Review: When worlds collide - poultry modeling in the 'Big Data' era

Area of Science:

• Agricultural Science
• Data Science
• Animal Science

Background:

• Poultry production systems have long utilized models for decision support and performance optimization.
• Advancements in digital and sensor technologies have led to the emergence of Big Data streams.
• Machine learning (ML) modeling approaches are well-suited for analyzing Big Data, offering enhanced forecasting and prediction capabilities.

Purpose of the Study:

• To review the evolution of empirical and mechanistic models in poultry production.
• To explore the integration of new digital tools and technologies with existing models.
• To examine the impact of ML and Big Data on precision feeding and automation in poultry production.

Main Methods:

• Review of existing literature on poultry production modeling.
• Analysis of the application of Big Data analytics and ML methodologies.
• Exploration of hybrid modeling approaches combining data-driven and mechanistic methods.

Main Results:

• ML and Big Data analytics offer significant potential for precise feeding tailored to individual animal needs.
• Hybrid models combining data-driven and mechanistic approaches can improve decision support and forecasting.
• Precision feeding systems and automation are emerging as key applications of these technologies.

Conclusions:

• The integration of Big Data and ML represents a paradigm shift in poultry production management.
• Future directions include leveraging sensor technologies and advanced ML algorithms for enhanced precision feeding.
• Hybrid modeling strategies are crucial for bridging decision support systems with advanced predictive capabilities.