Identificación del crecimiento de los Nauplios por medio de Deep Learning

Abstract

This study focuses on the development of a Deep Learning (DL) model for the identification of populations and the evaluation of shrimp larvae using critical parameters such as Oxygen, Saturation, and Temperature. Analyzing data enables making correct and timely decisions focused on optimizing time and resources by leveraging technological advancements and DL algorithm development. These tools allow extracting complex patterns to achieve desired results, tailored to the area of interest in terms of fine-tuned predictions based on DL application. This approach involves comprehensive data collection on shrimp larvae growth using detailed information on each water quality parameter. The integration of advanced technologies like DL to validate larval development emerges as a useful tool, centered on the efficiency and precision of predictions, enabling producers to make quick and effective decisions to optimize larval growth conditions. The development of this research will provide a better understanding of the applicability of deep learning algorithms, an advanced technology used in predicting survival based on critical parameters in the stages of shrimp larvae development. The investigative work significantly contributes to smart aquaculture practices focused on the incorporation of advanced methods.