(49-6) 13 * << * >> * Russian * English * Content * All Issues

Algae bloom intensity classification using machine learning methods and UAV hyperspectral data
I.A. Novikov 1, A.R. Makarov 2,3, V.V. Podlipnov 2,3, V.I. Platonov 3, D.D. Ryskova 3, O.V. Kalashnikova 3, R.M. Khabibullin 2,3, R.V. Skidanov 2,3, S.V. Illarionova 1, Y.V. Vybornova 3, A.V. Nikonorov 2,31, D.G. Shadrin 1, T.V. Podladchikova 1

1 Skolkovo Institute of Science and Technology,
Bolshoy Boulevard, 30, Bld. 1, Skolkovo, 121205, Moscow, Russia;
2 Institute of Image Processing Systems, NRC "Kurchatov Institute",
Molodogvardeyskaya Str. 151, Samara, 443001, Russia;
3 Samara National Research University,
Moskovskoye Shosse 34, Samara, 443086, Russia

 PDF, 4420 kB

DOI: 10.18287/2412-6179-CO-1539

Pages: 972-985.

Full text of article: Russian language.

Abstract:
This paper presents an approach for high spatial resolution hyperspectral image analysis in an applied task of river water condition assessment. The method allows the detection of algal blooms or water pollution by foreign substances. High-resolution hyperspectral images were obtained using a hyperspectrometer mounted on a small unmanned aerial vehicle. A difference between the spectra of river parts with varying intensity of algal blooms was demonstrated. Water samples were taken, and chemical analysis confirmed the varying levels of magnesium and calcium across all samples, corresponding to the intensity of algal blooms in the water. Several machine learning-based classification algorithms and vegetation indices were considered for classifying water areas with varying intensities of algal blooms. The effectiveness of machine learning algorithms compared to vegetation indices was shown. In addition, to improve the performance of the most effective classification algorithms, a comparison of several dimensionality reduction approaches based on spectral channel selection was carried out.

Keywords:
hyperspectrometer, spectral analysis, hyperspectral images, index images, machine learning.

Citation:
Novikov IA, Makarov AR, Podlipnov VV, Platonov VI, Ryskova DD, Kalashnikova OV, Khabibullin RM, Skidanov RV, Illarionova SV, Vybornova YV, Nikonorov AV, Shadrin DG, Podladchikova TV. Algae bloom intensity classification using machine learning methods and UAV hyperspectral data. Computer Optics 2025; 49(6): 972-985. DOI: 10.18287/2412-6179-CO-1539.

Acknowledgements:
The technical and experimental parts of the study were funded by the Ministry of Science and Higher Education of the Russian Federation Project FSSS-2024-0022 (registration number: 1023112900147-4 dated 31.01.24). The theoretical part of the study was funded by the Russian Science Foundation under grant No 22-19-00364.

