Skip to main content

Advertisement

Springer Nature Link
Log in

Deep learning-driven automatic detection of mucilage event in the Sea of Marmara, Turkey

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

A slimy and sticky structure is formed in sea surface due to the excessive proliferation of plantlike organisms called phytoplankton, which is formed by the combination of many biological and chemical conditions, the increase in sea temperature and bacterial activities accordingly. The rapid detection of this structure called mucilage is very important in terms of early intervention and cost determination. Remote sensing methods have been used quite frequently in recent years for the automatic classification and localization of such events with the help of satellite images. Deep convolutional neural networks (DCNNs) trained on mucilage images are applied as a very successful method thanks to their ability to automatically extract superior features. The studies carried out for the target point detection obtained as a result of extracting the visual features from natural images with these networks have reached the goal. In this study, transfer learning methods are proposed to improve the detection of mucilage areas from the satellite images. The Sea of Marmara, which has been difficult times due to the mucilage events, was selected as the study area. The dataset was trained to classify mucilage images with the convolutional neural network (CNN) models and then reused to localize mucilage areas. Residual networks (ResNet)-50, visual geometry group (VGG)-16, VGG-19, and Inception-V3 were used for individual CNN models. Gradient-weighted class activation mapping (Grad-CAM) technique was used to visualize the learned behavior. A custom CNN model was created, and comparisons were made with the real mucilage areas with the intersection over union considering the most efficient convolutional layer to better localize the mucilage areas. It was concluded that the custom CNN model has showed superior localization performance compared to other models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

Data availability

Data, models, and/or codes that support the findings of this study are available from the corresponding author upon reasonable request.

References

  1. Akkan T (2013) Determination of the seasonal changes in sea water quality in Giresun coastline, Master’s Thesis, Ondokuz Mayıs University

  2. Erüz C (1999) Seasonal dynamics of water mass and suspended matter in Southeastern Black Sea coastal waters, Philosophy PhD Thesis, Karadeniz Technical University

  3. Fukao T, Kimoto K, Yamatogi T et al (2009) Marine mucilage in Ariake Sound, Japan, is composed of transparent exopolymer particles produced by the diatom Coscinodiscus granii. Fish Sci 75:1007–1014. https://doi.org/10.1007/s12562-009-0122-0

    Article  Google Scholar 

  4. Mingazzini M, Colombob S, Ferrari GM (1995) Application of spectrofluorimetric techniques to the study of marine mucilages in the Adriatic Sea: preliminary results. Sci Total Environ 165:133–144. https://doi.org/10.1016/0048-9697(95)04547-E

    Article  Google Scholar 

  5. Penna N, Capellacci S, Ricci F et al (2009) Study on the maltooligosaccharide composition of mucilage samples collected along the northern Adriatic coast. Carbohydr Res 344:120–126. https://doi.org/10.1016/j.carres.2008.10.008

    Article  Google Scholar 

  6. Hauck F (1872) Aufzahlung einiger, in dem sogennaten Seeschleime der Adria vorkommenden Diatomeeen. Oesterreichische Botanische Zeitschrift 10:331–332. https://doi.org/10.1007/bf01616031

    Article  Google Scholar 

  7. Molin D, Guidoboni E, Lodovisi A (1992) Mucilage and the phenomena of algae in the history of the Adriatic: periodization and the anthropic context (17th–20th centuries). Sci Total Environ. https://doi.org/10.1016/B978-0-444-89990-3.50047-X

    Article  Google Scholar 

  8. Giani M, Sist P, Berto D et al (2012) The organic matrix of pelagic mucilaginous aggregates in the Tyrrhenian Sea (Mediterranean Sea). Mar Chem 132–133:83–94. https://doi.org/10.1016/j.marchem.2012.01.002

    Article  Google Scholar 

  9. Giani M, Cicero AM, Savelli F et al (1992) Marine snow in the Adriatic Sea: a multifactorial study. In: Science of the total environment. pp 539–550

  10. Precali R, Giani M, Marini M et al (2005) Mucilaginous aggregates in the northern Adriatic in the period 1999–2002: typology and distribution. Sci Total Environ 353:10–23. https://doi.org/10.1016/j.scitotenv.2005.09.066

