By 2030, the number of people experiencing food insecurity is expected to double. With this, the contribution of aquaculture to global aquatic food production is expected to increase 5-fold. Growth in the sector invariably affects the need to efficiently manage resources to maximize productivity. Moreover, issues such as climate change and emerging diseases contributes to the challenges in aquatic food farming. Therefore, it is essential that innovative technologies and solutions are leveraged to ensure a healthy yield outcome.
In this study, we analysed industry data consisting of 3 harvest cycles from 9 P. vannamei shrimp ponds in the Philippines. The dataset includes physio-chemical properties, feed and supplement data, and water management input data. The survival rate, indicating the health outcome of the shrimp culture at the end of each harvest cycle, was taken as the target variable for the study. The survival rate threshold was set to 80%. Statistical analysis was performed to identify important variables related to the yield outcome using statistical methods: Boruta and Random Forest. The resulting variables were validated using Pearson’s correlation. All statistical tests were implemented using Python.
From the feed and supplement variables, we identified feed data labeled V3S, PVO3, V3P, V2, PVO4, PVO1, and TOP_S as significant variables for a healthy yield. From the set of physio-chemical property variables, dissolved oxygen, PH level, depth, temperature, and salinity were revealed to be important parameters. From the set of water management input variables, Ammonia and Magnesium levels were revealed to be significant parameters for farm yield. These results validate the importance of specific parameters already used in best practices in the industry. Moreover, it reveals additional variables, such as specific feed and supplement types that can inform industry practices.