OpenLB
Open Library of Bioscience
Advanced Search
Scientific reports
08 08, 2022;12 (1): 13529.

Chlorophyll soft-sensor based on machine learning models for algal bloom predictions.

Alberto Mozo, Jesús Morón-López, Stanislav Vakaruk, Ángel G Pompa-Pernía, Ángel González-Prieto, Juan Antonio Pascual Aguilar, Sandra Gómez-Canaval, Juan Manuel Ortiz
Author Information
  1. Alberto Mozo: Universidad Politécnica de Madrid, Madrid, Spain. a.mozo@upm.es.
  2. Jesús Morón-López: European Regional Centre for Ecohydrology of the Polish Academy of Sciences, Lodz, Poland. jesus.moron@imdea.org.
  3. Stanislav Vakaruk: Universidad Politécnica de Madrid, Madrid, Spain.
  4. Ángel G Pompa-Pernía: IMDEA Water Institute, Madrid, Spain.
  5. Ángel González-Prieto: Universidad Complutense de Madrid, Madrid, Spain.
  6. Juan Antonio Pascual Aguilar: IMDEA Water Institute, Madrid, Spain.
  7. Sandra Gómez-Canaval: Universidad Politécnica de Madrid, Madrid, Spain.
  8. Juan Manuel Ortiz: IMDEA Water Institute, Madrid, Spain.
PMID: 35941263 DOI: 10.1038/s41598-022-17299-5

Abstract

Harmful algal blooms (HABs) are a growing concern to public health and aquatic ecosystems. Long-term water monitoring conducted by hand poses several limitations to the proper implementation of water safety plans. This work combines automatic high-frequency monitoring (AFHM) systems with machine learning (ML) techniques to build a data-driven chlorophyll-a (Chl-a) soft-sensor. Massive data for water temperature, pH, electrical conductivity (EC) and system battery were taken for three years at intervals of 15 min from two different areas of As Conchas freshwater reservoir (NW Spain). We designed a set of soft-sensors based on compact and energy efficient ML algorithms to infer Chl-a fluorescence by using low-cost input variables and to be deployed on buoys with limited battery and hardware resources. Input and output aggregations were applied in ML models to increase their inference performance. A component capable of triggering a 10 [Formula: see text]g/L Chl-a alert was also developed. The results showed that Chl-a soft-sensors could be a rapid and inexpensive tool to support manual sampling in water bodies at risk.

References

  1. Sci Total Environ. 2019 Feb 15;651(Pt 2):2985-3001 [PMID: 30463149]
  2. Microorganisms. 2014 Jan 08;2(1):33-57 [PMID: 27694775]
  3. Harmful Algae. 2020 Jun;96:101828 [PMID: 32560841]
  4. PLoS One. 2019 Apr 16;14(4):e0215463 [PMID: 30990831]
  5. Sci Data. 2018 Oct 23;5:180226 [PMID: 30351308]
  6. Water Res. 2021 Jun 15;198:117133 [PMID: 33895586]
  7. Nat Rev Microbiol. 2018 Aug;16(8):471-483 [PMID: 29946124]
  8. Arch Toxicol. 2019 Sep;93(9):2429-2481 [PMID: 31350576]
  9. Harmful Algae. 2020 Jan;91:101594 [PMID: 32057340]
  10. Water Res. 2017 Jan 1;108:222-231 [PMID: 27847147]
  11. J Environ Sci (China). 2020 Jul;93:23-29 [PMID: 32446456]
  12. Environ Sci Pollut Res Int. 2019 Oct;26(29):30524-30532 [PMID: 31482526]
  13. Water Res. 2018 Sep 15;141:152-162 [PMID: 29783168]
  14. Sci Total Environ. 2019 Apr 10;660:329-339 [PMID: 30640101]
  15. Harmful Algae. 2016 Apr;54:213-222 [PMID: 28073478]
  16. Toxins (Basel). 2018 Apr 13;10(4): [PMID: 29652856]
  17. Environ Sci Pollut Res Int. 2018 Jan;25(2):1079-1088 [PMID: 29079975]
  18. Harmful Algae. 2019 Jun;86:128-137 [PMID: 31358272]
  19. Nature. 2020 Sep;585(7825):357-362 [PMID: 32939066]
  20. Water Res. 2020 Apr 1;172:115490 [PMID: 31972414]
  21. Life (Basel). 2014 Dec 15;4(4):988-1012 [PMID: 25517134]
  22. Sci Total Environ. 2017 Jan 1;575:294-308 [PMID: 27744157]
  23. Harmful Algae. 2020 Jan;91:101583 [PMID: 32057336]
  24. Environ Sci Pollut Res Int. 2018 Sep;25(25):25175-25189 [PMID: 29943249]
  25. Harmful Algae. 2020 Nov;99:101906 [PMID: 33218452]
  26. Environ Sci Technol. 2016 Oct 18;50(20):10780-10794 [PMID: 27597444]
  27. Environ Sci Pollut Res Int. 2013 Dec;20(12):8546-56 [PMID: 23677755]
  28. Environ Toxicol Chem. 2016 Jan;35(1):6-13 [PMID: 26771345]
  29. PLoS One. 2018 Feb 6;13(2):e0191939 [PMID: 29408936]
  30. Water Res. 2021 Mar 1;191:116806 [PMID: 33454652]
  31. Sci Rep. 2020 Jan 20;10(1):737 [PMID: 31959832]
  32. Science. 2008 Apr 4;320(5872):57-8 [PMID: 18388279]
  33. Ecol Indic. 2021 Sep 1;128:1-107822 [PMID: 35558093]
  34. Sci Total Environ. 2019 Feb 15;651(Pt 1):1-11 [PMID: 30223216]
  35. J Math Biol. 2018 Mar;76(4):817-840 [PMID: 28712030]

MeSH Term

Chlorophyll
Ecosystem
Environmental Monitoring
Harmful Algal Bloom
Machine Learning
Water

Chemicals

Water
Chlorophyll
Journal Article Research Support, Non-U.S. Gov't
Article has an altmetric score of 7

Word Cloud

Created with Highcharts 10.0.0waterChl-aMLalgalmonitoringmachinelearningsoft-sensorbatterysoft-sensorsbasedmodelsHarmfulbloomsHABsgrowingconcernpublichealthaquaticecosystemsLong-termconductedhandposesseverallimitationsproperimplementationsafetyplansworkcombinesautomatichigh-frequencyAFHMsystemstechniquesbuilddata-drivenchlorophyll-aMassivedatatemperaturepHelectricalconductivityECsystemtakenthreeyearsintervals15mintwodifferentareasConchasfreshwaterreservoirNWSpaindesignedsetcompactenergyefficientalgorithmsinferfluorescenceusinglow-costinputvariablesdeployedbuoyslimitedhardwareresourcesInputoutputaggregationsappliedincreaseinferenceperformancecomponentcapabletriggering10[Formula:seetext]g/LalertalsodevelopedresultsshowedrapidinexpensivetoolsupportmanualsamplingbodiesriskChlorophyllbloompredictions

Similar Articles

Cited By