References:
  1. Ritchie JC, Zimba PV, Everitt JH. Remote sensing techniques to assess water quality. Photogramm Eng Remote Sens 2003; 6: 695-704. DOI: 10.14358/PERS.69.6.695.
  2. Fan C. Spectral analysis of water reflectance for hyperspectral remote sensing of water quailty in estuarine water. Journal of Geoscience and Environment Protection 2014; 2: 19-27. DOI: 10.4236/gep.2014.22004.
  3. Illarionova S, Shadrin D, Tregubova P, Ignatiev V, Efimov A, Oseledets I, Burnaev E. A survey of computer vision techniques for forest characterization and carbon monitoring tasks. Remote Sens 2022; 14(22): 5861. DOI: 10.3390/rs14225861.
  4. Chandler O, Young F, Maraseni T, Apan A. Opportunities and limitations of remote sensing for crop loss (hail damage) assessment in the insurance industry. 2005. Source: <https://www.researchgate.net/publication/228863171_Opportunities_and_limitations_of_remote_sensing_for_crop_loss_hail_damage_assessment_in_the_insurance_industry#read>.
  5. Chen Y, Fan R, Yang X, Wang J, Latif A. “Extraction of urban water bodies from high-resolution remote-sensing imagery using deep learning. Water 2018; 10(5): 585. DOI: 10.3390/w10050585.
  6. Avdan ZY, Kaplan G, Goncu S, Avdan U. Monitoring the water quality of small water bodies using high-resolution remote sensing data. ISPRS Int J Geo-Inf 2019; 8(12): 553. DOI: 10.3390/ijgi8120553.
  7. Illarionova S, Nesteruk S, Shadrin D, Ignatiev V, Pukalchik M, Oseledets I. MixChannel: Advanced Augmentation for Multispectral Satellite Images. Remote Sens 2021; 13(11): 2181. DOI: 10.3390/rs13112181.
  8. Chen J, Wang J, Feng S, Zhao Z, Wang M, Sun C, Song N, Yang J. Study on parameter inversion model construction and evaluation method of UAV hyperspectral urban inland water pollution dynamic monitoring. Water 2023; 15(23): 4131. DOI: 10.3390/w15234131.
  9. Podlipnov VV, Shchedrin VN, Babichev AN, Vasilyev SM, Blank VA. Experimental determination of soil moisture on hyperspectral images. Computer Optics 2018; 42(5): 877-884. DOI: 10.18287/2412-6179-2017-42-5-877-884.
  10. Karpeev SV, Khonina SN, Murdagulov AR, Petrov MV. Alignment and study of prototypes of the Offner hyperspectrometer. Vestnik of the Samara State Aerospace University 2016; 15(1): 197-206. DOI: 10.18287/2412-7329-2016-15-1-197-206.
  11. Popandopulo G, Illarionova S, Shadrin D, Evteeva K, Sotiriadi N, Burnaev E. Flood extent and volume estimation using remote sensing data. Remote Sens 2023; 15(18): 4463. DOI: 10.3390/rs15184463.
  12. Elshorbagy W, Chowdhury RK. Water treatment. Rijeka: IntechOpen; 2013. ISBN: 978-953-51-0928-0.
  13. Park Y, Pyo JC, Kwon Y, Cha Y, Lee H, Kang T, Cho K. Evaluating physico-chemical influences on cyanobacterial blooms using hyperspectral images in Inland Water, Korea. Water Res 2017; 126: 319-328. DOI: 10.1016/j.watres.2017.09.026.
  14. Yang C, Everitt J, Bradford J. Use of spectral angle mapper (SAM) and hyperspectral imagery for yield estimation. 2006. Source:       <https://elibrary.asabe.org/abstract.asp?JID=5&AID=20649&CID=por2006&T=1>. DOI: 10.13031/2013.20649.
  15. Kiage LM, Walker ND. Using NDVI from MODIS to monitor duckweed bloom in Lake Maracaibo, Venezuela. Water Resour Manag 2009; 23(6): 1125-1135. DOI: 10.1007/s11269-008-9318-9.
  16. Zhang T, Hu H, Ma X, Zhang Y. Long-term spatiotemporal variation and environmental driving forces analyses of algal blooms in Taihu Lake based on multi-source satellite and land observations. Water 2020; 12(4): 1035. DOI: 10.3390/w12041035.
  17. Adamiak M, Będkowski K, Majchrowska A. Aerial imagery feature engineering using bidirectional generative adversarial networks: A case study of the Pilica River Region, Poland. Remote Sens 2021; 13(02): 306. DOI: 10.3390/rs13020306.
  18. Ghaderi D, Rahbani M. Tracing suspended matter in Tiab Estuary applying ANN and remote sensing. Reg Stud Mar Sci 2021; 44: 101788. DOI: 10.1016/j.rsma.2021.101788.
  19. He Z, Wen X, Liu H, Du J. A comparative study of artificial neural network, adaptive neuro fuzzy inference system and support vector machine for forecasting river flow in the Semiarid Mountain Region. J Hydrol 2014; 509: 379-386. DOI: 10.1016/j.jhydrol.2013.11.054.
  20. Boyer JN, Kelble CR, Ortner PB, Rudnick DT. Phytoplankton bloom status: Chlorophyll a biomass as an indicator of water quality condition in the southern estuaries of Florida, USA. Ecol Indic 2009; 9(6, Suppl): S56-S67. DOI: 10.1016/j.ecolind.2008.11.013.
  21. Park Y, Cho KH, Park J, Cha SM, Kim JH. Development of early-warning protocol for predicting chlorophyll-a concentration using machine learning models in freshwater and estuarine reservoirs, Korea. Sci Total Environ 2015; 502: 31-41. DOI: 10.1016/j.scitotenv.2014.09.005.
  22. Yan H, Zhang J, Rahman SS, Zhou N, Suo Y. Predicting permeability changes with injecting co2 in coal seams during CO2 geological sequestration: a comparative study among six SVM-based hybrid models. Sci Total Environ 2020; 705: 135941. DOI: 10.1016/j.scitotenv.2019.135941.