    Article  Google Scholar 

  11. Cappiello A, Trufelli H, Famiglini G et al (2007) Study on the oligosaccharides composition of the water-soluble fraction of marine mucilage by electrospray tandem mass spectrometry. Water Res 41:2911–2920. https://doi.org/10.1016/j.watres.2007.04.003

    Article  Google Scholar 

  12. Calvo S, Barone R, Flores LN (1995) Observations on mucus aggregates along Sicilian coasts during 1991–1992. Sci Total Environ 165:23–31. https://doi.org/10.1016/0048-9697(95)04540-H

    Article  Google Scholar 

  13. Innamorati M (1995) Hyperproduction of mucilages by micro and macro algae in the Tyrrhenian Sea. Sci Total Environ 165:65–81. https://doi.org/10.1016/0048-9697(95)04544-B

    Article  Google Scholar 

  14. Rinaldi A, Vollenweideratb RA, Montanaria G et al (1995) Mucilages in Italian seas: the Adriatic and Tyrrhenian Seas, 1988–1991. Sci Total Environ 165:165–183. https://doi.org/10.1016/0048-9697(95)04550-K

    Article  Google Scholar 

  15. Giuliani S, Virno Lamberti C, Sonni C, Pellegrini D (2005) Mucilage impact on gorgonians in the Tyrrhenian sea. Sci Total Environ 353:340–349. https://doi.org/10.1016/j.scitotenv.2005.09.023

    Article  Google Scholar 

  16. Gotsis-Skretas O (1995) Mucilage appearances in Greek waters during 1982–1994. Sci Total Environ 165:229–230. https://doi.org/10.1016/0048-9697(95)04665-N

    Article  Google Scholar 

  17. Metaxatos A, Panagiotopoulos C, Ignatiades L (2003) Monosaccharide and aminoacid composition of mucilage material produced from a mixture of four phytoplanktonic taxa. J Exp Mar Biol Ecol 294:203–217. https://doi.org/10.1016/S0022-0981(03)00269-7

    Article  Google Scholar 

  18. Genitsaris S, Stefanidou N, Sommer U, Moustaka-Gouni M (2019) Phytoplankton blooms, red tides and mucilaginous aggregates in the urban Thessaloniki Bay. East Mediterr Divers (Basel). https://doi.org/10.3390/d11080136

    Article  Google Scholar 

  19. Zingone A, Escalera L, Aligizaki K et al (2021) Toxic marine microalgae and noxious blooms in the Mediterranean Sea: a contribution to the Global HAB Status Report. Harmful Algae. https://doi.org/10.1016/j.hal.2020.101843

    Article  Google Scholar 

  20. Aktan Y, Topaloğlu B (2011) First record of Chrysophaeum tayloriiLewis & Bryan and their benthic mucilaginous aggregates in the Aegean Sea (Eastern Mediterranean). J Black Sea/Mediterr Environ 17:159–170

    Google Scholar 

  21. Altın A, Özen Ö, Ayyıldız H (2015) Temporal variations of the demersal fish community in the shallow waters of Çanakkale strait, north Aegean Sea, during the course of a mucilage event. Turk J Fish Aquat Sci 15:359–365. https://doi.org/10.4194/1303-2712-v15_2_18

    Article  Google Scholar 

  22. Aktan Y, Dede A, Ciftci PS (2008) Mucilage event associated with diatoms and dinoflagellates in Sea of Marmara, Turkey. Harmful Algae News 1–4

  23. Artüz ML (2008) Marmara Denizi genelinde gözlemlenen karışık alg patlaması sonucunda oluşan musilaj agregat konusunda rapor. İstanbul

  24. Balkis N, Atabay H, Türetgen I et al (2011) Role of single-celled organisms in mucilage formation on the shores of Bykada Island (the Marmara Sea). J Mar Biol Assoc UK 91:771–781. https://doi.org/10.1017/S0025315410000081

    Article  Google Scholar 

  25. Tufekçi V, Balkis N, Polat Beken C et al (2010) Phytoplankton composition and environmental conditions of a mucilage event in the Sea of Marmara. Turk J Biol 34:199–210. https://doi.org/10.3906/biy-0812-1

    Article  Google Scholar 

  26. İşinibilir-Okyar M, Üstün F, Orun DA (2015) Changes in abundance and community structure of the zooplankton population during the 2008 mucilage event in the northeastern Marmara Sea. Turk J Zool 39:28–38. https://doi.org/10.3906/zoo-1308-11

