Intelligent feeding technique based on predicting shrimp growth in recirculating aquaculture system

Abstract

Precise feeding in the recirculating aquaculture mode is a critical scientific problem that urgently needs a solution. This study aimed to develop an intelligent feeding technique in a recirculating aquaculture system for rearing Litopenaeus vannamei. The core of the intelligent feeding technique is the shrimp biomass prediction model. Accurate prediction of shrimp biomass could determine the appropriate feeding amount and ensure stable water quality. The data‐driven prediction model was developed based on water quality indicators and aquaculture management data collected during shrimp rearing. Multiple linear regression, artificial neural networks and a support vector machine (SVM) were introduced to develop the shrimp biomass predicting model. Results showed that the SVM model gave the lowest root mean square error (0.6500), mean absolute error (0.4368) and mean absolute percentage error (3.70%), as well as the highest accuracy (90.91%). By analysing the predictive ability of the machine learning models, it was determined that the SVM model was the optimal model for predicting biomass. The intelligent feeding machine can apply the optimal model to calculate the shrimp biomass and determine the appropriate feeding amount by reading the sensors in real time.

Exploring opportunities of Artificial Intelligence in aquaculture to meet increasing food demand

“…Cameras, for instance, can be used to observe fish behaviour and spot alterations that can point to stress or disease, such decreased activity levels or unusual swimming behaviour. Chen et al (2022) reported that advanced disease identification based on fish behaviour and external appearance has been identified as a promising field for AI use. In addition, this detection system is based on underwater cameras or sensors to capture images that are sent through the cloud to the processing unit and scoring system.…”

“…Through waste and the chance of overfeeding, this can have a detrimental effect on the environment by resulting in contaminated water. By reading the sensors in real-time, an optimal model for artificial intelligence may be employed to determine the shrimp biomass and determine the proper amount ( Chen et al, 2022 ).…”

“… Deep learning techniques InceptionV3 pre-trained model for classifying three different types of abnormal appearance of grouper can reach average 98.94 % accuracy in phase II task. Chen et al, 2022 3. AI based disease detection Covers periodical optical monitoring of the fishes in the farm, detecting the onset of any disease, with a minimum time lag.…”

“… Intelligent feeding technique To calculate the shrimp biomass and determine the appropriate feeding amount by reading the sensors in real time. Chen et al, 2022 5. Intelligent feeding Intelligent equipment can replace people, reduce labor intensity, reduce risk, and improve work efficiency.…”

Digitalization in Small-Scale Urban Recirculation Aquaculture: Data Analytics in Sub-Saharan Africa

“…In contrast, the conventional approach of water monitoring involves periodic onsite measurements using handheld meters or sensors. While these instruments provide immediate measurements when staff members are available during office hours, they are limited in their ability to capture unexpected variations, changes or alterations in water parameters that may occur outside of these hours (Chen et al, 2022). It is during these unmonitored periods that one or more key water parameters can deviate beyond safe levels, potentially leading to detrimental consequences that go unnoticed until the next scheduled measurement.…”