Utilization of Artificial Intelligence to Assess The Percentage Cover of Seagrass Beds
Keywords:
Artificial intelligence, Conventional, Percentage, Seagrass bedsAbstract
Seagrass meadows are vital coastal ecosystems that play a crucial role in the survival of marine life and maintaining the balance of coastal ecosystems. Traditional assessments of seagrass meadow health are conducted through field survey methods that are intensive, time-consuming, and expensive. These methods are often limited in spatial and temporal coverage. This study aims to examine the conventional methods for assessing seagrass cover and describe the application of Artificial Intelligence in seagrass meadow cover analysis. Through a comprehensive literature review, this research analyzes various previous studies on conventional methods and the use of AI for assessing seagrass meadow cover. The results of the review show that conventional methods for assessing seagrass cover can provide accurate and detailed data on seagrass meadow conditions, including cover percentage, seagrass species, and seagrass health. These methods are flexible and can be adapted to various field conditions and research objectives. However, conventional methods also have several limitations. They require significant time and financial resources, especially for large areas. Additionally, their spatial coverage is limited, and the analysis results can be influenced by observer subjectivity. Artificial Intelligence (AI) has opened new opportunities in marine ecology, particularly in seagrass meadow monitoring. Deep learning techniques, a branch of AI, enable automated and accurate image analysis to identify and measure seagrass meadow cover. Thus, AI offers a more efficient, accurate, and objective solution compared to conventional methods. The ability of AI to process large and complex datasets allows for broader and more frequent seagrass meadow monitoring, providing more comprehensive information on the condition of seagrass ecosystems.
References
Alam, I. F., Ihsan Sarita, M., & Sajiah, A. M. (2019). Implementasi Deep Learning Dengan Metode Convolutional Neural Network Untuk Identifikasi Objek Secara Real Time Berbasis Android. 5(2), 237–244. https://doi.org/10.5281/zenodo.3459374
Bongga, M., Sondak, C. F., Kumampung, D. R., Roeroe, K. A., Olivia Tilaar, S., & Sangari, J. R. (2021). Kajian Kondisi Kesehatan Padang Lamun Di Perairan Mokupa Kecamatan Tombariri Kabupaten Minahasa. Jurnal Pesisir Dan Laut Tropis, 9(3), 44–54.
Cholissodin, I., & Soebroto, A. A. (2019). Buku Ajar AI, Machine Learning & Deep Learning Deep Intelligent Robotic System View project Optimasi Asupan Makanan Harian Ibu Hamil Penderita Hipertensi Menggunakan Algoritme Genetika View project. https://www.researchgate.net/publication/348003841
I Wayan Suartika E.P, Wijaya Yudhi Arya, & Rully Soelaiman. (2016). Klasifikasi Citra Menggunakan Convolutional Neural Network (CNN) Pada Caltech 101. JURNAL TEKNIK ITS.
M. Sobron, & Yamin Lubis. (2021). Implementasi artificial intelligence pada system manufaktur terpadu.
Navastara Adni Dini, Safitri Julia, & Diana Purwitasatri. (2018). Kombinasi Metode Multilayer Perceptron Dan Teori Fuzzy Untuk Klasifikasi Data Medus. IKRAITH -INFORMATIKA.
Tangke, U. (2010). Ekosistem Padang Lamun (Manfaat, Fungsi dan Rehabilitasi). Jurnal Ilmiah Agribisnis Dan Perikanan (Agrikan UMMU-Ternate), 3(1), 9–29.
Tangke, U., & Faperta, S. P. (2010). Jurnal Ilmiah agribisnis dan Perikanan (agrikan UMMU-Ternate) (Vol. 3, Issue 1).
Tarkus, D., Sompie, S. R. U. A., & Jacobus, A. (2020). Implementasi Metode Recurrent Neural Network pada Pengklasifikasian Kualitas Telur Puyuh. Jurnal Teknik Informatika, 15(2), 137–144.
