3 OLCI, and Sentinel-2 MSI to train an extreme learning machine (ELM), a support vector regression (SVR) and a linear regression (LR) for estimating Chlorophyll-a (Chl-a), Turbidity, Total Suspended Matter (TSM) and Secchi Disk Depth (SDD). Additionally, OLCI Level-2 Products for Chl-a and TSM are compared against the RNMCA data. We observed that OLCI Level-2 Products are poorly correlated with the RNMCA data and it is not feasible to rely only on them to support monitoring operations. However, OLCI atmospherically corrected data is useful to develop accurate models using an ELM, particularly for Turbidity (R2 =0.7). We conclude that remote sensing is useful to support monitoring systems tasks, and its progressive integration will improve the quality of water quality monitoring programs.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Chlorophyll-a, Extreme learning machine, Inland waters, Landsat 8 OLI, Secchi disk depth, Sentinel 2 MSI, Sentinel 3 OLCI, Support vector regression, Turbidity, Water quality monitoring system
in
Sensors
volume
21
issue
12
article number
4118
publisher
MDPI AG
external identifiers
  • pmid:34203863
  • scopus:85107832470
ISSN
1424-8220
DOI
10.3390/s21124118
language
English
LU publication?
yes
id
ef0c410e-05e5-4918-90cd-a9530b101ce0
date added to LUP
2021-06-28 14:01:40
date last changed
2024-04-20 07:58:08
@article{ef0c410e-05e5-4918-90cd-a9530b101ce0,
  abstract     = {{<p>Remote Sensing, as a driver for water management decisions, needs further integration with monitoring water quality programs, especially in developing countries. Moreover, usage of remote sensing approaches has not been broadly applied in monitoring routines. Therefore, it is necessary to assess the efficacy of available sensors to complement the often limited field measurements from such programs and build models that support monitoring tasks. Here, we integrate field measurements (2013–2019) from the Mexican national water quality monitoring system (RNMCA) with data from Landsat-8 OLI, Sentinel-3 OLCI, and Sentinel-2 MSI to train an extreme learning machine (ELM), a support vector regression (SVR) and a linear regression (LR) for estimating Chlorophyll-a (Chl-a), Turbidity, Total Suspended Matter (TSM) and Secchi Disk Depth (SDD). Additionally, OLCI Level-2 Products for Chl-a and TSM are compared against the RNMCA data. We observed that OLCI Level-2 Products are poorly correlated with the RNMCA data and it is not feasible to rely only on them to support monitoring operations. However, OLCI atmospherically corrected data is useful to develop accurate models using an ELM, particularly for Turbidity (R<sup>2</sup> =0.7). We conclude that remote sensing is useful to support monitoring systems tasks, and its progressive integration will improve the quality of water quality monitoring programs.</p>}},
  author       = {{Arias-Rodriguez, Leonardo F. and Duan, Zheng and Díaz-Torres, José de Jesús and Basilio Hazas, Mónica and Huang, Jingshui and Kumar, Bapitha Udhaya and Tuo, Ye and Disse, Markus}},
  issn         = {{1424-8220}},
  keywords     = {{Chlorophyll-a; Extreme learning machine; Inland waters; Landsat 8 OLI; Secchi disk depth; Sentinel 2 MSI; Sentinel 3 OLCI; Support vector regression; Turbidity; Water quality monitoring system}},
  language     = {{eng}},
  month        = {{06}},
  number       = {{12}},
  publisher    = {{MDPI AG}},
  series       = {{Sensors}},
  title        = {{Integration of remote sensing and Mexican water quality monitoring system using an extreme learning machine}},
  url          = {{http://dx.doi.org/10.3390/s21124118}},
  doi          = {{10.3390/s21124118}},
  volume       = {{21}},
  year         = {{2021}},
}