Regression-Based Optical Intensity and Image Processing Techniques for Diatom Algae Content Estimation

Authors

DOI:

https://doi.org/10.31436/iiumej.v27i3.4333

Keywords:

Microalgae, RGB, Image Processing, Regression, Optical Intensity

Abstract

Microalgae are responsible for oxygen production, pH stabilization, and nitrogen waste absorption in shrimp pond ecosystems, serving as essential biological indicators of water quality. Within the unicellular microalgae group, diatoms such as Skeletonema sp. and Thalassiosira sp. confer major ecological benefits, excessive growth can disturb pond environments. Despite their significance, monitoring these diatoms, particularly in Indonesian aquaculture systems, remains constrained by time-consuming manual counting. This study proposes a non-invasive integrated framework combining direct raw optical intensity (OI) sensing and digital image processing (IP) techniques to estimate the concentration of Skeletonema sp. and Thalassiosira sp. across varying laboratory-grown concentration ranges. The proposed regression models demonstrated high predictive performance across all concentration ranges, with test set coefficients of determination exceeding 0.95 (R2 > 0.95). The results indicate that biomass estimations derived from image processing are more accurate than those obtained from direct optical intensity, with data suggesting that species-specific optical properties are modulated by cellular pigment responses. Overall, this non-destructive RGB regression framework offers reliable microalgae biomass estimation for precision aquaculture.

ABSTRAK: Mikroalga bertanggungjawab menghasilkan oksigen, menstabilkan pH, dan menyerap sisa nitrogen dalam ekosistem kolam udang, berfungsi sebagai penunjuk biologi penting kualiti air. Dalam kumpulan mikroalga bersel tunggal, diatom seperti Skeletonema sp. dan Thalassiosira sp. memberikan manfaat ekologi besar, namun pertumbuhan berlebihan boleh mengganggu persekitaran kolam. Walaupun kepentingannya, pemantauan diatom ini, terutamanya dalam sistem akuakultur Indonesia, masih terhad oleh pengiraan manual yang memakan masa. Kajian ini mencadangkan rangka kerja terintegrasi tidak invasif yang menggabungkan pengesanan intensiti optik mentah secara langsung (OI) dan teknik pemprosesan imej digital (IP) untuk menganggarkan kepekatan Skeletonema sp. dan Thalassiosira sp. merentasi julat kepekatan yang ditanam di makmal. Model regresi yang dicadangkan menunjukkan prestasi peramalan yang tinggi merentasi semua julat kepekatan, dengan pekali determinan set ujian melebihi 0.95 (R2 > 0.95). Keputusan menunjukkan bahawa anggaran biomassa yang diperoleh daripada pemprosesan imej adalah lebih tepat berbanding yang diperoleh daripada intensiti optik langsung, dengan data mencadangkan bahawa sifat optik spesies tertentu dimodulasi oleh tindak balas pigmen selular. Secara keseluruhannya, rangka kerja regresi RGB bukan merosakkan ini menawarkan anggaran biomassa mikroalga yang boleh dipercayai untuk akuakultur tepat.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

References

Yusoff FM, Umi WAD, Ramli NM, Harun R (2024) Water quality management in aquaculture. Cambridge Prism. Water, 2:e8. https://doi.org/10.1017/wat.2024.6

Terkula B, Azman N (2021) Recent advances in shrimp aquaculture wastewater management. Heliyon, 7:e08283. https://doi.org/10.1016/j.heliyon.2021.e08283

Moayedi A, Yargholi B, Pazira E, Babazadeh H (2021) Investigation of bio-desalination potential algae and their effect on water quality. Desalin. Water Treat., 212:78-86. https://doi.org/10.5004/dwt.2021.26638

Yin S, Jin W, Xi T, Zhou X, He Z, Meng X, Naushad M, Jiang G, Li X (2024) Factors affect the oxygen production of Chlorella pyrenoidosa in a bacterial-algal symbiotic system: Light intensity, temperature, pH and static magnetic field. Process Saf. Environ. Prot., 184:492-501. https://doi.org/10.1016/j.psep.2024.02.004

Ende S, Henjes J, Spiller M, Elshobary M, Hanelt D (2024) Recent advances in recirculating aquaculture systems and role of microalgae to close system loop. Bioresour. Technol., 407:131107. https://doi.org/10.1016/j.biortech.2024.131107

Winata HN, Nasution MA, Ahamed T, Noguchi R (2021) Prediction of concentration for microalgae using image analysis. Multimed. Tools Appl., 80(6):8541-8561. https://doi.org/10.1007/s11042-020-10052-y

Yang W, Zheng Z, Lu K, Zheng C, Du Y, Wang J, Zhu J (2020) Manipulating the phytoplankton community has the potential to create a stable bacterioplankton community in a shrimp rearing environment. Aquaculture, 520:734789. https://doi.org/10.1016/j.aquaculture.2019.734789

M (1997) Phytoplankton dynamics in shrimp ponds. Aquac. Res., 28(5):351-360. https://doi.org/10.1046/j.1365-2109.1997.00865.x