    Article  Google Scholar 

  27. Taş S, Ergül HA, Balkıs N (2016) Harmful algal blooms (HABs) and mucilage formations in the Sea of Marmara, 1st edn. Turkish Marine Research Foundation TUDAV, İstanbul

    Google Scholar 

  28. Tas S, Kus D, Yilmaz IN (2020) Temporal variations in phytoplankton composition in the north-eastern Sea of Marmara: potentially toxic species and mucilage event. Mediterr Mar Sci 21:668–683. https://doi.org/10.12681/mms.22562

    Article  Google Scholar 

  29. Lancelot C (1995) The mucilage phenomenon in the continental coastal waters of the North Sea. Sci Total Environ 165:83–102. https://doi.org/10.1016/0048-9697(95)04545-C

    Article  Google Scholar 

  30. Toklu-Alicli B, Balkis-Ozdelice N, Durmus T, Balci M (2021) Relationship between environmental factors and zooplankton diversity in the Gulf of Bandırma (the Sea of Marmara). Biologia (Bratisl) 76:1727–1736. https://doi.org/10.2478/s11756-020-00668-8/Published

    Article  Google Scholar 

  31. Liénart C, Susperregui N, Rouaud V et al (2016) Dynamics of particulate organic matter in a coastal system characterized by the occurrence of marine mucilage—a stable isotope study. J Sea Res 116:12–22. https://doi.org/10.1016/j.seares.2016.08.001

    Article  Google Scholar 

  32. Rouaud V, Susperrégui N, Fahy A et al (2019) Dynamics of microbial communities across the three domains of life over an annual cycle with emphasis on marine mucilage in the Southern Bay of Biscay resolved by microbial fingerprinting. Cont Shelf Res 186:127–137. https://doi.org/10.1016/j.csr.2019.06.003

    Article  Google Scholar 

  33. Balkıs N, Sivri N, Fraim NL et al (2013) Excessive growth of Cladophora laetevirens (Dillwyn) Kutzing and enteric bacteria in mats in the Southwestern Istanbul coast, Sea of Marmara. IUFS J Biol Res Article IUFS J Biol 72:41–48

    Google Scholar 

  34. Giani M, Zangrando V, Berto D (2006) 3C/12C isotope ratio in the organic matter forming the mucilaginous aggregates in the Northern Adriatic Sea. Conference: Isotopes Environ Health Stud, Volume: IAEA-CN-118/8, pp 93–96

  35. Zambianchi E, Calvitti C, Cecamore P, D’Amico F, Ferulano E, Lanciano P (1992) The mucilage phenomenon in the Northern Adriatic Sea, summer 1989: a study carried out with remote sensing techniques. Mar Coast Eutrophication 126:581–598

    Article  Google Scholar 

  36. Tassan S (1993) An algorithm for the detection of the white-tide (“mucilage”) phenomenon in the adriatic sea using AVHRR data. Remote Sens Environ 45:29–42

    Article  Google Scholar 

  37. Gigliotti A (2013) Extracting temporal and spatial distributions information about marine mucilage phenomenon based on Modis satellite images; a case study of the Tyrrhenian and the Adriatic Sea, 2010–2012. In: Master of science in geospatial technologies

  38. Acar U, Yılmaz OS, Çelen M et al (2021) Determination of mucilage in the Sea of Marmara using remote sensing techniques with Google Earth Engine. Int J Environ Geoinform 8:423–434. https://doi.org/10.30897/ijegeo.957284

    Article  Google Scholar 

  39. Sunar F, Dervisoglu A, Yagmur N et al (2022) How efficient can Sentinel-2 data help spatial mapping of mucilage event in the Marmara Sea? Int Arch Photogram Remote Sens Spatial Inf Sci XLIII-B3-2022:181–186. https://doi.org/10.5194/isprs-archives-XLIII-B3-2022-181-2022

    Article  Google Scholar 

  40. Hu C (2022) Sea snots in the marmara sea as observed from medium-resolution satellites. IEEE Geosci Remote Sens Lett. https://doi.org/10.1109/LGRS.2022.3173997

