Ocean Modeling Analysis and Modeling Based on Deep Learning

• Published in: Mobile information systems Vol. 2022; pp. 1 - 6
• Main Authors: Niu, Ming Hui, Cho, Joung Hyung
• Format: Journal Article
• Language: English
• Published: Amsterdam Hindawi 30.07.2022; Hindawi Limited
• Subjects: Aesthetics; Archaea; Artificial intelligence; Artificial neural networks; Deep learning; Earth surface; Flaw detection; Marine animals; Marine plants; Microorganisms; Neural networks; Ocean models; Open source software; Saline water; Seawater; Toys
• ISSN: 1574-017X; 1875-905X
• DOI: 10.1155/2022/1019564

The ocean comprises an uninterrupted body of salt water confined within a vast basin on the earth’s surface. The ocean is the largest ecosystem on earth with rich and diverse biological resources. Organisms that reside in salty water are referred to as “marine life.” Plants, animals, and microorganisms including archaea and bacteria are examples of these. The existence of marine life is not only a biological resource but also an economic source. Toys and other industries that imitate marine life have emerged in the market. A different modeling design of marine life has improved with the passage of time and the concept of modeling aesthetics has been incorporated. The identification of marine life images is challenging due to the complexity of the maritime environment, and there are several flaws in marine life models. The rise of deep learning has brought some new ideas for the weaknesses in marine life modeling, and the advantages of convolutional neural networks have contributed to some of the concepts based on deep learning. This research analyses marine modeling by using the benefits of convolutional neural networks, so that people can better understand marine life modeling. The experimental results indicate that the proposed approach has achieved good results in marine life detection, and the modeling effect of ocean modeling analysis based on deep learning is good.