Xiao X, Peng Y, Zhang W, Yang X, Zhang Z, Ren B, Zhu G, Zhou S (2024) Current status and prospects of algal bloom early warning technologies: A review. J. Environ. Manage., 349:119510. https://doi.org/10.1016/j.jenvman.2023.119510

Hotos GN, Avramidou D, Bekiari V (2020) Calibration curves of culture density assessed by spectrophotometer for three microalgae (Nephroselmis sp., Amphidinium carterae and Phormidium sp.). Eur. J. Biol. Biotechnol., 1(6):e132. https://doi.org/10.24018/ejbio.2020.1.6.132

D?bowski M, Kazimierowicz J, Zieli?ski M (2025) Multi-sensing monitoring of the microalgae biomass cultivation systems for biofuels and added value products synthesis—challenges and opportunities. Appl. Sci., 15(13):7324. https://doi.org/10.3390/app15137324

Sunoj S, Hammed A, Igathinathane C, Eshkabilov S, Simsek H (2021) Identification, quantification, and growth profiling of eight different microalgae species using image analysis. Algal Res., 60:102487. https://doi.org/10.1016/j.algal.2021.102487

Cvjetinovic J, Perkov SA, Kurochkin MA, Sergeev IS, German SV, Bedoshvili YD, Davidovich NA, Korsunsky AM, Gorin DA (2023) Concentration dependence of optical transmission and extinction of different diatom cultures. J. Biomed. Photonics Eng., 9(1):010303. https://doi.org/10.18287/JBPE23.09.010303

Castaldello C, Gubert A, Sforza E, Facco P, Bezzo F (2021) Microalgae monitoring in microscale photobioreactors via multivariate image analysis. ChemEngineering, 5(3):49. https://doi.org/10.3390/chemengineering5030049

Badraeni, Trijuno DD, Eriswandi I (2021) Use of bioassay CG (Colour Graduation) to determine density of Skeletonema sp. at hatchery. IOP Conf. Ser. Earth Environ. Sci., 763(1):012039. https://doi.org/10.1088/1755-1315/763/1/012039

Kamaluddin MW, Gunawan AI, Setiawardhana, Dewantara BSB, Insivitawati E, Asmarany A, Pratama AE (2024) Algae content estimation utilizing optical density and image processing method. Int. J. Electr. Comput. Eng., 14(6):6248-6257. https://doi.org/10.11591/ijece.v14i6.pp6248-6257

Kondzior P, Tyniecki D, Butarewicz A (2019) Influence of color temperature of white LED diodes and illumination intensity on the content of photosynthetic pigments in Chlorella vulgaris algae cells. MDPI AG, pp. 46.

Al-amshawee S, Bin Mohd Yunus MY (2020) Influence of light emitting diode (LED) on microalgae. J. Chem. Eng. Ind. Biotechnol., 5(2):9-16. https://doi.org/10.15282/jceib.v5i2.3771

Wood NJ, Baker A, Quinnell RJ, Camargo-Valero MA (2020) A simple and non-destructive method for chlorophyll quantification of Chlamydomonas cultures using digital image analysis. Front. Bioeng. Biotechnol., 8:00746. https://doi.org/10.3389/fbioe.2020.00746

Phycokey - Skeletonema images. Available: https://cfb.unh.edu/phycokey/Choices/Bacillariophyceae/Centric/Centric_Filaments/SKELETONEMA/Skeletonema_Image_page.html

Phycokey - Thalassiosira. Available: https://cfb.unh.edu/phycokey/Choices/Bacillariophyceae/Centric/Centric_Filaments/THALASSIOSIRA/Thalassiosira_key.html

Stenger-Kovács C, Béres VB, Buczkó K, Al-Imari JT, Lázár D, Padisák J, Lengyel E (2023) Review of phenotypic response of diatoms to salinization with biotechnological relevance. Hydrobiologia, 850(20):4665-4688. https://doi.org/10.1007/s10750-023-05194-7

Mishra B, Tiwari A (2021) Spirulina platensis for the production of C-Phycocyanin, C-Phycoerythrin and Thalassiosira, Skeletonema, Chaetoceros for fucoxanthin. Syst. Microbiol. Biomanufacturing. https://doi.org/10.1007/s43393-020-00020-w

Sharma A, Singh P, Srivastava P (2023) Photosynthetic pigments in diatoms. In: Insights into the World of Diatoms: From Essentials to Applications. Srivastava P, Khan AS, Verma J, Dhyani S (Eds.). Springer Nature Singapore, Singapore; pp. 1-20.

Downloads

Published

2026-09-11

How to Cite

Alwafi, R. M., Gunawan, A. I., & Setiawardhana. (2026). Regression-Based Optical Intensity and Image Processing Techniques for Diatom Algae Content Estimation. IIUM Engineering Journal, 27(3), 173–185. https://doi.org/10.31436/iiumej.v27i3.4333

Issue

Section

Electrical, Computer and Communications Engineering