Hydrophysics

Hydrophysics

Comparison of Linear and Nonlinear Regression Models based on Machine Learning for Estimating Chlorophyll-a values in Coastal Waters of Qeshm and Hormoz Island

Document Type : Original Article

Authors
Mitra Naimi 1
Zahra Azizi 2
Mohammad Seddiq Mortazavi 3
Seyedeh Laili Mohebbi-Nozar 3
Mojtaba Ezam 4
1 , Remote Sensing and GIS Department, Faculty of Natural Resources and Environment, Science and Research Branch, Islamic Azad University, Tehran, IRAN
2 Remote Sensing and GIS Department, Faculty of Natural Resources and Environment, Science and Research Branch, Islamic Azad University, Tehran, IRAN
3 Persian Gulf and Oman Sea Ecological Research Institute, Iranian fisheries science Research Center, Agricultural Education and Extension Research Organization, Bandar Abbas, IRAN
4 Physical Oceanography Department, Faculty of Natural Resources and Environment, Science and Research Branch, Islamic Azad University, Tehran, IRAN
Abstract
Chlorophyll-a, as an important indicator of algal blooms and water quality, holds significant importance in marine studies. This research aims to compare linear and nonlinear regression models based on machine learning algorithms for estimating the chlorophyll-a levels in the coastal waters of Bandar Abbas, Hormuz, and Qeshm Island. The study utilizes data from the TERRA sensor’s MODIS satellite and field measurements from various points within the study area. The examined models include linear regression, generalized linear model with Poisson distribution, random forest, and support vector machine. The performance of these models is evaluated using metrics such as root mean square error (RMSE), mean percentage error (MPE), mean absolute error (MAE), and coefficient of determination (R-squared). The results demonstrate that linear regression and generalized linear models perform poorly, while random forest and support vector machine exhibit better performance. Particularly, the random forest model shows the highest performance with an RMSE of 0.5725 and R-squared of 0.6632. This model has the capability to detect nonlinear and complex patterns and can effectively handle large datasets by employing a large number of decision trees. Overall, this research highlights the effectiveness of machine learning models, especially random forests, in accurately predicting chlorophyll-a levels as a crucial factor in managing marine ecosystems in the study area.
Keywords
Chlorophyll-a
machine learning
regression model
random forest
support vector machine
Qeshm Island
Hormuz Island

Subjects

  1. Harvey ET, Kratzer S, Philipson P. Satellite-based water quality monitoring for improved spatial and temporal retrieval of chlorophyll-a in coastal waters. Remote Sensing of Environment. 2015;158:417-30.
  2. Blix K, Li J, Massicotte P, Matsuoka A. Developing a new machine-learning algorithm for estimating chlorophyll-a concentration in optically complex waters: A case study for high northern latitude waters by using Sentinel 3 OLCI. Remote Sensing. 2019;11(18):2076.
  3. Harding Jr L, Mallonee M, Perry E. Toward a predictive understanding of primary productivity in a temperate, partially stratified estuary. Estuarine, Coastal and Shelf Science. 2002;55(3):437-63.
  4. Moses WJ, Gitelson AA, Berdnikov S, Povazhnyy V. Estimation of chlorophyll-a concentration in case II waters using MODIS and MERIS data—successes and challenges. Environmental research letters. 2009;4(4):045005.
  5. Hafeez S, Wong MS, Ho HC, Nazeer M, Nichol J, Abbas S, et al. Comparison of machine learning algorithms for retrieval of water quality indicators in case-II waters: A case study of Hong Kong. Remote sensing. 2019;11(6):617.
  6. Gordon HR, Clark DK, Brown JW, Brown OB, Evans RH, Broenkow WW. Phytoplankton pigment concentrations in the Middle Atlantic Bight: comparison of ship determinations and CZCS estimates. Applied optics. 1983;22(1):20-36.
  7. Gower J, Doerffer R, Borstad G. Interpretation of the 685nm peak in water-leaving radiance spectra in terms of fluorescence, absorption and scattering, and its observation by MERIS. International Journal of Remote Sensing. 1999;20(9):1771-86.
  8. Mauri E, Poulain PM, Južnič‐Zonta Ž. MODIS chlorophyll variability in the northern Adriatic Sea and relationship with forcing parameters. Journal of Geophysical Research: Oceans. 2007;112(C3).
  9. Mozetič P, Solidoro C, Cossarini G, Socal G, Precali R, Francé J, et al. Recent trends towards oligotrophication of the northern Adriatic: evidence from chlorophyll a time series. Estuaries and coasts. 2010;33:362-75.
  10. Pahlevan N, Smith B, Schalles J, Binding C, Cao Z, Ma R, et al. Seamless retrievals of chlorophyll-a from sentinel-2 (MSI) and sentinel -3 (OLCI) in inland and coastal waters: A machine-learning approach. Remote Sensing of Environment. 2020;240:111604.
  11. Nelder JA, Wedderburn RW. Generalized linear models. Journal of the Royal Statistical Society: Series A (General). 1972;135(3):370-84.
  12. Vapnik V. The Nature of Statistical Learning Theory, Springer‐Verlag; New York, Inc. 1995.
  13. Breiman L. Random forests. Machine learning. 2001;45:5-32.
  14. Zhao X, Li Y, Chen Y, Qiao X, Qian W. Water Chlorophyll a Estimation Using UAV-Based Multispectral Data and Machine Learning. Drones. 2023;7(1):2.
  15. Lv H, Feng Q. A review of random forests algorithm. Journal of the Hebei Academy of Sciences. 2019;36:37-41.
  16. Barraza-Moraga F, Alcayaga H, Pizarro A, Félez-Bernal J, Urrutia R. Estimation of Chlorophyll-a Concentrations in Lanalhue Lake Using sentiel2 MSI Satellite Images. Remote Sensing. 2022;14(22):5647.

17.Hamzehei S. Field study and numerical simulation of developing red tide in the northern Strait of Hormuz. 2012, Islamic Azad University, Science and Research Branch, Tehran, Marine Physics.

18.Su H, Lu X, Chen Z, Zhang H, Lu W, Wu W. Estimating coastal chlorophyll-a concentration from time-series OLCI data based on machine learning. Remote Sensing. 2021 Feb 6;13(4):576.

  1. Azizi Z, Montazeri Z. Effects of microtopography on the spatial pattern of woody species in West Iran. Arabian Journal of Geosciences. 2018 May;11(10):244.
  2. Azizi Z, Najafi A. Fuzzy classification in forest area for road design, (Case study: Lirehsar forest, Tonekabon). Iranian Journal of Forest and Poplar Research. 2011;19(1): 43-54. (In Persian)

  • Receive Date 10 June 2023
  • Revise Date 26 June 2023
  • Accept Date 21 July 2023