    Article  Google Scholar 

  41. Tuzcu Kokal A, Olgun N, Musaoğlu N (2022) Detection of mucilage phenomenon in the Sea of Marmara by using multi-scale satellite data. Environ Monit Assess 194:1–18. https://doi.org/10.1007/S10661-022-10267-6

    Article  Google Scholar 

  42. Quetglas A, Ordines F, Guijarro B (2011) The use of artificial neural networks (ANNs) in aquatic ecology. In: Artificial neural networks—application. pp 1–22

  43. Guirado E, Tabik S, Rivas ML et al (2019) Whale counting in satellite and aerial images with deep learning. Sci Rep. https://doi.org/10.1038/s41598-019-50795-9

    Article  Google Scholar 

  44. Segura Velandia N, Hernandez Beleno RD, Jimenez Moreno R (2017) Applications of deep neural networks. Int J Signal Syst Control Eng Appl 10:61–76

    Google Scholar 

  45. Ates AM, Yilmaz OS, Gulgen F (2020) Using remote sensing to calculate floating photovoltaic technical potential of a Dam’s surface. Sustain Energy Technol Assess 41:100799. https://doi.org/10.1016/j.seta.2020.100799

    Article  Google Scholar 

  46. Garcia-Garin O, Monleón-Getino T, López-Brosa P et al (2021) Automatic detection and quantification of floating marine macro-litter in aerial images: introducing a novel deep learning approach connected to a web application in R. Environ Pollut. https://doi.org/10.1016/j.envpol.2021.116490

    Article  Google Scholar 

  47. Emna A, Alexandre B, Bolon P et al (2020) Offshore oil slicks detection from SAR ımages through the mask-RCNN deep learning model. In: Proceedings of the ınternational joint conference on neural networks. pp 1–8

  48. Kavzoğlu T, Yusuf M (2021) Detection and analysis of marine Mucilage Bloom in the Sea of Marmara by a machine learning algorithm from multi-temporal optical and thermal satellite images. Harita Dergisi 166:1–9

    Google Scholar 

  49. Kim H, Kim D, Jung S, et al (2015) Development of a UAV-type jellyfish monitoring system using deep learning. In: 2015 12th ınternational conference on ubiquitous robots and ambient ıntelligence, URAI 2015. Institute of Electrical and Electronics Engineers Inc., pp 495–497

  50. Temitope Yekeen S, Balogun AL, Wan Yusof KB (2020) A novel deep learning instance segmentation model for automated marine oil spill detection. ISPRS J Photogram Remote Sens 167:190–200. https://doi.org/10.1016/j.isprsjprs.2020.07.011

    Article  Google Scholar 

  51. Samantaray A, Yang B, Dietz JE, Min B-C (2018) Algae detection using computer vision and deep learning. arXiv preprintarXiv preprint arXiv:1811.10847

  52. Bilgili L, Çetinkaya AY, Sarı M (2022) Analysis of the effects of domestic waste disposal methods on mucilage with life cycle assessment. Mar Pollut Bull 180:113813. https://doi.org/10.1016/J.MARPOLBUL.2022.113813

    Article  Google Scholar 

  53. Karadurmuş U, Sari M (2022) Marine mucilage in the Sea of Marmara and its effects on the marine ecosystem: mass deaths. Turk J Zool 46:93–102. https://doi.org/10.3906/zoo-2108-14

    Article  Google Scholar 

  54. Hu C, Qi L, Xie Y et al (2022) Spectral characteristics of sea snot reflectance observed from satellites: implications for remote sensing of marine debris. Remote Sens Environ 269:112842. https://doi.org/10.1016/J.RSE.2021.112842

    Article  Google Scholar 

  55. Yagci AL, Colkesen I, Kavzoglu T, Sefercik UG (2022) Daily monitoring of marine mucilage using the MODIS products: a case study of 2021 mucilage bloom in the Sea of Marmara. Turkey Environ Monit Assess. https://doi.org/10.1007/S10661-022-09831-X

    Article  Google Scholar 

  56. Goxhaj O, Yilmaz NG, Kouhalvandi L et al (2022) Underwater image detection for cleaning purposes; techniques used for detection based on machine learning. Acta Marisiensis Seria Technologica 19:28–35. https://doi.org/10.2478/AMSET-2022-0006

