Total views : 302
Classification of Remotely Sensed Algal Blooms along the Coast of India using Support Vector Machines and Regularized Least Squares
Background/Objectives: The recent times have observed an inflation in frequency of occurrence of Algal Blooms (ABs). In this work, seven most commonly occurring species (i.e., Trichodesmium erythraeum, Noctiluca scintillans/miliaris, Cocholodinium ploykrikoides, Chattonella marina, Karenia mikimotoi and Protoperidinium species) that have contributed to major ABs along the coastline of India in the years 2002 to 2015 are classified. Methods/Statistical Analysis: Processing the data procured by MODIS Aqua sensor, classification of seven species of algae is performed based only on the feature of Remote Sensing Reflectance (Rrs). In contrast to the existing algorithms like band-ratio and interpretation of water discoloration, classification of blooms is based on Support Vector Machine (SVM) and Regularized Least Squares (RLS) algorithms. Findings: Classification is executed using LIBSVM and GURLS library for fast and efficient performance. The classification accuracies achieved using both the classifiers are comparable; the overall accuracy using SVM classifier is 88.37%, whereas that obtained with RLS classifier is 89.98%. Applications/Improvements: These results reveal that the above mentioned algorithms are capable of effectively detecting these ABs which is of immense interest in fisheries and healthcare industries. The algorithms can be further trained with bloom parameters based on in-situ datasets from additional occurrences.
Algal Bloom, MODIS Aqua Data, Rrs, RLS, SVM.
- Falkowski P. Physiological responses of phytoplankton to natural light regimes. Journal of Plankton Research. 1984 Jan; 6(2):295–307.
- DSilva MS, Anil AC, Naik RK, DCosta PM. Algal blooms: a perspective from the coasts of India. Natural Hazards. 2012 Sep; 62(2):1225–53.
- Cracknell A, Newcombe S, Black A, Kirby N. The abdmap (algal bloom detection, monitoring and prediction) concerted action. International Journal of Remote Sensing. 2001; 22(2-3):205–47.
- Shen L, Xu H, Guo X. Satellite remote sensing of harmful algal blooms (habs) and a potential synthesized framework. Sensors. 2012 Jun; 12(6):7778–803.
- OReilly JE, Maritorena S, Siegel DA, Obrien MC, Toole D, Mitchell BG, Kahru M, Chavez FP, Strutton P, Cota GF. Ocean color chlorophyll a algorithms for seawifs, oc2, and oc4: Version 4. SeaWiFS post launch calibration and validation analyses, Part 2000.
- Simon A, Shanmugam P. An algorithm for classification of algal blooms using modis-aqua data in oceanic waters around India. Advances in Remote Sensing. 2012 Sep;1(2):35–51.
- Trescott A. Remote sensing models of algal blooms and cyanobacteria in lake champlain. 2012.
- Soman K, Loganathan R, Ajay V. Machine Learning with SVM and other Kernel methods. PHI Learning Pvt. Ltd., 2009 Feb.
- Chang C-C, Lin C-J. Libsvm: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology (TIST). 2011 Mar; 1–39.
- Rifkin R, Yeo G, Poggio T. Regularized least squares classification. Nato Science Series Sub Series III Computer and Systems Sciences. 2003; 131–54.
- Haridas N, Sowmya V, Soman K. Gurls vs libsvm: Performance comparison of kernel methods for hyperspectral image classification. Indian Journal of Science and Technology. 2015 Sep; 8(24):1–10.
- Jensen J. Remote sensing of the environment an earth resource perspective, person prentice hall. Upper Saddle River, NJ, 2007.
- Krishnan AA, Krishnakumar PK, Rajagopalan M. Trichodesmium erythraeum (ehrenberg) bloom along the southwest coast of India (arabian sea) and its impact on trace metal concentrations in seawater. Estuarine, Coastal and Shelf Science. 2007 Feb; 71(3-4):641–6.
- Padmakumar KB, SreeRenjima G, Fanimol CL, Menon NR, Sanjeevan VN. Preponderance of heterotrophic Noctiluca scintillans during a multi-species diatom bloom along the southwest coast of India. International Journal of Oceans and Oceanography. 2010 Jan; 1:55–63.
- Arumugam RRR, Hemalatha A, Kannathasan A, Sampathkumar P, Balasubramanian T, Anantharaman P, Thirumaran RG. Monitoring of Noctiluca bloom in mandapam and keelakarai coastal waters; southeast coast of India, Recent Research in Science and Technology. 2010 Jan; 2(10):51–5.
- Dharani G, Abdul Nazar AK, Kanagu L, Venkateshwaran P, Kumar TS, Ratnam K, Venkatesan R, Ravindran M. On the recurrence of Noctiluca scintillans bloom in minnie bay, port blair: Impact on water quality and bioactivity of extracts. Current science. 2004 Oct; 87(7):1–5.
- Sahu G, Sasmal SK, Sahu BK, Panigrahy RC, Mohanty AK, Satpathy KK. Red tide of Noctiluca scintillans and its impact on the coastal water quality of the near-shore waters, off the rushikulya river, bay of Bengal. Current science. 2007 Sep; 93(5):616–8.
- Gopakumar G, Bindu Sulochanan, Venkatesan V. Bloom of noctiluca scintillans (macartney) in gulf of mannar, southeast coast of India. Journal of the Marine Biological Association of India. 2009; 51(1):75–80.
- Sanilkumar MG, Thomas AM, Shyamkumar S, Philip R, Mohammed Hatha AA, Sanjeevan VN, Saramma AV. First report of protoperidinium bloom from Indian waters. Harmful Algae News letter. 2009.
- Padmakumar KB, Sanilkumar MG, Saramma AV, Sanjeevan VN, Menon NR. Green tide of Noctiluca miliaris in the Northern Arabian Sea. Harmful Algae News. 2007 Dec; 1–16.
- Jugnu R, Kripa V. Effect of Chattonella marina [(subrahmanyan) hara et chihara, bloom on the coastal fishery resources along Kerala coast, India. Indian Journal of Marine Sciences. 2009; 38(1):77–88.
- Padmakumar KB, Thomas LC, Salini TC, John E, Menon NR, Sanjeevan VN. Monospecific bloom of noxious raphidophyte Chattonella marina in coastal waters of south west coast of India. Int J Biosciences. 2011; 1(1):57–69.
- Iyer CS, Robin RS. Karenia mikimotoi bloom in Arabian Sea. Harmful algae news. 2008; (37):9–10.
- Madhu NV, Reny PD, Paul M, Ullas N, Resmi P. Occurrence of red tide caused by Karenia mikimotoi (toxic dinoagellate) in the southwest coast of India. Indian Journal of Geo – Marine Science. 2011 Dec; 40(6):821–5.
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.