Monitoring Water Quality of Valle de Bravo Reservoir, Mexico, Using Entire Lifespan of MERIS Data and Machine Learning Approaches
Remote-sensing-based machine learning approaches for water quality parameters estimation, Secchi Disk Depth (SDD) and Turbidity, were developed for the Valle de Bravo reservoir in central Mexico. This waterbody is a multipurpose reservoir, which provides drinking water to the metropolitan area of Me...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/10/1586 |
| _version_ | 1797567808012288000 |
|---|---|
| author | Leonardo F. Arias-Rodriguez Zheng Duan Rodrigo Sepúlveda Sergio I. Martinez-Martinez Markus Disse |
| author_facet | Leonardo F. Arias-Rodriguez Zheng Duan Rodrigo Sepúlveda Sergio I. Martinez-Martinez Markus Disse |
| author_sort | Leonardo F. Arias-Rodriguez |
| collection | DOAJ |
| description | Remote-sensing-based machine learning approaches for water quality parameters estimation, Secchi Disk Depth (SDD) and Turbidity, were developed for the Valle de Bravo reservoir in central Mexico. This waterbody is a multipurpose reservoir, which provides drinking water to the metropolitan area of Mexico City. To reveal the water quality status of inland waters in the last decade, evaluation of MERIS imagery is a substantial approach. This study incorporated in-situ collected measurements across the reservoir and remote sensing reflectance data from the Medium Resolution Imaging Spectrometer (MERIS). Machine learning approaches with varying complexities were tested, and the optimal model for SDD and Turbidity was determined. Cross-validation demonstrated that the satellite-based estimates are consistent with the in-situ measurements for both SDD and Turbidity, with R<sup>2</sup> values of 0.81 to 0.86 and RMSE of 0.15 m and 0.95 nephelometric turbidity units (NTU). The best model was applied to time series of MERIS images to analyze the spatial and temporal variations of the reservoir’s water quality from 2002 to 2012. Derived analysis revealed yearly patterns caused by dry and rainy seasons and several disruptions were identified. The reservoir varied from trophic to intermittent hypertrophic status, while SDD ranged from 0–1.93 m and Turbidity up to 23.70 NTU. Results suggest the effects of drought events in the years 2006 and 2009 on water quality were correlated with water quality detriment. The water quality displayed slow recovery through 2011–2012. This study demonstrates the usefulness of satellite observations for supporting inland water quality monitoring and water management in this region. |
| first_indexed | 2024-03-10T19:46:45Z |
| format | Article |
| id | doaj.art-82ec975bb2804d12b0380259b10f6061 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T19:46:45Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-82ec975bb2804d12b0380259b10f60612023-11-20T00:43:12ZengMDPI AGRemote Sensing2072-42922020-05-011210158610.3390/rs12101586Monitoring Water Quality of Valle de Bravo Reservoir, Mexico, Using Entire Lifespan of MERIS Data and Machine Learning ApproachesLeonardo F. Arias-Rodriguez0Zheng Duan1Rodrigo Sepúlveda2Sergio I. Martinez-Martinez3Markus Disse4Hydrology and River Basin Management, Technical University of Munich, Arcisstrasse 21, 80333 Munich, GermanyHydrology and River Basin Management, Technical University of Munich, Arcisstrasse 21, 80333 Munich, GermanyDepartment of Sanitary and Environmental Engineering, National Autonomous University of Mexico, Ciudad Universitaria, Mexico City 04510, MexicoCenter of Design and Construction Sciences, Autonomous University of Aguascalientes, Av. Universidad 940, 20131 Aguascalientes, MexicoHydrology and River Basin Management, Technical University of Munich, Arcisstrasse 21, 80333 Munich, GermanyRemote-sensing-based machine learning approaches for water quality parameters estimation, Secchi Disk Depth (SDD) and Turbidity, were developed for the Valle de Bravo reservoir in central Mexico. This waterbody is a multipurpose reservoir, which provides drinking water to the metropolitan area of Mexico City. To reveal the water quality status of inland waters in the last decade, evaluation of MERIS imagery is a substantial approach. This study incorporated in-situ collected measurements across the reservoir and remote sensing reflectance data from the Medium Resolution Imaging Spectrometer (MERIS). Machine learning approaches with varying complexities were tested, and the optimal model for SDD and Turbidity was determined. Cross-validation demonstrated that the satellite-based estimates are consistent with the in-situ measurements for both SDD and Turbidity, with R<sup>2</sup> values of 0.81 to 0.86 and RMSE of 0.15 m and 0.95 nephelometric turbidity units (NTU). The best model was applied to time series of MERIS images to analyze the spatial and temporal variations of the reservoir’s water quality from 2002 to 2012. Derived analysis revealed yearly patterns caused by dry and rainy seasons and several disruptions were identified. The reservoir varied from trophic to intermittent hypertrophic status, while SDD ranged from 0–1.93 m and Turbidity up to 23.70 NTU. Results suggest the effects of drought events in the years 2006 and 2009 on water quality were correlated with water quality detriment. The water quality displayed slow recovery through 2011–2012. This study demonstrates the usefulness of satellite observations for supporting inland water quality monitoring and water management in this region.https://www.mdpi.com/2072-4292/12/10/1586turbiditysecchi disk depthtrophic stateremote sensinggaussian processes regressionsupport vector machines |
| spellingShingle | Leonardo F. Arias-Rodriguez Zheng Duan Rodrigo Sepúlveda Sergio I. Martinez-Martinez Markus Disse Monitoring Water Quality of Valle de Bravo Reservoir, Mexico, Using Entire Lifespan of MERIS Data and Machine Learning Approaches Remote Sensing turbidity secchi disk depth trophic state remote sensing gaussian processes regression support vector machines |
| title | Monitoring Water Quality of Valle de Bravo Reservoir, Mexico, Using Entire Lifespan of MERIS Data and Machine Learning Approaches |
| title_full | Monitoring Water Quality of Valle de Bravo Reservoir, Mexico, Using Entire Lifespan of MERIS Data and Machine Learning Approaches |
| title_fullStr | Monitoring Water Quality of Valle de Bravo Reservoir, Mexico, Using Entire Lifespan of MERIS Data and Machine Learning Approaches |
| title_full_unstemmed | Monitoring Water Quality of Valle de Bravo Reservoir, Mexico, Using Entire Lifespan of MERIS Data and Machine Learning Approaches |
| title_short | Monitoring Water Quality of Valle de Bravo Reservoir, Mexico, Using Entire Lifespan of MERIS Data and Machine Learning Approaches |
| title_sort | monitoring water quality of valle de bravo reservoir mexico using entire lifespan of meris data and machine learning approaches |
| topic | turbidity secchi disk depth trophic state remote sensing gaussian processes regression support vector machines |
| url | https://www.mdpi.com/2072-4292/12/10/1586 |
| work_keys_str_mv | AT leonardofariasrodriguez monitoringwaterqualityofvalledebravoreservoirmexicousingentirelifespanofmerisdataandmachinelearningapproaches AT zhengduan monitoringwaterqualityofvalledebravoreservoirmexicousingentirelifespanofmerisdataandmachinelearningapproaches AT rodrigosepulveda monitoringwaterqualityofvalledebravoreservoirmexicousingentirelifespanofmerisdataandmachinelearningapproaches AT sergioimartinezmartinez monitoringwaterqualityofvalledebravoreservoirmexicousingentirelifespanofmerisdataandmachinelearningapproaches AT markusdisse monitoringwaterqualityofvalledebravoreservoirmexicousingentirelifespanofmerisdataandmachinelearningapproaches |