International Journal of Aquaculture, 2025, Vol.15, No.3, 135-148 http://www.aquapublisher.com/index.php/ija 145 the tilapia genome. CRISPR/Cas9 technology can perform "site-point knockout" or "site-point insertion" of specific genes in the tilapia genome, thus giving them new traits. Cases that have been successfully implemented in tilapia include: knocking out the DMRT1 gene to turn genetic males into functional females to achieve the purpose of breeding supermale; knocking out the myostatin gene (muscle growth inhibitor) to relieve the restrictions on muscle growth and obtaining individuals with tilapia whose muscle yield is increased by about 20%. These experimental results prove that gene editing has the potential to target the improvement of important economic traits of tilapia. Especially in disease-resistant breeding, gene editing can play a unique role. 8.2 Intelligent aquaculture system and data-driven management The deep integration of information technology and aquaculture is promoting the development of tilapia farming in the direction of intelligence. The application of technologies such as the Internet of Things (IoT), big data and artificial intelligence (AI) is expected to significantly improve the efficiency of breeding management, reduce labor costs and optimize production decisions. At present, in tilapia farming, intelligent exploration focuses on the following aspects: first, online monitoring and regulation of water quality. The Internet of Things-based water quality monitoring system can collect key parameters such as dissolved oxygen, temperature, pH, ammonia nitrogen in real time, and transmit it to the breeder's mobile phone or control center through wireless network. The second is intelligent feeding and image recognition. The feed cost of tilapia accounts for about 70% of the total cost, and traditional manual feeding can easily lead to feed waste and deterioration of water quality. The intelligent feeding machine realizes timing, quantitative and on-demand feeding through pre-set programs combined with monitoring of fish feeding behavior. The third is big data analysis of the breeding environment and diseases. By collecting long-term environmental and production data, data mining can be used to identify key factors that affect tilapia growth and health, and to predict potential risks. In a pilot project in Malaysia, applied machine learning models successfully predicted more than 90% of streptococcal disease outbreaks, winning time for farmers to prevent and control (Abid et al., 2024). The fourth is unmanned and automation. In future smart fishing grounds, pond patrol robots, underwater drones, etc. will undertake routine inspection tasks, and can monitor the status of fish schools and the operation of facilities 24 hours a day, and detect abnormalities in a timely manner (Figure 3). Figure 3 Smart biofloc monitoring system (Adopted from Abid et al., 2024) 8.3 Application of comprehensive environment-genetic model in industrial layout In order to guide the sustainable layout of the tilapia industry at a more macro level, scholars have proposed to build a comprehensive environmental-genetic model, combining environmental factors with strain genetic characteristics for analysis and simulation. The concept of this model is that different tilapia strains (or species)
RkJQdWJsaXNoZXIy MjQ4ODYzNA==