  23. Aleshin M, Illarionova S, Shadrin D, Ivanov V, Vanovskiy V, Burnaev E. Machine learning-based modeling of chl-a concentration in Northern marine regions using oceanic and atmospheric data. Front Mar Sci 2024; 11: 1412883. DOI: 10.3389/fmars.2024.1412883.
  24. Zhu S, Wu Y, Ma X. Deep learning-based algal bloom identification method from remote sensing images – Take China’s Chaohu Lake as an example. Sustainability 2023; 15(05): 4545. DOI: 10.3390/su15054545.
  25. Oppelt NM, Schulze F, Doernhoefer K, Eisenhardt I, Bartsch I. Hyperspectral classification approaches for intertidal macroalgae habitat mapping: A case study in Heligoland. Optical Engineering 2012; 51(11): 111703. DOI: 10.1117/1.OE.51.11.111703.
  26. Diruit W, Bris A, Bajjouk T, Richier S, Helias M, Burel T, Lennon M, Guyot A, Gall E. Seaweed habitats on the shore: Characterization Through Hyperspectral UAV imagery and field sampling. Remote Sens 2022; 14(13): 3124. DOI: 10.3390/rs14133124.
  27. Lin Y, Gao J, Tu Y, Zhang Y, Gao J. Estimating low concentration heavy metals in water through hyperspectral analysis and genetic algorithm-partial least squares regression. Sci Total Environ 2024; 916: 170225. DOI: 10.1016/j.scitotenv.2024.170225.
  28. Mu T, Han F, Bao D, Zhang C, Liang R. Compact snapshot optically replicating and remapping imaging spectrometer (ORRIS) using a focal plane continuous variable filter. Opt Lett 2019. 44(5): 1281-1284. DOI: 10.1364/OL.44.001281.
  29. Sweeney DW, Sommargren GE. Harmonic diffractive lenses. Appl Opt 1995; 34(14): 2469-2475. DOI: 10.1364/AO.34.002469.
  30. Malmir M, Tahmasbian I, Xu Z, Farrar M, Bai SH. Prediction of soil macro-and micro-elements in sieved and ground air-dried soils using laboratory-based hyperspectral imaging technique. Geoderma 2019; 340: 70-80. DOI: 10.1016/j.geoderma.2018.12.049.
  31. Becker F, Choudhury BJ. Relative Sensitivity of Normalized Difference Vegetation Index (NDVI) and Microwave Polarization Difference Index (MPDI) for vegetation and desertification monitoring. Remote Sens Environ 1988; 24(2): 297-311. DOI: 10.1016/0034-4257(88)90031-4.
  32. Savorskiy V, Kashnitskii A, Konstantinova AM, Balashov IV, Krasheninnikova YuS, Tolpin V, Maklakov S, Savchenko E. Capabilities of hyperspectral indices analysis of the vega-constellation remote monitoring information systems. Current Problems in Remote Sensing of the Earth from Space 2016; 13: 28-45. DOI: 10.21046/2070-7401-2016-13-3-28-45.
  33. McFeeters SK. The use of the normalized difference water index (NDWI) in the delineation of open water features. Int J Remote Sens 1996; 17(7): 1425-1432. DOI: 10.1080/01431169608948714.
  34. Barnes RJ, Dhanoa MS, Lister SJ. Standard normal variate transformation and de-trending of near-infrared diffuse reflectance spectra. Applied Spectroscopy 1989; 43(5): 772-777. DOI: 10.1366/0003702894202201.
  35. Rota G-C. The advanced theory of statistics: M. G. Kendall and A. Stuart, 3 vols., 4th ed., Macmillan, 1977-1983. Adv Math 1986; 60(1): 123. DOI: 10.1016/0001-8708(86)90015-0.
  36. Hu W, Huang Y, Li W, Zhang F, Li H. Deep convolutional neural networks for hyperspectral image classification. J Sens 2015; 2015(1): 258619. DOI: 10.1155/2015/258619.
  37. Firsov NA, Podlipnov VV, Ivliev NA, Nikolaev PP, Mashkov SV, Ishkin PA, Skidanov RV, Nikonorov AV. Neural network-aided classification of hyperspectral vegetation images with a training sample generated using an adaptive vegetation index. Computer Optics 2021; 45(6): 887-896. DOI: 10.18287/2412-6179-CO-1038.
  38. Kruse FA, Lefkoff AB, Boardman JW, Heidebrecht KB, Shapiro A, Barloon PJ, Goetz AFH. The Spectral Image Processing System (SIPS) – interactive visualization and analysis of imaging spectrometer data. Remote Sens Environ 1993; 44(2-3): 145-163. DOI: 10.1016/0034-4257(93)90013-N.
  39. Awad M, Khanna R. Support vector machines for classification. In Book: Awad M, Khanna R, eds. Efficient learning machines: Theories, concepts, and applications for engineers and system designers. New York: Springer Science+Business Media; 2015: 39-66. DOI: 10.1007/978-1-4302-5990-9_3.
  40. Hughes GP. On the mean accuracy of statistical pattern recognizers. IEEE Trans Inf Theory 1968; 14(1): 55-63. DOI: 10.1109/TIT.1968.1054102.
  41. Rodarmel C, Shan J. Principal component analysis for hyperspectral image classification. Surv Land Inf Syst 2002; 62(2): 115-123.
  42. Gillis N. Successive nonnegative projection algorithm for robust nonnegative blind source separation. SIAM Journal on Imaging Sciences 2014; 7(2). Source: <https://epubs.siam.org/doi/10.1137/130946782>. DOI: 10.1137/130946782.
  43. Chauvin J, Duran R, Tavakolian K, et al. Simulated annealing-based hyperspectral data optimization for fish species classification: Can the number of measured wavelengths be reduced? Appl Sci 2021; 11(22): 10628. DOI: 10.3390/app112210628.
  44. Centeno JAS, Kern J, Mitishita EA, Palma MEJ. PCA band selection method for a hyperspectral sensors onboard an UAV. ISPRS Ann Photogramm Remote Sens Spat Inf Sci 2020; IV-3/W2-2020: 77-81. DOI: 10.5194/isprs-annals-IV-3-W2-2020-77-2020.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20