Environmental Engineering Research

Korean Society of Environmental Engineers (대한환경공학회)
권호 표지
DOI QR코드

DOI QR Code

Estimating chlorophyll-A concentration in the Caspian Sea from MODIS images using artificial neural networks

  • Received : 2019.03.15
  • Accepted : 2019.07.30
  • Published : 2020.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Nowadays, due to various pollution sources, it is essential for environmental scientists to monitor water quality. Phytoplanktons form the end of the food chain in water bodies and are one of the most important biological indicators in water pollution studies. Chlorophyll-A, a green pigment, is found in all phytoplankton. Chlorophyll-A concentration indicates phytoplankton biomass directly. Therefore, Chlorophyll-A is an indirect indicator of pollutants, including phosphorus and nitrogen, and their refinement and control are important. The present study, Moderate Resolution Imaging Spectroradiometer (MODIS) satellite images were used to estimate the chlorophyll-A concentration in southern coastal waters in the Caspian Sea. For this purpose, Multi-layer perceptron neural networks (NNs) were applied which contained three and four feed-forward layers. The best three-layer NN has 15 neurons in its hidden layer and the best four-layer one has 5 in each. The three- and four- layer networks both resulted in similar root mean square errors (RMSE), 0.1($\frac{{\mu}g}{l}$), however, the four-layer NNs proved superior in terms of R2 and also required less training data. Accordingly, a four-layer feed-forward NN with 5 neurons in each hidden layer, is the best network structure for estimating Chlorophyll-A concentration in the southern coastal waters of the Caspian Sea.

Keywords

References

  1. Jensen JR. Remote sensing of the environment: An earth resource perspective. 2nd ed. Univ. of South Carolina: Pearson Prentice Hall; 2007. p. 409-440.
  2. Tang D, Kawamura H, Lee M, Dien TV. Seasonal and Spatial Distribution of Chlorophyll a Concentrations and Water Conditions in the Gulf of Tonkin, South China Sea. Remote Sens. Environ. 2003;85:475-483. https://doi.org/10.1016/S0034-4257(03)00049-X
  3. Gregg WW, Casey NW. Global and regional evaluation of the seaWiFS Chlorophyll data set. Remote Sens. Environ. 2004;93:463-479 https://doi.org/10.1016/j.rse.2003.12.012
  4. Pinkerton MH, Richardson KM, Boyd PW, et al. Intercomparison of ocean colour band-ratio algorithms for Chlorophyll concentration in the subtropical front East of New Zealand. Remote Sens. Environ. 2005;97:382-402. https://doi.org/10.1016/j.rse.2005.05.004
  5. Allan MG, Hamilton DP, Hicks BJ, Brabyn L. Landsat remote sensing of chlorophyll a concentration in central North Island lakes of New Zealand. Int. J. Remote Sens. 2011;32:2037-2055. https://doi.org/10.1080/01431161003645840
  6. O'Reilly JE. Ocean Color Chlorophyll Algorithms for SeaWiFS, OC2, and OC4: Version 4. In: Hooker SB, Firestone ER Eds. Sea WiFS Postlaunch Calibration and Validation Analyses, Part 3. Washington D.C.: NASA Technical Memorandum; 2000. p. 9-11
  7. Carder K, Chen F, Lee Z, Hawes S, Cannizzaro J. Modis ocean science team algorithm theoretical basis document, Case 2 Chlorophyll a [Internet]. Available From: http://modis.gsfc.nasa.gov/data/atbd/atbd_mod19.pdf.
  8. Miles TN, He R. Temporal and spatial variability of Chl-a and SST on the South Atlantic Bight: Revisiting with cloud-free reconstructions of MODIS satellite imagery. Cont. Shelf Res. 2010;30:1951-1962. https://doi.org/10.1016/j.csr.2010.08.016
  9. Kavak MT, Karadogan S. The relationship between sea surface temperature and chlorophyll concentration of phytoplankton in the Black Sea using remote sensing techniques. J. Environ. Biol. 2012;32:493-498.
  10. Hu C, Chen Z, Clayton T, Swarzenski P, Brock J, Muller-Karager F. Assessment of estuarine water-quality indicators using MODIS medium Resolution bands: Initial results from Tampa Bay. Remote Sens. Environ. 2004;93:423-441. https://doi.org/10.1016/j.rse.2004.08.007
  11. Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Netw. 1989;2:359-366. https://doi.org/10.1016/0893-6080(89)90020-8
  12. Parlos AG, Chong KT, Atiya AF. Application of the recurrent multilayer perceptron in modeling complex process dynamics. Neural Netw. 1994;5:255-266. https://doi.org/10.1109/72.279189
  13. Lippmann RP. An introduction to computing with neural networks. IEEE ASSP Magazine 1987;4-22.
  14. Looney CG. Pattern recognition using neural networks: Theory and algorithms for engineers and scientists. Oxford: Oxford Univ. Press.; 1997.
  15. Holyer R, Sandidge J. Coastal bathymetry from hyperspectral observation of water radiance. Appl. Optics 1998;65:341-345.
  16. Lee Z, Zhang M, Carder K, Hall L. A neural network approach to deriving optical properties and depths of shallow waters. In Proceedings, Ocean Optics XIV, SG Ackleson, J. Campbell, Eds. Washington D.C.: Office of Naval Research; 1998.
  17. Kishino M, Tanaka A, Ishizaka J. Retrieval of Chlorophyll a, suspended solids, and colored dissolved organic matter in Tokyo Bay using ASTER data. Remote Sens. Environ. 2005;99:66-74. https://doi.org/10.1016/j.rse.2005.05.016
  18. Doerffer R, Schiller H. The MERIS Case 2 water algorithm. Int. J. Remote Sens. 2007;28:517-535. https://doi.org/10.1080/01431160600821127
  19. Gholamalifard M. Satellite monitoring of optically active components of Caspian Sea by inverse modeling of radiative transfer equation [dissertation]. Tehran: Tarbiat Modares Univ.; 2013.
  20. Martin S. An introduction to ocean remote sensing. Cambridge:Cambridge Univ. Press; 2004. p.426.
  21. Hagan MT, Menhaj MB. Training feedforward networks with the marquardt algorithm. IEEE Trans. Neural Netw. 1994;5:989-993. https://doi.org/10.1109/72.329697

Cited by

  1. A Meta-Analysis on Harmful Algal Bloom (HAB) Detection and Monitoring: A Remote Sensing Perspective vol.13, pp.21, 2021, https://doi.org/10.3390/rs13214347