    Article  Google Scholar 

  57. Abaci B, Dede M, Yüksel Erdem SE, Yilmaz M (2022) Mucilage detection from hyperspectral and multispectral satellite data. In: Algorithms, technologies, and applications for multispectral and hyperspectral ımaging XXVIII. SPIE-Intl Soc Optical Eng

  58. Snoek CGM, Worring M, Smeulders AWM (2005) Early versus late fusion in semantic video analysis. In: Proceedings of the 13th ACM ınternational conference on multimedia, MM 2005

  59. Scherer D, Müller A, Behnke S (2010) Evaluation of pooling operations in convolutional architectures for object recognition. In: Lecture notes in computer science (including subseries lecture notes in artificial ıntelligence and lecture notes in bioinformatics)

  60. Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science (1979). https://doi.org/10.1126/science.1127647

    Article  MATH  Google Scholar 

  61. Singh D, Kumar V, Yadav V, Kaur M (2020) Deep neural network-based screening model for COVID-19-ınfected patients using chest X-ray ımages. Int J Pattern Recogn Artif Intell. https://doi.org/10.1142/S0218001421510046

    Article  Google Scholar 

  62. Bengio Y (2009) Learning deep architectures for AI. Found Trends Mach Learn. https://doi.org/10.1561/2200000006

    Article  MATH  Google Scholar 

  63. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition. IEEE Computer Society, pp 770–778

  64. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: 3rd ınternational conference on learning representations, ICLR 2015—conference track proceedings. pp 1–14

  65. Szegedy C, Vanhoucke V, Ioffe S, et al (2016) Rethinking the Inception Architecture for Computer Vision. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition. IEEE Computer Society, pp 2818–2826

  66. Liu J, Guo F, Gao H et al (2021) Image classification method on class imbalance datasets using multi-scale CNN and two-stage transfer learning. Neural Comput Appl. https://doi.org/10.1007/s00521-021-06066-8

    Article  Google Scholar 

  67. Nwankpa C, Ijomah W, Gachagan A, Marshall S (2018) Activation functions: comparison of trends in practice and research for deep learning. arXiv preprint arXiv:1811.03378

  68. Selvaraju RR, Cogswell M, Das A et al (2020) Grad-CAM: visual explanations from deep networks via gradient-based localization. Int J Comput Vis 128:336–359. https://doi.org/10.1007/s11263-019-01228-7

    Article  Google Scholar 

  69. Kutupoğlu V (2017) Long–term spatial differences in the model results and performances of SWAN models forced with the CFSR and ERA Interim winds in the Sea of Marmara, Master's Thesis, Uludağ University

  70. Achmanj DR, Hornbuckle KC, Eisenreich SJ (1993) Volatilization of Polychlorinated Biphenyls from Green Bay, Lake Michigian. Environ Sci Technol 27:75–87

    Article  Google Scholar 

  71. Taşdemir Y (2002) The Marmara sea: pollutants and environment related precautions. Uludağ Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi 7:39–45

    Google Scholar 

  72. Salamon J, Bello JP (2016) Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process Lett 24:279–283. https://doi.org/10.1109/LSP.2017.2657381

    Article  Google Scholar 

  73. Zweig MH, Campbell G (1993) Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clin Chem 39:561–577. https://doi.org/10.1093/clinchem/39.4.561

    Article  Google Scholar 

Download references

Funding

No funding to declare.

Author information

Authors and Affiliations

  1. Department of Civil Engineering, Faculty of Engineering, Karadeniz Technical University, 61080, Trabzon, Turkey

    Kemal Hacıefendioğlu, Hasan Basri Başağa, Osman Tuğrul Baki & Adem Bayram

Authors
  1. Kemal Hacıefendioğlu
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Hasan Basri Başağa
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Osman Tuğrul Baki
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Adem Bayram
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

All authors have been personally and actively involved in substantial work leading to the paper and acknowledge public responsibility for its content.

Corresponding author

Correspondence to Kemal Hacıefendioğlu.

Ethics declarations

Conflicts of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hacıefendioğlu, K., Başağa, H.B., Baki, O.T. et al. Deep learning-driven automatic detection of mucilage event in the Sea of Marmara, Turkey. Neural Comput & Applic 35, 7063–7079 (2023). https://doi.org/10.1007/s00521-022-08097-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-08097-1

Keywords