The use of artificial intelligence–based approaches and image processing in the process of successful management of sturgeon aquaculture | ||
| ماهیان خاویاری | ||
| Volume 8, Issue 15, March 2026, Pages 22-29 PDF (906.99 K) | ||
| Document Type: Tarvij | ||
| Authors | ||
| Ashkan Banan* 1; Shirin Jamshidi2 | ||
| 1Department of Fisheries and Environmental Sciences and Engineering, Faculty of Natural Resources, Lorestan University; Data Science and Computational Intelligence Research Institute of Lorestan University | ||
| 2International Sturgeon Research Institute, Iranian Fisheries Science Research Institute,Agricultural Research, Education and Extension Organization (AREEO) | ||
| Abstract | ||
| Addressing the application of artificial intelligence–based methods in image processing can provide a new perspective for the intelligent and sustainable management of sturgeon aquaculture. Given the considerable economic value and the biological sensitivity of sturgeons to any form of manipulation, the development of innovative, precise, and non-invasive methods for monitoring, assessment, and management in the aquaculture industry of these valuable species is essential. In this study, image processing methods, including the extraction of morphological and behavioral features from images and their analysis using artificial intelligence models such as neural networks, machine learning algorithms, and machine vision systems, have been considered. In recent years, these techniques have been introduced as effective, cost-efficient, and technology-driven tools for optimizing fish farming processes. In the present study, various applications of this advanced technology in sturgeon farms are reviewed, including behavioral monitoring under environmental stressors such as ammonia, accurate non-contact weight estimation, automatic sorting, non-invasive assessment of ovarian fat, and enhancement of image quality under low-light conditions. Findings from the reviewed studies indicate that image processing can serve as a suitable alternative to traditional, costly, and time-consuming methods, and by improving accuracy, reducing stress on fish, lowering operational costs, and enabling continuous assessment, it can contribute to greater sustainability and productivity in sturgeon aquaculture. Finally, it is concluded that machine vision systems and machine learning algorithms should be more widely and integratively applied in the sturgeon aquaculture industry to pave the way for intelligent, safe, and sustainable development in this field. | ||
| Keywords | ||
| Aquaculture; Non-invasive monitoring; Weight estimation; Ovarian fat assessment; Automated sorting; Behavioral analysis | ||
| References | ||
|
| ||
|
Statistics Article View: 145 PDF Download: 100 |
||
Journal management system. designed by sinaweb